causal-falsify: A Python library with algorithms for falsifying the unconfoundedness assumption in a composite dataset from multiple sources.
-
Updated
Mar 6, 2026 - Python
causal-falsify: A Python library with algorithms for falsifying the unconfoundedness assumption in a composite dataset from multiple sources.
Code to reproduce the experiments from the paper "Self-Compatibility: Evaluating Causal Discovery without Ground Truth"
Finding Property Violations through Network Falsification: Challenges, Adaptations and Lessons Learned from OpenPilot
A multi‑country synthetic identity generator that produces full, internally consistent life profiles (personal data, family, employment history, historical context, etc.) designed for OPSEC, security research, and testing scenarios, never for impersonation of real individuals or any unlawful use.
Evidenced-negative taste object — failed the geometry-bearing fit gate (metric_fit 0.207 vs 0.6 threshold). The committed negative reference is preserved as the lab record. No positive taste codec is claimed.
Post-analysis and falsification layer for Ω-region behavior. No universal structural constant is declared.
MIT synthetic simulation sandbox for observable runs, falsifier examples and public-safe research boundary demos.
Validation, falsification, artifact traceability, reproducibility, and result-regression layer for OMNIA structural measurement. Evidence, limits, and failures; not a truth oracle.
PressureX is an engineering evaluation package for a passive layered structural mitigation concept using shear-thickening fluid behavior to broaden impulsive loads and reduce peak transmitted response in high-vibration aerospace structures. Targets are design-intent until validated.
Perception receipts for AI video pipelines. Cross-writer bit-exact under default settings (SHA-256 stable across writers in any language). Zero runtime dependencies; pure stdlib core. ~1.1 KB per video; per-frame CRC32 + schema + versioning. Useful now, improving continuously.
CPU-verified in silico materials research control plane. Battery + thermoelectric pipeline staged for H100 GPU evidence campaign. Research infrastructure, not a discovery engine.
Falsification-first biological law discovery — rejects 194 of 203 candidate laws, including its own.
CPU-verified Runpod-ready in-silico physics pipeline for electrochemistry & fusion. 475/475 strict, 79.72% coverage, 6/6 proof anchors. H100 enterprise authority pending (180–500 H100-hrs).
Falsification-first framework for validating time-order, interaction, and closure structure in time-series data.
Indus-script anchor application in the Zer0pa Gnosis Portfolio: clean-room search-without-decode runtime + Phase 4 conditional catalogue at k=70 + Phase 5 non-decipherment posture. No decipherment claimed. Useful now, improving continuously.
Push-T VW2-DirectAct falsification code and artifacts, including subgoal-distillation hard-stop results.
A formal multi-agent LLM framework for decision-making, AI evaluation, and uncertainty analysis using structured divergence.
Negative-control / no-go preservation lane in the Zer0pa Gnosis Portfolio. Manifest-validation smoke + failed-gate evidence chain. Methodology only; no decipherment claim. Useful now, improving continuously.
Deterministic computation substrate diagnostic — Zer0pa Computation portfolio. 380v C3-symmetric graph (P_95 □ K_4); ARM64 cross-platform determinism (claim τ); trimodal sawtooth + s50 cliff confirmed for shape; static reconstruction at Tier-2 (R8 OPEN).
Benchmark-first methods lane for Gnosis extraction in the Zer0pa portfolio: neutral route scoring, null metrics, stability battery, deterministic replay. Methodology surface; useful now, improving continuously.
Add a description, image, and links to the falsification topic page so that developers can more easily learn about it.
To associate your repository with the falsification topic, visit your repo's landing page and select "manage topics."