{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HVAIRJ6JU6P6KRZXFZSZQUYMN4","short_pith_number":"pith:HVAIRJ6J","schema_version":"1.0","canonical_sha256":"3d4088a7c9a79fe547372e6598530c6f3c731581dd53f827a25fa113e20b8ef9","source":{"kind":"arxiv","id":"2602.04163","version":2},"attestation_state":"computed","paper":{"title":"BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chaofan Tao, He Xiao, Hongxia Yang, Jing Xiong, Jungang Li, Junyu Chen, Long Shi, Mengzhao Chen, Ngai Wong, Qingyao Yang, Taiqiang Wu, Wenjie Wang, Zhen Li, Zhen Peng","submitted_at":"2026-02-04T02:54:37Z","abstract_excerpt":"Large language model inference is often bounded by memory footprint and bandwidth in resource-constrained deployments, making quantization fundamental to efficient serving. While post-training quantization (PTQ) maintains high fidelity at 4-bit, it deteriorates at 2-3 bits. In essence, existing methods enforce a shape-invariant quantization grid (e.g., the fixed uniform intervals of UINT2) for each group, severely restricting the feasible set for error minimization. To address this, we propose Bit-Plane Decomposition Quantization (BPDQ), which constructs a variable quantization grid via bit-pl"},"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":"2602.04163","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T02:54:37Z","cross_cats_sorted":[],"title_canon_sha256":"deb96d6e655c3d19b106eba7fdcad1d18c5cc53424db87eca0229cb846774e9a","abstract_canon_sha256":"f829d2f98d1251a44c632a47ced58a43d60b57a4f90a794df6fa5b9b8101822e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:33.538037Z","signature_b64":"yWQlv4mBDWv3f2J64SXdR61YTndYbKtjYy0UyM+3F02OGYGrgLg1i+isaSWqcznpUlw/LetQLGhg1RWUwta1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d4088a7c9a79fe547372e6598530c6f3c731581dd53f827a25fa113e20b8ef9","last_reissued_at":"2026-05-20T00:00:33.537565Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:33.537565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chaofan Tao, He Xiao, Hongxia Yang, Jing Xiong, Jungang Li, Junyu Chen, Long Shi, Mengzhao Chen, Ngai Wong, Qingyao Yang, Taiqiang Wu, Wenjie Wang, Zhen Li, Zhen Peng","submitted_at":"2026-02-04T02:54:37Z","abstract_excerpt":"Large language model inference is often bounded by memory footprint and bandwidth in resource-constrained deployments, making quantization fundamental to efficient serving. While post-training quantization (PTQ) maintains high fidelity at 4-bit, it deteriorates at 2-3 bits. In essence, existing methods enforce a shape-invariant quantization grid (e.g., the fixed uniform intervals of UINT2) for each group, severely restricting the feasible set for error minimization. To address this, we propose Bit-Plane Decomposition Quantization (BPDQ), which constructs a variable quantization grid via bit-pl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.04163","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/2602.04163/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":"2602.04163","created_at":"2026-05-20T00:00:33.537633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.04163v2","created_at":"2026-05-20T00:00:33.537633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.04163","created_at":"2026-05-20T00:00:33.537633+00:00"},{"alias_kind":"pith_short_12","alias_value":"HVAIRJ6JU6P6","created_at":"2026-05-20T00:00:33.537633+00:00"},{"alias_kind":"pith_short_16","alias_value":"HVAIRJ6JU6P6KRZX","created_at":"2026-05-20T00:00:33.537633+00:00"},{"alias_kind":"pith_short_8","alias_value":"HVAIRJ6J","created_at":"2026-05-20T00:00:33.537633+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/HVAIRJ6JU6P6KRZXFZSZQUYMN4","json":"https://pith.science/pith/HVAIRJ6JU6P6KRZXFZSZQUYMN4.json","graph_json":"https://pith.science/api/pith-number/HVAIRJ6JU6P6KRZXFZSZQUYMN4/graph.json","events_json":"https://pith.science/api/pith-number/HVAIRJ6JU6P6KRZXFZSZQUYMN4/events.json","paper":"https://pith.science/paper/HVAIRJ6J"},"agent_actions":{"view_html":"https://pith.science/pith/HVAIRJ6JU6P6KRZXFZSZQUYMN4","download_json":"https://pith.science/pith/HVAIRJ6JU6P6KRZXFZSZQUYMN4.json","view_paper":"https://pith.science/paper/HVAIRJ6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.04163&json=true","fetch_graph":"https://pith.science/api/pith-number/HVAIRJ6JU6P6KRZXFZSZQUYMN4/graph.json","fetch_events":"https://pith.science/api/pith-number/HVAIRJ6JU6P6KRZXFZSZQUYMN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HVAIRJ6JU6P6KRZXFZSZQUYMN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HVAIRJ6JU6P6KRZXFZSZQUYMN4/action/storage_attestation","attest_author":"https://pith.science/pith/HVAIRJ6JU6P6KRZXFZSZQUYMN4/action/author_attestation","sign_citation":"https://pith.science/pith/HVAIRJ6JU6P6KRZXFZSZQUYMN4/action/citation_signature","submit_replication":"https://pith.science/pith/HVAIRJ6JU6P6KRZXFZSZQUYMN4/action/replication_record"}},"created_at":"2026-05-20T00:00:33.537633+00:00","updated_at":"2026-05-20T00:00:33.537633+00:00"}