{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:N5NXNC2JNVB6YD3WHAUH66WD74","short_pith_number":"pith:N5NXNC2J","schema_version":"1.0","canonical_sha256":"6f5b768b496d43ec0f7638287f7ac3ff2fef0c69c5a6c432d9848c071994cdec","source":{"kind":"arxiv","id":"2305.09850","version":4},"attestation_state":"computed","paper":{"title":"MINT: Multiplier-less INTeger Quantization for Energy Efficient Spiking Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Abhishek Moitra, Priyadarshini Panda, Ruokai Yin, Yuhang Li","submitted_at":"2023-05-16T23:38:35Z","abstract_excerpt":"We propose Multiplier-less INTeger (MINT) quantization, a uniform quantization scheme that efficiently compresses weights and membrane potentials in spiking neural networks (SNNs). Unlike previous SNN quantization methods, MINT quantizes memory-intensive membrane potentials to an extremely low precision (2-bit), significantly reducing the memory footprint. MINT also shares the quantization scaling factor between weights and membrane potentials, eliminating the need for multipliers required in conventional uniform quantization. Experimental results show that our method matches the accuracy of f"},"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":"2305.09850","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2023-05-16T23:38:35Z","cross_cats_sorted":[],"title_canon_sha256":"924f6fced40d6e8dc0b2661c7dad692735a903550c38b31965bf318ad54af5b4","abstract_canon_sha256":"8799989701e4d2f6f07372353f4a1203fcd3b9d552dd1eafa461d0e7af9a7800"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:48.286798Z","signature_b64":"BUav6nG3sxqahb47MdvZiIPKGv0Abc7O1PVCI/EFSHyUctv5XQAqCdN13sqNajvd4e8/DtYxMcC+9u8dfKGICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f5b768b496d43ec0f7638287f7ac3ff2fef0c69c5a6c432d9848c071994cdec","last_reissued_at":"2026-07-05T07:09:48.286182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:48.286182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MINT: Multiplier-less INTeger Quantization for Energy Efficient Spiking Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Abhishek Moitra, Priyadarshini Panda, Ruokai Yin, Yuhang Li","submitted_at":"2023-05-16T23:38:35Z","abstract_excerpt":"We propose Multiplier-less INTeger (MINT) quantization, a uniform quantization scheme that efficiently compresses weights and membrane potentials in spiking neural networks (SNNs). Unlike previous SNN quantization methods, MINT quantizes memory-intensive membrane potentials to an extremely low precision (2-bit), significantly reducing the memory footprint. MINT also shares the quantization scaling factor between weights and membrane potentials, eliminating the need for multipliers required in conventional uniform quantization. Experimental results show that our method matches the accuracy of f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09850","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/2305.09850/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":"2305.09850","created_at":"2026-07-05T07:09:48.286273+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.09850v4","created_at":"2026-07-05T07:09:48.286273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09850","created_at":"2026-07-05T07:09:48.286273+00:00"},{"alias_kind":"pith_short_12","alias_value":"N5NXNC2JNVB6","created_at":"2026-07-05T07:09:48.286273+00:00"},{"alias_kind":"pith_short_16","alias_value":"N5NXNC2JNVB6YD3W","created_at":"2026-07-05T07:09:48.286273+00:00"},{"alias_kind":"pith_short_8","alias_value":"N5NXNC2J","created_at":"2026-07-05T07:09:48.286273+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.07066","citing_title":"PTQ4SNN: Membrane-Aware Post-Training Quantization for Spiking Neural Networks","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N5NXNC2JNVB6YD3WHAUH66WD74","json":"https://pith.science/pith/N5NXNC2JNVB6YD3WHAUH66WD74.json","graph_json":"https://pith.science/api/pith-number/N5NXNC2JNVB6YD3WHAUH66WD74/graph.json","events_json":"https://pith.science/api/pith-number/N5NXNC2JNVB6YD3WHAUH66WD74/events.json","paper":"https://pith.science/paper/N5NXNC2J"},"agent_actions":{"view_html":"https://pith.science/pith/N5NXNC2JNVB6YD3WHAUH66WD74","download_json":"https://pith.science/pith/N5NXNC2JNVB6YD3WHAUH66WD74.json","view_paper":"https://pith.science/paper/N5NXNC2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.09850&json=true","fetch_graph":"https://pith.science/api/pith-number/N5NXNC2JNVB6YD3WHAUH66WD74/graph.json","fetch_events":"https://pith.science/api/pith-number/N5NXNC2JNVB6YD3WHAUH66WD74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N5NXNC2JNVB6YD3WHAUH66WD74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N5NXNC2JNVB6YD3WHAUH66WD74/action/storage_attestation","attest_author":"https://pith.science/pith/N5NXNC2JNVB6YD3WHAUH66WD74/action/author_attestation","sign_citation":"https://pith.science/pith/N5NXNC2JNVB6YD3WHAUH66WD74/action/citation_signature","submit_replication":"https://pith.science/pith/N5NXNC2JNVB6YD3WHAUH66WD74/action/replication_record"}},"created_at":"2026-07-05T07:09:48.286273+00:00","updated_at":"2026-07-05T07:09:48.286273+00:00"}