{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:323UMSSZSH2QXWYVVCGNN264LM","short_pith_number":"pith:323UMSSZ","schema_version":"1.0","canonical_sha256":"deb7464a5991f50bdb15a88cd6ebdc5b2b78db47089038d4c9f5d32c605fda27","source":{"kind":"arxiv","id":"2008.03658","version":3},"attestation_state":"computed","paper":{"title":"DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Kaushik Roy, Nitin Rathi","submitted_at":"2020-08-09T05:07:17Z","abstract_excerpt":"Bio-inspired spiking neural networks (SNNs), operating with asynchronous binary signals (or spikes) distributed over time, can potentially lead to greater computational efficiency on event-driven hardware. The state-of-the-art SNNs suffer from high inference latency, resulting from inefficient input encoding, and sub-optimal settings of the neuron parameters (firing threshold, and membrane leak). We propose DIET-SNN, a low-latency deep spiking network that is trained with gradient descent to optimize the membrane leak and the firing threshold along with other network parameters (weights). The "},"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":"2008.03658","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2020-08-09T05:07:17Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"c7ff1c612b2146a5682d2f7739e25744eb281ee99ee8626542ec955856e4e93b","abstract_canon_sha256":"52e4794106f3c8a376a77143c2108f0dca94ac071ba939f007a8bb1054256654"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:31.002739Z","signature_b64":"jWhiAWH60fSC9nwdfiq+p1/VyX0TXDs/O/UgbGCeofcyDzKkzYD1QRjmgDXBRer6nkRTQz8TDsSwovUA7GAtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"deb7464a5991f50bdb15a88cd6ebdc5b2b78db47089038d4c9f5d32c605fda27","last_reissued_at":"2026-07-05T01:56:31.002305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:31.002305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Kaushik Roy, Nitin Rathi","submitted_at":"2020-08-09T05:07:17Z","abstract_excerpt":"Bio-inspired spiking neural networks (SNNs), operating with asynchronous binary signals (or spikes) distributed over time, can potentially lead to greater computational efficiency on event-driven hardware. The state-of-the-art SNNs suffer from high inference latency, resulting from inefficient input encoding, and sub-optimal settings of the neuron parameters (firing threshold, and membrane leak). We propose DIET-SNN, a low-latency deep spiking network that is trained with gradient descent to optimize the membrane leak and the firing threshold along with other network parameters (weights). The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03658","kind":"arxiv","version":3},"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/2008.03658/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":"2008.03658","created_at":"2026-07-05T01:56:31.002374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.03658v3","created_at":"2026-07-05T01:56:31.002374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03658","created_at":"2026-07-05T01:56:31.002374+00:00"},{"alias_kind":"pith_short_12","alias_value":"323UMSSZSH2Q","created_at":"2026-07-05T01:56:31.002374+00:00"},{"alias_kind":"pith_short_16","alias_value":"323UMSSZSH2QXWYV","created_at":"2026-07-05T01:56:31.002374+00:00"},{"alias_kind":"pith_short_8","alias_value":"323UMSSZ","created_at":"2026-07-05T01:56:31.002374+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27412","citing_title":"Advancing Direct Training for Spiking Neural Networks with Circulate-Firing Neurons and Learnable Gradients","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/323UMSSZSH2QXWYVVCGNN264LM","json":"https://pith.science/pith/323UMSSZSH2QXWYVVCGNN264LM.json","graph_json":"https://pith.science/api/pith-number/323UMSSZSH2QXWYVVCGNN264LM/graph.json","events_json":"https://pith.science/api/pith-number/323UMSSZSH2QXWYVVCGNN264LM/events.json","paper":"https://pith.science/paper/323UMSSZ"},"agent_actions":{"view_html":"https://pith.science/pith/323UMSSZSH2QXWYVVCGNN264LM","download_json":"https://pith.science/pith/323UMSSZSH2QXWYVVCGNN264LM.json","view_paper":"https://pith.science/paper/323UMSSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.03658&json=true","fetch_graph":"https://pith.science/api/pith-number/323UMSSZSH2QXWYVVCGNN264LM/graph.json","fetch_events":"https://pith.science/api/pith-number/323UMSSZSH2QXWYVVCGNN264LM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/323UMSSZSH2QXWYVVCGNN264LM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/323UMSSZSH2QXWYVVCGNN264LM/action/storage_attestation","attest_author":"https://pith.science/pith/323UMSSZSH2QXWYVVCGNN264LM/action/author_attestation","sign_citation":"https://pith.science/pith/323UMSSZSH2QXWYVVCGNN264LM/action/citation_signature","submit_replication":"https://pith.science/pith/323UMSSZSH2QXWYVVCGNN264LM/action/replication_record"}},"created_at":"2026-07-05T01:56:31.002374+00:00","updated_at":"2026-07-05T01:56:31.002374+00:00"}