1 files changed, 190 insertions, 0 deletions
diff --git a/worldalign/split_half.py b/worldalign/split_half.py
new file mode 100644
index 0000000..ee3f273
--- /dev/null
+++ b/worldalign/split_half.py
@@ -0,0 +1,190 @@
+"""The ceiling nobody measured: can a modality identify a scene against itself?
+
+Every deficit so far has been read as a cross-modal one, and that assumed each
+side describes its scenes well enough to identify them. Nothing tested the
+assumption. Split each scene's parts into two disjoint halves -- odd and even
+regions, odd and even segments -- build a relation field from each half, and
+match the halves against each other with the anchor bound. Both halves come
+from the same modality and the same scene, so any failure is that modality
+failing to pin down its own scenes.
+
+This upper-bounds anything cross-modal. If one half of an image's description
+cannot pick that image out from among the others given the other half, no
+vision encoder can be blamed for failing to, and no better cross-modal recipe
+exists to find. It costs one pass over data already on disk, and it should have
+been the first measurement on natural data rather than one of the last.
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+import re
+from pathlib import Path
+
+import numpy as np
+import torch
+import torch.nn.functional as F
+from scipy.optimize import linear_sum_assignment
+
+from .common import seed_everything, write_json
+from .natural_families import load_phrases
+from .natural_pipeline import content_directions, word_vectors
+from .synth_cc_battery import moment_field
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--vg-dir", default="artifacts/vg_5k")
+    parser.add_argument("--objects", default="artifacts/vg_5k/nobj_base_gpu.pt")
+    parser.add_argument("--samples", type=int, default=256)
+    parser.add_argument("--fit-scenes", type=int, default=1200)
+    parser.add_argument("--word-vectors", type=int, default=128)
+    parser.add_argument("--min-count", type=int, default=60)
+    parser.add_argument("--max-vocabulary", type=int, default=600)
+    parser.add_argument("--context-window", type=int, default=2)
+    parser.add_argument("--keep", type=int, default=64)
+    parser.add_argument("--shrinkage", type=float, default=0.05)
+    parser.add_argument("--weight-power", type=float, default=0.5)
+    parser.add_argument("--seed", type=int, default=0)
+    parser.add_argument("--output", default="artifacts/vg_5k/split_half.json")
+    return parser.parse_args()
+
+
+def standardise(matrix: np.ndarray) -> np.ndarray:
+    values = matrix[~np.eye(len(matrix), dtype=bool)]
+    out = (matrix - values.mean()) / values.std()
+    np.fill_diagonal(out, 0.0)
+    return out
+
+
+def anchor_bound(first: np.ndarray, second: np.ndarray, repeats: int = 5) -> float:
+    size = len(first)
+    scores = []
+    for repeat in range(repeats):
+        generator = np.random.default_rng(repeat)
+        order = generator.permutation(size)
+        half = size // 2
+        anchors, probe = order[:half], order[half:]
+
+        def profile(field):
+            block = field[np.ix_(probe, anchors)]
+            block = block - block.mean(1, keepdims=True)
+            return block / block.std(1, keepdims=True).clip(1e-9)
+
+        similarity = profile(first) @ profile(second).T / half
+        _, columns = linear_sum_assignment(-similarity)
+        scores.append(float((columns == np.arange(len(probe))).mean()))
+    return float(np.mean(scores))
+
+
+def build_field(sets, fitted, keep, power) -> torch.Tensor:
+    centre, basis, values = fitted
+    width = min(keep, basis.shape[1])
+    scale = values[:width] ** power if power else 1.0
+    projected = [
+        F.normalize(
+            torch.tensor((item - centre) @ basis[:, :width] * scale, dtype=torch.float32),
+            dim=-1,
+        )
+        for item in sets
+    ]
+    return moment_field(projected)
+
+
+def main() -> None:
+    args = parse_args()
+    seed_everything(args.seed)
+    vg_dir = Path(args.vg_dir)
+    truth = [
+        json.loads(line)
+        for line in (vg_dir / "ground_truth.private.jsonl").read_text(encoding="utf-8").splitlines()
+        if line.strip()
+    ]
+    records = {
+        json.loads(line)["node_id"]: json.loads(line)
+        for line in (vg_dir / "text_nodes.jsonl").read_text(encoding="utf-8").splitlines()
+        if line.strip()
+    }
+    state = torch.load(args.objects, map_location="cpu", weights_only=False)
+    index = {node: position for position, node in enumerate(state["node_ids"])}
+    vectors = word_vectors(load_phrases(vg_dir / "text_nodes.jsonl", "region_closed"), args)
+
+    def text_parts(node):
+        rows = []
+        for phrase in records[node]["region_closed"]:
+            hits = [vectors[t] for t in re.findall(r"[a-z]+", phrase.lower()) if t in vectors]
+            if hits:
+                rows.append(np.mean(hits, axis=0))
+        return rows
+
+    def vision_parts(node):
+        return [s["feature"].astype(np.float64) for s in state["segments"][index[node]]]
+
+    pairs = [p for p in truth if p["vision_node_id"] in index and p["text_node_id"] in records]
+
+    def collect(getter, key, rows, minimum):
+        out = []
+        for pair in rows:
+            parts = getter(pair[key])
+            out.append(np.stack(parts) if len(parts) >= minimum else None)
+        return out
+
+    results = {}
+    for name, getter, key in (
+        ("text", text_parts, "text_node_id"),
+        ("vision", vision_parts, "vision_node_id"),
+    ):
+        fit_rows = pairs[args.samples : args.samples + args.fit_scenes]
+        fit = [x for x in collect(getter, key, fit_rows, 2) if x is not None]
+        fitted = content_directions(fit, args.shrinkage)
+
+        evaluated, first_half, second_half = [], [], []
+        for pair in pairs[: args.samples]:
+            parts = getter(pair[key])
+            if len(parts) < 4:
+                continue
+            stacked = np.stack(parts)
+            evaluated.append(pair)
+            first_half.append(stacked[0::2])
+            second_half.append(stacked[1::2])
+
+        field_a = standardise(
+            build_field(first_half, fitted, args.keep, args.weight_power).double().numpy()
+        )
+        field_b = standardise(
+            build_field(second_half, fitted, args.keep, args.weight_power).double().numpy()
+        )
+        mask = ~np.eye(len(evaluated), dtype=bool)
+        results[name] = {
+            "scenes": len(evaluated),
+            "mean_parts": float(np.mean([len(getter(p[key])) for p in evaluated])),
+            "split_half_correlation": float(
+                np.corrcoef(field_a[mask], field_b[mask])[0, 1]
+            ),
+            "split_half_anchor_bound": anchor_bound(field_a, field_b),
+        }
+        print(
+            f"{name:<7} scenes={results[name]['scenes']:4d} "
+            f"parts={results[name]['mean_parts']:5.1f}  "
+            f"rho={results[name]['split_half_correlation']:.3f}  "
+            f"self-identification bound={results[name]['split_half_anchor_bound']:.3f}",
+            flush=True,
+        )
+
+    summary = {
+        "protocol": (
+            "Each scene's parts split into disjoint halves within one modality; "
+            "a relation field is built from each half and the two are matched by "
+            "the anchor bound. Both halves describe the same scenes, so this "
+            "upper-bounds any cross-modal result."
+        ),
+        "results": results,
+        "cross_modal_bound_for_reference": 0.291,
+    }
+    print(json.dumps(summary["results"]))
+    write_json(args.output, summary)
+
+
+if __name__ == "__main__":
+    main()