{
  "schema": "profiling-summary",
  "version": 2,
  "project": "autofit_profiling",
  "scope": "pyautofit-profiling",
  "generated_at": "2026-10-14T14:45:45Z",
  "evidence_updated_at": "2026-10-14T14:45:45Z",
  "valid_until": null,
  "producer_revision": null,
  "comparison_policy": {
    "id": "no-temporal-comparisons"
  },
  "coverage": {
    "expected": {
      "cells": 32
    },
    "observed": {
      "setups": 9,
      "records": 31,
      "selected": 31
    },
    "excluded": []
  },
  "setups": [
    {
      "id": "analytic_gaussian/parity/seed0_n5",
      "label": "analytic Gaussian parity: closed form | minimal EP | autofit graphical | autofit EP",
      "dataset": "analytic_gaussian",
      "model": "conjugate hierarchical gaussian",
      "instrument": null,
      "unknowns": {
        "instrument": "toy 1-D dataset; no instrument"
      },
      "configuration_id": "analytic_gaussian/parity/seed0_n5@1",
      "configuration": {
        "data_pixels": {
          "value": 100,
          "unit": "count"
        },
        "free_parameters": {
          "value": 7,
          "unit": "count"
        },
        "kl_tol": {
          "value": 0.0001,
          "unit": "dimensionless"
        },
        "likelihood": {
          "value": "numpy (GaussianDataAnalysis, no JAX)",
          "unit": "name"
        },
        "max_steps": {
          "value": 30,
          "unit": "count"
        },
        "maxcall": {
          "value": 30000,
          "unit": "count"
        },
        "n_datasets": {
          "value": 5,
          "unit": "count"
        },
        "nlive": {
          "value": 100,
          "unit": "count"
        },
        "output_config": {
          "value": "autofit_workspace_test config (the parity script's CI home)",
          "unit": "name"
        },
        "sample": {
          "value": "unif",
          "unit": "name"
        },
        "search": {
          "value": "DynestyStatic (graphical) + LaplaceOptimiser(projection='moments') (EP)",
          "unit": "name"
        },
        "seed": {
          "value": 0,
          "unit": "count"
        }
      }
    },
    {
      "id": "gaussian_1d_ep/ep/N10",
      "label": "factor_graph.optimise EP, 10 datasets (per-factor DynestyStatic + Laplace cavity)",
      "dataset": "gaussian_1d_ep",
      "model": "gaussian, centre shared across datasets",
      "instrument": null,
      "unknowns": {
        "instrument": "toy 1-D dataset; no instrument"
      },
      "configuration_id": "gaussian_1d_ep/ep/N10@1",
      "configuration": {
        "data_pixels": {
          "value": 1000,
          "unit": "count"
        },
        "free_parameters": {
          "value": 21,
          "unit": "count"
        },
        "kl_tol": {
          "value": 0.05,
          "unit": "dimensionless"
        },
        "likelihood": {
          "value": "af.ex.Analysis(use_jax=True), af.FactorGraphModel(use_jax=True)",
          "unit": "name"
        },
        "max_steps": {
          "value": 5,
          "unit": "count"
        },
        "n_datasets": {
          "value": 10,
          "unit": "count"
        },
        "nlive": {
          "value": 100,
          "unit": "count"
        },
        "optimiser": {
          "value": "LaplaceOptimiser",
          "unit": "name"
        },
        "output_config": {
          "value": "scripts/gaussian_1d_ep/config (verbatim from the developer packages)",
          "unit": "name"
        },
        "sample": {
          "value": "rwalk",
          "unit": "name"
        },
        "search": {
          "value": "DynestyStatic+LaplaceOptimiser (EP)",
          "unit": "name"
        }
      }
    },
    {
      "id": "gaussian_1d_ep/ep/N3",
      "label": "factor_graph.optimise EP, 3 datasets (per-factor DynestyStatic + Laplace cavity)",
      "dataset": "gaussian_1d_ep",
      "model": "gaussian, centre shared across datasets",
      "instrument": null,
      "unknowns": {
        "instrument": "toy 1-D dataset; no instrument"
      },
      "configuration_id": "gaussian_1d_ep/ep/N3@1",
      "configuration": {
        "data_pixels": {
          "value": 300,
          "unit": "count"
        },
        "free_parameters": {
          "value": 7,
          "unit": "count"
        },
        "kl_tol": {
          "value": 0.05,
          "unit": "dimensionless"
        },
        "likelihood": {
          "value": "af.ex.Analysis(use_jax=True), af.FactorGraphModel(use_jax=True)",
          "unit": "name"
        },
        "max_steps": {
          "value": 5,
          "unit": "count"
        },
        "n_datasets": {
          "value": 3,
          "unit": "count"
        },
        "nlive": {
          "value": 100,
          "unit": "count"
        },
        "optimiser": {
          "value": "LaplaceOptimiser",
          "unit": "name"
        },
        "output_config": {
          "value": "scripts/gaussian_1d_ep/config (verbatim from the developer packages)",
          "unit": "name"
        },
        "sample": {
          "value": "rwalk",
          "unit": "name"
        },
        "search": {
          "value": "DynestyStatic+LaplaceOptimiser (EP)",
          "unit": "name"
        }
      }
    },
    {
      "id": "gaussian_1d_ep/ep/N30",
      "label": "factor_graph.optimise EP, 30 datasets (per-factor DynestyStatic + Laplace cavity)",
      "dataset": "gaussian_1d_ep",
      "model": "gaussian, centre shared across datasets",
      "instrument": null,
      "unknowns": {
        "instrument": "toy 1-D dataset; no instrument"
      },
      "configuration_id": "gaussian_1d_ep/ep/N30@1",
      "configuration": {
        "data_pixels": {
          "value": 3000,
          "unit": "count"
        },
        "free_parameters": {
          "value": 61,
          "unit": "count"
        },
        "kl_tol": {
          "value": 0.05,
          "unit": "dimensionless"
        },
        "likelihood": {
          "value": "af.ex.Analysis(use_jax=True), af.FactorGraphModel(use_jax=True)",
          "unit": "name"
        },
        "max_steps": {
          "value": 5,
          "unit": "count"
        },
        "n_datasets": {
          "value": 30,
          "unit": "count"
        },
        "nlive": {
          "value": 100,
          "unit": "count"
        },
        "optimiser": {
          "value": "LaplaceOptimiser",
          "unit": "name"
        },
        "output_config": {
          "value": "scripts/gaussian_1d_ep/config (verbatim from the developer packages)",
          "unit": "name"
        },
        "sample": {
          "value": "rwalk",
          "unit": "name"
        },
        "search": {
          "value": "DynestyStatic+LaplaceOptimiser (EP)",
          "unit": "name"
        }
      }
    },
    {
      "id": "gaussian_1d_ep/graphical/N10",
      "label": "joint DynestyStatic search.fit on factor_graph.global_prior_model, 10 datasets",
      "dataset": "gaussian_1d_ep",
      "model": "gaussian, centre shared across datasets",
      "instrument": null,
      "unknowns": {
        "instrument": "toy 1-D dataset; no instrument"
      },
      "configuration_id": "gaussian_1d_ep/graphical/N10@1",
      "configuration": {
        "bound": {
          "value": "multi",
          "unit": "name"
        },
        "data_pixels": {
          "value": 1000,
          "unit": "count"
        },
        "free_parameters": {
          "value": 21,
          "unit": "count"
        },
        "likelihood": {
          "value": "af.ex.Analysis(use_jax=True), af.FactorGraphModel(use_jax=True)",
          "unit": "name"
        },
        "n_datasets": {
          "value": 10,
