{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:S2J23ZLKY264QYN4Q644JZXKCL","short_pith_number":"pith:S2J23ZLK","schema_version":"1.0","canonical_sha256":"9693ade56ac6bdc861bc87b9c4e6ea12d5cacb16e386007f90c7d8b22ac928df","source":{"kind":"arxiv","id":"2202.05239","version":1},"attestation_state":"computed","paper":{"title":"F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.AR","cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Jian Ren, Kaiyuan Yang, Qing Jin, Richard Zhuang, Sergey Tulyakov, Sumant Hanumante, Yanzhi Wang, Zhengang Li, Zhiyu Chen","submitted_at":"2022-02-10T18:48:56Z","abstract_excerpt":"Neural network quantization is a promising compression technique to reduce memory footprint and save energy consumption, potentially leading to real-time inference. However, there is a performance gap between quantized and full-precision models. To reduce it, existing quantization approaches require high-precision INT32 or full-precision multiplication during inference for scaling or dequantization. This introduces a noticeable cost in terms of memory, speed, and required energy. To tackle these issues, we present F8Net, a novel quantization framework consisting of only fixed-point 8-bit multi"},"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":"2202.05239","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-10T18:48:56Z","cross_cats_sorted":["cs.AI","cs.AR","cs.LG","cs.NE"],"title_canon_sha256":"b463473ddfa73134da02aff5c0dfa983c599764546d4efbd2ec86bb68a47ae79","abstract_canon_sha256":"648e12329d0083e24b9e622ddc367edcf660e0b35520816a420fff551ec8f759"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:55:58.690000Z","signature_b64":"D/uB8SxLvfXvbMtBjsI7cFZx3Pi0A8Ep2q2ZnV1+A7LzVxFVQ8NQMWCv91w5gwmGm0MzW7VZBxGy0ka2yixBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9693ade56ac6bdc861bc87b9c4e6ea12d5cacb16e386007f90c7d8b22ac928df","last_reissued_at":"2026-07-05T03:55:58.689603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:55:58.689603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.AR","cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Jian Ren, Kaiyuan Yang, Qing Jin, Richard Zhuang, Sergey Tulyakov, Sumant Hanumante, Yanzhi Wang, Zhengang Li, Zhiyu Chen","submitted_at":"2022-02-10T18:48:56Z","abstract_excerpt":"Neural network quantization is a promising compression technique to reduce memory footprint and save energy consumption, potentially leading to real-time inference. However, there is a performance gap between quantized and full-precision models. To reduce it, existing quantization approaches require high-precision INT32 or full-precision multiplication during inference for scaling or dequantization. This introduces a noticeable cost in terms of memory, speed, and required energy. To tackle these issues, we present F8Net, a novel quantization framework consisting of only fixed-point 8-bit multi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.05239","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/2202.05239/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":"2202.05239","created_at":"2026-07-05T03:55:58.689652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.05239v1","created_at":"2026-07-05T03:55:58.689652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.05239","created_at":"2026-07-05T03:55:58.689652+00:00"},{"alias_kind":"pith_short_12","alias_value":"S2J23ZLKY264","created_at":"2026-07-05T03:55:58.689652+00:00"},{"alias_kind":"pith_short_16","alias_value":"S2J23ZLKY264QYN4","created_at":"2026-07-05T03:55:58.689652+00:00"},{"alias_kind":"pith_short_8","alias_value":"S2J23ZLK","created_at":"2026-07-05T03:55:58.689652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2208.07339","citing_title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","ref_index":141,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S2J23ZLKY264QYN4Q644JZXKCL","json":"https://pith.science/pith/S2J23ZLKY264QYN4Q644JZXKCL.json","graph_json":"https://pith.science/api/pith-number/S2J23ZLKY264QYN4Q644JZXKCL/graph.json","events_json":"https://pith.science/api/pith-number/S2J23ZLKY264QYN4Q644JZXKCL/events.json","paper":"https://pith.science/paper/S2J23ZLK"},"agent_actions":{"view_html":"https://pith.science/pith/S2J23ZLKY264QYN4Q644JZXKCL","download_json":"https://pith.science/pith/S2J23ZLKY264QYN4Q644JZXKCL.json","view_paper":"https://pith.science/paper/S2J23ZLK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.05239&json=true","fetch_graph":"https://pith.science/api/pith-number/S2J23ZLKY264QYN4Q644JZXKCL/graph.json","fetch_events":"https://pith.science/api/pith-number/S2J23ZLKY264QYN4Q644JZXKCL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S2J23ZLKY264QYN4Q644JZXKCL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S2J23ZLKY264QYN4Q644JZXKCL/action/storage_attestation","attest_author":"https://pith.science/pith/S2J23ZLKY264QYN4Q644JZXKCL/action/author_attestation","sign_citation":"https://pith.science/pith/S2J23ZLKY264QYN4Q644JZXKCL/action/citation_signature","submit_replication":"https://pith.science/pith/S2J23ZLKY264QYN4Q644JZXKCL/action/replication_record"}},"created_at":"2026-07-05T03:55:58.689652+00:00","updated_at":"2026-07-05T03:55:58.689652+00:00"}