Remove release manifest bookkeeping

data/release_manifest.json

@@ -1,77 +0,0 @@
-{
-  "figure_set": "Figures 2-5 and Supplementary Figures 1-27",
-  "latent_coordinate_spaces": [
-    "per_session_whitened_reference_aligned_3d"
-  ],
-  "manuscript_working_version": "manuscript_v8",
-  "schema_version": 1,
-  "source": "paper/results, active consistency and feature-attribution artifacts, benchmark dataset arrays, and Figure 5 prediction sidecars",
-  "source_git_revision": "1779782610eeb1d09d7eec2a181a513e77ae5de3",
-  "source_repository": "https://github.com/TangLab-UBC/behavior_benchmarking",
-  "tables": {
-    "clean_prediction_summary.csv": {
-      "rows": 115,
-      "sha256": "7f91e3b06c3f9015dafecd8d3d33ad162a12eafb798728c8f8f179def93ab511"
-    },
-    "consistency_summary.csv": {
-      "rows": 54,
-      "sha256": "7039c0d38c288576e39ea6a1147a41eb2d395559b1d9b1de1b14eac3b3801b7f"
-    },
-    "dataset_example_neural.csv": {
-      "rows": 43110,
-      "sha256": "d42387c65325728657bb3aca12a54f4ca7df7ac225b765e4d0b5552a2e7eb815"
-    },
-    "dataset_example_targets.csv": {
-      "rows": 214,
-      "sha256": "e91f6bca5096ddd604ed53a69c2f258731c33001fb7daa9ee8339ea543650f5c"
-    },
-    "dataset_overview.csv": {
-      "rows": 5,
-      "sha256": "c8b616a738e033d63cac781c956349a135ce7970bf44ebeddfb7b51c002386bb"
-    },
-    "dataset_targets.csv": {
-      "rows": 72260,
-      "sha256": "13fb909fde8919ae9a9818b6fb81bfa8986f0d6bfa18fe7df4dc8432187dc3b4"
-    },
-    "feature_example_raster.csv": {
-      "rows": 1057,
-      "sha256": "8474b69e3857faf3235cef27324b147050c2c8d2709ce199d1aeb5a7e39bd5b6"
-    },
-    "latent_samples.csv": {
-      "rows": 31140,
-      "sha256": "bb484c47b78bd7a7d0a2bfea94296e726aa80034f87368b32302aaba0c5aa622"
-    },
-    "latent_trajectories.csv": {
-      "rows": 75040,
-      "sha256": "d15a19b50d7dbc517b4bf5de60a550fda6870327e5e59fb4a5ec37f01921abf5"
-    },
-    "neuron_attributions.csv": {
-      "rows": 21906,
-      "sha256": "bcab4237ad69c826a3dc54aeccbd3233422de3a41ecb9a982f4c78e47734487c"
-    },
-    "neuron_shap_summary.csv": {
-      "rows": 106,
-      "sha256": "19ab79da509e25b0d4c75cacbfd309319dc816831c93a17f9a50eb5a24985ff0"
-    },
-    "robustness_summary.csv": {
-      "rows": 115,
-      "sha256": "935381b401d26402c18bb4d32020169e63f8d081ba69fb7bbc594a4adebd6ca6"
-    },
-    "scalability_summary.csv": {
-      "rows": 115,
-      "sha256": "99921519a3af02ab660e8138c2089dd1ed781f0567fae0444349ae3bb62cf971"
-    },
-    "trial_historical_trajectories.csv": {
-      "rows": 4725,
-      "sha256": "605373599d4bd46c1379ab99b791bd82060544843be8eb880a9f9bcb523d1cda"
-    },
-    "trial_shapley_retrain_summary.csv": {
-      "rows": 99,
-      "sha256": "d2e38d7aff1cea5735d4766cb8a7612e7cc63fb1acbeb5e7b46be0dcf4ef87ad"
-    },
-    "trial_shapley_summary.csv": {
-      "rows": 81,
-      "sha256": "bba3435afa6a0e2755d30199e995f53bfa33df8b7200b066ea9b575d6125133b"
-    }
-  }
-}

validate_data.py

@@ -9,8 +9,6 @@ against ``paper/results`` in the main benchmark repository.
 from __future__ import annotations
 
 import argparse
-import hashlib
-import json
 from pathlib import Path
 from typing import Iterable
 
@@ -150,14 +148,6 @@ class ValidationError(RuntimeError):
     """Raised when Space data violates its manuscript-facing contract."""
 
 
-def _sha256(path: Path) -> str:
-    digest = hashlib.sha256()
-    with path.open("rb") as handle:
-        for chunk in iter(lambda: handle.read(1024 * 1024), b""):
-            digest.update(chunk)
-    return digest.hexdigest()
-
-
 def _active_mask(frame: pd.DataFrame) -> pd.Series:
     if "status" in frame.columns:
         return frame["status"].fillna("").eq("present")
@@ -274,57 +264,6 @@ def validate_local(data_dir: Path) -> dict[str, pd.DataFrame]:
             continue
         frames[name] = frame
 
-    manifest_path = data_dir / "release_manifest.json"
-    if not manifest_path.exists():
-        errors.append(f"missing release manifest: {manifest_path}")
-    else:
-        try:
-            manifest = json.loads(manifest_path.read_text(encoding="utf-8"))
-        except (json.JSONDecodeError, OSError) as exc:
-            errors.append(f"invalid release manifest: {exc}")
-            manifest = {}
-        if not isinstance(manifest, dict):
-            errors.append("invalid release manifest: top-level value must be an object")
-            manifest = {}
-        raw_manifest_spaces = manifest.get("latent_coordinate_spaces", [])
-        if not isinstance(raw_manifest_spaces, list):
-            errors.append("release manifest: latent_coordinate_spaces must be a list")
-            raw_manifest_spaces = []
-        elif not all(isinstance(value, str) for value in raw_manifest_spaces):
-            errors.append("release manifest: coordinate-space values must be strings")
-            raw_manifest_spaces = []
-        manifest_spaces = set(raw_manifest_spaces)
-        _require(
-            manifest_spaces == {LATENT_COORDINATE_SPACE},
-            f"release manifest: coordinate spaces {sorted(manifest_spaces)}",
-            errors,
-        )
-        manifest_tables = manifest.get("tables", {})
-        if not isinstance(manifest_tables, dict):
-            errors.append("release manifest: tables must be an object")
-            manifest_tables = {}
-        for name in REQUIRED_COLUMNS:
-            entry = manifest_tables.get(name)
-            if not isinstance(entry, dict):
-                errors.append(f"release manifest: missing table entry {name}")
-                continue
-            path = data_dir / name
-            if not path.exists():
-                continue
-            expected_hash = entry.get("sha256")
-            actual_hash = _sha256(path)
-            _require(
-                expected_hash == actual_hash,
-                f"release manifest: SHA-256 mismatch for {name}",
-                errors,
-            )
-            if name in frames:
-                _require(
-                    entry.get("rows") == len(frames[name]),
-                    f"release manifest: row-count mismatch for {name}",
-                    errors,
-                )
-
     for name, (n_rows, n_active) in EXPECTED_COVERAGE.items():
         if name not in frames:
             continue