{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F43YNSQHWZUMSYSIDE4NLWOYZK","merge_version":"pith-open-graph-merge-v1","event_count":5,"valid_event_count":5,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1d44b4d5504e5fdf8d099d21cfa6a6bcc968772ebe8b7ac604585502ddc7023f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2026-05-14T16:50:15Z","title_canon_sha256":"64d938c5f029bce8af36d31103e8e1ee7290d1b8ee270e0d34d6e08f8a1d1805"},"schema_version":"1.0","source":{"id":"2605.15058","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15058","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15058v1","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15058","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"pith_short_12","alias_value":"F43YNSQHWZUM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"F43YNSQHWZUMSYSI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"F43YNSQH","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:8d5796ab08510ab7874d99963d9f5f029e52da9d549e5f1e668086c7777bc045","target":"graph","created_at":"2026-05-17T23:38:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The survey provides a comprehensive taxonomy of SNN training algorithms spanning surrogate-gradient backpropagation, local and three-factor learning rules, biologically inspired plasticity, ANN-to-SNN conversion, and non-standard optimization, supported by the release of NeuroTrain for consistent benchmarking."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the representative algorithms implemented in NeuroTrain sufficiently capture the diversity and key properties of the broader literature without significant omissions or implementation biases."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A taxonomy of SNN training algorithms is presented with the release of NeuroTrain, an open benchmarking framework for reproducible comparisons across datasets and architectures."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A single taxonomy sorts spiking neural network training methods by their signals and locality while a shared code base lets researchers test them together."}],"snapshot_sha256":"d25edcc6fccd85dbcc11ba11551f6b9b58cb4b53031a51c144b848849b88d2fa"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8d7cbe5f335559ad18688527134f727d70ec23dc538a3823d18e255808eddf9b"},"paper":{"abstract_excerpt":"The rapid expansion of spiking neural networks (SNNs) has led to a proliferation of training algorithms that differ widely in biological inspiration, computational structure, and hardware suitability. Despite this progress, the field lacks a unified, fine-grained taxonomy that systematically organizes these approaches and clarifies their conceptual relationships. This survey provides a comprehensive taxonomy of SNN training algorithms, spanning surrogate-gradient backpropagation, local and three-factor learning rules, biologically inspired plasticity mechanisms, ANN-to-SNN conversion pipelines","authors_text":"Alessandro Savino, Alessio Caviglia, Filippo Marostica, Roberta Bardini, Stefano Di Carlo","cross_cats":["cs.AI"],"headline":"A single taxonomy sorts spiking neural network training methods by their signals and locality while a shared code base lets researchers test them together.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2026-05-14T16:50:15Z","title":"NeuroTrain: Surveying Local Learning Rules for Spiking Neural Networks with an Open Benchmarking Framework"},"references":{"count":191,"internal_anchors":1,"resolved_work":191,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Maass, Networks of spiking neurons: The third generation of neural network models, Neural Net- works 10 (9) (1997) 1659–1671.doi:10.1016/ S0893-6080(97)00011-7","work_id":"f9c322e9-cc35-4211-b971-7dd7265b6cb5","year":1997},{"cited_arxiv_id":"","doi":"10.1109/mm.2018","is_internal_anchor":false,"ref_index":2,"title":"M. Davies, N. Srinivasa, T.-H. Lin, G. Chinya, Y . Cao, S. H. Choday, G. Dimou, P. Joshi, N. Imam, S. Jain, Y . Liao, C.