โ€บNavigation
Orthogonality measurement instruments ยท BTCUSD-applicable
PHASE 2 ยท SELECTION SWEEPฮพ SELECTION-PARTIALCODEC SKIPPED ยท O-INFO REWORKED

๐Ÿ“ Measurement Instruments Dashboard

State-of-the-art metrics for measuring feature orthogonality in financial time-series forecasting. The full catalog spans 3 tiers ร— 8 categories, with FOSS implementation status verified per metric. Catalog answers a different question from the 64-candidate sibling audit: this is the tools, that was the things being measured.

Phase 2 update โ€” Selection sweep run; ฮพ validated (Selection-partial), CODEC skipped, O-info reworked

The CODEC/FOCI cascade was run through the Selection gates (S0โ€“S5). Chatterjee ฮพ (A1 pairwise) is the only validated sieve โ€” S1/S2/S3/S5 PASS โ€” but value-add over the Pearson/Spearman baseline is unproven (S4 deferred: the redundant/orthogonal labels are Pearson-derived, so the test is circular). CODEC (A2) is skipped โ€” nearly inert on the crypto panel (0.16 flags/cell, T(canary)โ‰ˆ0) and no faithful FOSS null. O-information (A3) is de-scoped to a cheap bias-centered permutation-null watch (the naive |ฮฉ|โ‰ฅ0.5 flag manufactures false synergy). Feasible replacements for the conditional/synergy gap: GCM, RCoT (A2) and the bias-centered O-info permutation null (A3) โ€” see the priority list. Max achievable verdict is Selection-partial until a Pearson-independent S4 label exists; deployment stays ๐Ÿ”’ BLOCKED on Terry.

Catalog totals

Total catalog
100
metric ร— library entries
Tier A
59
direct measurement
Tier B
19
adjacent question
Tier C
22
downstream consumer
Permissive FOSS
46
MIT/BSD/Apache

8 categories across 3 tiers

A1-A4 measure ยท B1-B2 adjacent ยท C1-C2 downstream
๐Ÿ”— TIER A ยท A1 โ€” PAIRWISE DEPENDENCE Measurement 27 metrics

A1 โ€” Pairwise dependence (incl. MI estimators)

Fills gap: Non-linear redundancy (ฮพ: S1/S2/S3/S5 PASS; value-add pending S4)

Top pick: Chatterjee ฮพโ‚™ โ€” xicorpy (MIT) โ€” VALIDATED (Selection-partial)

Total
27
metrics
Permissive FOSS
11
MIT / BSD / Apache
GPL
10
research-OK; relicense check
Unpackaged
1
code released, integration needed
Explore A1 category โ†—
๐Ÿงญ TIER A ยท A2 โ€” CONDITIONAL DEPENDENCE Measurement 11 metrics

A2 โ€” Conditional dependence

Fills gap: Conditional redundancy (CODEC SKIPPED โ€” inert on substrate + no faithful FOSS null)

Top pick: GCM / RCoT โ€” GeneralisedCovarianceMeasure (CRAN) ยท RCIT/RCoT (causal-learn)

Total
11
metrics
Permissive FOSS
2
MIT / BSD / Apache
GPL
7
research-OK; relicense check
Unpackaged
0
code released, integration needed
Explore A2 category โ†—
๐Ÿ”บ TIER A ยท A3 โ€” HIGHER-ORDER / SYNERGY Measurement 6 metrics

A3 โ€” Higher-order / synergy

Fills gap: Synergy (higher-order) โ€” de-scoped to a cheap permutation-null watch

Top pick: O-information + permutation null โ€” hoi (BSD-3) โ€” bias-centered shuffle null; naive |ฮฉ|โ‰ฅ0.5 flag dropped

Total
6
metrics
Permissive FOSS
3
MIT / BSD / Apache
GPL
2
research-OK; relicense check
Unpackaged
1
code released, integration needed
Explore A3 category โ†—
๐Ÿงฎ TIER A ยท A4 โ€” MATRIX DECOMPOSITION Measurement 15 metrics

A4 โ€” Matrix decomposition / RMT / spectral

Fills gap: Matrix-level orthogonality

Top pick: Marchenko-Pastur + RIE โ€” pyRMT (BSD-style)

Total
15
metrics
Permissive FOSS
10
MIT / BSD / Apache
GPL
5
research-OK; relicense check
Unpackaged
0
code released, integration needed
Explore A4 category โ†—
โžก๏ธ TIER B ยท B1 โ€” CAUSAL DIRECTION Adjacent 15 metrics

B1 โ€” Causal direction

Fills gap: Causal direction

Top pick: Reduced TE (Kirkley 2025) โ€” author GitHub (TBD)

Total
15
metrics
Permissive FOSS
6
MIT / BSD / Apache
GPL
7
research-OK; relicense check
Unpackaged
1
code released, integration needed
Explore B1 category โ†—
๐ŸŒ— TIER B ยท B2 โ€” REGIME STABILITY Adjacent 4 metrics

B2 โ€” Regime stability / distribution shift

Fills gap: Stability across regimes

Top pick: Sliced Wasserstein dependency โ€” POT (MIT)

Total
4
metrics
Permissive FOSS
1
MIT / BSD / Apache
GPL
1
research-OK; relicense check
Unpackaged
2
code released, integration needed
Explore B2 category โ†—
๐ŸŽฏ TIER C ยท C1 โ€” FDR-CONTROLLED SELECTION Downstream 14 metrics

C1 โ€” FDR-controlled feature selection

Fills gap: FDR aggregation (meta)

Top pick: DeepLINK-T + e-BH โ€” knockpy + e-BH (MIT + open)

Total
14
metrics
Permissive FOSS
8
MIT / BSD / Apache
GPL
3
research-OK; relicense check
Unpackaged
2
code released, integration needed
Explore C1 category โ†—
๐Ÿ’ผ TIER C ยท C2 โ€” FINANCE FRAMEWORKS Downstream 8 metrics

C2 โ€” Finance-specific applied frameworks

Fills gap: Portfolio-level orthogonality

Top pick: Lรณpez de Prado cMDA + HRP โ€” mlfinlab / PyPortfolioOpt (mixed)

Total
8
metrics
Permissive FOSS
5
MIT / BSD / Apache
GPL
0
research-OK; relicense check
Unpackaged
0
code released, integration needed
Explore C2 category โ†—

Instrument campaigns

1 published ยท loop-emitted

Research loops that validate a measurement instrument from this catalog on real data. Each card opens that campaign's detailed pages.

๐Ÿ”— A1 PAIRWISE ยท ฮพ KEEPER GATE 2026-06-06 ยท 4 pages

Forex Chatterjee ฮพ โ€” Keeper Confirmation Gate

The asymmetric, non-monotone confirmation Spearman cannot give โ€” validates the A1 Chatterjee ฮพ instrument by adjudicating the 16 Spearman-cleared forex keepers (14 KEEP + 2 HOLD), confirming the direction-clique collapse, and flipping implementation_ready for survivors โ€” delivered as two operator-reviewed PRs (harness build; survivor promotion).

Open campaign โ†—

Source catalog (full markdown)