{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:37MRKZOT6N74ZVDFTGN62UIASC","short_pith_number":"pith:37MRKZOT","schema_version":"1.0","canonical_sha256":"dfd91565d3f37fccd465999bed510090b5970146a41bcecf56b2a4c9716ddf00","source":{"kind":"arxiv","id":"2105.08810","version":2},"attestation_state":"computed","paper":{"title":"Sparse Spiking Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.ET","cs.LG","q-bio.NC"],"primary_cat":"cs.NE","authors_text":"Dan F.M. Goodman, Nicolas Perez-Nieves","submitted_at":"2021-05-18T20:00:55Z","abstract_excerpt":"There is an increasing interest in emulating Spiking Neural Networks (SNNs) on neuromorphic computing devices due to their low energy consumption. Recent advances have allowed training SNNs to a point where they start to compete with traditional Artificial Neural Networks (ANNs) in terms of accuracy, while at the same time being energy efficient when run on neuromorphic hardware. However, the process of training SNNs is still based on dense tensor operations originally developed for ANNs which do not leverage the spatiotemporally sparse nature of SNNs. We present here the first sparse SNN back"},"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":"2105.08810","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2021-05-18T20:00:55Z","cross_cats_sorted":["cs.ET","cs.LG","q-bio.NC"],"title_canon_sha256":"68e48eb6a9a4df805cf142ba7ff5b9cd5baa5cd67237fd235cf8bfff69e53baa","abstract_canon_sha256":"2ed1424111f54f2183ad6c56bf5a875587e6cada333ae537b54f5d65e1937929"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:06.139229Z","signature_b64":"ja1kXVeVTwMWZSnbSHpAZxv3vm2++jRQYaZ+c0JJyCW+mMlYyfLmub6Us+OWzE0ycSmGLIomQEuIm4G/eG7kDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfd91565d3f37fccd465999bed510090b5970146a41bcecf56b2a4c9716ddf00","last_reissued_at":"2026-07-05T03:48:06.138830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:06.138830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse Spiking Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.ET","cs.LG","q-bio.NC"],"primary_cat":"cs.NE","authors_text":"Dan F.M. Goodman, Nicolas Perez-Nieves","submitted_at":"2021-05-18T20:00:55Z","abstract_excerpt":"There is an increasing interest in emulating Spiking Neural Networks (SNNs) on neuromorphic computing devices due to their low energy consumption. Recent advances have allowed training SNNs to a point where they start to compete with traditional Artificial Neural Networks (ANNs) in terms of accuracy, while at the same time being energy efficient when run on neuromorphic hardware. However, the process of training SNNs is still based on dense tensor operations originally developed for ANNs which do not leverage the spatiotemporally sparse nature of SNNs. We present here the first sparse SNN back"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08810","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/2105.08810/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":"2105.08810","created_at":"2026-07-05T03:48:06.138886+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.08810v2","created_at":"2026-07-05T03:48:06.138886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08810","created_at":"2026-07-05T03:48:06.138886+00:00"},{"alias_kind":"pith_short_12","alias_value":"37MRKZOT6N74","created_at":"2026-07-05T03:48:06.138886+00:00"},{"alias_kind":"pith_short_16","alias_value":"37MRKZOT6N74ZVDF","created_at":"2026-07-05T03:48:06.138886+00:00"},{"alias_kind":"pith_short_8","alias_value":"37MRKZOT","created_at":"2026-07-05T03:48:06.138886+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.11407","citing_title":"A Truly Sparse and General Implementation of Gradient-Based Synaptic Plasticity","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/37MRKZOT6N74ZVDFTGN62UIASC","json":"https://pith.science/pith/37MRKZOT6N74ZVDFTGN62UIASC.json","graph_json":"https://pith.science/api/pith-number/37MRKZOT6N74ZVDFTGN62UIASC/graph.json","events_json":"https://pith.science/api/pith-number/37MRKZOT6N74ZVDFTGN62UIASC/events.json","paper":"https://pith.science/paper/37MRKZOT"},"agent_actions":{"view_html":"https://pith.science/pith/37MRKZOT6N74ZVDFTGN62UIASC","download_json":"https://pith.science/pith/37MRKZOT6N74ZVDFTGN62UIASC.json","view_paper":"https://pith.science/paper/37MRKZOT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.08810&json=true","fetch_graph":"https://pith.science/api/pith-number/37MRKZOT6N74ZVDFTGN62UIASC/graph.json","fetch_events":"https://pith.science/api/pith-number/37MRKZOT6N74ZVDFTGN62UIASC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37MRKZOT6N74ZVDFTGN62UIASC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37MRKZOT6N74ZVDFTGN62UIASC/action/storage_attestation","attest_author":"https://pith.science/pith/37MRKZOT6N74ZVDFTGN62UIASC/action/author_attestation","sign_citation":"https://pith.science/pith/37MRKZOT6N74ZVDFTGN62UIASC/action/citation_signature","submit_replication":"https://pith.science/pith/37MRKZOT6N74ZVDFTGN62UIASC/action/replication_record"}},"created_at":"2026-07-05T03:48:06.138886+00:00","updated_at":"2026-07-05T03:48:06.138886+00:00"}