Add targeted ICASSP manuscript draft

manuscript/targeted/REVIEWER_REPORT.md

@@ -0,0 +1,87 @@
+# Internal ICASSP-style review loop
+
+## Review 1: reject in original method framing
+
+**Main concerns**
+
+1. The novelty claim was too broad. EgoSpeak already defines egocentric
+   when-to-speak prediction, while MuVAP, AV-CONV, and 3M-Transformer cover
+   adjacent multiparty audiovisual structure.
+2. The learned visual method did not support the intended speaker-grounding
+   claim. Pooled vision gave only `+0.291` mean-mAP points over `G+A`, and the
+   current-frame person-set screen did not exceed the historical pooled row.
+3. Dense mAP, raw endpoint AP, and semantic floor events were conflated.
+4. Planned tail, context, transfer, and behavior experiments occupied too much
+   of a four-page argument despite being unmeasured.
+
+**Revision**
+
+The paper was reframed from a successful visual adapter to a causal
+global--local evidence audit. The claim is now that recent audio and global
+context are complementary, while generic visual access remains insufficient.
+All semantic event numbers and planned cross-backbone claims were removed.
+
+## Review 2: weak reject after reframing
+
+**Strengths**
+
+- Clear task asymmetry: visible interlocutors condition prediction of an
+  invisible wearer.
+- Strict causal cutoff and fixed 5-Hz / ten-horizon contract.
+- A coherent positive result for `G+A`, especially wearer-offset anticipation.
+- An unusually informative negative result: visible-activity labels help, but
+  current generic visual features do not recover that signal.
+- Oracle controls distinguish visibility, timeliness, aggregation, and
+  identity continuity.
+
+**Remaining concerns**
+
+1. The deployable main comparison is single seed; only the oracle has three
+   seeds.
+2. Sessions 1--3 have been inspected repeatedly, so the current matrix is not
+   a clean confirmatory test.
+3. `G+A` changes history, feature access, and trainable capacity relative to
+   `A` or `G`; a matched wider/temporal control is missing.
+4. Raw onset/offset AP is not a one-event-one-vote behavioral metric.
+5. Checkpoint hashes, common valid-pair counts, and original predictions are
+   not all archived on this host.
+
+**Revision**
+
+The abstract and results now identify single-seed versus three-seed evidence,
+avoid significance language, separate endpoint diagnostics from events, and
+state the capacity/history confound. The main paper no longer claims reduced
+false entry, semantic yield, speaker identity, or real-time throughput.
+
+## Review 3: current verdict
+
+**Score: 5/10, borderline, structurally ready but not yet confirmatory.**
+
+The manuscript is substantially clearer and more defensible than a paper that
+claims a successful visual grounding method. Its strongest publishable insight
+is the controlled mismatch between oracle information value and learned visual
+access. However, writing quality cannot replace the missing confirmatory
+evidence. Calling the current artifact "accepted-paper ready" would overstate
+the science.
+
+## Minimum gates for a credible accept recommendation
+
+1. Re-run `A`, `G`, `G+A`, and the selected visual condition for seeds 0/1/2
+   under one frozen recipe and common valid pairs; archive predictions,
+   checkpoint/config hashes, per-session values, and trainable parameter counts.
+2. Add a parameter- and history-matched control. The central `G+A` gain must
+   remain larger than seed variance and the matched-capacity alternative.
+3. Run the corrected competing-risk evaluator with training-side calibration,
+   manually audit real timelines, and report matched-recall false-entry and
+   false-stop rates only if denominators and invalid counts agree.
+4. If visual grounding remains a contribution, replace generic pooling with a
+   causal active-speaker/floor estimator and require correct-time evidence to
+   beat delayed, removed, and capacity-matched controls. Otherwise retain the
+   honest audio-local paper and remove visual-method language.
+5. Rebuild with the official 2027 kit, keep technical content within four
+   pages, put only references on an optional fifth page, and retain the IEEE
+   AI-assisted drafting disclosure.
+
+Passing gates 1--3 would support a solid ICASSP empirical paper. Passing gate
+4 with a meaningful matched-recall behavior gain would support the stronger
+method paper originally envisioned.