Family swept: crypto-spot liquidity-quality & integrity + volume-clock bars · campaign regime-invariant-orthogonality · append-only
The integrity & clock axis — crypto-native. Every prior measure assumes the tape is real. This iteration harvests the tools that test that assumption and the tools that resample the tape by activity. Integrity: the three Cong et al. wash-trading tests (Benford first/second-digit, trade-size roundness-clustering, power-law tail), the Deng–Zhou liquidity jump/diffusion decomposition, pump-and-dump detectors (Kamps–Kleinberg, Xu–Livshits, La Morgia), and CUSUM/Bai–Perron volume structural-breaks — anchored by the Nigrini forensic baseline. Clocks: the Volume Clock and the AFML information-driven bars (tick/volume/dollar + imbalance + run) — the liquidity-adaptive alternatives to this project's open-deviation (price-threshold) clock.
Provenance was load-bearing this iteration. The Aloosh–Li (2024) validation (H77) is the authority: ground-truthed against the Mt.Gox trader-ID leak, it finds Benford / size-clustering / lognormal / structural-break tests useful but the power-law-tail test (H76) misleading — so H76 is WATCH-flagged. On FOSS: mlfinlab is proprietary (Nov-2021 commercial click-through, not open source) → use mlfinpy; xujiahuayz/pumpdump carries no license → not FOSS-usable. Two on-chain/L2 detectors are out-of-scope per principle #8.
| # | Name | Family | Measures / samples | Cascade / liquidity mapping | Spot? | Param | Stable-ID | FOSS |
|---|---|---|---|---|---|---|---|---|
| H73 | Benford first-digit test (Cong et al.) | fake-volume test | first-significant-digit distribution of trade sizes vs Benford (χ²/MAD) | flags fabricated liquidity; authentic sizes obey Benford, wash trades deviate | [T/O] | PF | Cong, Li, Tang, Yang 2023, Mgmt Sci — DOI 10.1287/mnsc.2021.02709; arXiv 2108.10984 | VER benfordslaw (Py, MIT); benford_py (Py, BSD-3); benford.analysis (R, GPL-3) |
| H74 | Benford second-digit test | fake-volume test | second-digit distribution (tighter vs near-uniform fabrication) | same integrity flag; more sensitive to crude size-generation | [T] | PF | Cong et al. 2023 · parent H73 | VER as H73 |
| H75 | Trade-size roundness / clustering (Cong et al.) | trade-size-distribution | excess mass at round multiples (×10, integer BTC) vs authentic baseline | flags synthetic order generation; the roundness-ratio is Cong et al.'s main wash estimator | [T] | DIM | Cong et al. 2023 (as H73) | VER benford_py (roundness); hand-rolled |
| H76 | Power-law tail of trade sizes | trade-size-distribution | Pareto-tail exponent α of large trade sizes (KS-optimal x_min) | integrity flag — WATCH Aloosh-Li find this gives the OPPOSITE verdict vs ground truth | [T] | PP | fit: Clauset, Shalizi, Newman 2009, SIAM Rev — DOI 10.1137/070710111; application Cong et al. | VER powerlaw-devs/powerlaw (Py, MIT) |
| H77 | Aloosh–Li wash-trade validation | wash-trading-detection (validation authority) | ground-truth wash via trader-ID (Mt.Gox leak), then benchmarks the indirect tests | the authoritative verdict: Benford / clustering / lognormal / structural-break useful; power-law-tail misleading | direct OOS verdict spot-usable | — | Aloosh & Li 2024, Mgmt Sci — DOI 10.1287/mnsc.2021.01448; SSRN 3362153 | UNV |
| H78 | Liquidity Jump / Liquidity Diffusion (Deng–Zhou) | liquidity-quality-decomposition | Jump = ratio(regular ret / liq-adj ret); Diffusion = ratio(regular vol / liq-adj vol) | decomposes liquidity into level vs variance of price-pressure; high diffusion = fragile/manipulated → exit-difficulty | [T] | PP | Deng & Zhou 2025, arXiv 2411.05803 (succ. 2404.07222) | UNV |
