Adriano Dal Pastro cb122683fe feat(research): harness condiviso dispersion/correlation index (feature causali + cache) ...

Feature realized causali (avg pairwise corr, cross-sectional dispersion, beta vs
indice EW, componente idiosincratica) su universo 8-asset, finestra comune dal
2022-07. NO implied (opzioni non backtestabili). Check no-look-ahead OK. Cache su
disco per il fan-out di ricerca. Base per la ricerca multi-agente dispersion.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-07 21:16:10 +00:00

..

exit_policies

research(exit-lab): 34 agenti su exit dinamiche → EXIT-16 close-confirm SL PROMOSSO a livello PORT06

2026-06-04 21:16:58 +00:00

sh01_exit_policies

config(PORT06): cap SHAPE 0.0588 — SH01 resta senza SL (ricerca multi-agente: 11 famiglie di stop, 0 sopravvissute)

2026-06-05 17:56:16 +00:00

__init__.py

feat(strategie): 3 nuove fade mean-reversion validate OOS fee-aware (MR02/MR03/MR07)

2026-05-28 23:26:21 +02:00

combine_portfolio.py

feat(strategie): portafogli master (PORT02/PORT03) + waste delle peggiori (MR03, ROT01)

2026-05-29 00:21:37 +02:00

combine_v2.py

feat(explore): 3a ondata - PAIRS a 6 coppie + verdetti su 4 nuove famiglie

2026-05-29 01:13:54 +02:00

dip01_exit16_impact.py

feat(DIP01): EXIT-16 close-confirm SL (gate gap-aware 36/36 BTC, PORT06 promosso)

2026-06-07 16:19:25 +00:00

dispersion_lab.py

feat(research): harness condiviso dispersion/correlation index (feature causali + cache)

2026-06-07 21:16:10 +00:00

exit16_port06_impact.py

research(exit-lab): 34 agenti su exit dinamiche → EXIT-16 close-confirm SL PROMOSSO a livello PORT06

2026-06-04 21:16:58 +00:00

exit_lab.py

research(exit-lab): 34 agenti su exit dinamiche → EXIT-16 close-confirm SL PROMOSSO a livello PORT06

2026-06-04 21:16:58 +00:00

explore_lab.py

feat(explore): esplora 9 famiglie alternative -> PAIRS (nuovo edge forte) + TSM01

2026-05-29 01:07:08 +02:00

fade_diag_by_regime.py

research(fade-lossguard): diagnostici perdite fade per regime + workflow anti-perdite

2026-06-02 13:35:44 +00:00

fade_loss_by_regime.py

research(fade-lossguard): diagnostici perdite fade per regime + workflow anti-perdite

2026-06-02 13:35:44 +00:00

fade_lossguard_port_test.py

feat(fade): loss-guard Hurst (skip regime persistente) — dimezza il DD del PORT06

2026-06-02 14:08:15 +00:00

fade_lossguard_workflow.js

research(fade-lossguard): diagnostici perdite fade per regime + workflow anti-perdite

2026-06-02 13:35:44 +00:00

fractal_argo_master_corr.py

test(research): FR01 NON migliora PORT06 (verdetto decisivo)

2026-06-02 11:48:02 +00:00

fractal_argo_peryear.py

feat(research): FR01 Hurst-Calm Fade + analisi per-anno/mercato (ricerca 100 agenti)

2026-06-02 07:22:10 +00:00

fractal_argo_workflow.js

feat(research): substrato ricerca frattali x regime ARGO

2026-06-02 00:05:14 +00:00

honest_final.py

feat(analysis): 3 strategie oneste validate OOS multi-crypto (DIP/TR/ROT)

2026-05-28 23:28:00 +02:00

honest_improve2.py

feat(ROT02): riduce il DD diversificando (top_k 2 -> 3)

2026-05-29 00:30:55 +02:00

honest_improve.py

feat(analysis): miglioramenti - ROT02 dual-momentum + portafoglio (DD 12%)

2026-05-28 23:49:14 +02:00

honest_lab.py

feat(analysis): 3 strategie oneste validate OOS multi-crypto (DIP/TR/ROT)

2026-05-28 23:28:00 +02:00

honest_matrix.py

feat(analysis): matrice PnL/anno consolidata (confronto strategie + portafoglio)

2026-05-28 23:53:37 +02:00

honest_rotation.py

feat(analysis): 3 strategie oneste validate OOS multi-crypto (DIP/TR/ROT)

2026-05-28 23:28:00 +02:00

honest_trend.py

feat(analysis): 3 strategie oneste validate OOS multi-crypto (DIP/TR/ROT)

2026-05-28 23:28:00 +02:00

intrabar_test.py

feat(analysis): validazione out-of-sample fee-aware delle strategie

2026-05-28 19:57:15 +00:00

live_exec_smoke.py

feat(live): esecuzione REALE su Deribit testnet (shadow) per i 6 fade sui lineari USDC

2026-06-03 10:11:26 +00:00

live_shadow_smoke.py

feat(live): disaster-bracket on-book sui fade reali + alert FEED_OUTAGE + osservabilita' multi-asset

2026-06-07 09:36:11 +00:00

live_smoke_pairs.py

fix(live): smoke test REALE pairs -> live solo ETH/BTC (alt assenti su Deribit)

