{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WJLK7ST6OPBXYP5Y6NLKZYDDFR","short_pith_number":"pith:WJLK7ST6","schema_version":"1.0","canonical_sha256":"b256afca7e73c37c3fb8f356ace0632c4fa3995dc6c4a3c1ac877ac280d0efb1","source":{"kind":"arxiv","id":"2512.05906","version":2},"attestation_state":"computed","paper":{"title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Amirreza Movahedin, Christos Strydis, Lennart P. L. Landsmeer, Said Hamdioui","submitted_at":"2025-12-05T17:39:59Z","abstract_excerpt":"Spiking neural networks (SNNs), central to computational neuroscience and neuromorphic machine learning (ML), require efficient simulation and gradient-based training. While AI accelerators offer promising speedups, gradient-based SNNs typically implement sparse spike events using dense, memory-heavy data-structures. Existing exact gradient methods lack generality, and current simulators often omit or inefficiently handle delayed spikes. We address this by deriving gradient computation through spike event queues, including delays, and implementing this into memory-efficient, autodifferentiable"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2512.05906","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2025-12-05T17:39:59Z","cross_cats_sorted":[],"title_canon_sha256":"ca39e70e3a4c7942240b162ff3a7f6594e0005d82d60116c862dbaf4cf311686","abstract_canon_sha256":"f0fbac5921fcbc9752b0416f98f7f2e995447648962827fc0e72f70ab767b9d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:19:08.729569Z","signature_b64":"qQfBnHhteqh7gI5HEgQdgNxNu/GbRffxJhHcVAUn5FEMZv4bVyjT7Efr9ABwYDiWJJSAAUIzlNTO119t2ntpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b256afca7e73c37c3fb8f356ace0632c4fa3995dc6c4a3c1ac877ac280d0efb1","last_reissued_at":"2026-07-08T01:19:08.728999Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:19:08.728999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ADSEQ: A delay-aware autograd-compatible framework for spike-event delivery in SNNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Amirreza Movahedin, Christos Strydis, Lennart P. L. Landsmeer, Said Hamdioui","submitted_at":"2025-12-05T17:39:59Z","abstract_excerpt":"Spiking neural networks (SNNs), central to computational neuroscience and neuromorphic machine learning (ML), require efficient simulation and gradient-based training. While AI accelerators offer promising speedups, gradient-based SNNs typically implement sparse spike events using dense, memory-heavy data-structures. Existing exact gradient methods lack generality, and current simulators often omit or inefficiently handle delayed spikes. We address this by deriving gradient computation through spike event queues, including delays, and implementing this into memory-efficient, autodifferentiable"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.05906","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.05906/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2512.05906","created_at":"2026-07-08T01:19:08.729065+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.05906v2","created_at":"2026-07-08T01:19:08.729065+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.05906","created_at":"2026-07-08T01:19:08.729065+00:00"},{"alias_kind":"pith_short_12","alias_value":"WJLK7ST6OPBX","created_at":"2026-07-08T01:19:08.729065+00:00"},{"alias_kind":"pith_short_16","alias_value":"WJLK7ST6OPBXYP5Y","created_at":"2026-07-08T01:19:08.729065+00:00"},{"alias_kind":"pith_short_8","alias_value":"WJLK7ST6","created_at":"2026-07-08T01:19:08.729065+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WJLK7ST6OPBXYP5Y6NLKZYDDFR","json":"https://pith.science/pith/WJLK7ST6OPBXYP5Y6NLKZYDDFR.json","graph_json":"https://pith.science/api/pith-number/WJLK7ST6OPBXYP5Y6NLKZYDDFR/graph.json","events_json":"https://pith.science/api/pith-number/WJLK7ST6OPBXYP5Y6NLKZYDDFR/events.json","paper":"https://pith.science/paper/WJLK7ST6"},"agent_actions":{"view_html":"https://pith.science/pith/WJLK7ST6OPBXYP5Y6NLKZYDDFR","download_json":"https://pith.science/pith/WJLK7ST6OPBXYP5Y6NLKZYDDFR.json","view_paper":"https://pith.science/paper/WJLK7ST6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.05906&json=true","fetch_graph":"https://pith.science/api/pith-number/WJLK7ST6OPBXYP5Y6NLKZYDDFR/graph.json","fetch_events":"https://pith.science/api/pith-number/WJLK7ST6OPBXYP5Y6NLKZYDDFR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WJLK7ST6OPBXYP5Y6NLKZYDDFR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WJLK7ST6OPBXYP5Y6NLKZYDDFR/action/storage_attestation","attest_author":"https://pith.science/pith/WJLK7ST6OPBXYP5Y6NLKZYDDFR/action/author_attestation","sign_citation":"https://pith.science/pith/WJLK7ST6OPBXYP5Y6NLKZYDDFR/action/citation_signature","submit_replication":"https://pith.science/pith/WJLK7ST6OPBXYP5Y6NLKZYDDFR/action/replication_record"}},"created_at":"2026-07-08T01:19:08.729065+00:00","updated_at":"2026-07-08T01:19:08.729065+00:00"}