χONN · Historical archive
Ontology Neural Network — audited.
The original higher-order/cohomological thesis was audited to a scoped No-Go boundary. The paper remains the historical record; a modest direction-channel signal, a scalar delayed-recurrence Schur-stability result, and the audit method survive. A coupled system-level control certificate is not established, and active development has moved to ULR.
Suggested reading order
Track overview
The high-level research-track page — the original programme, the audit boundary, what survives, and the move to its successor line.
Canonical audit & status
The authoritative audited boundary statement: original commitments, surviving scoped results, withdrawn claims, and named open gaps.
Research roadmap & status
Dated audits recording what is settled, what was withdrawn, what remains open, and what moved to the successor programme.
- updated 10 Jul 2026
ONN Research Status — 2026
Current, audited status of the ONN / ORTSF programme: the central higher-order question resolved to a scoped No-Go boundary, one modest positive survived, control results were narrowed to model-level certificates, and the programme moved to ULR.
- updated 10 Jul 2026
ONN — Feb-2026 Snapshot (superseded)
A dated 2026-02-18 development snapshot of the ONN repository, kept for history. Its framing (a 'PLAUSIBLE' stability theorem heading to deployment) has been superseded by the programme's audited resolution — a scoped No-Go boundary. See the current research status.
Integration & north-star
The proposed SCC–ONN coupling as an audited design target. The integration note records both the intended architecture and the links that are not established.
Mathematical results
Audits and scoped results specific to ONN — withdrawn topology/cohomology claims and the surviving scalar delayed-recurrence stability condition.
Essays & working notes
Exploratory documents, working notes, and essay-form writing in the ONN thread.
- updated 10 Jul 2026
Audit — the 'Cohomological Stability Certificate'
The claimed 'cohomology = Lyapunov certificate' does not exist in the research source. What remains is a model-level phase-margin gate and a separate single-mode scalar delay certificate, neither derived from cohomology.
- updated 10 Jul 2026
ONN vs Transformer — Experiment Plan
A Feb-2026 pre-registered protocol for a constraint-satisfaction (CSR/ASR/SVR) benchmark of an ONN LOGOS solver vs. Transformer baselines. Kept as a methodology record; its sibling results docs are not reflected in the current authoritative research source.
Manuscripts
Every ONN-track paper — published, accepted, or in preprint.
- published · 2026 · partially-superseded · International Journal of Topology (MDPI), 3(2), 9
Ontology Neural Network and ORTSF: A Framework for Topological Reasoning and Delay-Robust Control
Paper of record for the original ONN + ORTSF framing. A later audit found that the higher-order/cohomological thesis adds no information beyond pairwise data under the stated observation contract. The implemented control
- preprint · 2025 · withdrawn
Advanced Topology-Preserving Neural Networks: An Extension of ONN/ORTSF Framework with Dynamic Structural Optimization
The headline empirical figures and transfer results are not reproducible from the current authoritative research source. This preprint is retained as a historical manuscript, but its validation claims are withdrawn.
- preprint · 2025 · withdrawn
Constructive Lyapunov Functions via Topology-Preserving Neural Networks
The claimed constructive cohomological Lyapunov certificate, together with the 177 microsecond / 3M-node and 99.75% figures, is not supported by the current authoritative research source. Those claims are withdrawn.
- preprint · 2025 · withdrawn
Ontology Neural Networks for Topologically Conditioned Constraint Satisfaction
The reported topology-loss and 95% constraint-satisfaction figures are not reproducible from the current authoritative research source. This manuscript is retained as a historical, unverified draft; its empirical claims