Add causal oracle person information screen

local_turn_features.py

@@ -14,6 +14,7 @@ from typing import Any
 import torch
 
 LOCAL_FORMAT = "qwen-local-pooled-v1"
+ORACLE_FORMAT = "easycom-oracle-person-history-v1"
 MODALITIES = {"visual": ("visual",), "audio": ("audio",), "av": ("visual", "audio")}
 
 
@@ -277,12 +278,14 @@ def _load_validated_payload(
     dataset: str,
     modalities: str,
     expected_contract: dict[str, Any] | None,
+    oracle_analysis: bool = False,
 ) -> tuple[torch.Tensor, torch.Tensor, dict[str, Any], dict[str, Any], dict[str, Any]]:
     if modalities not in MODALITIES:
         raise ValueError(f"Unknown local modalities: {modalities}")
     times, indices = reference_alignment(reference)
     payload = torch.load(path, map_location="cpu", weights_only=False)
-    if not isinstance(payload, dict) or payload.get("format") != LOCAL_FORMAT:
+    expected_format = ORACLE_FORMAT if oracle_analysis else LOCAL_FORMAT
+    if not isinstance(payload, dict) or payload.get("format") != expected_format:
         raise ValueError(f"Invalid local feature format: {path}")
     if payload.get("sample_id") != sample_id or payload.get("dataset") != dataset:
         raise ValueError(f"Local sample/dataset mismatch: {path}")
@@ -295,9 +298,22 @@ def _load_validated_payload(
     if local_times.shape != times.shape or not torch.allclose(local_times, times, atol=1e-7, rtol=0):
         raise ValueError(f"Local times mismatch: {path}")
     config = payload.get("config", {})
-    if config.get("causal_policy") != "half-open-trailing-window" or config.get("uses_speech_labels") is not False:
+    if oracle_analysis:
+        if (
+            dataset != "easycom"
+            or config.get("causal_policy") != "fully-observed-half-open-5hz-bins"
+            or config.get("uses_speech_labels") is not True
+            or config.get("oracle_analysis") is not True
+        ):
+            raise ValueError(
+                f"Oracle features lack the explicit causal/oracle contract: {path}"
+            )
+    elif (
+        config.get("causal_policy") != "half-open-trailing-window"
+        or config.get("uses_speech_labels") is not False
+    ):
         raise ValueError(f"Local features lack the causal/no-speech-label contract: {path}")
-    contract = {"format": LOCAL_FORMAT, "modalities": modalities, "config": config}
+    contract = {"format": expected_format, "modalities": modalities, "config": config}
     if expected_contract is not None and contract != expected_contract:
         raise ValueError(f"Local encoder/pooling contract differs across sessions/checkpoint: {path}")
     return times, indices, payload, config, contract
@@ -348,6 +364,7 @@ def load_frame_set_features(
     dataset: str,
     expected_contract: dict[str, Any] | None = None,
     track_max_gap_seconds: float | None = None,
+    oracle_analysis: bool = False,
 ) -> tuple[torch.Tensor, FramePersonFeatures, dict[str, Any]]:
     """Load direct audio and the latest causal per-frame person set per 5 Hz row."""
 
@@ -358,6 +375,7 @@ def load_frame_set_features(
         dataset=dataset,
         modalities="av",
         expected_contract=expected_contract,
+        oracle_analysis=oracle_analysis,
     )
     audio = payload.get("audio")
     audio_valid = payload.get("audio_valid")