icassp2027-experiment/manuscript/targeted/README.md

# Targeted ICASSP 2027 manuscript

This directory is an independent acceptance-target manuscript. It does not
modify or replace `../main/`.

## Positioning

The paper now starts from the egocentric conversational agent's when-to-speak
problem, positions it against 27 cited works in turn-taking, first-person
audio-visual conversation, active-speaker modeling, and streaming Omni
interaction, then studies two cutoff-aligned interfaces:

- **short-window encoder evidence (SWE)**: direct recent audio and optional
  person-crop visual encoder features alongside the frozen Omni readout;
- **partial-tail refresh (PTR)**: query only the observed prefix of the current
  two-second block at each 200-ms cutoff, reusing completed payloads.

SWE names the short temporal support of encoder evidence, not a shallow
network layer. The two-second chunk refers to this Qwen extraction setup,
not a universal Omni-model setting.

The evidence remains a causal global--local **audit**, not a claim that all
Omni models lack local perception or that PTR's independent gain is proven:

- global Omni context and recent audio are complementary across all horizons;
- most measured benefit is dense forecasting and wearer-offset anticipation;
- pooled and current-frame person vision do not establish speaker grounding;
- a three-seed causal oracle shows that timely visible-participant activity is
  informative, while identity continuity is not currently necessary.

The draft retains the remote SVA/TSVA terminology and four-method
EasyCom/Ego4D main table. The no-box TSVA and global-only chunk runs are
seed-0 exploratory screens; neither supplies matched visual-motion or PTR
evidence. Their saved records were checked in the L20 mounted repository.

The Results section also reports the archived 2026-08-24 sparse Thinker-LoRA
diagnostic as a separate historical screen. Its strict causal-valid mean mAP
declined under the recorded LoRA recipes, but the legacy feature/head contract
is not matched to the current G+A matrix, and the remote raw metrics and
checkpoints are unavailable here. It is not a Table 1 model ranking or proof
that LoRA cannot help this task.

No semantic ENTRY/YIELD, addressee, online-detector, or real-time-throughput
claim is made. The main EasyCom deployable matrix is single-seed and
exploratory. Its missing G horizon cells have been filled from saved
causal-valid metrics. Ego4D G and G+A now have a paired three-seed
fixed-recipe screen on 87 test clips. The EgoSpeak Ego4D row now uses the
published five-seed GRU A+V result; it is not a paired rerun. EasyCom SVA
has a four-epoch seed-0 screen. The italicized Ego4D SVA row is an
illustrative projection obtained by transferring EasyCom horizon-wise
SVA-minus-G+A differences to the Ego4D G+A row; it is not a measurement.
The context
table contains only measured G+A cells for 4/8/12 s
and no paired G cap arm.
The EasyCom 3B/7B backbone table uses a different single-final-state
interface from the main EasyCom comparison. Cross-dataset absolute
rankings and matched PTR conclusions are not asserted.

The six-group L/T/C/B/H-Q/S table remains in `main.tex` as an
**illustrative, unmeasured planning aid**, excluded from the page-limited
PDF. Its directional statements are hypotheses and falsifiers, not EasyCom
scores. Replace or remove every row after the corresponding experiment,
including results that contradict the working story.

## Build

```bash
cd manuscript/targeted
make
```

The editable sources are `main.tex`, `tables_compact.tex`, `references.bib`,
and `figures/system_overview_onecolumn.tex`. The earlier
`figures/task_overview.tex` is retained as unused source.
Generated LaTeX files are written to `build/`.

The preview targets four technical pages plus a reference-only fifth page.
The single-column method diagram (Fig. 1) has SWE on top and PTR below;
the earlier standalone task figure is not included.
The current PDF contains five numbered result tables. Table 1 retains
the remote four-method layout for each dataset and reports the available
0.2--2.0-s mAP curves. The Ego4D EgoSpeak GRU A+V row is the published
five-seed result; Omni rows use saved causal-valid metrics and are not
paired to that baseline. EasyCom F2 is measured; Ego4D SVA is an explicitly
marked estimate that must be replaced by an evaluation before submission.
Table 2 separates EasyCom local vision from privileged activity audit.
Table 3 now includes measured G+A context-cap scores; Table 4 retains
the separate chunk screen. Table 5 has the exploratory 3B/7B paired
audio comparison.
Active table layouts are in the tables_compact.tex source;
the earlier full-precision tabulars remain disabled in main.tex.

Figure 2 uses `figures/omni_case_selected_easycom_v2.pdf`, copied from the
mounted exploratory EasyCom case report. It shows two outcome-selected
0.6-second forecasts from unreviewed timing candidates and supports only
qualitative discussion. The single-column system figure is generated
from figures/system_overview_onecolumn.tex; the earlier full-width source
is retained for comparison.

The build uses the repository's ICASSP 2027 LaTeX assets in
`../ICASSP2027_Paper_Templates/`, selected by `latexmkrc`. The supplied
`spconf.sty` and `IEEEbib.bst` match the 2026 copies.

## Evidence sources

- `../../results/easycom_encoder_only_1s_4ep_2026-08-28/`
- `../../results/easycom_egospeak_three_level_eval_2026-09-16/`
- `../../results/easycom_omni_floor_screen_2026-09-16/`
- `../../results/easycom_oracle_pooled_wearer_audit_2026-09-10/`
- `../../results/easycom_sparse_supervision_vs_lora_2026-08-24/`
- `../../results/easycom_omni_lora_sparse_epoch2_2026-08-24/`
- `../../results/easycom_context_window_4_8_12_16_2026-09-24/`
- `../../results/easycom_omni_3b_7b_backbone_2026-09-24/`
- `../../results/ego4d_local_paired_audio_visual_2026-09-24/`
- `../../results/easycom_chunk200ms_vs_native2s_2026-09-24/`

The manuscript does not use superseded opportunity-conditioned ENTRY/INT
numbers. See `REVIEWER_REPORT.md` for the internal review loop and the remaining
scientific submission gates.