          "unit": "count"
        },
        "nlive": {
          "value": 50,
          "unit": "count"
        },
        "number_of_cores": {
          "value": 1,
          "unit": "count"
        },
        "output_config": {
          "value": "scripts/gaussian_1d_ep/config (verbatim from the developer packages)",
          "unit": "name"
        },
        "sample": {
          "value": "rwalk",
          "unit": "name"
        },
        "search": {
          "value": "DynestyStatic (joint)",
          "unit": "name"
        },
        "walks": {
          "value": 5,
          "unit": "count"
        }
      }
    },
    {
      "id": "gaussian_1d_ep/graphical/N3",
      "label": "joint DynestyStatic search.fit on factor_graph.global_prior_model, 3 datasets",
      "dataset": "gaussian_1d_ep",
      "model": "gaussian, centre shared across datasets",
      "instrument": null,
      "unknowns": {
        "instrument": "toy 1-D dataset; no instrument"
      },
      "configuration_id": "gaussian_1d_ep/graphical/N3@1",
      "configuration": {
        "bound": {
          "value": "multi",
          "unit": "name"
        },
        "data_pixels": {
          "value": 300,
          "unit": "count"
        },
        "free_parameters": {
          "value": 7,
          "unit": "count"
        },
        "likelihood": {
          "value": "af.ex.Analysis(use_jax=True), af.FactorGraphModel(use_jax=True)",
          "unit": "name"
        },
        "n_datasets": {
          "value": 3,
          "unit": "count"
        },
        "nlive": {
          "value": 50,
          "unit": "count"
        },
        "number_of_cores": {
          "value": 1,
          "unit": "count"
        },
        "output_config": {
          "value": "scripts/gaussian_1d_ep/config (verbatim from the developer packages)",
          "unit": "name"
        },
        "sample": {
          "value": "rwalk",
          "unit": "name"
        },
        "search": {
          "value": "DynestyStatic (joint)",
          "unit": "name"
        },
        "walks": {
          "value": 5,
          "unit": "count"
        }
      }
    },
    {
      "id": "gaussian_1d_ep/graphical/N30",
      "label": "joint DynestyStatic search.fit on factor_graph.global_prior_model, 30 datasets",
      "dataset": "gaussian_1d_ep",
      "model": "gaussian, centre shared across datasets",
      "instrument": null,
      "unknowns": {
        "instrument": "toy 1-D dataset; no instrument"
      },
      "configuration_id": "gaussian_1d_ep/graphical/N30@1",
      "configuration": {
        "bound": {
          "value": "multi",
          "unit": "name"
        },
        "data_pixels": {
          "value": 3000,
          "unit": "count"
        },
        "free_parameters": {
          "value": 61,
          "unit": "count"
        },
        "likelihood": {
          "value": "af.ex.Analysis(use_jax=True), af.FactorGraphModel(use_jax=True)",
          "unit": "name"
        },
        "n_datasets": {
          "value": 30,
          "unit": "count"
        },
        "nlive": {
          "value": 50,
          "unit": "count"
        },
        "number_of_cores": {
          "value": 1,
          "unit": "count"
        },
        "output_config": {
          "value": "scripts/gaussian_1d_ep/config (verbatim from the developer packages)",
          "unit": "name"
        },
        "sample": {
          "value": "rwalk",
          "unit": "name"
        },
        "search": {
          "value": "DynestyStatic (joint)",
          "unit": "name"
        },
        "walks": {
          "value": 5,
          "unit": "count"
        }
      }
    },
    {
      "id": "gaussian_x1/nautilus/search_fit",
      "label": "af.Nautilus search.fit (PyAutoFit, checkpointing and output on)",
      "dataset": "gaussian_x1",
      "model": "gaussian",
      "instrument": null,
      "unknowns": {
        "instrument": "toy 1-D dataset; no instrument"
      },
      "configuration_id": "gaussian_x1/nautilus/search_fit@1",
      "configuration": {
        "data_pixels": {
          "value": 100,
          "unit": "count"
        },
        "free_parameters": {
          "value": 3,
          "unit": "count"
        },
        "likelihood": {
          "value": "numpy, no JAX",
          "unit": "name"
        },
        "n_live": {
          "value": 200,
          "unit": "count"
        },
        "n_networks": {
          "value": 4,
          "unit": "count"
        },
        "number_of_cores": {
          "value": 1,
          "unit": "count"
        },
        "output_config": {
          "value": "config/general.yaml (library output defaults; version check off)",
          "unit": "name"
        },
        "search": {
          "value": "Nautilus",
          "unit": "name"
        },
        "seed": {
          "value": 1,
          "unit": "dimensionless"
        },
        "variant": {
          "value": "search_fit",
          "unit": "name"
        }
      }
    },
    {
      "id": "gaussian_x1/nautilus/bare_sampler",
      "label": "bare nautilus.Sampler (the findings page's measurement; no PyAutoFit, no checkpoint)",
      "dataset": "gaussian_x1",
      "model": "gaussian",
      "instrument": null,
      "unknowns": {
        "instrument": "toy 1-D dataset; no instrument"
      },
      "configuration_id": "gaussian_x1/nautilus/bare_sampler@1",
      "configuration": {
        "data_pixels": {
          "value": 100,
          "unit": "count"
        },
        "free_parameters": {
          "value": 3,
          "unit": "count"
        },
        "likelihood": {
          "value": "numpy, no JAX",
          "unit": "name"
        },
        "n_live": {
          "value": 200,
          "unit": "count"
        },
        "n_networks": {
          "value": 4,
          "unit": "count"
        },
        "number_of_cores": {
          "value": 1,
          "unit": "count"
        },
        "output_config": {
          "value": "config/general.yaml (library output defaults; version check off)",
          "unit": "name"
        },
        "search": {
          "value": "Nautilus",
          "unit": "name"
        },
        "seed": {
          "value": 1,
          "unit": "dimensionless"
        },
        "variant": {
          "value": "bare_sampler",
          "unit": "name"
        }
      }
    }
  ],
  "records": [
    {
      "id": "analytic_gaussian/parity/seed0_n5/runtime/wall",
      "setup_id": "analytic_gaussian/parity/seed0_n5",
      "run_id": "analytic_gaussian/parity/seed0_n5@2026-10-14T14:45:45Z",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "measurement": {
        "wall": 130.01728060000096
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "autofit_workspace_test": "26877bc69b4a0302f5be9106ec735bebf89d2a1a",
          "dynesty": "2.1.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "parity-script-subprocess-wall/wall",
        "statistic": "single",
        "repetitions": 1,
        "warmup": "none; one run of the parity script in a fresh child process",
        "synchronization": "none (numpy, single process)",
        "cache_state": "cold process; imports inside the timed interval"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T14:45:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage; parity PASS (41/41); host contended during the run (see provenance.host_contention)"
      },
      "evidence": {
        "path": "results/analytic_gaussian/parity/seed0_n5.json",
        "fragment": "/wall_s"
      }
    },
    {
      "id": "analytic_gaussian/parity/seed0_n5/memory/host_peak_rss",
      "setup_id": "analytic_gaussian/parity/seed0_n5",
