{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZIG5QBP5L6PE5RTWAGC5RNXK7Z","short_pith_number":"pith:ZIG5QBP5","schema_version":"1.0","canonical_sha256":"ca0dd805fd5f9e4ec6760185d8b6eafe5aea2f751d7993af12cf7cb53383e3b6","source":{"kind":"arxiv","id":"2406.17542","version":3},"attestation_state":"computed","paper":{"title":"CDQuant: Greedy Coordinate Descent for Accurate LLM Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Arun Sai Suggala, Pranav Ajit Nair","submitted_at":"2024-06-25T13:29:14Z","abstract_excerpt":"Large language models (LLMs) have recently demonstrated remarkable performance across diverse language tasks. But their deployment is often constrained by their substantial computational and storage requirements. Quantization has emerged as a key technique for addressing this challenge, enabling the compression of large models with minimal impact on performance. The recent GPTQ algorithm, a post-training quantization (PTQ) method, has proven highly effective for compressing LLMs, sparking a wave of research that leverages GPTQ as a core component. Recognizing the pivotal role of GPTQ in the PT"},"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":"2406.17542","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T13:29:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"2709938d851a71dd33183b44b1bed58b2c24a6c7068263a3ce9e8031b6f638ab","abstract_canon_sha256":"1920e1e4636fe7affcfee5e21d6e88b460912086588b8b91cbbe672f55e9a154"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:17.105614Z","signature_b64":"jMIA/nlPsDD3oIOWrmApunCWDNkjZMiuVn6lFxIlfHQopznUuFc3JeXldXhtcqUT+hMB/nbfZ1feZl4sS61EBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca0dd805fd5f9e4ec6760185d8b6eafe5aea2f751d7993af12cf7cb53383e3b6","last_reissued_at":"2026-07-05T09:24:17.104991Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:17.104991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CDQuant: Greedy Coordinate Descent for Accurate LLM Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Arun Sai Suggala, Pranav Ajit Nair","submitted_at":"2024-06-25T13:29:14Z","abstract_excerpt":"Large language models (LLMs) have recently demonstrated remarkable performance across diverse language tasks. But their deployment is often constrained by their substantial computational and storage requirements. Quantization has emerged as a key technique for addressing this challenge, enabling the compression of large models with minimal impact on performance. The recent GPTQ algorithm, a post-training quantization (PTQ) method, has proven highly effective for compressing LLMs, sparking a wave of research that leverages GPTQ as a core component. Recognizing the pivotal role of GPTQ in the PT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17542","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/2406.17542/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":"2406.17542","created_at":"2026-07-05T09:24:17.105058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17542v3","created_at":"2026-07-05T09:24:17.105058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17542","created_at":"2026-07-05T09:24:17.105058+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZIG5QBP5L6PE","created_at":"2026-07-05T09:24:17.105058+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZIG5QBP5L6PE5RTW","created_at":"2026-07-05T09:24:17.105058+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZIG5QBP5","created_at":"2026-07-05T09:24:17.105058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10890","citing_title":"Optimal Post-Training Quantization Scales and Where to Find Them","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2602.05902","citing_title":"CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZIG5QBP5L6PE5RTWAGC5RNXK7Z","json":"https://pith.science/pith/ZIG5QBP5L6PE5RTWAGC5RNXK7Z.json","graph_json":"https://pith.science/api/pith-number/ZIG5QBP5L6PE5RTWAGC5RNXK7Z/graph.json","events_json":"https://pith.science/api/pith-number/ZIG5QBP5L6PE5RTWAGC5RNXK7Z/events.json","paper":"https://pith.science/paper/ZIG5QBP5"},"agent_actions":{"view_html":"https://pith.science/pith/ZIG5QBP5L6PE5RTWAGC5RNXK7Z","download_json":"https://pith.science/pith/ZIG5QBP5L6PE5RTWAGC5RNXK7Z.json","view_paper":"https://pith.science/paper/ZIG5QBP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17542&json=true","fetch_graph":"https://pith.science/api/pith-number/ZIG5QBP5L6PE5RTWAGC5RNXK7Z/graph.json","fetch_events":"https://pith.science/api/pith-number/ZIG5QBP5L6PE5RTWAGC5RNXK7Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZIG5QBP5L6PE5RTWAGC5RNXK7Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZIG5QBP5L6PE5RTWAGC5RNXK7Z/action/storage_attestation","attest_author":"https://pith.science/pith/ZIG5QBP5L6PE5RTWAGC5RNXK7Z/action/author_attestation","sign_citation":"https://pith.science/pith/ZIG5QBP5L6PE5RTWAGC5RNXK7Z/action/citation_signature","submit_replication":"https://pith.science/pith/ZIG5QBP5L6PE5RTWAGC5RNXK7Z/action/replication_record"}},"created_at":"2026-07-05T09:24:17.105058+00:00","updated_at":"2026-07-05T09:24:17.105058+00:00"}