| H79 | The Volume Clock (Easley–LdP–O'Hara) | volume-clock | samples one observation per fixed volume bucket (time subordinate to activity) | the canonical liquidity-adaptive alternative to the open-deviation (price-threshold) clock | [T] | PP | Easley, López de Prado, O'Hara 2012, JPM — DOI 10.3905/jpm.2012.39.1.019; SSRN 2034858 | VER mlfinpy; BlackArbsCEO |
| H80 | Tick / Volume / Dollar bars (AFML) | information-driven-bar | emit a bar every N ticks / N units volume / N dollars traded | activity clocks → returns closer to IID-Gaussian; dollar bars robust to price/supply drift | [T] | PP | López de Prado, AFML (Wiley 2018) ch.2 — DOI 10.1002/9781119482086 | VER baobach/mlfinpy (Py, MIT); BlackArbsCEO (Py, MIT) |
| H81 | Imbalance Bars (TIB/VIB/DIB, AFML) | information-driven-bar | sample when cumulative signed order-flow imbalance exceeds EWMA-expected threshold | strong cascade relevance: fires on imbalance build-up → anticipates trend break; is_buyer_maker gives direction directly | [T] | PP | López de Prado, AFML §2.3.2 · parent H80 | VER mlfinpy (imbalance_bars); BlackArbsCEO |
| H82 | Run Bars (TRB/VRB/DRB, AFML) | information-driven-bar | sample when a run of same-direction ticks/volume/dollars exceeds expectation | detects persistent one-sided pressure (metaorder / directional cascade) | [T] | PP | López de Prado, AFML §2.3.2 · parent H80 | VER mlfinpy; BlackArbsCEO |
| H83 | Kamps–Kleinberg P&D detector | pump-and-dump-detection | moving-window thresholds on % price rise + volume spike define a P&D point | flags acute manipulation / exit-difficulty windows | [O] | MN | Kamps & Kleinberg 2018, Crime Science 7:18 — DOI 10.1186/s40163-018-0093-5 | UNV |
| H84 | Xu–Livshits pump predictor | pump-and-dump-detection | ML on pre-pump features (volume, price, mktcap, age) → pump likelihood | predicts manipulation onset; core features spot-legal, mktcap adds metadata | [O] core | PP | Xu & Livshits 2019, USENIX Security — arXiv 1811.10109 | UNV xujiahuayz/pumpdump — NO LICENSE (not FOSS-usable) |
| H85 | La Morgia et al. "Doge of Wall Street" | pump-and-dump-detection | real-time ML (chart/volume-window) detects P&D ~25s after start, F1≈94.5% | real-time cascade / exit-difficulty flag; trade-only features | [T/O] | PP | La Morgia et al. 2023, ACM TOIT — DOI 10.1145/3561300; arXiv 2105.00733 | UNV SystemsLab-Sapienza/pump-and-dump-dataset; Bayi-Hu (SIGMOD'23) |
| H86 | CUSUM / Bai–Perron volume structural-break | fake-volume / structural-break | change-point detection on volume/trade-count series | regime shifts in liquidity supply (fabrication onset/offset); Aloosh-Li confirm useful for wash | [O] | PP | Page 1954, Biometrika 41:100-15 — DOI 10.1093/biomet/41.1-2.100; Bai & Perron 2003 — DOI 10.1002/jae.659 | VER deepcharles/ruptures (Py, BSD-2); strucchange (R, GPL-2|3) |
| H87 | Benford forensic baseline (Nigrini) | fake-volume test (foundational) | general digit-law forensic framework (MAD conformity; 1st/2nd/first-two digits) | foundational integrity test under H73/H74; volume/qty digit conformity | [T/O] | PF | Nigrini 2012, Wiley (ISBN 978-1-118-15285-0); Benford 1938, PAPS 78(4):551 (JSTOR 984802) | VER benford.analysis (R, GPL-3); benford_py (Py, BSD-3); benfordslaw (Py, MIT) |
| H88 | Victor–Weintraud DEX wash trading | wash-trading-detection | graph SCC over on-chain account trade-graph | on-chain contagion | OOS needs on-chain metadata | — | Victor & Weintraud 2021, WWW'21 — DOI 10.1145/3442381.3449824; arXiv 2102.07001 | OUT-OF-SCOPE |
| H89 | Amiram–Lyandres–Rabetti "Cooking the Order Books" | wash-trading-detection | lower-bound wash from order-book / cross-exchange competition | integrity | OOS needs-L2 / cross-exchange | — | Amiram, Lyandres, Rabetti (SSRN WP; weak provenance) | OUT-OF-SCOPE |
xujiahuayz/pumpdump carries no license ⇒ all-rights-reserved, not FOSS-usable. aleibovici/cryptopump is a trading bot, not a detector (excluded).axis-2-cascade-free/CANDIDATE-CATALOG.md · back to loop hub