Audit infrastructure
For external methodology changes filed after 2026-04-25, Convexly pre-registers hypotheses on AsPredicted before any analysis runs. The verdict + run date + effect-size CI are reported within 24 hours of the test running. The original V1 and V1-M papers were not retroactively pre-registered; they remain frozen-coefficient methodology with ex-ante version-controlled commitment via the SHA-256 audit chain. Failed pre-registrations land in the negative-result registry; the audit chain is verifiable in your browser at /research/verify.
Machine-readable manifest at /research/preregistrations.json.
Last updated 2026-05-01T18:00:00Z.8 entries
AsPredicted #287368
Filed 2026-04-25 · Ran 2026-04-27
E2 per-wallet temporal holdout: ρ = +0.111 [+0.046, +0.175], well below the +0.30 pre-reg threshold. E7 per-quarter IC stability: median ρ = +0.038, only 3 of 5 quarters positive vs ≥5/6 required. Both failed.
Audit-chain anchor: v1_5_analyses_results_20260427_191717
AsPredicted #287436
Filed 2026-04-26 · Ran 2026-04-26
Initial in-sample test of skill-weighted aggregation as per-market price prior. 24 aggregator variants tested; all rejected. Cohort substitution amendment filed as #287714.
Audit-chain anchor: marketalpha_v2_in_sample_run
AsPredicted #287442
Filed 2026-04-26 · Ran 2026-04-26
Forward-only complement to #287436. Same 24 aggregator variants on a held-out forward window. All variants rejected forward.
Audit-chain anchor: marketalpha_v2_forward_run
AsPredicted #287714
Filed 2026-04-27 · Ran 2026-04-27
Cohort substitution from V1 (8,656 wallets) to V1-M (8,778 wallets) to verify the negative result is not cohort-specific. All 24 aggregator variants rejected on V1-M as well; consistent with the original finding.
Audit-chain anchor: marketalpha_v2_cohort_substitution
AsPredicted #287983
Filed 2026-04-28 · Ran 2026-04-29
Wash-filter robustness check on the V2.8.2 negative result. Brier delta CI [+0.16028, +0.19287] sits inside the pre-registered TOST equivalence range [+0.154, +0.204]. Movement after wash filtering: +0.00243 Brier (1.4% relative). The V2.8.2 finding (skill-weighted aggregation rejected) is robust to wash-trader filtering at composite-z >= 3.0.
Audit-chain anchor: v28_2_wash_filter_tost_passed_2026_04_29
AsPredicted #288046
Filed 2026-04-29 · Runs 2026-07-29
90-day walk-forward backtest of the CME V0.2 constraint-projection pipeline pre-registered. Hyperparameters frozen ex-ante (thresholds, sizing, cost model, performance metrics). No hyperparameter tuning based on backtest results allowed by the pre-reg.
Audit-chain anchor: cme_v0_2_0_methodology_frozen_commit_8616a63
AsPredicted #288610
Filed 2026-05-01
Pre-registers the form (4 pillars: CRPS-posture, conviction, discipline, funding-capture) + 7 validation gates for the V2-Perps Edge Score composite. Form locked at freeze commit 8c86dd4; coefficients TBD pending Hyperliquid 90-day cohort fit. Composite reduces to V1 / V3b on binary outcomes (Brier-equivalence identity) and extends across crypto perps, equity perps, compute futures, AI benchmark markets, valuation futures, and prediction markets per spec Section 6.
Audit-chain anchor: v2_perps_methodology_frozen_commit_8c86dd4
AsPredicted #288615
Filed 2026-05-01 · Runs 2026-07-30
90-day walk-forward backtest of the V0.2-Perps coherence-violation engine (7 constraints: cash-and-carry, triangle, put-call parity, Carr-Madan butterfly, Litterman-Scheinkman PCA calendar, cross-venue 4-corner, vertical-spread monotonicity). H1 net Sharpe > 1.0; H2 capacity ceiling < 50K USD/day; H3 each constraint contributes positive Sharpe with 95% bootstrap CI excluding zero. Methodology code freezes at commit adb99d6; emit cron at .github/workflows/cme-v0-2-perps-emit.yml.
Audit-chain anchor: cme_v0_2_perps_methodology_frozen_commit_adb99d6