Status report · 13 September 2026
Drawn from Martinez-Methods/mm-fm-taxonomy and from the live equivalence-class database, queried directly rather than reported from documentation.
The shape of the work
105 named failure modes with mechanism descriptions, published in gozonerd/bobotax-failure-mode-taxonomy. This is what the rest of the world can cite.
Published
Martinez-Methods/mm-fm-taxonomy holds the audit trail, the equivalence-class database, the evidence ledger, and coverage analysis. Held privately pending anonymization.
Private · going-public: true
The database
A PostgreSQL 16 instance holding 38 tables in the public schema. The counts below were read from the running database on 13 September 2026.
| Table | Rows | What it holds |
|---|---|---|
failure_mode | 336 | Failure modes extracted from every mapped source taxonomy |
equivalence_class | 152 | Deduplicated classes that unify equivalent FMs across sources |
fm_ec_mapping | 449 | Which source FM belongs to which equivalence class |
taxonomy | 25 | Source taxonomies and frameworks ingested |
family | 22 | Top-level groupings the classes roll up into |
remediation_coverage | 176 | Which ASAE aspect remediates which class, across 96 classes — STRONG 149 · PARTIAL 13 · OUT-OF-SCOPE 13 · UMBRELLA 1 |
bobotax_classification | 0 | Per-class leverage scoring — methodology in design, see below |
The repo README described 12 published taxonomies while the database had grown to 25 — the ingest kept going after the README was last written. The README was corrected on 13 September 2026 and now matches the deployed schema. The table below is the current set.
Source coverage
Sources are typed, because a failure-mode catalog, a process framework, an incident database and a use-case classification do not answer the same question and should not be flattened together.
| Source | Kind |
|---|---|
| NIST AI 100-2 Adversarial Machine Learning | FM taxonomy |
| OWASP LLM Top 10 for LLM Applications | FM taxonomy |
| OWASP Agentic Security Initiatives + Threats Catalogue | FM taxonomy |
| MITRE ATLAS — Adversarial Threat Landscape for AI Systems | FM taxonomy |
| MIT AI Risk Repository | FM taxonomy |
| Microsoft AI Red Team Failure Mode Taxonomy | FM taxonomy |
| Multi-Agent Security Taxonomy (MAST) | FM taxonomy |
| OWASP Machine Learning Security Top 10 | FM taxonomy |
| Hidden Technical Debt in Machine Learning Systems (Sculley et al.) | FM taxonomy |
| AI Vulnerability Database | FM taxonomy |
| Model Evaluation and Threat Research (METR) | FM taxonomy |
| AI Fairness 360 (IBM, LF AI) | FM taxonomy |
| CSET (Georgetown) AI Harms Taxonomy | FM taxonomy |
| Apollo Research — Scheming Evaluations Framework | Process framework |
| Anthropic Responsible Scaling Policy | Process framework |
| DeepMind Frontier Safety Framework | Process framework |
| NIST AI 600-1 Generative AI Profile (AI RMF) | Process framework |
| NIST AI Risk Management Framework 2.0 | Process framework |
| ISO/IEC 23894:2023 AI Risk Management | Process framework |
| Google Secure AI Framework (SAIF) | Process framework |
| FDA SaMD + Good ML Practice for Medical Device Development | Process framework |
| Federal Reserve SR 11-7 Model Risk Management (AI-extended 2024) | Process framework |
| OpenAI Preparedness Framework | Process framework |
| AI Incident Database (McGregor et al.) | Incident catalog |
| EU AI Act Annex III High-Risk Classification | Use-case classification |
Families
In design
bobotax_classification stands at zero rows by design, not by neglect. The table is the destination for per-class leverage scores; the methodology for mining transcripts to produce them is still being designed.
Scoring classes before that methodology is settled would bake an unexamined extraction method into the primary research output — the table stays empty until the method is worth trusting.
The classification table carries three axis columns — stochasticity, human-user, and human-developer — from the May baseline.
The quad-axes instrument adds D, the deployer-org axis, in June — the rubric runs ahead of the schema.
No migration to four axes is scheduled or recorded. An earlier version of this page said the schema would pick up axis D when the mining methodology landed; no decision record supports that linkage, and it has been withdrawn. Any such migration would touch the bobotax_dominant_axis enum and the bobotax_distribution view as well as the three columns.
Process & activity
Five consecutive passes plus two independent raters before a taxonomy decision stands.
Numbered ASAE gate logs through gate-27, plus a raw-receipts directory, retained in the repo.
Most recent commit 31 July 2026. Database baseline deployed via sqitch on 23 May 2026.
Intake
The proposed-failure-modes/ directory is a pre-canon staging area: entries live there awaiting taxonomy-owner consideration, and no FM number is claimed until they are considered.
Currently staged: PFM-001 — Review channel silently drops annotations, a tooling-integrity failure in which a human reviewer's annotations are lost with no error surfaced, converting the scarcest input in the loop into zero yield.
How these numbers were taken
Martinez-Methods/mm-fm-taxonomy.gozonerd/bobotax-failure-mode-taxonomy.