# STATE — Current snapshot

**Date**: 2026-05-12
**Active milestone**: Paper A v4.0 — Big-4 reframe
**Active branch**: `paper-a-v4-big4` (3 commits ahead of `yolo-signature-pipeline`)
**Active phase**: Phase 1 — Foundation: Big-4 subset script reruns (not yet started)

## Recently completed (preceding this milestone)

- Paper A v3.20.0 shipped to partner Jimmy 2026-04-27, DOCX `~/Downloads/Paper_A_IEEE_Access_Draft_v3.20.0_20260505.docx`
- Spike Scripts 32-35 (commits `e1d81e3` `8ac0988` `55f9f94`) confirming Big-4-only scope is methodologically superior:
  - Script 32: non-Firm-A calibration verdict C (negative, but with the bifurcation twist)
  - Script 33: reverse-anchor PAPER_C_STRONG (rho=+0.744 directional / -0.927 bifurcation)
  - Script 34: Big-4-only K=2 with dip-test multimodal p<0.0001, bootstrap CI [0.974, 0.977] / [3.48, 3.97]
  - Script 35: firm × cluster cross-tab — Firm A 0% C1 / 82.5% C3, PwC 23.5% C1

## Pending — Phase 1 entry

- [ ] Refactor scripts 19, 20, 21, 24, 25 to accept `--scope=big4|full` flag
- [ ] Define `reports/v4_big4/` output convention
- [ ] Decide whether to retire Script 32-35 spikes or keep as historical artifacts (recommend: keep, treated as "v4.0 origin evidence")

## Blockers

None.

## Open questions deferred from spike

- Bootstrap stability of cosine and dHash crossings *jointly* (not just marginally) — addressed in Phase 1 if time permits
- K=2 vs K=3 final choice for §III-J — both reported, but operational classifier needs to commit to one (recommend K=2 for interpretability; K=3 in supplementary)

## Things to remember (per memory)

- Provenance-verify all empirical claims against fresh sqlite/grep ([[feedback-provenance-fabrication]])
- Don't mock the DB or use placeholders — every number must trace to a script + query
- Partner Jimmy already proposed Big-4 direction (this is execution, not pitching a new direction)
- Paper C standalone is shelved — folded into v4.0 §IV-K