Add manuscript-aligned EasyCom EOT INT review workflow

docs/README.md

@@ -33,6 +33,7 @@ tests.
 | [`easycom_oracle_information.md`](easycom_oracle_information.md) | Causal oracle per-person speaking-history upper bound and Session-12 screening commands |
 | [`easycom_competing_risk_floor_evaluation.md`](easycom_competing_risk_floor_evaluation.md) | Running and auditing the competing-risk entry/yield evaluator with training-side threshold calibration |
 | [`easycom_floor_event_diagnostics.md`](easycom_floor_event_diagnostics.md) | Separating boundary observability, event-objective mismatch and addressee information with remote commands |
+| [`easycom_event_review_tool.md`](easycom_event_review_tool.md) | Reviewing automatically mined EasyCom floor-event candidates against local video and transcripts |
 
 ## Design history and implementation options
 

docs/easycom_event_review_tool.md

@@ -0,0 +1,97 @@
+# EasyCom EOT/INT review workspace
+
+`review_floor_events.py` is a local annotation workspace for reviewing the
+manuscript-aligned regions produced by `prepare_easycom_eot_int_review.py`.
+It can also open the older timing/transcript proxy reports from
+`derive_easycom_interaction_events.py` and `audit_easycom_floor_events.py`, but
+those older reports do not have the directionality or hard-negative region
+contract required by the current manuscript. Raw EasyCom media stays read-only;
+human decisions are stored separately as JSONL and CSV.
+
+## Prepare manuscript-aligned candidates
+
+Develop the annotation guide on training-side Sessions 4--12:
+
+```bash
+python3 prepare_easycom_eot_int_review.py \
+  --dataset-root /path/to/easycom \
+  --sessions Session_4 Session_5 Session_6 Session_7 Session_8 Session_9 Session_10 Session_11 Session_12 \
+  --output-dir reports/easycom_floor_event_candidates
+```
+
+For a one-event pilot, add `--max-candidates 1`. The generator follows the
+manuscript direction exactly:
+
+- EOT-response begins at an aggregate-other offset while the wearer is silent.
+- INT-yield begins at an aggregate-other onset while the wearer is active.
+- An observed wearer transition before the competing other transition is a
+  timing-positive candidate.
+- A competing other transition, or a fully observed no-transition window, is a
+  timing hard-negative candidate.
+- A source boundary without a complete outcome/window is marked for exclusion.
+
+Automatic labels remain candidates until independent human semantic review.
+
+## Optional DeepSeek suggestion
+
+DeepSeek suggestions are triage metadata and never count as a human label. The
+script sends only the candidate transcript excerpt and timing fields. Inspect
+the exact request without network access first:
+
+```bash
+python3 adjudicate_easycom_eot_int_candidates.py \
+  --input reports/easycom_floor_event_candidates/easycom_eot_int_candidates.jsonl \
+  --output reports/easycom_floor_event_candidates/easycom_eot_int_deepseek.jsonl \
+  --model deepseek-v4-flash \
+  --max-events 1 \
+  --dry-run
+```
+
+After setting `DEEPSEEK_API_KEY`, make the authorized request:
+
+```bash
+python3 adjudicate_easycom_eot_int_candidates.py \
+  --input reports/easycom_floor_event_candidates/easycom_eot_int_candidates.jsonl \
+  --output reports/easycom_floor_event_candidates/easycom_eot_int_deepseek.jsonl \
+  --model deepseek-v4-flash \
+  --max-events 1 \
+  --allow-external-transcript-upload
+```
+
+Point the review server at the DeepSeek-enriched JSONL to show its suggestion
+beside the video. Keep suggestions hidden from an initial independent human
+pass if anchoring bias is a concern.
+
+## Start the local workspace
+
+```bash
+python3 review_floor_events.py \
+  --dataset-root /path/to/easycom \
+  --events reports/easycom_floor_event_candidates/easycom_eot_int_candidates.jsonl \
+  --output reports/easycom_event_reviews/reviewer_1.jsonl
+```
+
+Open `http://127.0.0.1:8765`. The page resolves the source MP4 and transcript,
+seeks to a six-second event context, and supports session/split/task/status
+filtering.
+
+Each save atomically rewrites both JSONL and CSV. The review explicitly records
+`positive`, `hard_negative`, `exclude`, or `uncertain`; the hard-negative
+subtype; boundary validity; onset function; conversational routing; offset
+outcome; three 200 ms anchor/region corrections; confidence; and reviewer ID.
+
+## Freeze discipline
+
+Develop the annotation guide and resolve category disagreements on training
+Sessions 4--12. Freeze the guide before reviewing official test Sessions 1--3.
+Do not use test reviews to change candidate windows, label categories, or the
+R=.8 threshold calibration rule.
+
+For paper-quality labels, use two independent reviewers with separate
+`--output` files and adjudicate disagreements in a third output. A non-empty
+reviewer ID is required on every saved row. DeepSeek is not one of the two
+reviewers.
+
+This workspace produces audited labels. It does not yet convert them into the
+final committed-event matching metrics; that integration follows only after
+the schema and real-data pilot are frozen.