Add causal person track GRU residual experiment

PROJECT_CONTEXT.md

@@ -43,17 +43,27 @@ result.
 - Ego4D batch and 8-GPU local-feature launchers, with strict frame audits.
 - Timing-derived wearer floor-state and event diagnostics.
 
+### Measured screening result
+
+- F1 Frame-set Attention uses fused G+A as one query over the latest half-open
+  causal person set. On the existing three-seed, four-epoch test screen it
+  obtained `81.77745 +/- 0.15638` 0.2-second mAP and
+  `64.95099 +/- 0.09451` ten-horizon mean mAP. This is stable, but is not a
+  matched improvement over the historical no-dev pooled result; correct/wrong
+  visual controls remain missing.
+
 ### Implemented, awaiting remote runtime verification
 
-- F1 Frame-set Attention loader/head/train/infer path. It uses fused G+A as
-  one query over the latest half-open causal person set, retains direct A in
-  the head, and dynamically pads people per batch. Do not report it as a
-  measured method until the L20 smoke and full controls pass.
 - Two current-sidecar screening controls: `audio-person-frame-set` adds a
   zero-gated audio-to-person read before the F1 query, and
   `gated-person-state-adapter` adds a zero-gated person residual after the
   frozen Thinker readout. They are explicitly recorded as F5/F6 screening,
   not full history-conditioned F5 or an internal Thinker F6 adapter.
+- `track-gru-residual` builds strictly causal histories from anonymous provided
+  track IDs, applies one shared GRU per track, lets G+A query current track
+  states, and adds a zero-gated correction to an exactly initialized pooled
+  `G+A+V` checkpoint. See
+  [`docs/easycom_track_gru_residual.md`](docs/easycom_track_gru_residual.md).
 
 ### Current blocker
 
@@ -69,12 +79,17 @@ semantic event ground truth.
 
 ### Next experiment gates
 
+The user has temporarily chosen to run the dense-AP model screen while P0 is
+unfinished. This does not relax the paper claim: event numbers remain proxy
+diagnostics until competing-risk censoring is fixed.
+
 1. **P0:** fix/freeze event attribution, splits and scenario definitions.
 2. **P1:** probe aggregate activity and per-person active-speaker grounding;
    compare correct, wrong-person and time-shifted visual inputs.
 3. **P2:** re-evaluate `G`, `G+A`, `G+A+pooled-V` under the frozen event protocol.
-4. **P3:** begin the progressive person-fusion route with Frame-set Attention,
-   then add spatial or track-temporal structure only after its controls pass.
+4. **P3:** run the matched pooled/anonymous-track-GRU residual screen, then add
+   broken-ID, wrong-time and remove-person controls before claiming that track
+   continuity matters.
 5. **P4:** attempt person-memory adapter/Thinker LoRA only if P1/P3 pass.
 
 The detailed architecture, controls and stopping gates for P3 are frozen in
@@ -227,6 +242,7 @@ Do not reorganize them physically without compatibility wrappers.
 | `infer_turn_head.py` | Save EgoSpeak-compatible predictions and AP/mAP |
 | `evaluate_floor_state_changes.py` | CPU floor-state/event proxy evaluation |
 | `summarize_local_baselines.py` | Aggregate local baseline `metrics.json` files |
+| `run_easycom_track_gru_residual.sh` | Matched pooled and anonymous track-GRU training/inference launcher |
 | `train_omni_turn_lora.py` | Thinker LoRA training from cached AV |
 | `eval_omni_turn_lora.py` | Thinker LoRA evaluation |