Each card opens that campaign, its closing reconciliation and its iteration pages. Chips are lifecycle โ where the work sits in its process, never a judgement of what it found.
Cap reached, definition-of-done NOT met. LOOP_PROMPT.md: 'STATUS: CAP REACHED 2026-07-30. 14 iterations run, 14 of 17 items addressed, loop stopped and its cron cancelled.' Attack items L-3/L-4/L-5 remain 'OPEN โ not reached beforโฆ
manifest: 'NOT OPERATIONAL (2026-07-31). 0 of 120 decided.' with decided 0, cohort_size 120, admitted 0, rejected 0, what_held 'no candidate verdict was ever written'; iteration 13 'blocks_next: all three are operator decisions; tโฆ
Self-contradictory, plus a LIVE blocker. manifest claims 'OPERATIONAL (H8 ruled 2026-07-10) โฆ WIRING FOLLOW-UP in progress', while next_iteration says 'CONVERGED โ ROBUST-ENOUGH โ OPERATOR REVIEW (handoff H8). The loop idlesโฆ' witโฆ
manifest: 'STOPPED BY OPERATOR 2026-07-09 (iter 32; resume via LOOP-PROMPT.md โ queue preserved: S-11 -> B-07 -> cross-cutting)', then 'Operator decision: resume, convert to slow-refill cadence, or close the campaign'. Coverage 10โฆ
Parked by operator directive. manifest: 'PARKED (row 117) โ all actionable evaluation complete: 57/68 โฆ B-05 gated on Frontier-#4 โฆ ADR-LIVE-EXPIRY proposed (4 questions open)'; next_iteration 'NONE โ PARKED per operator directiveโฆ
manifest: 'CAMPAIGN-COMPLETE โ all 20 instruments terminal (19 GROUNDED, 1 REJECTED); loop ended 2026-07-24 (iter 34)'; nature 'BOUNDED (20 candidates #0-#19 -> STOP)'; graduation_tally terminal 20/20.โฆ
2026-08-14 reconciliation, HALTED -> SATURATED. The harvest delivered a frozen, downstream-consumed cohort and has no completion criterion by design; more firings would only widen a list that is already frozen elsewhere. That is sโฆ
Operator ruling, 2026-08-14: this campaign is settled. Recorded as a ruling rather than re-derived from the folder โ the file-based reading that preceded it is kept verbatim in _status_evidence_superseded so the disagreement staysโฆ
All 11 manifest rows status DONE; iteration 11 'Semantic Tier-3 (abbreviation expansion) โ the last gap closed, blueprint complete'.โฆ
manifest status 'E4 COMPLETE'; iteration 14 'FINAL: E4 verdict โ skill, calibration, stamps all CONFIRMED'.โฆ
manifest verdict: 'FORMALIZED โ three probes + one promotion gate; agnostic axis provenance-corrected'. No open queue, no next_iteration.โฆ
manifest: 'evaluator_pass: COMPLETE (all 6 reported)'; questions_resolved 4, partial 2, pending 0. Its page still says 'Do NOT merge PR #543' โ stale, #543 merged 2026-08-07. Gated rather than exempt despite the undated slug: it hโฆ
SUBSTRATE, NOT A LOOP โ kept in the gate anyway so it cannot sit outside the accounting. index: 'The single substrate folder every orthogonality probe reads from โ the locked data scope, the registries, and the rotation engine โฆ Oโฆ
Campaigns live under campaigns/ โ one directory for all of them, each with its lifecycle status and the evidence behind it.
opendeviationbar-py ยท feature-column discipline ยท living reference
Every feature column must be orthogonal ยท parameterless ยท agnostic (Terry msg id=428). Each axis is a runnable probe; one gate combines them into a single promote/skip verdict. This area is the living current-state reference โ the dated campaign spoke is the frozen record of how it was built.
Does this feature tell us something no existing feature already tells us?
