{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N5LXT6S6IDYBSSK6HNHVAZB5RI","short_pith_number":"pith:N5LXT6S6","schema_version":"1.0","canonical_sha256":"6f5779fa5e40f019495e3b4f50643d8a1cb009e94a3b593b82d36553045b6c90","source":{"kind":"arxiv","id":"2407.20708","version":4},"attestation_state":"computed","paper":{"title":"Integer-Valued Training and Spike-Driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Xu, Guoqi Li, Man Yao, Xinhao Luo, Yuhong Chou","submitted_at":"2024-07-30T10:04:16Z","abstract_excerpt":"Brain-inspired Spiking Neural Networks (SNNs) have bio-plausibility and low-power advantages over Artificial Neural Networks (ANNs). Applications of SNNs are currently limited to simple classification tasks because of their poor performance. In this work, we focus on bridging the performance gap between ANNs and SNNs on object detection. Our design revolves around network architecture and spiking neuron. First, the overly complex module design causes spike degradation when the YOLO series is converted to the corresponding spiking version. We design a SpikeYOLO architecture to solve this proble"},"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":"2407.20708","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-30T10:04:16Z","cross_cats_sorted":[],"title_canon_sha256":"998c5aa42632c46cc781b7047dadd7759fc0caf4bdca5ecd8a4a58bd386e3b7a","abstract_canon_sha256":"45a0cf40a665c7a8533f31304e9038e2e2e9518c0008a910b3202c9c79d25268"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:07.613916Z","signature_b64":"4CXgtzYOMdkA/nSIFNXeIvA7ANHYonVkagGY0cbOWgvwpcNzg1jBlWMhcId6yr0Y4utnqTSrnCuG3f2H3+cACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f5779fa5e40f019495e3b4f50643d8a1cb009e94a3b593b82d36553045b6c90","last_reissued_at":"2026-07-05T10:49:07.613465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:07.613465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Integer-Valued Training and Spike-Driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Xu, Guoqi Li, Man Yao, Xinhao Luo, Yuhong Chou","submitted_at":"2024-07-30T10:04:16Z","abstract_excerpt":"Brain-inspired Spiking Neural Networks (SNNs) have bio-plausibility and low-power advantages over Artificial Neural Networks (ANNs). Applications of SNNs are currently limited to simple classification tasks because of their poor performance. In this work, we focus on bridging the performance gap between ANNs and SNNs on object detection. Our design revolves around network architecture and spiking neuron. First, the overly complex module design causes spike degradation when the YOLO series is converted to the corresponding spiking version. We design a SpikeYOLO architecture to solve this proble"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20708","kind":"arxiv","version":4},"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/2407.20708/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":"2407.20708","created_at":"2026-07-05T10:49:07.613523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.20708v4","created_at":"2026-07-05T10:49:07.613523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20708","created_at":"2026-07-05T10:49:07.613523+00:00"},{"alias_kind":"pith_short_12","alias_value":"N5LXT6S6IDYB","created_at":"2026-07-05T10:49:07.613523+00:00"},{"alias_kind":"pith_short_16","alias_value":"N5LXT6S6IDYBSSK6","created_at":"2026-07-05T10:49:07.613523+00:00"},{"alias_kind":"pith_short_8","alias_value":"N5LXT6S6","created_at":"2026-07-05T10:49:07.613523+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.17674","citing_title":"SVL: Empowering Spiking Neural Networks for Efficient 3D Open-World Understanding","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12874","citing_title":"LIFE -- an energy efficient advanced continual learning agentic AI framework for frontier systems","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N5LXT6S6IDYBSSK6HNHVAZB5RI","json":"https://pith.science/pith/N5LXT6S6IDYBSSK6HNHVAZB5RI.json","graph_json":"https://pith.science/api/pith-number/N5LXT6S6IDYBSSK6HNHVAZB5RI/graph.json","events_json":"https://pith.science/api/pith-number/N5LXT6S6IDYBSSK6HNHVAZB5RI/events.json","paper":"https://pith.science/paper/N5LXT6S6"},"agent_actions":{"view_html":"https://pith.science/pith/N5LXT6S6IDYBSSK6HNHVAZB5RI","download_json":"https://pith.science/pith/N5LXT6S6IDYBSSK6HNHVAZB5RI.json","view_paper":"https://pith.science/paper/N5LXT6S6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.20708&json=true","fetch_graph":"https://pith.science/api/pith-number/N5LXT6S6IDYBSSK6HNHVAZB5RI/graph.json","fetch_events":"https://pith.science/api/pith-number/N5LXT6S6IDYBSSK6HNHVAZB5RI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N5LXT6S6IDYBSSK6HNHVAZB5RI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N5LXT6S6IDYBSSK6HNHVAZB5RI/action/storage_attestation","attest_author":"https://pith.science/pith/N5LXT6S6IDYBSSK6HNHVAZB5RI/action/author_attestation","sign_citation":"https://pith.science/pith/N5LXT6S6IDYBSSK6HNHVAZB5RI/action/citation_signature","submit_replication":"https://pith.science/pith/N5LXT6S6IDYBSSK6HNHVAZB5RI/action/replication_record"}},"created_at":"2026-07-05T10:49:07.613523+00:00","updated_at":"2026-07-05T10:49:07.613523+00:00"}