      "run_id": "analytic_gaussian/parity/seed0_n5@2026-10-14T14:45:45Z",
      "axis": "memory",
      "metric": "host_peak_rss",
      "unit": "KiB",
      "measurement": {
        "host_peak_rss": 340284
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "autofit_workspace_test": "26877bc69b4a0302f5be9106ec735bebf89d2a1a",
          "dynesty": "2.1.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "parity-script-subprocess-wall/peak_rss",
        "statistic": "single",
        "repetitions": 1,
        "warmup": "none; one run of the parity script in a fresh child process",
        "synchronization": "none (numpy, single process)",
        "cache_state": "cold process; imports inside the timed interval"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T14:45:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage; parity PASS (41/41); host contended during the run (see provenance.host_contention)"
      },
      "evidence": {
        "path": "results/analytic_gaussian/parity/seed0_n5.json",
        "fragment": "/peak_rss_kib"
      }
    },
    {
      "id": "gaussian_1d_ep/ep/N10/runtime/wall",
      "setup_id": "gaussian_1d_ep/ep/N10",
      "run_id": "gaussian_1d_ep/ep/N10@2026-10-14T14:29:09Z",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "measurement": {
        "wall": 152.9010105999987
      },
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "fresh-process-single-fit/wall",
        "statistic": "single",
        "repetitions": 1,
        "warmup": "none; one fit per fresh process from an empty output directory (never a resume)",
        "synchronization": "none (JAX CPU, results read back to Python floats)",
        "cache_state": "cold process; JAX compilation falls inside the timed fit"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T14:29:09Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage; sanity PASS (committed baseline PASS); host contended during the run (see provenance.host_contention)"
      },
      "evidence": {
        "path": "results/gaussian_1d_ep/ep/N10.json",
        "fragment": "/wall_s"
      }
    },
    {
      "id": "gaussian_1d_ep/ep/N10/memory/host_peak_rss",
      "setup_id": "gaussian_1d_ep/ep/N10",
      "run_id": "gaussian_1d_ep/ep/N10@2026-10-14T14:29:09Z",
      "axis": "memory",
      "metric": "host_peak_rss",
      "unit": "KiB",
      "measurement": {
        "host_peak_rss": 412424
      },
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "fresh-process-single-fit/peak_rss",
        "statistic": "single",
        "repetitions": 1,
        "warmup": "none; one fit per fresh process from an empty output directory (never a resume)",
        "synchronization": "none (JAX CPU, results read back to Python floats)",
        "cache_state": "cold process; JAX compilation falls inside the timed fit"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T14:29:09Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage; sanity PASS (committed baseline PASS); host contended during the run (see provenance.host_contention)"
      },
      "evidence": {
        "path": "results/gaussian_1d_ep/ep/N10.json",
        "fragment": "/peak_rss_kib"
      }
    },
    {
      "id": "gaussian_1d_ep/ep/N3/runtime/wall",
      "setup_id": "gaussian_1d_ep/ep/N3",
      "run_id": "gaussian_1d_ep/ep/N3@2026-10-14T14:26:33Z",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "measurement": {
        "wall": 37.0929971000005
      },
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "fresh-process-single-fit/wall",
        "statistic": "single",
        "repetitions": 1,
        "warmup": "none; one fit per fresh process from an empty output directory (never a resume)",
        "synchronization": "none (JAX CPU, results read back to Python floats)",
        "cache_state": "cold process; JAX compilation falls inside the timed fit"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T14:26:33Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage; sanity PASS (committed baseline PASS); host contended during the run (see provenance.host_contention)"
      },
      "evidence": {
        "path": "results/gaussian_1d_ep/ep/N3.json",
        "fragment": "/wall_s"
      }
    },
    {
      "id": "gaussian_1d_ep/ep/N3/memory/host_peak_rss",
      "setup_id": "gaussian_1d_ep/ep/N3",
      "run_id": "gaussian_1d_ep/ep/N3@2026-10-14T14:26:33Z",
      "axis": "memory",
      "metric": "host_peak_rss",
      "unit": "KiB",
      "measurement": {
        "host_peak_rss": 361292
      },
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "fresh-process-single-fit/peak_rss",
        "statistic": "single",
        "repetitions": 1,
        "warmup": "none; one fit per fresh process from an empty output directory (never a resume)",
        "synchronization": "none (JAX CPU, results read back to Python floats)",
        "cache_state": "cold process; JAX compilation falls inside the timed fit"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T14:26:33Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage; sanity PASS (committed baseline PASS); host contended during the run (see provenance.host_contention)"
      },
      "evidence": {
        "path": "results/gaussian_1d_ep/ep/N3.json",
        "fragment": "/peak_rss_kib"
      }
    },
    {
      "id": "gaussian_1d_ep/ep/N30/runtime/wall",
      "setup_id": "gaussian_1d_ep/ep/N30",
      "run_id": "gaussian_1d_ep/ep/N30@2026-10-14T14:43:14Z",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "measurement": {
        "wall": 842.7632974000007
      },
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "fresh-process-single-fit/wall",
        "statistic": "single",
        "repetitions": 1,
        "warmup": "none; one fit per fresh process from an empty output directory (never a resume)",
        "synchronization": "none (JAX CPU, results read back to Python floats)",
        "cache_state": "cold process; JAX compilation falls inside the timed fit"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T14:43:14Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage; sanity FAIL (committed baseline FAIL); host contended during the run (see provenance.host_contention)"
      },
      "evidence": {
        "path": "results/gaussian_1d_ep/ep/N30.json",
        "fragment": "/wall_s"
      }
    },
    {
      "id": "gaussian_1d_ep/ep/N30/memory/host_peak_rss",
      "setup_id": "gaussian_1d_ep/ep/N30",
      "run_id": "gaussian_1d_ep/ep/N30@2026-10-14T14:43:14Z",
      "axis": "memory",
      "metric": "host_peak_rss",
      "unit": "KiB",
      "measurement": {
        "host_peak_rss": 657556
      },
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "fresh-process-single-fit/peak_rss",
        "statistic": "single",
        "repetitions": 1,
        "warmup": "none; one fit per fresh process from an empty output directory (never a resume)",
        "synchronization": "none (JAX CPU, results read back to Python floats)",
        "cache_state": "cold process; JAX compilation falls inside the timed fit"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T14:43:14Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage; sanity FAIL (committed baseline FAIL); host contended during the run (see provenance.host_contention)"
      },
      "evidence": {
        "path": "results/gaussian_1d_ep/ep/N30.json",
        "fragment": "/peak_rss_kib"
      }
    },
    {
      "id": "gaussian_1d_ep/graphical/N10/runtime/wall",
      "setup_id": "gaussian_1d_ep/graphical/N10",
      "run_id": "gaussian_1d_ep/graphical/N10@2026-10-14T14:25:32Z",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "measurement": {
        "wall": 7.1306849000029615