2026-05-29 09:16:50 +02:00

make_strategy_doc.py

docs: statistiche per anno (trd/PnL%/maxDD) per strategia e mercato nel doc HTML

2026-06-07 17:32:00 +00:00

oos_validation.py

feat(analysis): validazione out-of-sample fee-aware delle strategie

2026-05-28 19:57:15 +00:00

pairs_research.py

docs: statistiche per anno (trd/PnL%/maxDD) per strategia e mercato nel doc HTML

2026-06-07 17:32:00 +00:00

pairspos_port06_impact.py

feat(pairs): position_size per-famiglia, PAIRS 0.5->0.20 (gate PORT06)

2026-06-07 10:44:15 +00:00

paper_status.py

refactor: riorganizzazione script — Strategy ABC, folder strategies/waste/analysis

2026-05-27 23:01:36 +02:00

partial_tp_ladder.py

docs(diary): exit ladder 80/20 con runner+stop dinamico SCARTATO (il runner non corre: TP=media, ~3% oltre TP, −38% ret su MR02 ETH)

2026-06-04 19:48:45 +00:00

projection_3y.py

feat(analysis): proiezione 3 anni capitale PORT06 (live 2x, esclude 2024)

2026-05-30 19:29:07 +00:00

regime_fetcher.py

feat(fade): loss-guard Hurst (skip regime persistente) — dimezza il DD del PORT06

2026-06-02 14:08:15 +00:00

regime_lab.py

feat(fade): loss-guard Hurst (skip regime persistente) — dimezza il DD del PORT06

2026-06-02 14:08:15 +00:00

report_families.py

report(shape): integra SH01 (sleeve SHAPE) nel report per-anno e nell'integrazione MASTER

2026-05-29 12:43:19 +02:00

report.py

feat(analysis): report.py aggiornato con numero trade per anno

2026-05-29 00:33:00 +02:00

risk_management.py

feat(strategie): portafogli master (PORT02/PORT03) + waste delle peggiori (MR03, ROT01)

2026-05-29 00:21:37 +02:00

sh01_exit_lab.py

config(PORT06): cap SHAPE 0.0588 — SH01 resta senza SL (ricerca multi-agente: 11 famiglie di stop, 0 sopravvissute)

2026-06-05 17:56:16 +00:00

sh01_trainwindow_validate.py

feat(SH01): bootstrap storia full-history + last_block_only (punto-10: regime live non robusto)

2026-06-07 16:48:22 +00:00

shape_analog_research.py

research(shape): 5 famiglie di pattern-forma su harness onesto

2026-05-29 12:09:28 +02:00

shape_candle_research.py

research(shape): 5 famiglie di pattern-forma su harness onesto

2026-05-29 12:09:28 +02:00

shape_lab.py

research(shape): 5 famiglie di pattern-forma su harness onesto

2026-05-29 12:09:28 +02:00

shape_ml_research.py

feat(SH01): bootstrap storia full-history + last_block_only (punto-10: regime live non robusto)

2026-06-07 16:48:22 +00:00

shape_ml_validate.py

feat(shape): SH01 Shape-ML validato come diversificatore + doc

2026-05-29 12:31:26 +02:00

shape_pivot_research.py

research(shape): 5 famiglie di pattern-forma su harness onesto

2026-05-29 12:09:28 +02:00

shape_template_research.py

research(shape): 5 famiglie di pattern-forma su harness onesto

2026-05-29 12:09:28 +02:00

sleeve_clustering.py

analysis(portfolio): clustering sleeve per correlazione + contributo rischio

2026-05-29 13:09:27 +02:00

smoke_portfolio.py

feat(portfolio): PortfolioRunner live (data v2, tick, ribilancio giornaliero, ledger)

2026-05-29 16:05:07 +02:00

strategy_research_v2.py

feat(strategie): 3 nuove fade mean-reversion validate OOS fee-aware (MR02/MR03/MR07)

2026-05-28 23:26:21 +02:00

strategy_research.py

refactor(strategie): tieni solo MR01 mean-reversion, squeeze -> waste

2026-05-28 20:22:11 +00:00

trendmax_port06_impact.py

feat(fade): swap filtro live hurst->trend_max 3.0 (gate PORT06 sul path live)

2026-06-07 10:29:57 +00:00

tsmom_research.py

refactor(explore): irrobustimento anti-overfit di pairs/TSM01/master

2026-05-29 08:11:33 +02:00

validate_fade_intrabar.py

test(live): demo numerica exit intrabar fade -- worker replay ~= backtest

2026-05-29 18:43:38 +02:00

validate_honest_workers.py

test(portfolio): valida worker honest/TSM01 vs backtest reference

2026-05-29 17:50:08 +02:00

validate_portfolio_runner.py

test(portfolio): valida runner pool+ribilancio+ledger == backtest (identico)

2026-05-29 17:28:03 +02:00

validate_worker_mr01.py

feat(live): worker con exit TP/SL/max_bars per MR01 + doc aggiornata

2026-05-28 20:46:35 +00:00

validate_worker_pairs.py

feat(live): worker a 2 gambe per i pairs (PR01 market-neutral)

2026-05-29 09:12:25 +02:00