{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:52G4CBWN6FWNVNGE7BTQDXC2PW","short_pith_number":"pith:52G4CBWN","schema_version":"1.0","canonical_sha256":"ee8dc106cdf16cdab4c4f86701dc5a7dac7c1f50b3a06f2a9ac5eaa7dd639e13","source":{"kind":"arxiv","id":"2412.04180","version":2},"attestation_state":"computed","paper":{"title":"SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Liu, Qiang Liu, Runsheng Bai","submitted_at":"2024-12-05T14:19:59Z","abstract_excerpt":"Large Language Models (LLMs) exhibit impressive performance across various tasks, but deploying them for inference poses challenges. Their high resource demands often necessitate complex, costly multi-GPU pipelines, or the use of smaller, less capable models. While quantization offers a promising solution utilizing lower precision for model storage, existing methods frequently experience significant performance drops at lower precision levels. Additionally, they typically provide only a limited set of solutions at specific bit levels, many of which are extensively manually tuned. To address th"},"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":"2412.04180","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T14:19:59Z","cross_cats_sorted":[],"title_canon_sha256":"909215e6599ff36aa970588b6e5ae5262f3486670f7b0080390e8364ee7db351","abstract_canon_sha256":"df531072f79acc2daa036f13f751c9925b3bf88362a4331d266b2d88430c4569"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:00.367227Z","signature_b64":"dbMIX2klOF44vbXpUXjI/InqxnXN/H+Fe2S9dofrEJM7bjBThuQ7fwQyKr5EiJvT2Y87LN5w4Kn9UhYvbVIJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee8dc106cdf16cdab4c4f86701dc5a7dac7c1f50b3a06f2a9ac5eaa7dd639e13","last_reissued_at":"2026-07-05T09:46:00.366794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:00.366794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Liu, Qiang Liu, Runsheng Bai","submitted_at":"2024-12-05T14:19:59Z","abstract_excerpt":"Large Language Models (LLMs) exhibit impressive performance across various tasks, but deploying them for inference poses challenges. Their high resource demands often necessitate complex, costly multi-GPU pipelines, or the use of smaller, less capable models. While quantization offers a promising solution utilizing lower precision for model storage, existing methods frequently experience significant performance drops at lower precision levels. Additionally, they typically provide only a limited set of solutions at specific bit levels, many of which are extensively manually tuned. To address th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04180","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/2412.04180/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":"2412.04180","created_at":"2026-07-05T09:46:00.366849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04180v2","created_at":"2026-07-05T09:46:00.366849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04180","created_at":"2026-07-05T09:46:00.366849+00:00"},{"alias_kind":"pith_short_12","alias_value":"52G4CBWN6FWN","created_at":"2026-07-05T09:46:00.366849+00:00"},{"alias_kind":"pith_short_16","alias_value":"52G4CBWN6FWNVNGE","created_at":"2026-07-05T09:46:00.366849+00:00"},{"alias_kind":"pith_short_8","alias_value":"52G4CBWN","created_at":"2026-07-05T09:46:00.366849+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12038","citing_title":"LCD: Advancing Extreme Low-Bit Clustering for Large Language Models via Knowledge Distillation","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/52G4CBWN6FWNVNGE7BTQDXC2PW","json":"https://pith.science/pith/52G4CBWN6FWNVNGE7BTQDXC2PW.json","graph_json":"https://pith.science/api/pith-number/52G4CBWN6FWNVNGE7BTQDXC2PW/graph.json","events_json":"https://pith.science/api/pith-number/52G4CBWN6FWNVNGE7BTQDXC2PW/events.json","paper":"https://pith.science/paper/52G4CBWN"},"agent_actions":{"view_html":"https://pith.science/pith/52G4CBWN6FWNVNGE7BTQDXC2PW","download_json":"https://pith.science/pith/52G4CBWN6FWNVNGE7BTQDXC2PW.json","view_paper":"https://pith.science/paper/52G4CBWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04180&json=true","fetch_graph":"https://pith.science/api/pith-number/52G4CBWN6FWNVNGE7BTQDXC2PW/graph.json","fetch_events":"https://pith.science/api/pith-number/52G4CBWN6FWNVNGE7BTQDXC2PW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/52G4CBWN6FWNVNGE7BTQDXC2PW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/52G4CBWN6FWNVNGE7BTQDXC2PW/action/storage_attestation","attest_author":"https://pith.science/pith/52G4CBWN6FWNVNGE7BTQDXC2PW/action/author_attestation","sign_citation":"https://pith.science/pith/52G4CBWN6FWNVNGE7BTQDXC2PW/action/citation_signature","submit_replication":"https://pith.science/pith/52G4CBWN6FWNVNGE7BTQDXC2PW/action/replication_record"}},"created_at":"2026-07-05T09:46:00.366849+00:00","updated_at":"2026-07-05T09:46:00.366849+00:00"}