      },
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "fresh-process-single-fit/wall",
        "statistic": "single",
        "repetitions": 1,
        "warmup": "none; one fit per fresh process from an empty output directory (never a resume)",
        "synchronization": "none (JAX CPU, results read back to Python floats)",
        "cache_state": "cold process; JAX compilation falls inside the timed fit"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T14:25:32Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage; sanity PASS (committed baseline PASS); host contended during the run (see provenance.host_contention)"
      },
      "evidence": {
        "path": "results/gaussian_1d_ep/graphical/N10.json",
        "fragment": "/wall_s"
      }
    },
    {
      "id": "gaussian_1d_ep/graphical/N10/memory/host_peak_rss",
      "setup_id": "gaussian_1d_ep/graphical/N10",
      "run_id": "gaussian_1d_ep/graphical/N10@2026-10-14T14:25:32Z",
      "axis": "memory",
      "metric": "host_peak_rss",
      "unit": "KiB",
      "measurement": {
        "host_peak_rss": 456628
      },
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "fresh-process-single-fit/peak_rss",
        "statistic": "single",
        "repetitions": 1,
        "warmup": "none; one fit per fresh process from an empty output directory (never a resume)",
        "synchronization": "none (JAX CPU, results read back to Python floats)",
        "cache_state": "cold process; JAX compilation falls inside the timed fit"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T14:25:32Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage; sanity PASS (committed baseline PASS); host contended during the run (see provenance.host_contention)"
      },
      "evidence": {
        "path": "results/gaussian_1d_ep/graphical/N10.json",
        "fragment": "/peak_rss_kib"
      }
    },
    {
      "id": "gaussian_1d_ep/graphical/N3/runtime/wall",
      "setup_id": "gaussian_1d_ep/graphical/N3",
      "run_id": "gaussian_1d_ep/graphical/N3@2026-10-14T14:25:23Z",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "measurement": {
        "wall": 5.984727600000042
      },
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "fresh-process-single-fit/wall",
        "statistic": "single",
        "repetitions": 1,
        "warmup": "none; one fit per fresh process from an empty output directory (never a resume)",
        "synchronization": "none (JAX CPU, results read back to Python floats)",
        "cache_state": "cold process; JAX compilation falls inside the timed fit"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T14:25:23Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage; sanity PASS (committed baseline PASS); host contended during the run (see provenance.host_contention)"
      },
      "evidence": {
        "path": "results/gaussian_1d_ep/graphical/N3.json",
        "fragment": "/wall_s"
      }
    },
    {
      "id": "gaussian_1d_ep/graphical/N3/memory/host_peak_rss",
      "setup_id": "gaussian_1d_ep/graphical/N3",
      "run_id": "gaussian_1d_ep/graphical/N3@2026-10-14T14:25:23Z",
      "axis": "memory",
      "metric": "host_peak_rss",
      "unit": "KiB",
      "measurement": {
        "host_peak_rss": 429952
      },
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "fresh-process-single-fit/peak_rss",
        "statistic": "single",
        "repetitions": 1,
        "warmup": "none; one fit per fresh process from an empty output directory (never a resume)",
        "synchronization": "none (JAX CPU, results read back to Python floats)",
        "cache_state": "cold process; JAX compilation falls inside the timed fit"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T14:25:23Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage; sanity PASS (committed baseline PASS); host contended during the run (see provenance.host_contention)"
      },
      "evidence": {
        "path": "results/gaussian_1d_ep/graphical/N3.json",
        "fragment": "/peak_rss_kib"
      }
    },
    {
      "id": "gaussian_1d_ep/graphical/N30/runtime/wall",
      "setup_id": "gaussian_1d_ep/graphical/N30",
      "run_id": "gaussian_1d_ep/graphical/N30@2026-10-14T14:25:53Z",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "measurement": {
        "wall": 18.954002700000274
      },
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "fresh-process-single-fit/wall",
        "statistic": "single",
        "repetitions": 1,
        "warmup": "none; one fit per fresh process from an empty output directory (never a resume)",
        "synchronization": "none (JAX CPU, results read back to Python floats)",
        "cache_state": "cold process; JAX compilation falls inside the timed fit"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T14:25:53Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage; sanity FAIL (committed baseline FAIL); host contended during the run (see provenance.host_contention)"
      },
      "evidence": {
        "path": "results/gaussian_1d_ep/graphical/N30.json",
        "fragment": "/wall_s"
      }
    },
    {
      "id": "gaussian_1d_ep/graphical/N30/memory/host_peak_rss",
      "setup_id": "gaussian_1d_ep/graphical/N30",
      "run_id": "gaussian_1d_ep/graphical/N30@2026-10-14T14:25:53Z",
      "axis": "memory",
      "metric": "host_peak_rss",
      "unit": "KiB",
      "measurement": {
        "host_peak_rss": 527420
      },
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "fresh-process-single-fit/peak_rss",
        "statistic": "single",
        "repetitions": 1,
        "warmup": "none; one fit per fresh process from an empty output directory (never a resume)",
        "synchronization": "none (JAX CPU, results read back to Python floats)",
        "cache_state": "cold process; JAX compilation falls inside the timed fit"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T14:25:53Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage; sanity FAIL (committed baseline FAIL); host contended during the run (see provenance.host_contention)"
      },
      "evidence": {
        "path": "results/gaussian_1d_ep/graphical/N30.json",
        "fragment": "/peak_rss_kib"
      }
    },
    {
      "id": "gaussian_x1/nautilus/search_fit/runtime/wall",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "run_id": "gaussian_x1/nautilus/search_fit@2026-10-14T09:19:45Z",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "measurement": {
        "wall": 28.41256609999982
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "search-fit-exclusive-component-wall/wall",
        "statistic": "median",
        "repetitions": 3,
        "warmup": "none; each repeat is a fresh fit (output removed, never a resume)",
        "synchronization": "none (numpy, single process)",
        "cache_state": "warm process: imports and first-touch costs fall in the first repeat"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T09:19:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage"
      },
      "evidence": {
        "path": "results/gaussian_x1/nautilus/breakdown.json",
        "fragment": "/wall_s"
      }
    },
    {
      "id": "gaussian_x1/nautilus/search_fit/breakdown/nn_training",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "run_id": "gaussian_x1/nautilus/search_fit@2026-10-14T09:19:45Z",
      "axis": "breakdown",
      "metric": "nn_training",
      "unit": "s",
      "measurement": {
        "nn_training": 11.872448799996164
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "search-fit-exclusive-component-wall/components",
        "statistic": "median",
        "repetitions": 3,
