AutoHebb: Self-Modifying Neural Networks that Zero-Shot Infer and Continually Learn
Source check: Source checked. Not independent scientific confirmation.
Finding: Networks rank unseen item pairs and link previously separate rankings. Meta-learning fits fixed Hebbian parameters; weight analysis exposes task algorithms. Testing: Held-out item pairs and minimal-network comparisons test the inferred mechanisms.. Primary v1 full text establishes zero-shot ranking and list-linking behavior in meta-learned Hebbian networks. Source affiliation was not stated in the reviewed case checks and was unavailable in the local bibliographic cache.
Technology: Meta-learning fits fixed Hebbian parameters; weight analysis exposes task algorithms.
Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Meta-learning fits fixed Hebbian parameters; weight analysis exposes task algorithms.
- Test and result
- Held-out item pairs and minimal-network comparisons test the inferred mechanisms.
- Limitation / still unknown
- Generalizability beyond the reported study population, data, and protocol was not established in the reviewed material.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://arxiv.org/html/2610.40757v1
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.