โ€บNavigation
Orthogonality Dashboard ยท NET-NEW family
NET-NEW FAMILY 5 CANDIDATES 1 PILOT-APPLIED FRAMEWORK GAP L0-1

๐Ÿ”ท TDA family โ€” Topological Data Analysis

Five candidates that measure the shape of the price trajectory across multiple bars, distinct from the scalar-moment features in the original 64-list. None existed in the original FRAMEWORK.md family taxonomy โ€” TDA is the first net-new family surfaced during the broader 56-candidate research extension after PR #493.

Total
5
candidates (#65โ€“#69)
Empirically tested
1
#65 (pilot application)
FOSS ready
5
all permissive (MIT)
Framework gaps
22
surfaced via #65 pilot application
What is "Topological Data Analysis" in plain English?

Imagine you took the last 100 BTC price moves and plotted them as a path through 3D space. Most of the time that path is either smoothly trending or aimlessly noisy โ€” both produce simple shapes. But when the market is between regimes โ€” buyers and sellers fighting, no winner emerging โ€” the path makes loops as price revisits the same regions repeatedly. TDA lets us count those loops, weighted by how persistent they are, with one number per bar. Scalar features (volume, OFI, kyle_lambda, etc.) can't see the loops โ€” they only measure within-bar moments. That's why TDA is genuinely orthogonal to everything we ship today.

Candidates in this family

#65 PILOT APPLICATION 2026-05-19 AXIS 1 PASS AXIS 2 FAIL AXIS 3 INCONCLUSIVE

Persistence Landscape Lยฒ-norm

Bubenik 2015's functional summary of the persistence diagram, distilled to one scalar per 100-bar window. The single empirical spike of this family โ€” used as the pilot application of FRAMEWORK.md before Terry's accuracy review.

Source
Bubenik 2015 ยท DOI 10.5555/2627435.2697060
FOSS
scikit-tda/persim @ f2918f4843a5 ยท MIT
Empirical max |ฯ|
0.361 vs `high`
Deep dive โ†—
#66 NOT YET TESTED

Persistent Entropy (Atienza-Gonzalez-Soriano)

Shannon entropy of the normalized birth-death lifespans of the persistence diagram. Empirically robust on Indian stock markets (Sornapudi 2024).

Source
Atienza 2020 ยท DOI 10.1016/j.patcog.2019.107096
FOSS
scikit-tda/persim ยท MIT
Axis 2
TUNABLE (m, ฯ„, hom dim)
#67 NOT YET TESTED PERMISSIVE FOSS (GUDHI MIT)

Betti curves / Integral Betti signature

Curves Bk(ฮต) counting alive k-dim topological features as filtration radius grows. Integral encodes curvature of the bar-correlation network.

Source
Caputi-Pidnebesna-Hlinka 2024 ยท arXiv:2406.15505
FOSS
GUDHI BettiCurve ยท MIT
Note
Initial citation pointed to giotto-tda (AGPL); GUDHI is the permissive alternative
#68 NOT YET TESTED

Wasserstein / Bottleneck distance between persistence diagrams

Topological change-point per bar transition. Distinct from sliced-Wasserstein (parallel-session-claimed); full-W is open territory.

Source
Skraba-Turner 2020 ยท arXiv:2006.16824
FOSS
scikit-tda/persim ยท MIT
Output shape
Scalar per bar-pair
#69 NOT YET TESTED R-ONLY (needs Python port)

CROCKER plot statistics

Concatenated Betti curves over rolling windows; extract CROCKER-variance and contour-length scalars. Captures chronotopological evolution.

Source
Persistent homology for chaos transitions 2025 ยท DOI 10.1016/j.chaos.2025.116025
FOSS
lxiancode/tda-crocker ยท MIT (R)
Note
Python port required before Phase 2

Cross-references