        "warmup": "none; each repeat is a fresh fit (output removed, never a resume)",
        "synchronization": "none (numpy, single process)",
        "cache_state": "warm process: imports and first-touch costs fall in the first repeat"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T09:19:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage"
      },
      "evidence": {
        "path": "results/gaussian_x1/nautilus/breakdown.json",
        "fragment": "/components_s/nn_training"
      }
    },
    {
      "id": "gaussian_x1/nautilus/search_fit/breakdown/bound_geometry",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "run_id": "gaussian_x1/nautilus/search_fit@2026-10-14T09:19:45Z",
      "axis": "breakdown",
      "metric": "bound_geometry",
      "unit": "s",
      "measurement": {
        "bound_geometry": 5.604948700006389
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "search-fit-exclusive-component-wall/components",
        "statistic": "median",
        "repetitions": 3,
        "warmup": "none; each repeat is a fresh fit (output removed, never a resume)",
        "synchronization": "none (numpy, single process)",
        "cache_state": "warm process: imports and first-touch costs fall in the first repeat"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T09:19:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage"
      },
      "evidence": {
        "path": "results/gaussian_x1/nautilus/breakdown.json",
        "fragment": "/components_s/bound_geometry"
      }
    },
    {
      "id": "gaussian_x1/nautilus/search_fit/breakdown/proposal_sampling",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "run_id": "gaussian_x1/nautilus/search_fit@2026-10-14T09:19:45Z",
      "axis": "breakdown",
      "metric": "proposal_sampling",
      "unit": "s",
      "measurement": {
        "proposal_sampling": 0.21894529999826773
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "search-fit-exclusive-component-wall/components",
        "statistic": "median",
        "repetitions": 3,
        "warmup": "none; each repeat is a fresh fit (output removed, never a resume)",
        "synchronization": "none (numpy, single process)",
        "cache_state": "warm process: imports and first-touch costs fall in the first repeat"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T09:19:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage"
      },
      "evidence": {
        "path": "results/gaussian_x1/nautilus/breakdown.json",
        "fragment": "/components_s/proposal_sampling"
      }
    },
    {
      "id": "gaussian_x1/nautilus/search_fit/breakdown/likelihood",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "run_id": "gaussian_x1/nautilus/search_fit@2026-10-14T09:19:45Z",
      "axis": "breakdown",
      "metric": "likelihood",
      "unit": "s",
      "measurement": {
        "likelihood": 0.3219049000008454
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "search-fit-exclusive-component-wall/components",
        "statistic": "median",
        "repetitions": 3,
        "warmup": "none; each repeat is a fresh fit (output removed, never a resume)",
        "synchronization": "none (numpy, single process)",
        "cache_state": "warm process: imports and first-touch costs fall in the first repeat"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T09:19:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage"
      },
      "evidence": {
        "path": "results/gaussian_x1/nautilus/breakdown.json",
        "fragment": "/components_s/likelihood"
      }
    },
    {
      "id": "gaussian_x1/nautilus/search_fit/breakdown/checkpoint_io",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "run_id": "gaussian_x1/nautilus/search_fit@2026-10-14T09:19:45Z",
      "axis": "breakdown",
      "metric": "checkpoint_io",
      "unit": "s",
      "measurement": {
        "checkpoint_io": 7.0924251000005825
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "search-fit-exclusive-component-wall/components",
        "statistic": "median",
        "repetitions": 3,
        "warmup": "none; each repeat is a fresh fit (output removed, never a resume)",
        "synchronization": "none (numpy, single process)",
        "cache_state": "warm process: imports and first-touch costs fall in the first repeat"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T09:19:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage"
      },
      "evidence": {
        "path": "results/gaussian_x1/nautilus/breakdown.json",
        "fragment": "/components_s/checkpoint_io"
      }
    },
    {
      "id": "gaussian_x1/nautilus/search_fit/breakdown/sampler_bookkeeping",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "run_id": "gaussian_x1/nautilus/search_fit@2026-10-14T09:19:45Z",
      "axis": "breakdown",
      "metric": "sampler_bookkeeping",
      "unit": "s",
      "measurement": {
        "sampler_bookkeeping": 0.667890200003967
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "search-fit-exclusive-component-wall/components",
        "statistic": "median",
        "repetitions": 3,
        "warmup": "none; each repeat is a fresh fit (output removed, never a resume)",
        "synchronization": "none (numpy, single process)",
        "cache_state": "warm process: imports and first-touch costs fall in the first repeat"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T09:19:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage"
      },
      "evidence": {
        "path": "results/gaussian_x1/nautilus/breakdown.json",
        "fragment": "/components_s/sampler_bookkeeping"
      }
    },
    {
      "id": "gaussian_x1/nautilus/search_fit/breakdown/samples_output",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "run_id": "gaussian_x1/nautilus/search_fit@2026-10-14T09:19:45Z",
      "axis": "breakdown",
      "metric": "samples_output",
      "unit": "s",
      "measurement": {
        "samples_output": 0.48924609999903623
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "search-fit-exclusive-component-wall/components",
        "statistic": "median",
        "repetitions": 3,
        "warmup": "none; each repeat is a fresh fit (output removed, never a resume)",
        "synchronization": "none (numpy, single process)",
        "cache_state": "warm process: imports and first-touch costs fall in the first repeat"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T09:19:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage"
      },
      "evidence": {
        "path": "results/gaussian_x1/nautilus/breakdown.json",
        "fragment": "/components_s/samples_output"
      }
    },
    {
      "id": "gaussian_x1/nautilus/search_fit/breakdown/visualisation",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "run_id": "gaussian_x1/nautilus/search_fit@2026-10-14T09:19:45Z",
      "axis": "breakdown",
      "metric": "visualisation",
      "unit": "s",
      "measurement": {
        "visualisation": 1.1609661000002234
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "search-fit-exclusive-component-wall/components",
        "statistic": "median",
        "repetitions": 3,
        "warmup": "none; each repeat is a fresh fit (output removed, never a resume)",
        "synchronization": "none (numpy, single process)",
        "cache_state": "warm process: imports and first-touch costs fall in the first repeat"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T09:19:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage"
      },
      "evidence": {
        "path": "results/gaussian_x1/nautilus/breakdown.json",
        "fragment": "/components_s/visualisation"
      }
    },
    {
