Add causal person track GRU residual experiment

README.md

@@ -1899,6 +1899,31 @@ acceptance rule using Sessions 1--3.  LLM-adjudicated candidates are deliberatel
 kept in a separate JSONL until pilot precision is accepted; they are not yet
 silently merged into the training arrays.
 
+## Anonymous person-track GRU residual
+
+The first person-temporal experiment is implemented as
+`--local-fusion track-gru-residual`. It preserves an exactly initialized
+`G+A+pooled-V` head and learns a zero-gated correction from shared causal GRU
+states over temporary person tracks. IDs route history only; they are not model
+inputs. Source-clip boundaries, gaps over the configured maximum and unknown
+IDs reset history. Existing local Qwen sidecars can be reused without
+re-extraction.
+
+Run the matched pooled/track development protocol with:
+
+```bash
+CUDA_VISIBLE_DEVICES=0 bash run_easycom_track_gru_residual.sh all 0
+```
+
+Use separate GPUs for additional seeds, then summarize the common result root
+with `summarize_local_baselines.py --paired-deltas`. After method selection is
+frozen, `bash run_easycom_track_gru_residual.sh test 0 1 2` evaluates the saved
+checkpoints once on Sessions 1--3. The exact causal contract,
+EgoSpeak code comparison, L20 smoke command and stopping rule are in
+[`docs/easycom_track_gru_residual.md`](docs/easycom_track_gru_residual.md).
+This is a frozen-backbone side branch, not an internal Thinker modification or
+an EgoSpeak MiniROAD reproduction.
+
 ## Candidate improvement: explicit working and long memory
 
 Motivated by EgoSpeak's separation of long-term and working memory, test an