{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:URYCJOPRPURBEDPF5FYMLLHHTG","short_pith_number":"pith:URYCJOPR","schema_version":"1.0","canonical_sha256":"a47024b9f17d22120de5e970c5ace799b73b4f4c94848431caeb6af8014495d5","source":{"kind":"arxiv","id":"2310.19067","version":1},"attestation_state":"computed","paper":{"title":"Expanding memory in recurrent spiking networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Fabien Alibart, Ismael Balafrej, Jean Rouat","submitted_at":"2023-10-29T16:46:26Z","abstract_excerpt":"Recurrent spiking neural networks (RSNNs) are notoriously difficult to train because of the vanishing gradient problem that is enhanced by the binary nature of the spikes. In this paper, we review the ability of the current state-of-the-art RSNNs to solve long-term memory tasks, and show that they have strong constraints both in performance, and for their implementation on hardware analog neuromorphic processors. We present a novel spiking neural network that circumvents these limitations. Our biologically inspired neural network uses synaptic delays, branching factor regularization and a nove"},"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":"2310.19067","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2023-10-29T16:46:26Z","cross_cats_sorted":[],"title_canon_sha256":"0e26103ae9ce6b687518f80d97ccb9d5a0c7f64a4cc4980742fe7f41e486fa5c","abstract_canon_sha256":"7b413cc403b8c3ee4bcead16b71051de04143c21e19efc3ffa15dd02f85172a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:45.620303Z","signature_b64":"wx2RYLuZRat7AoIv6oDDYSJH1xyOj7CYZbHaQBbt6yM4N/ZaglGqoCeVKEppomnZ0WPjc61yAihApj4Ta2YrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a47024b9f17d22120de5e970c5ace799b73b4f4c94848431caeb6af8014495d5","last_reissued_at":"2026-07-05T07:06:45.619800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:45.619800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expanding memory in recurrent spiking networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Fabien Alibart, Ismael Balafrej, Jean Rouat","submitted_at":"2023-10-29T16:46:26Z","abstract_excerpt":"Recurrent spiking neural networks (RSNNs) are notoriously difficult to train because of the vanishing gradient problem that is enhanced by the binary nature of the spikes. In this paper, we review the ability of the current state-of-the-art RSNNs to solve long-term memory tasks, and show that they have strong constraints both in performance, and for their implementation on hardware analog neuromorphic processors. We present a novel spiking neural network that circumvents these limitations. Our biologically inspired neural network uses synaptic delays, branching factor regularization and a nove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19067","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/2310.19067/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":"2310.19067","created_at":"2026-07-05T07:06:45.619858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.19067v1","created_at":"2026-07-05T07:06:45.619858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19067","created_at":"2026-07-05T07:06:45.619858+00:00"},{"alias_kind":"pith_short_12","alias_value":"URYCJOPRPURB","created_at":"2026-07-05T07:06:45.619858+00:00"},{"alias_kind":"pith_short_16","alias_value":"URYCJOPRPURBEDPF","created_at":"2026-07-05T07:06:45.619858+00:00"},{"alias_kind":"pith_short_8","alias_value":"URYCJOPR","created_at":"2026-07-05T07:06:45.619858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02532","citing_title":"Feature Attribution Stability Suite: How Stable Are Post-Hoc Attributions?","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/URYCJOPRPURBEDPF5FYMLLHHTG","json":"https://pith.science/pith/URYCJOPRPURBEDPF5FYMLLHHTG.json","graph_json":"https://pith.science/api/pith-number/URYCJOPRPURBEDPF5FYMLLHHTG/graph.json","events_json":"https://pith.science/api/pith-number/URYCJOPRPURBEDPF5FYMLLHHTG/events.json","paper":"https://pith.science/paper/URYCJOPR"},"agent_actions":{"view_html":"https://pith.science/pith/URYCJOPRPURBEDPF5FYMLLHHTG","download_json":"https://pith.science/pith/URYCJOPRPURBEDPF5FYMLLHHTG.json","view_paper":"https://pith.science/paper/URYCJOPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.19067&json=true","fetch_graph":"https://pith.science/api/pith-number/URYCJOPRPURBEDPF5FYMLLHHTG/graph.json","fetch_events":"https://pith.science/api/pith-number/URYCJOPRPURBEDPF5FYMLLHHTG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URYCJOPRPURBEDPF5FYMLLHHTG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URYCJOPRPURBEDPF5FYMLLHHTG/action/storage_attestation","attest_author":"https://pith.science/pith/URYCJOPRPURBEDPF5FYMLLHHTG/action/author_attestation","sign_citation":"https://pith.science/pith/URYCJOPRPURBEDPF5FYMLLHHTG/action/citation_signature","submit_replication":"https://pith.science/pith/URYCJOPRPURBEDPF5FYMLLHHTG/action/replication_record"}},"created_at":"2026-07-05T07:06:45.619858+00:00","updated_at":"2026-07-05T07:06:45.619858+00:00"}