      "id": "gaussian_x1/nautilus/search_fit/breakdown/other",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "run_id": "gaussian_x1/nautilus/search_fit@2026-10-14T09:19:45Z",
      "axis": "breakdown",
      "metric": "other",
      "unit": "s",
      "measurement": {
        "other": 0.29422839999915595
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "search-fit-exclusive-component-wall/components",
        "statistic": "median",
        "repetitions": 3,
        "warmup": "none; each repeat is a fresh fit (output removed, never a resume)",
        "synchronization": "none (numpy, single process)",
        "cache_state": "warm process: imports and first-touch costs fall in the first repeat"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T09:19:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage"
      },
      "evidence": {
        "path": "results/gaussian_x1/nautilus/breakdown.json",
        "fragment": "/components_s/other"
      }
    },
    {
      "id": "gaussian_x1/nautilus/bare_sampler/runtime/wall",
      "setup_id": "gaussian_x1/nautilus/bare_sampler",
      "run_id": "gaussian_x1/nautilus/bare_sampler@2026-10-14T09:19:45Z",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "measurement": {
        "wall": 22.533835900000668
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "bare-sampler-exclusive-component-wall/wall",
        "statistic": "median",
        "repetitions": 3,
        "warmup": "none; each repeat is a fresh fit (output removed, never a resume)",
        "synchronization": "none (numpy, single process)",
        "cache_state": "warm process: imports and first-touch costs fall in the first repeat"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T09:19:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage"
      },
      "evidence": {
        "path": "results/gaussian_x1/nautilus/breakdown_bare_sampler.json",
        "fragment": "/wall_s"
      }
    },
    {
      "id": "gaussian_x1/nautilus/bare_sampler/breakdown/nn_training",
      "setup_id": "gaussian_x1/nautilus/bare_sampler",
      "run_id": "gaussian_x1/nautilus/bare_sampler@2026-10-14T09:19:45Z",
      "axis": "breakdown",
      "metric": "nn_training",
      "unit": "s",
      "measurement": {
        "nn_training": 12.11267449999832
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "bare-sampler-exclusive-component-wall/components",
        "statistic": "median",
        "repetitions": 3,
        "warmup": "none; each repeat is a fresh fit (output removed, never a resume)",
        "synchronization": "none (numpy, single process)",
        "cache_state": "warm process: imports and first-touch costs fall in the first repeat"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T09:19:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage"
      },
      "evidence": {
        "path": "results/gaussian_x1/nautilus/breakdown_bare_sampler.json",
        "fragment": "/components_s/nn_training"
      }
    },
    {
      "id": "gaussian_x1/nautilus/bare_sampler/breakdown/bound_geometry",
      "setup_id": "gaussian_x1/nautilus/bare_sampler",
      "run_id": "gaussian_x1/nautilus/bare_sampler@2026-10-14T09:19:45Z",
      "axis": "breakdown",
      "metric": "bound_geometry",
      "unit": "s",
      "measurement": {
        "bound_geometry": 5.800184900003842
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "bare-sampler-exclusive-component-wall/components",
        "statistic": "median",
        "repetitions": 3,
        "warmup": "none; each repeat is a fresh fit (output removed, never a resume)",
        "synchronization": "none (numpy, single process)",
        "cache_state": "warm process: imports and first-touch costs fall in the first repeat"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T09:19:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage"
      },
      "evidence": {
        "path": "results/gaussian_x1/nautilus/breakdown_bare_sampler.json",
        "fragment": "/components_s/bound_geometry"
      }
    },
    {
      "id": "gaussian_x1/nautilus/bare_sampler/breakdown/proposal_sampling",
      "setup_id": "gaussian_x1/nautilus/bare_sampler",
      "run_id": "gaussian_x1/nautilus/bare_sampler@2026-10-14T09:19:45Z",
      "axis": "breakdown",
      "metric": "proposal_sampling",
      "unit": "s",
      "measurement": {
        "proposal_sampling": 1.3069437999929505
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "bare-sampler-exclusive-component-wall/components",
        "statistic": "median",
        "repetitions": 3,
        "warmup": "none; each repeat is a fresh fit (output removed, never a resume)",
        "synchronization": "none (numpy, single process)",
        "cache_state": "warm process: imports and first-touch costs fall in the first repeat"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T09:19:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage"
      },
      "evidence": {
        "path": "results/gaussian_x1/nautilus/breakdown_bare_sampler.json",
        "fragment": "/components_s/proposal_sampling"
      }
    },
    {
      "id": "gaussian_x1/nautilus/bare_sampler/breakdown/likelihood",
      "setup_id": "gaussian_x1/nautilus/bare_sampler",
      "run_id": "gaussian_x1/nautilus/bare_sampler@2026-10-14T09:19:45Z",
      "axis": "breakdown",
      "metric": "likelihood",
      "unit": "s",
      "measurement": {
        "likelihood": 2.658846300001642
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "bare-sampler-exclusive-component-wall/components",
        "statistic": "median",
        "repetitions": 3,
        "warmup": "none; each repeat is a fresh fit (output removed, never a resume)",
        "synchronization": "none (numpy, single process)",
        "cache_state": "warm process: imports and first-touch costs fall in the first repeat"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T09:19:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage"
      },
      "evidence": {
        "path": "results/gaussian_x1/nautilus/breakdown_bare_sampler.json",
        "fragment": "/components_s/likelihood"
      }
    },
    {
      "id": "gaussian_x1/nautilus/bare_sampler/breakdown/sampler_bookkeeping",
      "setup_id": "gaussian_x1/nautilus/bare_sampler",
      "run_id": "gaussian_x1/nautilus/bare_sampler@2026-10-14T09:19:45Z",
      "axis": "breakdown",
      "metric": "sampler_bookkeeping",
      "unit": "s",
      "measurement": {
        "sampler_bookkeeping": 0.6964637999963088
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "bare-sampler-exclusive-component-wall/components",
        "statistic": "median",
        "repetitions": 3,
        "warmup": "none; each repeat is a fresh fit (output removed, never a resume)",
        "synchronization": "none (numpy, single process)",
        "cache_state": "warm process: imports and first-touch costs fall in the first repeat"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T09:19:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage"
      },
      "evidence": {
        "path": "results/gaussian_x1/nautilus/breakdown_bare_sampler.json",
        "fragment": "/components_s/sampler_bookkeeping"
      }
    },
    {
      "id": "gaussian_x1/nautilus/bare_sampler/breakdown/other",
      "setup_id": "gaussian_x1/nautilus/bare_sampler",
      "run_id": "gaussian_x1/nautilus/bare_sampler@2026-10-14T09:19:45Z",
      "axis": "breakdown",
      "metric": "other",
      "unit": "s",
      "measurement": {
        "other": 3.700000888784416e-06
      },
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "method": {
        "id": "bare-sampler-exclusive-component-wall/components",
        "statistic": "median",
        "repetitions": 3,
