{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:G6POOXV57NWFPDMGCSJK7AX2UJ","short_pith_number":"pith:G6POOXV5","schema_version":"1.0","canonical_sha256":"379ee75ebdfb6c578d861492af82faa2462db960ff1be02b16ea9c949ae59fee","source":{"kind":"arxiv","id":"2006.02642","version":2},"attestation_state":"computed","paper":{"title":"Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Jae-Joon Kim, Jinseok Kim, Kyungsu Kim","submitted_at":"2020-06-04T04:47:01Z","abstract_excerpt":"For the gradient computation across the time domain in Spiking Neural Networks (SNNs) training, two different approaches have been independently studied. The first is to compute the gradients with respect to the change in spike activation (activation-based methods), and the second is to compute the gradients with respect to the change in spike timing (timing-based methods). In this work, we present a comparative study of the two methods and propose a new supervised learning method that combines them. The proposed method utilizes each individual spike more effectively by shifting spike timings "},"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":"2006.02642","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2020-06-04T04:47:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4ef5763c08b05a61af8b3d03d4ebabe6ddd9e300ac320bfdc6d62cec6a641afa","abstract_canon_sha256":"4d97b534f74442e9653b55b77ab84f46d0fe0fd0012cb1ab0cb88ea271e75b4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:27.311091Z","signature_b64":"n0SnhGPdSz/re/4fIQut98pRaVkAZsGCgoHHklBir5CCOvcHdFlad7aNn20VsGZbmvnw/y+bxpJZVuolE9HeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"379ee75ebdfb6c578d861492af82faa2462db960ff1be02b16ea9c949ae59fee","last_reissued_at":"2026-07-05T01:45:27.310665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:27.310665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Jae-Joon Kim, Jinseok Kim, Kyungsu Kim","submitted_at":"2020-06-04T04:47:01Z","abstract_excerpt":"For the gradient computation across the time domain in Spiking Neural Networks (SNNs) training, two different approaches have been independently studied. The first is to compute the gradients with respect to the change in spike activation (activation-based methods), and the second is to compute the gradients with respect to the change in spike timing (timing-based methods). In this work, we present a comparative study of the two methods and propose a new supervised learning method that combines them. The proposed method utilizes each individual spike more effectively by shifting spike timings "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.02642","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/2006.02642/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":"2006.02642","created_at":"2026-07-05T01:45:27.310722+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.02642v2","created_at":"2026-07-05T01:45:27.310722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.02642","created_at":"2026-07-05T01:45:27.310722+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6POOXV57NWF","created_at":"2026-07-05T01:45:27.310722+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6POOXV57NWFPDMG","created_at":"2026-07-05T01:45:27.310722+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6POOXV5","created_at":"2026-07-05T01:45:27.310722+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17654","citing_title":"Enhanced Temporal Processing in Spiking Neural Networks for Static Object Detection Using 3D Convolutions","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6POOXV57NWFPDMGCSJK7AX2UJ","json":"https://pith.science/pith/G6POOXV57NWFPDMGCSJK7AX2UJ.json","graph_json":"https://pith.science/api/pith-number/G6POOXV57NWFPDMGCSJK7AX2UJ/graph.json","events_json":"https://pith.science/api/pith-number/G6POOXV57NWFPDMGCSJK7AX2UJ/events.json","paper":"https://pith.science/paper/G6POOXV5"},"agent_actions":{"view_html":"https://pith.science/pith/G6POOXV57NWFPDMGCSJK7AX2UJ","download_json":"https://pith.science/pith/G6POOXV57NWFPDMGCSJK7AX2UJ.json","view_paper":"https://pith.science/paper/G6POOXV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.02642&json=true","fetch_graph":"https://pith.science/api/pith-number/G6POOXV57NWFPDMGCSJK7AX2UJ/graph.json","fetch_events":"https://pith.science/api/pith-number/G6POOXV57NWFPDMGCSJK7AX2UJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6POOXV57NWFPDMGCSJK7AX2UJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6POOXV57NWFPDMGCSJK7AX2UJ/action/storage_attestation","attest_author":"https://pith.science/pith/G6POOXV57NWFPDMGCSJK7AX2UJ/action/author_attestation","sign_citation":"https://pith.science/pith/G6POOXV57NWFPDMGCSJK7AX2UJ/action/citation_signature","submit_replication":"https://pith.science/pith/G6POOXV57NWFPDMGCSJK7AX2UJ/action/replication_record"}},"created_at":"2026-07-05T01:45:27.310722+00:00","updated_at":"2026-07-05T01:45:27.310722+00:00"}