{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FBLV2D7Q2ELXUE4GKXPHMAHCXG","short_pith_number":"pith:FBLV2D7Q","schema_version":"1.0","canonical_sha256":"28575d0ff0d1177a138655de7600e2b996b47c8ba843e02d0177c2f610ca68c0","source":{"kind":"arxiv","id":"2210.12613","version":1},"attestation_state":"computed","paper":{"title":"Towards Energy-Efficient, Low-Latency and Accurate Spiking LSTMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.ET"],"primary_cat":"cs.NE","authors_text":"Gourav Datta, Haoqin Deng, Peter A. Beerel, Robert Aviles","submitted_at":"2022-10-23T04:10:27Z","abstract_excerpt":"Spiking Neural Networks (SNNs) have emerged as an attractive spatio-temporal computing paradigm for complex vision tasks. However, most existing works yield models that require many time steps and do not leverage the inherent temporal dynamics of spiking neural networks, even for sequential tasks. Motivated by this observation, we propose an \\rev{optimized spiking long short-term memory networks (LSTM) training framework that involves a novel ANN-to-SNN conversion framework, followed by SNN training}. In particular, we propose novel activation functions in the source LSTM architecture and judi"},"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":"2210.12613","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2022-10-23T04:10:27Z","cross_cats_sorted":["cs.ET"],"title_canon_sha256":"12efe4586d28a99abe5754f6a9bd29363771aa043dd6a124186b6363f57c784f","abstract_canon_sha256":"b316956f08f2c3a825b233980a9bd6e742d4df5dd0d4a3a446518dda617a1409"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:30.623759Z","signature_b64":"5l19ATmhPWM9F7ke16XI7r6ARUP9PtY4dsfEU4EDIjKrz2urLv88eS5X0qSG2b0MgXlL1uaL8PjMPBS5mu6TDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28575d0ff0d1177a138655de7600e2b996b47c8ba843e02d0177c2f610ca68c0","last_reissued_at":"2026-07-05T05:09:30.623252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:30.623252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Energy-Efficient, Low-Latency and Accurate Spiking LSTMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.ET"],"primary_cat":"cs.NE","authors_text":"Gourav Datta, Haoqin Deng, Peter A. Beerel, Robert Aviles","submitted_at":"2022-10-23T04:10:27Z","abstract_excerpt":"Spiking Neural Networks (SNNs) have emerged as an attractive spatio-temporal computing paradigm for complex vision tasks. However, most existing works yield models that require many time steps and do not leverage the inherent temporal dynamics of spiking neural networks, even for sequential tasks. Motivated by this observation, we propose an \\rev{optimized spiking long short-term memory networks (LSTM) training framework that involves a novel ANN-to-SNN conversion framework, followed by SNN training}. In particular, we propose novel activation functions in the source LSTM architecture and judi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12613","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/2210.12613/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":"2210.12613","created_at":"2026-07-05T05:09:30.623311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.12613v1","created_at":"2026-07-05T05:09:30.623311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12613","created_at":"2026-07-05T05:09:30.623311+00:00"},{"alias_kind":"pith_short_12","alias_value":"FBLV2D7Q2ELX","created_at":"2026-07-05T05:09:30.623311+00:00"},{"alias_kind":"pith_short_16","alias_value":"FBLV2D7Q2ELXUE4G","created_at":"2026-07-05T05:09:30.623311+00:00"},{"alias_kind":"pith_short_8","alias_value":"FBLV2D7Q","created_at":"2026-07-05T05:09:30.623311+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.21337","citing_title":"A 71.2-$\\mu$W Speech Recognition Accelerator with Recurrent Spiking Neural Network","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FBLV2D7Q2ELXUE4GKXPHMAHCXG","json":"https://pith.science/pith/FBLV2D7Q2ELXUE4GKXPHMAHCXG.json","graph_json":"https://pith.science/api/pith-number/FBLV2D7Q2ELXUE4GKXPHMAHCXG/graph.json","events_json":"https://pith.science/api/pith-number/FBLV2D7Q2ELXUE4GKXPHMAHCXG/events.json","paper":"https://pith.science/paper/FBLV2D7Q"},"agent_actions":{"view_html":"https://pith.science/pith/FBLV2D7Q2ELXUE4GKXPHMAHCXG","download_json":"https://pith.science/pith/FBLV2D7Q2ELXUE4GKXPHMAHCXG.json","view_paper":"https://pith.science/paper/FBLV2D7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.12613&json=true","fetch_graph":"https://pith.science/api/pith-number/FBLV2D7Q2ELXUE4GKXPHMAHCXG/graph.json","fetch_events":"https://pith.science/api/pith-number/FBLV2D7Q2ELXUE4GKXPHMAHCXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FBLV2D7Q2ELXUE4GKXPHMAHCXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FBLV2D7Q2ELXUE4GKXPHMAHCXG/action/storage_attestation","attest_author":"https://pith.science/pith/FBLV2D7Q2ELXUE4GKXPHMAHCXG/action/author_attestation","sign_citation":"https://pith.science/pith/FBLV2D7Q2ELXUE4GKXPHMAHCXG/action/citation_signature","submit_replication":"https://pith.science/pith/FBLV2D7Q2ELXUE4GKXPHMAHCXG/action/replication_record"}},"created_at":"2026-07-05T05:09:30.623311+00:00","updated_at":"2026-07-05T05:09:30.623311+00:00"}