{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:32L34SP25DG3ZGYTAV2QEZUBQ6","short_pith_number":"pith:32L34SP2","schema_version":"1.0","canonical_sha256":"de97be49fae8cdbc9b130575026681879b3f437584d0fabe0a8672f8cf96fc43","source":{"kind":"arxiv","id":"2302.11618","version":2},"attestation_state":"computed","paper":{"title":"Heterogeneous Neuronal and Synaptic Dynamics for Spike-Efficient Unsupervised Learning: Theory and Design Principles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.AI","authors_text":"Biswadeep Chakraborty, Saibal Mukhopadhyay","submitted_at":"2023-02-22T19:48:02Z","abstract_excerpt":"This paper shows that the heterogeneity in neuronal and synaptic dynamics reduces the spiking activity of a Recurrent Spiking Neural Network (RSNN) while improving prediction performance, enabling spike-efficient (unsupervised) learning. We analytically show that the diversity in neurons' integration/relaxation dynamics improves an RSNN's ability to learn more distinct input patterns (higher memory capacity), leading to improved classification and prediction performance. We further prove that heterogeneous Spike-Timing-Dependent-Plasticity (STDP) dynamics of synapses reduce spiking activity bu"},"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":"2302.11618","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-02-22T19:48:02Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"04de693123f154b171134377ed5ef651903cf444fe8de1572b4717063dba09e1","abstract_canon_sha256":"9f80403b081d882a888b2ffb9574434e1c57320cd289a3f346d89050a98c97eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:55.445038Z","signature_b64":"/6ujsdpRRaIcjNheKG/W7BPwgBiYqbqaoQ9XYB/0MgPfYyhrFVCNXX3ockXQTYquQVZLDzxVW8e+ABDoU2tFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de97be49fae8cdbc9b130575026681879b3f437584d0fabe0a8672f8cf96fc43","last_reissued_at":"2026-07-05T06:37:55.444638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:55.444638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heterogeneous Neuronal and Synaptic Dynamics for Spike-Efficient Unsupervised Learning: Theory and Design Principles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.AI","authors_text":"Biswadeep Chakraborty, Saibal Mukhopadhyay","submitted_at":"2023-02-22T19:48:02Z","abstract_excerpt":"This paper shows that the heterogeneity in neuronal and synaptic dynamics reduces the spiking activity of a Recurrent Spiking Neural Network (RSNN) while improving prediction performance, enabling spike-efficient (unsupervised) learning. We analytically show that the diversity in neurons' integration/relaxation dynamics improves an RSNN's ability to learn more distinct input patterns (higher memory capacity), leading to improved classification and prediction performance. We further prove that heterogeneous Spike-Timing-Dependent-Plasticity (STDP) dynamics of synapses reduce spiking activity bu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11618","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/2302.11618/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":"2302.11618","created_at":"2026-07-05T06:37:55.444695+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.11618v2","created_at":"2026-07-05T06:37:55.444695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11618","created_at":"2026-07-05T06:37:55.444695+00:00"},{"alias_kind":"pith_short_12","alias_value":"32L34SP25DG3","created_at":"2026-07-05T06:37:55.444695+00:00"},{"alias_kind":"pith_short_16","alias_value":"32L34SP25DG3ZGYT","created_at":"2026-07-05T06:37:55.444695+00:00"},{"alias_kind":"pith_short_8","alias_value":"32L34SP2","created_at":"2026-07-05T06:37:55.444695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.07243","citing_title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/32L34SP25DG3ZGYTAV2QEZUBQ6","json":"https://pith.science/pith/32L34SP25DG3ZGYTAV2QEZUBQ6.json","graph_json":"https://pith.science/api/pith-number/32L34SP25DG3ZGYTAV2QEZUBQ6/graph.json","events_json":"https://pith.science/api/pith-number/32L34SP25DG3ZGYTAV2QEZUBQ6/events.json","paper":"https://pith.science/paper/32L34SP2"},"agent_actions":{"view_html":"https://pith.science/pith/32L34SP25DG3ZGYTAV2QEZUBQ6","download_json":"https://pith.science/pith/32L34SP25DG3ZGYTAV2QEZUBQ6.json","view_paper":"https://pith.science/paper/32L34SP2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.11618&json=true","fetch_graph":"https://pith.science/api/pith-number/32L34SP25DG3ZGYTAV2QEZUBQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/32L34SP25DG3ZGYTAV2QEZUBQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/32L34SP25DG3ZGYTAV2QEZUBQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/32L34SP25DG3ZGYTAV2QEZUBQ6/action/storage_attestation","attest_author":"https://pith.science/pith/32L34SP25DG3ZGYTAV2QEZUBQ6/action/author_attestation","sign_citation":"https://pith.science/pith/32L34SP25DG3ZGYTAV2QEZUBQ6/action/citation_signature","submit_replication":"https://pith.science/pith/32L34SP25DG3ZGYTAV2QEZUBQ6/action/replication_record"}},"created_at":"2026-07-05T06:37:55.444695+00:00","updated_at":"2026-07-05T06:37:55.444695+00:00"}