-K. Lin, A. Lines, R. Liu, D. Mathaikutty, S. McCoy, A. Paul, J. Tse, G. Venkata","work_id":"9b6fde68-321e-4f9b-8f3a-6c06f85e761b","year":2018},{"cited_arxiv_id":"","doi":"10.1109/access.2025.3566717","is_internal_anchor":false,"ref_index":3,"title":"B. Huo, F. Li, S. Peng, H. Chen, S. Xin, H. Wang, Research on SNN Learning Algorithms and Networks Based on Biological Plausibility, IEEE Access 13 (2025) 95243–95256.doi:10.1109/ACCESS.2025.3566717","work_id":"073c7bbe-83c4-4882-be82-1e6bba14e580","year":2025},{"cited_arxiv_id":"","doi":"10.1007/s00422-008-0237-x","is_internal_anchor":false,"ref_index":4,"title":"P. Lansky, S. Ditlevsen, A review of the methods for signal estimation in stochastic diffusion leaky integrate- and-fire neuronal models, Biological cybernetics 99 (4) (2008) 253–262.doi:10.1007/s0042","work_id":"39e53955-83fe-4d31-9b11-d5a8507a6954","year":2008},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":6,"title":"B. Mészáros, J. C. Knight, T. Nowotny, Efficient event- based delay learning in spiking neural networks, Nature Communications 16 (1) (2025) 10422.doi:10.1038/ s41467-025-65394-8","work_id":"3121ec1a-8024-4525-b10b-a7a9c925f07e","year":2025}],"snapshot_sha256":"2db4a6c86d8313cb7a76ff232913296877c124acd05938c1e6e5aeb1d2536cb7"},"source":{"id":"2605.15058","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T03:05:56.906634Z","id":"224c3af4-49c6-4479-9886-ef8a778c1e4a","model_set":{"reader":"grok-4.3"},"one_line_summary":"A taxonomy of SNN training algorithms is presented with the release of NeuroTrain, an open benchmarking framework for reproducible comparisons across datasets and architectures.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A single taxonomy sorts spiking neural network training methods by their signals and locality while a shared code base lets researchers test them together.","strongest_claim":"The survey provides a comprehensive taxonomy of SNN training algorithms spanning surrogate-gradient backpropagation, local and three-factor learning rules, biologically inspired plasticity, ANN-to-SNN conversion, and non-standard optimization, supported by the release of NeuroTrain for consistent benchmarking.","weakest_assumption":"That the representative algorithms implemented in NeuroTrain sufficiently capture the diversity and key properties of the broader literature without significant omissions or implementation biases."}},"verdict_id":"224c3af4-49c6-4479-9886-ef8a778c1e4a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ed3b4454a29511b2f75ebd0bf36e9a304d5eb4cff59d39a24324d03657013428","target":"record","created_at":"2026-05-17T23:38:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1d44b4d5504e5fdf8d099d21cfa6a6bcc968772ebe8b7ac604585502ddc7023f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2026-05-14T16:50:15Z","title_canon_sha256":"64d938c5f029bce8af36d31103e8e1ee7290d1b8ee270e0d34d6e08f8a1d1805"},"schema_version":"1.0","source":{"id":"2605.15058","kind":"arxiv","version":1}},"canonical_sha256":"2f3786ca07b668c962481938d5d9d8cabcf10274409c095b96686dd5bc8eeb93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f3786ca07b668c962481938d5d9d8cabcf10274409c095b96686dd5bc8eeb93","first_computed_at":"2026-05-17T23:38:54.318833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:54.318833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZuQQs6twIFx9dKnLNM/TNCQGYsCJBXMizrmpQDHRvUqPmfqro2KuEDLwDhbiGWVePkciVPfNU2tGig8WId1NCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:54.319614Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15058","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:1b9f3e9c9112b81cc7a649da3c3be9e77d912f8a7751e5534db4093f58c8508b","sha256:5c26d0922df507f0c06ed489e537808db2d37627997c7c4426f5786c4da3678e","sha256:6f380da953b3e5551fb03cdfb6adb21f9dc8b8ec9d0ce2499eb824672f539882"]}],"invalid_events":[],"applied_event_ids":["sha256:ed3b4454a29511b2f75ebd0bf36e9a304d5eb4cff59d39a24324d03657013428","sha256:8d5796ab08510ab7874d99963d9f5f029e52da9d549e5f1e668086c7777bc045"],"state_sha256":"2028d0c7b39cd18585d096e2eb41883a3c0d46ee4503e91775f22c391773e1fe"}