6781c00d5b75b127d6de618eac15497d42523494
5
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
  gbanyanandClaude Opus 4.8
|
6781c00d5b |
Paper A v13 rev9.2: firm-key unification + canonical-number reconciliation (rev9.1 review R1-R6)
Resolve the Firm C/D "two-snapshot" inconsistency from the co-author rev9.1 review. Root cause was NOT stale data but two live firm-assignment keys (assigned_accountant-> registry firm vs the excel_firm column) used inconsistently across tables; standardize on the registry key, which the headline Table IV/II-b already use. Sole difference = 379 signatures with excel_firm=C but registry firm=D; A and B identical under both keys. Numbers (all DB-verified, registry key, n=150,442): - Table II-c Firm C/D recomputed (was mixing keys within firm C across periods, which manufactured the spurious "third value" 38,934); now C 22,449+16,164=38,613, D 9,945+7,188=17,133, all four firms reconcile. - Table VI C/D counts + S III-B prose + Fig 3/6 captions -> 150,442. - S V-B HC-rate text -> Firm C 21.6->26.7%, Firm D 22.0->28.0%. Note on R4: the reviewer (PDF-only) asked to change S IV-C to 26.5/28.5 to match Table II-c; DB verification showed the reverse - S IV-C's 26.7/28.0 are correct and Table II-c was the stale outlier, so II-c was aligned to S IV-C (data-correct, opposite to the literal instruction). Accountant counts (R2 reviewer "179>171 impossible" = false positive; three distinct, all-reproducible universes): Table I + S III-B -> 457 (>=2 sig, owns the 150,442 signatures); Table III documented as the 437 with >=10 signatures (K=3 GMM subset, reproduces A=82.5/B=0.0/C=1.0/D=1.9% exactly); bootstrap 179/280 unchanged (accountant_id key, correct and invariant to the A-vs-BCD contrast). R3 (corpus scope): S III-B reworded - corpus = all retrievable reports, Big-4 as the primary analysis sample (removes the "corpus = four firms" vs "non-Big-4 in robustness" contradiction); per-firm counts now explicitly labelled A/B/C/D. R5 (spelling): unify to American (artefact->artifact x11, centred->centered, behaviour->behavior, analyse(d)->analyze(d), favours->favors). R6: delete non-standard "(+)" marker in S IV-C. Figures regenerated under the registry key: make_fig3_density.py and make_fig6_sensitivity.py switched to the assigned_accountant join (fig3/fig6 n=150,442); fig4/fig5 refreshed. FE/LOYO/bootstrap re-validated exactly (ORs 0.116/0.061/0.070, LOYO 53.1-54.9pp, full 53.7pp). Add CANONICAL_NUMBERS_rev9.1.md with full provenance, the analyzable/GMM definitions, and the firm-key root cause. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01K35dXhb9XEM1mnYz6SSHpU |
||
|
gbanyanandClaude Opus 4.8
|
2a13f0d985 |
Paper A v13 rev9.1: HC-meaning + same-pair table + interview/framing rebalance, plus typesetting polish
Respond to a second hostile GPT-5.5 reviewer pass on rev9. Four substantive changes plus accumulated typesetting polish. Reviewer points addressed: - HC != reuse (Fatal 1): new Sec III-F "What HC Means and Does Not Mean" states plainly that HC denotes an extreme within-accountant repetition pattern that is rare between unrelated accountants, not a reuse label; reuse is one interpretation, carried at Firm A by byte-identity + context, never implied by HC alone; no reuse claim is made for Firms B/C/D. - Any-pair construction (Fatal 2): new Table VI gives the per-signature HC flag rate by firm under the deployed any-pair rule vs the strict same-pair rule (cosine and dHash from the same partner). Same-pair lowers all rates but widens the firm gap: Firm A 57.3% vs baseline 5-9%, ratio 2.4-3.4x -> 6.4-10.8x, so the HC region is not an artefact of combining extrema from different pairs. Reproducible via samepair_hc.py (Hamming on stored dHash vectors). - Interviews (Fatal 3): Sec III-A now states the interviews are used only to contextualize, are corroborative not confirmatory and not independently reproducible; their one load-bearing use (Firm A as known-positive benchmark) lowers rather than raises the claim. Empirical claims rest on calibration + byte-identity, which stand without them. - Framing (Fatal 4, rebalance not relabel): contribution 3 elevated to the methodological core (label-free construction/characterization of an operating point without labels), explicitly demonstrated/stress-tested on audit signatures "rather than a finished, fully general framework." The audit finding is kept as a headline result, not demoted to a mere case study, and no general-framework claim is made. Typesetting polish (verified by rendering pages to images): - Unify scientific notation in Table II ([4x10^-6, 2.3x10^-5]). - Tighten Table II row labels to cut excessive wrapping (3 lines -> 2). - Fix duplicated figure captions (empty image alt-text so pandoc no longer auto-captions on top of the hand-written caption); unify caption punctuation. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Qn59FdF9JMyfFg3sjcUNNG |
