{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DWHDEG657YRJQVMENZFQW4ISJZ","short_pith_number":"pith:DWHDEG65","schema_version":"1.0","canonical_sha256":"1d8e321bddfe229855846e4b0b71124e7f410fcbf60ca0384117a794e8b0ad04","source":{"kind":"arxiv","id":"2602.01027","version":2},"attestation_state":"computed","paper":{"title":"SFMP: Fine-Grained, Hardware-Friendly and Search-Free Mixed-Precision Quantization for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Beining Feng, Guiling Sun, Haicheng Zhang, Jinhong Weng, Liang Dong, Xin Nie","submitted_at":"2026-02-01T05:24:19Z","abstract_excerpt":"Mixed-precision quantization is a promising approach for compressing large language models under tight memory budgets. However, existing mixed-precision methods typically suffer from one of two limitations: they either rely on expensive discrete optimization to determine precision allocation, or introduce hardware inefficiencies due to irregular memory layouts. We propose SFMP, a search-free and hardware-friendly mixed-precision quantization framework for large language models. The framework is built upon four novel ideas: Fractional bit-width, which extends integer bit-width for weight matrix"},"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":"2602.01027","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-01T05:24:19Z","cross_cats_sorted":[],"title_canon_sha256":"03d9f3e16ee40d94b9c3b2d6ec2c0519002ee6b4be35bac5c67e60255aa5e4b8","abstract_canon_sha256":"471424d4d2024a22a0f30826b0a9cda7dd4fe6f6b5ca9babafdcf52fec0d0601"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:41.442954Z","signature_b64":"lgFYj6P5/wIshwHJVwfR/UqqRfJji+OlZalHxgkqTvCfky8+nQFVi7U0dxNJ0kLuayQ4uespwXW+blF8wzF2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d8e321bddfe229855846e4b0b71124e7f410fcbf60ca0384117a794e8b0ad04","last_reissued_at":"2026-06-04T01:09:41.442485Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:41.442485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SFMP: Fine-Grained, Hardware-Friendly and Search-Free Mixed-Precision Quantization for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Beining Feng, Guiling Sun, Haicheng Zhang, Jinhong Weng, Liang Dong, Xin Nie","submitted_at":"2026-02-01T05:24:19Z","abstract_excerpt":"Mixed-precision quantization is a promising approach for compressing large language models under tight memory budgets. However, existing mixed-precision methods typically suffer from one of two limitations: they either rely on expensive discrete optimization to determine precision allocation, or introduce hardware inefficiencies due to irregular memory layouts. We propose SFMP, a search-free and hardware-friendly mixed-precision quantization framework for large language models. The framework is built upon four novel ideas: Fractional bit-width, which extends integer bit-width for weight matrix"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.01027","kind":"arxiv","version":2},"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/2602.01027/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":"2602.01027","created_at":"2026-06-04T01:09:41.442545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.01027v2","created_at":"2026-06-04T01:09:41.442545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01027","created_at":"2026-06-04T01:09:41.442545+00:00"},{"alias_kind":"pith_short_12","alias_value":"DWHDEG657YRJ","created_at":"2026-06-04T01:09:41.442545+00:00"},{"alias_kind":"pith_short_16","alias_value":"DWHDEG657YRJQVME","created_at":"2026-06-04T01:09:41.442545+00:00"},{"alias_kind":"pith_short_8","alias_value":"DWHDEG65","created_at":"2026-06-04T01:09:41.442545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DWHDEG657YRJQVMENZFQW4ISJZ","json":"https://pith.science/pith/DWHDEG657YRJQVMENZFQW4ISJZ.json","graph_json":"https://pith.science/api/pith-number/DWHDEG657YRJQVMENZFQW4ISJZ/graph.json","events_json":"https://pith.science/api/pith-number/DWHDEG657YRJQVMENZFQW4ISJZ/events.json","paper":"https://pith.science/paper/DWHDEG65"},"agent_actions":{"view_html":"https://pith.science/pith/DWHDEG657YRJQVMENZFQW4ISJZ","download_json":"https://pith.science/pith/DWHDEG657YRJQVMENZFQW4ISJZ.json","view_paper":"https://pith.science/paper/DWHDEG65","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.01027&json=true","fetch_graph":"https://pith.science/api/pith-number/DWHDEG657YRJQVMENZFQW4ISJZ/graph.json","fetch_events":"https://pith.science/api/pith-number/DWHDEG657YRJQVMENZFQW4ISJZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DWHDEG657YRJQVMENZFQW4ISJZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DWHDEG657YRJQVMENZFQW4ISJZ/action/storage_attestation","attest_author":"https://pith.science/pith/DWHDEG657YRJQVMENZFQW4ISJZ/action/author_attestation","sign_citation":"https://pith.science/pith/DWHDEG657YRJQVMENZFQW4ISJZ/action/citation_signature","submit_replication":"https://pith.science/pith/DWHDEG657YRJQVMENZFQW4ISJZ/action/replication_record"}},"created_at":"2026-06-04T01:09:41.442545+00:00","updated_at":"2026-06-04T01:09:41.442545+00:00"}