{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZBL2IONTQIBLPUWR7BZPDYWGPA","short_pith_number":"pith:ZBL2IONT","schema_version":"1.0","canonical_sha256":"c857a439b38202b7d2d1f872f1e2c67800351971f5568120641ff930672b8dec","source":{"kind":"arxiv","id":"2110.14092","version":1},"attestation_state":"computed","paper":{"title":"BioGrad: Biologically Plausible Gradient-Based Learning for Spiking Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.NC"],"primary_cat":"cs.NE","authors_text":"Guangzhi Tang, Ioannis Polykretis, Konstantinos P. Michmizos, Neelesh Kumar","submitted_at":"2021-10-27T00:07:25Z","abstract_excerpt":"Spiking neural networks (SNN) are delivering energy-efficient, massively parallel, and low-latency solutions to AI problems, facilitated by the emerging neuromorphic chips. To harness these computational benefits, SNN need to be trained by learning algorithms that adhere to brain-inspired neuromorphic principles, namely event-based, local, and online computations. Yet, the state-of-the-art SNN training algorithms are based on backprop that does not follow the above principles. Due to its limited biological plausibility, the application of backprop to SNN requires non-local feedback pathways fo"},"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":"2110.14092","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2021-10-27T00:07:25Z","cross_cats_sorted":["cs.LG","q-bio.NC"],"title_canon_sha256":"83a96e304e16461726a5c5995e53c36479f78118291d613bdd8578537734e2b1","abstract_canon_sha256":"657325eefa4aa62af8e30c9c42cfca1f3287c311e59bd82d3f6af906fe330918"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:23.776501Z","signature_b64":"tFfzzu/7BBhzy9XWO6kjrhGy24pNsNaJU66tfs6bKZOArZn8OTbuSHA/guj0RjrwjFAp+9pUeFROXkeYFAoRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c857a439b38202b7d2d1f872f1e2c67800351971f5568120641ff930672b8dec","last_reissued_at":"2026-07-05T03:26:23.775886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:23.775886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BioGrad: Biologically Plausible Gradient-Based Learning for Spiking Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.NC"],"primary_cat":"cs.NE","authors_text":"Guangzhi Tang, Ioannis Polykretis, Konstantinos P. Michmizos, Neelesh Kumar","submitted_at":"2021-10-27T00:07:25Z","abstract_excerpt":"Spiking neural networks (SNN) are delivering energy-efficient, massively parallel, and low-latency solutions to AI problems, facilitated by the emerging neuromorphic chips. To harness these computational benefits, SNN need to be trained by learning algorithms that adhere to brain-inspired neuromorphic principles, namely event-based, local, and online computations. Yet, the state-of-the-art SNN training algorithms are based on backprop that does not follow the above principles. Due to its limited biological plausibility, the application of backprop to SNN requires non-local feedback pathways fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14092","kind":"arxiv","version":1},"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/2110.14092/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":"2110.14092","created_at":"2026-07-05T03:26:23.775991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.14092v1","created_at":"2026-07-05T03:26:23.775991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14092","created_at":"2026-07-05T03:26:23.775991+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBL2IONTQIBL","created_at":"2026-07-05T03:26:23.775991+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBL2IONTQIBLPUWR","created_at":"2026-07-05T03:26:23.775991+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBL2IONT","created_at":"2026-07-05T03:26:23.775991+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06636","citing_title":"Full Integer Arithmetic Online Training for Spiking Neural Networks","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZBL2IONTQIBLPUWR7BZPDYWGPA","json":"https://pith.science/pith/ZBL2IONTQIBLPUWR7BZPDYWGPA.json","graph_json":"https://pith.science/api/pith-number/ZBL2IONTQIBLPUWR7BZPDYWGPA/graph.json","events_json":"https://pith.science/api/pith-number/ZBL2IONTQIBLPUWR7BZPDYWGPA/events.json","paper":"https://pith.science/paper/ZBL2IONT"},"agent_actions":{"view_html":"https://pith.science/pith/ZBL2IONTQIBLPUWR7BZPDYWGPA","download_json":"https://pith.science/pith/ZBL2IONTQIBLPUWR7BZPDYWGPA.json","view_paper":"https://pith.science/paper/ZBL2IONT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.14092&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBL2IONTQIBLPUWR7BZPDYWGPA/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBL2IONTQIBLPUWR7BZPDYWGPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBL2IONTQIBLPUWR7BZPDYWGPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBL2IONTQIBLPUWR7BZPDYWGPA/action/storage_attestation","attest_author":"https://pith.science/pith/ZBL2IONTQIBLPUWR7BZPDYWGPA/action/author_attestation","sign_citation":"https://pith.science/pith/ZBL2IONTQIBLPUWR7BZPDYWGPA/action/citation_signature","submit_replication":"https://pith.science/pith/ZBL2IONTQIBLPUWR7BZPDYWGPA/action/replication_record"}},"created_at":"2026-07-05T03:26:23.775991+00:00","updated_at":"2026-07-05T03:26:23.775991+00:00"}