{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XHBNFFKD6WUN5LQASASS7KYNL6","short_pith_number":"pith:XHBNFFKD","schema_version":"1.0","canonical_sha256":"b9c2d29543f5a8deae0090252fab0d5f9c82e6f72593b0b90a0863f3b0f74f0a","source":{"kind":"arxiv","id":"2412.14633","version":1},"attestation_state":"computed","paper":{"title":"Progressive Fine-to-Coarse Reconstruction for Accurate Low-Bit Post-Training Quantization in Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haijun Liu, Jing Nie, Liang Yong, Lihui Chen, Rui Ding, Sihuan Zhao, Xichuan Zhou","submitted_at":"2024-12-19T08:38:59Z","abstract_excerpt":"Due to its efficiency, Post-Training Quantization (PTQ) has been widely adopted for compressing Vision Transformers (ViTs). However, when quantized into low-bit representations, there is often a significant performance drop compared to their full-precision counterparts. To address this issue, reconstruction methods have been incorporated into the PTQ framework to improve performance in low-bit quantization settings. Nevertheless, existing related methods predefine the reconstruction granularity and seldom explore the progressive relationships between different reconstruction granularities, whi"},"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":"2412.14633","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T08:38:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c1168d4a1873a5b9526107d95f46359f21f1a9543f966641c567d9564f0e6643","abstract_canon_sha256":"7c976169032f0d8b05332bbaa4c2462e3c28cf95e6a0475bc090f5ee5c48455d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:50.580020Z","signature_b64":"flX/OC9JqsAvj53OdzHeCY0BG7+cRMGwob/HuotoqvykbQhtizNfqrwHVaVSkSrs50T9xl6PXVvWw/7r1CTQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9c2d29543f5a8deae0090252fab0d5f9c82e6f72593b0b90a0863f3b0f74f0a","last_reissued_at":"2026-07-05T09:51:50.579560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:50.579560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Progressive Fine-to-Coarse Reconstruction for Accurate Low-Bit Post-Training Quantization in Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haijun Liu, Jing Nie, Liang Yong, Lihui Chen, Rui Ding, Sihuan Zhao, Xichuan Zhou","submitted_at":"2024-12-19T08:38:59Z","abstract_excerpt":"Due to its efficiency, Post-Training Quantization (PTQ) has been widely adopted for compressing Vision Transformers (ViTs). However, when quantized into low-bit representations, there is often a significant performance drop compared to their full-precision counterparts. To address this issue, reconstruction methods have been incorporated into the PTQ framework to improve performance in low-bit quantization settings. Nevertheless, existing related methods predefine the reconstruction granularity and seldom explore the progressive relationships between different reconstruction granularities, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14633","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/2412.14633/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":"2412.14633","created_at":"2026-07-05T09:51:50.579616+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14633v1","created_at":"2026-07-05T09:51:50.579616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14633","created_at":"2026-07-05T09:51:50.579616+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHBNFFKD6WUN","created_at":"2026-07-05T09:51:50.579616+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHBNFFKD6WUN5LQA","created_at":"2026-07-05T09:51:50.579616+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHBNFFKD","created_at":"2026-07-05T09:51:50.579616+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/XHBNFFKD6WUN5LQASASS7KYNL6","json":"https://pith.science/pith/XHBNFFKD6WUN5LQASASS7KYNL6.json","graph_json":"https://pith.science/api/pith-number/XHBNFFKD6WUN5LQASASS7KYNL6/graph.json","events_json":"https://pith.science/api/pith-number/XHBNFFKD6WUN5LQASASS7KYNL6/events.json","paper":"https://pith.science/paper/XHBNFFKD"},"agent_actions":{"view_html":"https://pith.science/pith/XHBNFFKD6WUN5LQASASS7KYNL6","download_json":"https://pith.science/pith/XHBNFFKD6WUN5LQASASS7KYNL6.json","view_paper":"https://pith.science/paper/XHBNFFKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14633&json=true","fetch_graph":"https://pith.science/api/pith-number/XHBNFFKD6WUN5LQASASS7KYNL6/graph.json","fetch_events":"https://pith.science/api/pith-number/XHBNFFKD6WUN5LQASASS7KYNL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHBNFFKD6WUN5LQASASS7KYNL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHBNFFKD6WUN5LQASASS7KYNL6/action/storage_attestation","attest_author":"https://pith.science/pith/XHBNFFKD6WUN5LQASASS7KYNL6/action/author_attestation","sign_citation":"https://pith.science/pith/XHBNFFKD6WUN5LQASASS7KYNL6/action/citation_signature","submit_replication":"https://pith.science/pith/XHBNFFKD6WUN5LQASASS7KYNL6/action/replication_record"}},"created_at":"2026-07-05T09:51:50.579616+00:00","updated_at":"2026-07-05T09:51:50.579616+00:00"}