{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N2ZVBWSAD6QFBBIQ7HE2W4HDJV","short_pith_number":"pith:N2ZVBWSA","schema_version":"1.0","canonical_sha256":"6eb350da401fa0508510f9c9ab70e34d56b0d268861e1f39b5a34e29191a6dc9","source":{"kind":"arxiv","id":"2503.00301","version":3},"attestation_state":"computed","paper":{"title":"Differential Coding for Training-Free ANN-to-SNN Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peng Xue, Tiejun Huang, Tong Bu, Wei Fang, Wenxuan Liu, Yuanhong Tang, Zecheng Hao, Zhaofei Yu, Zihan Huang","submitted_at":"2025-03-01T02:17:35Z","abstract_excerpt":"Spiking Neural Networks (SNNs) exhibit significant potential due to their low energy consumption. Converting Artificial Neural Networks (ANNs) to SNNs is an efficient way to achieve high-performance SNNs. However, many conversion methods are based on rate coding, which requires numerous spikes and longer time-steps compared to directly trained SNNs, leading to increased energy consumption and latency. This article introduces differential coding for ANN-to-SNN conversion, a novel coding scheme that reduces spike counts and energy consumption by transmitting changes in rate information rather th"},"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":"2503.00301","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-01T02:17:35Z","cross_cats_sorted":[],"title_canon_sha256":"6c37c2abe3a40a58836388bb62807dde2184cfc7198a3240737d3d9bb130bb73","abstract_canon_sha256":"e72a951edc465462fe5575609b3eadfed8b19937493ab4ea67438f74a36987c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:20.958256Z","signature_b64":"2OiFb6ujDckgpGTWZUdoonqiJMuC6z2XFARjY6XVoJYgSH4JBeBJJMluhOoEpapQ+NawdDSTVmR3hTBUr+kgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6eb350da401fa0508510f9c9ab70e34d56b0d268861e1f39b5a34e29191a6dc9","last_reissued_at":"2026-07-05T11:33:20.957732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:20.957732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differential Coding for Training-Free ANN-to-SNN Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peng Xue, Tiejun Huang, Tong Bu, Wei Fang, Wenxuan Liu, Yuanhong Tang, Zecheng Hao, Zhaofei Yu, Zihan Huang","submitted_at":"2025-03-01T02:17:35Z","abstract_excerpt":"Spiking Neural Networks (SNNs) exhibit significant potential due to their low energy consumption. Converting Artificial Neural Networks (ANNs) to SNNs is an efficient way to achieve high-performance SNNs. However, many conversion methods are based on rate coding, which requires numerous spikes and longer time-steps compared to directly trained SNNs, leading to increased energy consumption and latency. This article introduces differential coding for ANN-to-SNN conversion, a novel coding scheme that reduces spike counts and energy consumption by transmitting changes in rate information rather th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00301","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/2503.00301/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":"2503.00301","created_at":"2026-07-05T11:33:20.957790+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00301v3","created_at":"2026-07-05T11:33:20.957790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00301","created_at":"2026-07-05T11:33:20.957790+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2ZVBWSAD6QF","created_at":"2026-07-05T11:33:20.957790+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2ZVBWSAD6QFBBIQ","created_at":"2026-07-05T11:33:20.957790+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2ZVBWSA","created_at":"2026-07-05T11:33:20.957790+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20031","citing_title":"A Neuromorphic Reinforcement Learning Framework for Efficient Pathfinding in Robotic Mobile Fulfillment Systems","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27807","citing_title":"SpikeVLA: Vision-Language-Action Models with Spiking Neural Networks","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2ZVBWSAD6QFBBIQ7HE2W4HDJV","json":"https://pith.science/pith/N2ZVBWSAD6QFBBIQ7HE2W4HDJV.json","graph_json":"https://pith.science/api/pith-number/N2ZVBWSAD6QFBBIQ7HE2W4HDJV/graph.json","events_json":"https://pith.science/api/pith-number/N2ZVBWSAD6QFBBIQ7HE2W4HDJV/events.json","paper":"https://pith.science/paper/N2ZVBWSA"},"agent_actions":{"view_html":"https://pith.science/pith/N2ZVBWSAD6QFBBIQ7HE2W4HDJV","download_json":"https://pith.science/pith/N2ZVBWSAD6QFBBIQ7HE2W4HDJV.json","view_paper":"https://pith.science/paper/N2ZVBWSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00301&json=true","fetch_graph":"https://pith.science/api/pith-number/N2ZVBWSAD6QFBBIQ7HE2W4HDJV/graph.json","fetch_events":"https://pith.science/api/pith-number/N2ZVBWSAD6QFBBIQ7HE2W4HDJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2ZVBWSAD6QFBBIQ7HE2W4HDJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2ZVBWSAD6QFBBIQ7HE2W4HDJV/action/storage_attestation","attest_author":"https://pith.science/pith/N2ZVBWSAD6QFBBIQ7HE2W4HDJV/action/author_attestation","sign_citation":"https://pith.science/pith/N2ZVBWSAD6QFBBIQ7HE2W4HDJV/action/citation_signature","submit_replication":"https://pith.science/pith/N2ZVBWSAD6QFBBIQ7HE2W4HDJV/action/replication_record"}},"created_at":"2026-07-05T11:33:20.957790+00:00","updated_at":"2026-07-05T11:33:20.957790+00:00"}