||
|
gbanyanandClaude Opus 4.8
|
cb38d413ad |
Paper A v13 rev9: sensitivity surface + honesty fixes (GPT-5.5 hostile review)
Pre-emptively address the three residual points from a hostile GPT-5.5 reviewer pass that rev8 had not fully closed (the rest of that review matched the already-applied fusion revision): - Sensitivity surface (Major 5): new Figure 6 maps the deployed rule over the full (cosine cut x dHash cut) plane - clean-group flag rate and the Firm A-minus-B/C/D contrast. Shows no cliff at (0.95, dHash<=5), contrast >45pp across a broad region (58pp at 0.97/dHash<=3), and that extending to the MC bound (dHash<=15) halves the contrast - so the thresholds are not cherry-picked and the weaker MC band is shown, not hidden. Reproducible via make_fig6_sensitivity.py (DB columns only). - Soften "reuse-dominated" (Major 1): the assertion that Firm A "is" a reuse-dominated population now reads "behaves in the screen as," explicitly resting on interviews + byte-identity rather than per-signature ground truth; two other uses made conditional/generic. - Shared-pipeline contamination of ICCR (Major 2): Sec III-E now names the shared within-firm imaging pipeline (scanners, PDF assembly, red-stamp removal) as a channel that can lift the inter-CPA rate above true chance, distinct from "shared template," supported by the Sec V-B pipeline audit; bias direction (higher floor) keeps the Firm-A contrast conservative. rev9 docx rebuilt (6 figures embedded). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Qn59FdF9JMyfFg3sjcUNNG |
||
|
gbanyanandClaude Opus 4.8
|
da455791de |
Paper A v13 rev8: fusion-review revision (29 items) + verified data analysis
Address all 29 items from the fused reviewer report (Gemini 3.1 Pro + ChatGPT 5.5 + Opus 4.8): 3 fatal, 4 severe, arbitration A/B, 5 fusion-new, 15 minor. All new numbers computed from signature_analysis.db; nothing fabricated. Claim honesty (F1/F3/F4/F7/G3): - Retract all "139x the floor" comparisons; ICCR -> between-accountant specificity proxy throughout; state within-accountant FPR is not estimable and ICCR is not even a bound (anti-conservative direction). - Firm A reframed as quasi-positive known-positive benchmark (not blinded). - byte-identity recast as prevalence signal, not a recall/sanity check. - tunable -> single-direction conservativeness dial (no P-R frontier). New data analysis (verified, bit-reproducible via committed scripts): - F2/G1 (Sec V-B): 880-PDF imaging-pipeline audit (Table V) - plain scans 82% (2013) -> 1% (2021); producer strings name scanner hardware (Fuji Xerox D125 etc.); substrate transforms at 2020/21 = named confound. - F5 (Sec IV-C): four robustness checks - pool-size stratification, accountant-clustered bootstrap (gap 53.7pp [49.5,57.5]), firm+year FE logistic (B/C/D OR 0.06-0.12), leave-one-year-out (gap 53.1-54.9pp). - byte-identity era split: 30 scan-era (18 Firm A, pipeline-robust) vs 232 digital-era (detectability-inflated, hedged). - G5: archive-wide 888 expected chance HC flags [677,1098]. - M4: Figure 3 replaced with real 2D density (n=150,441). Structure/minor: abstract restructured (M1); operational definition (M2); interview disclaimer (M3); Threats to Validity subsection (M8); review protocol framed as design not evidence (M9); N reconciliations (M10/M11); Table II-c 2020-23 five-way (M12); Section refs, American spelling, notation table (M5/M13/M15); reference URLs verified (M14). Open (author-only): placeholders (M13), II-b/IV table merge (M15). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Qn59FdF9JMyfFg3sjcUNNG |
||
|
gbanyanandClaude Opus 4.8
|
66c9194fcf |
Paper A v13: filled submission draft (rev7) + reproducible build bundle
Fill all 18 placeholders in the condensed v13 submission draft with data verified against the analysis DB and LOCKED canonical scripts; close 12/13 co-author review items (only #8b protocol first-run open). Key changes (need co-author sign-off; see handoff doc): - Firm A out-of-sample HC 0.01% -> 0.42% (buggy 0.0001 from Script 49 same-pair bug, propagated v4.2->v13; never reuse 0.0001) - §III-D empty cell ~=0 -> 7,681 honest reframe (not degenerate crops) - low cosine cut 0.837 -> 0.8547 primary (BCD 2013-2019 closed-world, held-out discipline; 0.8489 confirmed = BCD all-period); HC/MC/HSC unchanged, UN/LH move <=0.4pp Adds Figures 1-5 (real-data plots + schematics), full references, Appendix A/B, UN/HSC ICCR, n-reconciliation, #13 MOPS-metadata survival verification, "參" set-level feasibility probe (negative). Two codex (gpt-5.5) adversarial rounds applied; no fabrication found. Bundle: paper/v13_build/ (markdown source, harvest/figure scripts, figures) for reproducibility. Handoff note for co-author included. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |