{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2DKPIKAFX6QGIXA2DQIDIWS76X","short_pith_number":"pith:2DKPIKAF","schema_version":"1.0","canonical_sha256":"d0d4f42805bfa0645c1a1c10345a5ff5e8496d12d82c8e835c4e7a61fc371f4c","source":{"kind":"arxiv","id":"2405.06001","version":3},"attestation_state":"computed","paper":{"title":"LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Chengtao Lv, Dacheng Tao, Ruihao Gong, Shiqiao Gu, Xianglong Liu, Yang Yong, Yunchen Zhang, Yushi Huang","submitted_at":"2024-05-09T11:49:05Z","abstract_excerpt":"Recent advancements in large language models (LLMs) are propelling us toward artificial general intelligence with their remarkable emergent abilities and reasoning capabilities. However, the substantial computational and memory requirements limit the widespread adoption. Quantization, a key compression technique, can effectively mitigate these demands by compressing and accelerating LLMs, albeit with potential risks to accuracy. Numerous studies have aimed to minimize the accuracy loss associated with quantization. However, their quantization configurations vary from each other and cannot be 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":"2405.06001","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-09T11:49:05Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1468194d4e8dd9bf5b3ac08ed4f32fbc616c1b30681f2c80563cfeea0e472b6b","abstract_canon_sha256":"919a46b72faa46e4bbcdfb48633f64ad654389715c3a13c5776a848031e07d9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:41.431655Z","signature_b64":"PXVFFan0gqiDC4WfEtJdB8Ldk/Gzenin8E1px6+toIutk68NRV1yz1Obk9VsnnayoXaoRT6Zjrmf1Nr018kzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0d4f42805bfa0645c1a1c10345a5ff5e8496d12d82c8e835c4e7a61fc371f4c","last_reissued_at":"2026-07-05T09:17:41.431152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:41.431152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Chengtao Lv, Dacheng Tao, Ruihao Gong, Shiqiao Gu, Xianglong Liu, Yang Yong, Yunchen Zhang, Yushi Huang","submitted_at":"2024-05-09T11:49:05Z","abstract_excerpt":"Recent advancements in large language models (LLMs) are propelling us toward artificial general intelligence with their remarkable emergent abilities and reasoning capabilities. However, the substantial computational and memory requirements limit the widespread adoption. Quantization, a key compression technique, can effectively mitigate these demands by compressing and accelerating LLMs, albeit with potential risks to accuracy. Numerous studies have aimed to minimize the accuracy loss associated with quantization. However, their quantization configurations vary from each other and cannot be f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.06001","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/2405.06001/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":"2405.06001","created_at":"2026-07-05T09:17:41.431210+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.06001v3","created_at":"2026-07-05T09:17:41.431210+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.06001","created_at":"2026-07-05T09:17:41.431210+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DKPIKAFX6QG","created_at":"2026-07-05T09:17:41.431210+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DKPIKAFX6QGIXA2","created_at":"2026-07-05T09:17:41.431210+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DKPIKAF","created_at":"2026-07-05T09:17:41.431210+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27205","citing_title":"Smaller Models, Unexpected Costs: Trade-offs in LLM Quantization for Automated Program Repair","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00658","citing_title":"Collaborative Few-Step Distillation and Low-Bit Quantization for Wan2.2 Dual-Expert Video Diffusion Models","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DKPIKAFX6QGIXA2DQIDIWS76X","json":"https://pith.science/pith/2DKPIKAFX6QGIXA2DQIDIWS76X.json","graph_json":"https://pith.science/api/pith-number/2DKPIKAFX6QGIXA2DQIDIWS76X/graph.json","events_json":"https://pith.science/api/pith-number/2DKPIKAFX6QGIXA2DQIDIWS76X/events.json","paper":"https://pith.science/paper/2DKPIKAF"},"agent_actions":{"view_html":"https://pith.science/pith/2DKPIKAFX6QGIXA2DQIDIWS76X","download_json":"https://pith.science/pith/2DKPIKAFX6QGIXA2DQIDIWS76X.json","view_paper":"https://pith.science/paper/2DKPIKAF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.06001&json=true","fetch_graph":"https://pith.science/api/pith-number/2DKPIKAFX6QGIXA2DQIDIWS76X/graph.json","fetch_events":"https://pith.science/api/pith-number/2DKPIKAFX6QGIXA2DQIDIWS76X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DKPIKAFX6QGIXA2DQIDIWS76X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DKPIKAFX6QGIXA2DQIDIWS76X/action/storage_attestation","attest_author":"https://pith.science/pith/2DKPIKAFX6QGIXA2DQIDIWS76X/action/author_attestation","sign_citation":"https://pith.science/pith/2DKPIKAFX6QGIXA2DQIDIWS76X/action/citation_signature","submit_replication":"https://pith.science/pith/2DKPIKAFX6QGIXA2DQIDIWS76X/action/replication_record"}},"created_at":"2026-07-05T09:17:41.431210+00:00","updated_at":"2026-07-05T09:17:41.431210+00:00"}