        "warmup": "none; each repeat is a fresh fit (output removed, never a resume)",
        "synchronization": "none (numpy, single process)",
        "cache_state": "warm process: imports and first-touch costs fall in the first repeat"
      },
      "provenance": {
        "host": "DESKTOP-H143S82",
        "measured_at": "2026-10-14T09:19:45Z",
        "has_provenance": true,
        "qualified": true
      },
      "validation": {
        "status": "unreviewed",
        "reason": "producer measurement on one laptop host; awaits the profiling conductor's triage"
      },
      "evidence": {
        "path": "results/gaussian_x1/nautilus/breakdown_bare_sampler.json",
        "fragment": "/components_s/other"
      }
    }
  ],
  "selections": [
    {
      "id": "select/analytic_gaussian/parity/seed0_n5/runtime/wall",
      "setup_id": "analytic_gaussian/parity/seed0_n5",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "method_id": "parity-script-subprocess-wall/wall",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "autofit_workspace_test": "26877bc69b4a0302f5be9106ec735bebf89d2a1a",
          "dynesty": "2.1.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "analytic_gaussian/parity/seed0_n5/runtime/wall",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/analytic_gaussian/parity/seed0_n5/memory/host_peak_rss",
      "setup_id": "analytic_gaussian/parity/seed0_n5",
      "axis": "memory",
      "metric": "host_peak_rss",
      "unit": "KiB",
      "method_id": "parity-script-subprocess-wall/peak_rss",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "autofit_workspace_test": "26877bc69b4a0302f5be9106ec735bebf89d2a1a",
          "dynesty": "2.1.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "analytic_gaussian/parity/seed0_n5/memory/host_peak_rss",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_1d_ep/ep/N10/runtime/wall",
      "setup_id": "gaussian_1d_ep/ep/N10",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "method_id": "fresh-process-single-fit/wall",
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_1d_ep/ep/N10/runtime/wall",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_1d_ep/ep/N10/memory/host_peak_rss",
      "setup_id": "gaussian_1d_ep/ep/N10",
      "axis": "memory",
      "metric": "host_peak_rss",
      "unit": "KiB",
      "method_id": "fresh-process-single-fit/peak_rss",
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_1d_ep/ep/N10/memory/host_peak_rss",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_1d_ep/ep/N3/runtime/wall",
      "setup_id": "gaussian_1d_ep/ep/N3",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "method_id": "fresh-process-single-fit/wall",
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_1d_ep/ep/N3/runtime/wall",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_1d_ep/ep/N3/memory/host_peak_rss",
      "setup_id": "gaussian_1d_ep/ep/N3",
      "axis": "memory",
      "metric": "host_peak_rss",
      "unit": "KiB",
      "method_id": "fresh-process-single-fit/peak_rss",
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_1d_ep/ep/N3/memory/host_peak_rss",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_1d_ep/ep/N30/runtime/wall",
      "setup_id": "gaussian_1d_ep/ep/N30",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "method_id": "fresh-process-single-fit/wall",
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_1d_ep/ep/N30/runtime/wall",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_1d_ep/ep/N30/memory/host_peak_rss",
      "setup_id": "gaussian_1d_ep/ep/N30",
      "axis": "memory",
      "metric": "host_peak_rss",
      "unit": "KiB",
      "method_id": "fresh-process-single-fit/peak_rss",
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_1d_ep/ep/N30/memory/host_peak_rss",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_1d_ep/graphical/N10/runtime/wall",
      "setup_id": "gaussian_1d_ep/graphical/N10",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "method_id": "fresh-process-single-fit/wall",
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_1d_ep/graphical/N10/runtime/wall",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_1d_ep/graphical/N10/memory/host_peak_rss",
      "setup_id": "gaussian_1d_ep/graphical/N10",
      "axis": "memory",
      "metric": "host_peak_rss",
      "unit": "KiB",
      "method_id": "fresh-process-single-fit/peak_rss",
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_1d_ep/graphical/N10/memory/host_peak_rss",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_1d_ep/graphical/N3/runtime/wall",
      "setup_id": "gaussian_1d_ep/graphical/N3",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "method_id": "fresh-process-single-fit/wall",
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_1d_ep/graphical/N3/runtime/wall",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_1d_ep/graphical/N3/memory/host_peak_rss",
      "setup_id": "gaussian_1d_ep/graphical/N3",
      "axis": "memory",
      "metric": "host_peak_rss",
      "unit": "KiB",
      "method_id": "fresh-process-single-fit/peak_rss",
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_1d_ep/graphical/N3/memory/host_peak_rss",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_1d_ep/graphical/N30/runtime/wall",
      "setup_id": "gaussian_1d_ep/graphical/N30",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "method_id": "fresh-process-single-fit/wall",
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_1d_ep/graphical/N30/runtime/wall",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_1d_ep/graphical/N30/memory/host_peak_rss",
      "setup_id": "gaussian_1d_ep/graphical/N30",
      "axis": "memory",
      "metric": "host_peak_rss",
      "unit": "KiB",
      "method_id": "fresh-process-single-fit/peak_rss",
      "identity": {
        "device": "cpu",
        "backend": "jax",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "df6d218f10cd75a7f0d79bb03dca5c131fd29d33",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "dynesty": "2.1.5",
          "jax": "0.10.2",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_1d_ep/graphical/N30/memory/host_peak_rss",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_x1/nautilus/search_fit/runtime/wall",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "method_id": "search-fit-exclusive-component-wall/wall",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_x1/nautilus/search_fit/runtime/wall",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_x1/nautilus/search_fit/breakdown/nn_training",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "axis": "breakdown",
      "metric": "nn_training",
      "unit": "s",
      "method_id": "search-fit-exclusive-component-wall/components",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_x1/nautilus/search_fit/breakdown/nn_training",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_x1/nautilus/search_fit/breakdown/bound_geometry",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "axis": "breakdown",
      "metric": "bound_geometry",
      "unit": "s",
      "method_id": "search-fit-exclusive-component-wall/components",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_x1/nautilus/search_fit/breakdown/bound_geometry",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_x1/nautilus/search_fit/breakdown/proposal_sampling",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "axis": "breakdown",
      "metric": "proposal_sampling",
      "unit": "s",
      "method_id": "search-fit-exclusive-component-wall/components",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_x1/nautilus/search_fit/breakdown/proposal_sampling",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_x1/nautilus/search_fit/breakdown/likelihood",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "axis": "breakdown",
