{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7N3E5MIHKQJDVMYFVBLTBIGGV7","short_pith_number":"pith:7N3E5MIH","schema_version":"1.0","canonical_sha256":"fb764eb10754123ab305a85730a0c6afec71ba03e7c7c6313a6122ece7dcdbf4","source":{"kind":"arxiv","id":"2303.04347","version":1},"attestation_state":"computed","paper":{"title":"Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Jianhao Ding, Penglin Dai, Tiejun Huang, Tong Bu, Wei Fang, Zhaofei Yu","submitted_at":"2023-03-08T03:04:53Z","abstract_excerpt":"Spiking Neural Networks (SNNs) have gained great attraction due to their distinctive properties of low power consumption and fast inference on neuromorphic hardware. As the most effective method to get deep SNNs, ANN-SNN conversion has achieved comparable performance as ANNs on large-scale datasets. Despite this, it requires long time-steps to match the firing rates of SNNs to the activation of ANNs. As a result, the converted SNN suffers severe performance degradation problems with short time-steps, which hamper the practical application of SNNs. In this paper, we theoretically analyze ANN-SN"},"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":"2303.04347","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2023-03-08T03:04:53Z","cross_cats_sorted":[],"title_canon_sha256":"ed710a0577daf6da41588e26d4b47e11f77ef1d41d7fa061dda2632f51bf4c57","abstract_canon_sha256":"fe7eadf3c13a83d499424060acb2a6d6ec4b485894af0feb0774ec043bf068a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:20.252967Z","signature_b64":"soVaDzayZrnE4EF3dwZGx2veezLL04vLJOrD3kh1nbxU1iA6dssMF3DyD3/npLQgt3/aOCKufJB9WulERhtHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb764eb10754123ab305a85730a0c6afec71ba03e7c7c6313a6122ece7dcdbf4","last_reissued_at":"2026-07-05T05:49:20.252492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:20.252492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Jianhao Ding, Penglin Dai, Tiejun Huang, Tong Bu, Wei Fang, Zhaofei Yu","submitted_at":"2023-03-08T03:04:53Z","abstract_excerpt":"Spiking Neural Networks (SNNs) have gained great attraction due to their distinctive properties of low power consumption and fast inference on neuromorphic hardware. As the most effective method to get deep SNNs, ANN-SNN conversion has achieved comparable performance as ANNs on large-scale datasets. Despite this, it requires long time-steps to match the firing rates of SNNs to the activation of ANNs. As a result, the converted SNN suffers severe performance degradation problems with short time-steps, which hamper the practical application of SNNs. In this paper, we theoretically analyze ANN-SN"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04347","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/2303.04347/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":"2303.04347","created_at":"2026-07-05T05:49:20.252554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.04347v1","created_at":"2026-07-05T05:49:20.252554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04347","created_at":"2026-07-05T05:49:20.252554+00:00"},{"alias_kind":"pith_short_12","alias_value":"7N3E5MIHKQJD","created_at":"2026-07-05T05:49:20.252554+00:00"},{"alias_kind":"pith_short_16","alias_value":"7N3E5MIHKQJDVMYF","created_at":"2026-07-05T05:49:20.252554+00:00"},{"alias_kind":"pith_short_8","alias_value":"7N3E5MIH","created_at":"2026-07-05T05:49:20.252554+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"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":12,"is_internal_anchor":false},{"citing_arxiv_id":"2403.16552","citing_title":"QKFormer: Hierarchical Spiking Transformer using Q-K Attention","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2501.06786","citing_title":"Temporal-Aware Spiking Transformer Hashing Based on 3D-DWT","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20680","citing_title":"DarkShake-DVS: Event-based Human Action Recognition under Low-light andShaking Camera Conditions","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20802","citing_title":"ELSA: An ELastic SNN Inference Architecture for Efficient Neuromorphic Computing","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7N3E5MIHKQJDVMYFVBLTBIGGV7","json":"https://pith.science/pith/7N3E5MIHKQJDVMYFVBLTBIGGV7.json","graph_json":"https://pith.science/api/pith-number/7N3E5MIHKQJDVMYFVBLTBIGGV7/graph.json","events_json":"https://pith.science/api/pith-number/7N3E5MIHKQJDVMYFVBLTBIGGV7/events.json","paper":"https://pith.science/paper/7N3E5MIH"},"agent_actions":{"view_html":"https://pith.science/pith/7N3E5MIHKQJDVMYFVBLTBIGGV7","download_json":"https://pith.science/pith/7N3E5MIHKQJDVMYFVBLTBIGGV7.json","view_paper":"https://pith.science/paper/7N3E5MIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.04347&json=true","fetch_graph":"https://pith.science/api/pith-number/7N3E5MIHKQJDVMYFVBLTBIGGV7/graph.json","fetch_events":"https://pith.science/api/pith-number/7N3E5MIHKQJDVMYFVBLTBIGGV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7N3E5MIHKQJDVMYFVBLTBIGGV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7N3E5MIHKQJDVMYFVBLTBIGGV7/action/storage_attestation","attest_author":"https://pith.science/pith/7N3E5MIHKQJDVMYFVBLTBIGGV7/action/author_attestation","sign_citation":"https://pith.science/pith/7N3E5MIHKQJDVMYFVBLTBIGGV7/action/citation_signature","submit_replication":"https://pith.science/pith/7N3E5MIHKQJDVMYFVBLTBIGGV7/action/replication_record"}},"created_at":"2026-07-05T05:49:20.252554+00:00","updated_at":"2026-07-05T05:49:20.252554+00:00"}