{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HLJMSDNX6CUR2PYUNZ5KEQ4OCV","short_pith_number":"pith:HLJMSDNX","schema_version":"1.0","canonical_sha256":"3ad2c90db7f0a91d3f146e7aa2438e156b2c25f71a7212b987a6839ff902bd28","source":{"kind":"arxiv","id":"2105.01868","version":1},"attestation_state":"computed","paper":{"title":"Q-Rater: Non-Convex Optimization for Post-Training Uniform Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Baeseong Park, Byeongwook Kim, Daehwan Oh, Dongsoo Lee, Se Jung Kwon, Yeonju Ro, Yongkweon Jeon","submitted_at":"2021-05-05T05:14:22Z","abstract_excerpt":"Various post-training uniform quantization methods have usually been studied based on convex optimization. As a result, most previous ones rely on the quantization error minimization and/or quadratic approximations. Such approaches are computationally efficient and reasonable when a large number of quantization bits are employed. When the number of quantization bits is relatively low, however, non-convex optimization is unavoidable to improve model accuracy. In this paper, we propose a new post-training uniform quantization technique considering non-convexity. We empirically show that hyper-pa"},"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":"2105.01868","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-05T05:14:22Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"4bfc4d80e030646fadfefb821aef97e49183f2e439b514c1ced93fca99c9130a","abstract_canon_sha256":"0651d008fcfd4ad4657b49cad8e985ae53e54ee3dbf4ef869fc4fd2c5648a4ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:49.556751Z","signature_b64":"1Hz1pDR8VKcYMtVQEu53NOGTjTlEaTyeF+vig8BFmKpNy0O7m247nGtRNwrfRfO/H/Ienx17jmepEwhRjZipBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ad2c90db7f0a91d3f146e7aa2438e156b2c25f71a7212b987a6839ff902bd28","last_reissued_at":"2026-07-05T02:37:49.556135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:49.556135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q-Rater: Non-Convex Optimization for Post-Training Uniform Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Baeseong Park, Byeongwook Kim, Daehwan Oh, Dongsoo Lee, Se Jung Kwon, Yeonju Ro, Yongkweon Jeon","submitted_at":"2021-05-05T05:14:22Z","abstract_excerpt":"Various post-training uniform quantization methods have usually been studied based on convex optimization. As a result, most previous ones rely on the quantization error minimization and/or quadratic approximations. Such approaches are computationally efficient and reasonable when a large number of quantization bits are employed. When the number of quantization bits is relatively low, however, non-convex optimization is unavoidable to improve model accuracy. In this paper, we propose a new post-training uniform quantization technique considering non-convexity. We empirically show that hyper-pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.01868","kind":"arxiv","version":1},"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/2105.01868/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":"2105.01868","created_at":"2026-07-05T02:37:49.556201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.01868v1","created_at":"2026-07-05T02:37:49.556201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.01868","created_at":"2026-07-05T02:37:49.556201+00:00"},{"alias_kind":"pith_short_12","alias_value":"HLJMSDNX6CUR","created_at":"2026-07-05T02:37:49.556201+00:00"},{"alias_kind":"pith_short_16","alias_value":"HLJMSDNX6CUR2PYU","created_at":"2026-07-05T02:37:49.556201+00:00"},{"alias_kind":"pith_short_8","alias_value":"HLJMSDNX","created_at":"2026-07-05T02:37:49.556201+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/HLJMSDNX6CUR2PYUNZ5KEQ4OCV","json":"https://pith.science/pith/HLJMSDNX6CUR2PYUNZ5KEQ4OCV.json","graph_json":"https://pith.science/api/pith-number/HLJMSDNX6CUR2PYUNZ5KEQ4OCV/graph.json","events_json":"https://pith.science/api/pith-number/HLJMSDNX6CUR2PYUNZ5KEQ4OCV/events.json","paper":"https://pith.science/paper/HLJMSDNX"},"agent_actions":{"view_html":"https://pith.science/pith/HLJMSDNX6CUR2PYUNZ5KEQ4OCV","download_json":"https://pith.science/pith/HLJMSDNX6CUR2PYUNZ5KEQ4OCV.json","view_paper":"https://pith.science/paper/HLJMSDNX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.01868&json=true","fetch_graph":"https://pith.science/api/pith-number/HLJMSDNX6CUR2PYUNZ5KEQ4OCV/graph.json","fetch_events":"https://pith.science/api/pith-number/HLJMSDNX6CUR2PYUNZ5KEQ4OCV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HLJMSDNX6CUR2PYUNZ5KEQ4OCV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HLJMSDNX6CUR2PYUNZ5KEQ4OCV/action/storage_attestation","attest_author":"https://pith.science/pith/HLJMSDNX6CUR2PYUNZ5KEQ4OCV/action/author_attestation","sign_citation":"https://pith.science/pith/HLJMSDNX6CUR2PYUNZ5KEQ4OCV/action/citation_signature","submit_replication":"https://pith.science/pith/HLJMSDNX6CUR2PYUNZ5KEQ4OCV/action/replication_record"}},"created_at":"2026-07-05T02:37:49.556201+00:00","updated_at":"2026-07-05T02:37:49.556201+00:00"}