      "metric": "likelihood",
      "unit": "s",
      "method_id": "search-fit-exclusive-component-wall/components",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_x1/nautilus/search_fit/breakdown/likelihood",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_x1/nautilus/search_fit/breakdown/checkpoint_io",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "axis": "breakdown",
      "metric": "checkpoint_io",
      "unit": "s",
      "method_id": "search-fit-exclusive-component-wall/components",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_x1/nautilus/search_fit/breakdown/checkpoint_io",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_x1/nautilus/search_fit/breakdown/sampler_bookkeeping",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "axis": "breakdown",
      "metric": "sampler_bookkeeping",
      "unit": "s",
      "method_id": "search-fit-exclusive-component-wall/components",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_x1/nautilus/search_fit/breakdown/sampler_bookkeeping",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_x1/nautilus/search_fit/breakdown/samples_output",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "axis": "breakdown",
      "metric": "samples_output",
      "unit": "s",
      "method_id": "search-fit-exclusive-component-wall/components",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_x1/nautilus/search_fit/breakdown/samples_output",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_x1/nautilus/search_fit/breakdown/visualisation",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "axis": "breakdown",
      "metric": "visualisation",
      "unit": "s",
      "method_id": "search-fit-exclusive-component-wall/components",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_x1/nautilus/search_fit/breakdown/visualisation",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_x1/nautilus/search_fit/breakdown/other",
      "setup_id": "gaussian_x1/nautilus/search_fit",
      "axis": "breakdown",
      "metric": "other",
      "unit": "s",
      "method_id": "search-fit-exclusive-component-wall/components",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_x1/nautilus/search_fit/breakdown/other",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_x1/nautilus/bare_sampler/runtime/wall",
      "setup_id": "gaussian_x1/nautilus/bare_sampler",
      "axis": "runtime",
      "metric": "wall",
      "unit": "s",
      "method_id": "bare-sampler-exclusive-component-wall/wall",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_x1/nautilus/bare_sampler/runtime/wall",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_x1/nautilus/bare_sampler/breakdown/nn_training",
      "setup_id": "gaussian_x1/nautilus/bare_sampler",
      "axis": "breakdown",
      "metric": "nn_training",
      "unit": "s",
      "method_id": "bare-sampler-exclusive-component-wall/components",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_x1/nautilus/bare_sampler/breakdown/nn_training",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_x1/nautilus/bare_sampler/breakdown/bound_geometry",
      "setup_id": "gaussian_x1/nautilus/bare_sampler",
      "axis": "breakdown",
      "metric": "bound_geometry",
      "unit": "s",
      "method_id": "bare-sampler-exclusive-component-wall/components",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_x1/nautilus/bare_sampler/breakdown/bound_geometry",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_x1/nautilus/bare_sampler/breakdown/proposal_sampling",
      "setup_id": "gaussian_x1/nautilus/bare_sampler",
      "axis": "breakdown",
      "metric": "proposal_sampling",
      "unit": "s",
      "method_id": "bare-sampler-exclusive-component-wall/components",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_x1/nautilus/bare_sampler/breakdown/proposal_sampling",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_x1/nautilus/bare_sampler/breakdown/likelihood",
      "setup_id": "gaussian_x1/nautilus/bare_sampler",
      "axis": "breakdown",
      "metric": "likelihood",
      "unit": "s",
      "method_id": "bare-sampler-exclusive-component-wall/components",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_x1/nautilus/bare_sampler/breakdown/likelihood",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_x1/nautilus/bare_sampler/breakdown/checkpoint_io",
      "setup_id": "gaussian_x1/nautilus/bare_sampler",
      "axis": "breakdown",
      "metric": "checkpoint_io",
      "unit": "s",
      "method_id": "bare-sampler-exclusive-component-wall/components",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "inapplicable",
      "record_id": null,
      "reason": "the bare sampler is run without a checkpoint file, so it writes none"
    },
    {
      "id": "select/gaussian_x1/nautilus/bare_sampler/breakdown/sampler_bookkeeping",
      "setup_id": "gaussian_x1/nautilus/bare_sampler",
      "axis": "breakdown",
      "metric": "sampler_bookkeeping",
      "unit": "s",
      "method_id": "bare-sampler-exclusive-component-wall/components",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_x1/nautilus/bare_sampler/breakdown/sampler_bookkeeping",
      "reason": "the cell's committed median row"
    },
    {
      "id": "select/gaussian_x1/nautilus/bare_sampler/breakdown/other",
      "setup_id": "gaussian_x1/nautilus/bare_sampler",
      "axis": "breakdown",
      "metric": "other",
      "unit": "s",
      "method_id": "bare-sampler-exclusive-component-wall/components",
      "identity": {
        "device": "cpu",
        "backend": "numpy",
        "precision": "float64",
        "library_version": "2026.10.12.1",
        "software": {
          "PyAutoFit": "911fe05e1c6b570df51789f0ab5b2cbf54c1f43a",
          "PyAutoNerves": "7f3055b7f3d1967f372bdb41ee732135bca0e68d",
          "nautilus-sampler": "1.0.5",
          "numpy": "2.2.6",
          "python": "3.12.10",
          "scikit-learn": "1.5.1",
          "scipy": "1.17.1"
        }
      },
      "host": "DESKTOP-H143S82",
      "status": "unreviewed",
      "record_id": "gaussian_x1/nautilus/bare_sampler/breakdown/other",
      "reason": "the cell's committed median row"
    }
  ],
  "hazards": [],
  "recommendations": [],
  "comparisons": [],
  "limitations": [
    "Laptop CPU only, pinned to one host (DESKTOP-H143S82, WSL2) so Pulse's same-host rule pairs every record; the epic's release-sweep pin (euclid-ral-gpu-2, an A100 node) does not fit CPU Dynesty runs. Cross-machine reproduction on RAL is a later campaign.",
    "Wall times vary up to \u00b140 % between sessions on this host, so breakdown shares are the comparable quantity, not seconds; the EP / graphical / parity rows are single fresh-process fits (repetitions 1).",
    "Component times are exclusive monkey-patched wall-clock intervals; 'other' is wall minus the instrumented total, not a measured phase.",
    "The EP / graphical rows carry a producer-side reproduction note against the committed autofit_workspace_developer baselines (runtime-drift-2x-1ms, in each row's `reference`); it is not a Pulse comparison, because those baselines recorded no host and no record pair exists.",
    "The N30 EP and graphical rows reproduce the committed sanity FAIL; their wall and memory are real measurements of a fit whose parameter recovery fails, not of a correct fit.",
    "Every record is unreviewed: the producer declares measurements, the Brain's profiling conductor judges them; nothing here is a verdict.",
    "No temporal comparisons: one baseline per setup."
  ]
}