Spearman |ฯ| matrix + h_norm per (symbol ร threshold ร slice) cell, regime-stratified across 7 epochs; ฮพโCODECโO-info cascade behind it.
orthogonality_probe.pyDoes this feature contain secret hand-tuned numbers?
Job 1: AST gate vs the constants registry (tunable knob โ BLOCK). Job 2: shared-knob promotion sweep across all candidates/families.
parameterless_probe.pyIs this ONE well-defined algorithm โ would two honest implementations agree?
Algorithm-invariance: no-dispatch scan + two-implementation convergence oracle + doc/code consistency. (NOT asset-agnostic โ provenance-corrected.)
agnostic_probe.pyOne promote/skip decision over the three probes. A tunable knob vetoes.
promote = parameterless โง agnostic โง orthogonal. Cost-ladder short-circuit: free static axes first. A feature-tunable knob vetoes everything.
three_axis_gate.pyWill a feature that is orthogonal today STILL be orthogonal tomorrow?
Leakage-gated walk-forward over 20 named regime slices: persistence 94-95%, flip-ranking AUC 0.88-0.95, ACI-calibrated intervals, FDR≤10% declared sets. Regime-conditional by evidence (ICP 0/92).
e123_v3_walk_forward.pyThe one consolidated substrate folder every probe reads from: the locked data scope, the registries, and the byte-identical rotation engine โ split into Crypto Shared Artifacts and Forex Shared Artifacts. Read-only ClickHouse on bigblack.
Bounded loop grounding the 20 candidate instruments (#0-#19) that judge whether a promoted feature is REAL and USEFUL โ one per iteration in dependency order (SEAL -> substrate #1/#0 -> realness -> usefulness -> conditional -> increment/mechanism -> robustness/detector), then STOP. Real-data-only (no synthetic data), hard-capped read-only ClickHouse + 5c/5G/no-swap. Laptop-drives-bigblack. Per-iteration HTML + append-only ledger; metric tables twin at dashboard/realness/.
Autonomous logically-absurd (Popperian) attack/defend loop that hardens the rotational orthogonal probe until no attack can break it, then proves โ empirically, zero meta-evaluation โ that it is far more robust than the legacy orthogonality_probe.py on the 10 candidates (writing the 7 missing kernels first). Hardcaps: read-only ClickHouse, 2 CPU / 2 GB, no synthetic data, frozen bands. Runs on bigblack via ccmax-claude in tmux Rotation-Orthogonal-Probe-Operational-Campaign; offline SOTA in KB.md.
Candidate-sourcing expedition feeding the admission lab: harvest + provenance-verify + dedup + M0/M1 paper-screen 300-400 candidate matrices across ALL status boundaries (STABLE >=100 first), one-way handoff via FRONTIER-FEED batches. Paper-only, laptop-hosted, zero ClickHouse.
Standing certification lab for forward matrices: six-gate admission ladder (M0-M5), frozen pre-registration, self-test seal, append-only ledger + boneyard. Goal: FAIL/FRAGILE/CONDITIONAL/STABLE statuses empirically assignable on both substrates using admitted matrices only.
Cross-asset parameterless orthogonal-candidate discovery sweep (crypto + forex) toward a 100-candidate target โ the discovery surface feeding both candidate hubs.
Hardening the candidate registry + turning the manual 'already covered?' novelty check into a fast, automatic, evidence-backed catalogue-uniqueness pre-filter. Per-iteration loop record.
Full-grid forward-orthogonality evaluation at matrix scale โ the scale-up behind the Forward probe, with leakage-gated walk-forward across the named regime slices.
How the three probes + the one gate were built (the frozen origin record of this area).
promote = parameterless.PASS AND agnostic.PASS AND orthogonal.PASS3. Agnostic โ algorithm-invariant. Two correct implementations of the same feature should converge to the same answer. A column that silently dispatches between ApEn and PE based on window size is two columns wearing one name.
โ Terry, msg id=428 (verbatim). Full sources: PROVENANCE.md