{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:A6SMLW5MRP72SRQO6SIEDWGUEX","short_pith_number":"pith:A6SMLW5M","schema_version":"1.0","canonical_sha256":"07a4c5dbac8bffa9460ef49041d8d425f2b1b76d61da830081e0eac60b169ade","source":{"kind":"arxiv","id":"2303.13003","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bingzhe Wu, Dawei Yang, Guangyu Sun, Jiawei Liu, Jiaxiang Wu, Qiang Wu, Wenyu Liu, Xinggang Wang, Zhihang Yuan","submitted_at":"2023-03-23T02:55:50Z","abstract_excerpt":"Post-training quantization (PTQ) is a popular method for compressing deep neural networks (DNNs) without modifying their original architecture or training procedures. Despite its effectiveness and convenience, the reliability of PTQ methods in the presence of some extrem cases such as distribution shift and data noise remains largely unexplored. This paper first investigates this problem on various commonly-used PTQ methods. We aim to answer several research questions related to the influence of calibration set distribution variations, calibration paradigm selection, and data augmentation or s"},"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":"2303.13003","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-23T02:55:50Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ef1f8bc1589d417fba5bb9dc5a0d96a02f4edaf5dad7d9a9c1be04b5c8575df6","abstract_canon_sha256":"e13b255805af54df93d107961ff398db1658352d3443153cdeac92d94557dfd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:56.844054Z","signature_b64":"76wH6jqgwbtS29nKxFj7m/SNMI0aDzW2+xzexeESXqvPDKQAwPXM4NPg3NVncZX2Ny0oSYBr/iKS/a4NylfiBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07a4c5dbac8bffa9460ef49041d8d425f2b1b76d61da830081e0eac60b169ade","last_reissued_at":"2026-07-05T05:53:56.843599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:56.843599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bingzhe Wu, Dawei Yang, Guangyu Sun, Jiawei Liu, Jiaxiang Wu, Qiang Wu, Wenyu Liu, Xinggang Wang, Zhihang Yuan","submitted_at":"2023-03-23T02:55:50Z","abstract_excerpt":"Post-training quantization (PTQ) is a popular method for compressing deep neural networks (DNNs) without modifying their original architecture or training procedures. Despite its effectiveness and convenience, the reliability of PTQ methods in the presence of some extrem cases such as distribution shift and data noise remains largely unexplored. This paper first investigates this problem on various commonly-used PTQ methods. We aim to answer several research questions related to the influence of calibration set distribution variations, calibration paradigm selection, and data augmentation or s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13003","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/2303.13003/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":"2303.13003","created_at":"2026-07-05T05:53:56.843658+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.13003v1","created_at":"2026-07-05T05:53:56.843658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13003","created_at":"2026-07-05T05:53:56.843658+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6SMLW5MRP72","created_at":"2026-07-05T05:53:56.843658+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6SMLW5MRP72SRQO","created_at":"2026-07-05T05:53:56.843658+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6SMLW5M","created_at":"2026-07-05T05:53:56.843658+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/A6SMLW5MRP72SRQO6SIEDWGUEX","json":"https://pith.science/pith/A6SMLW5MRP72SRQO6SIEDWGUEX.json","graph_json":"https://pith.science/api/pith-number/A6SMLW5MRP72SRQO6SIEDWGUEX/graph.json","events_json":"https://pith.science/api/pith-number/A6SMLW5MRP72SRQO6SIEDWGUEX/events.json","paper":"https://pith.science/paper/A6SMLW5M"},"agent_actions":{"view_html":"https://pith.science/pith/A6SMLW5MRP72SRQO6SIEDWGUEX","download_json":"https://pith.science/pith/A6SMLW5MRP72SRQO6SIEDWGUEX.json","view_paper":"https://pith.science/paper/A6SMLW5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.13003&json=true","fetch_graph":"https://pith.science/api/pith-number/A6SMLW5MRP72SRQO6SIEDWGUEX/graph.json","fetch_events":"https://pith.science/api/pith-number/A6SMLW5MRP72SRQO6SIEDWGUEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6SMLW5MRP72SRQO6SIEDWGUEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6SMLW5MRP72SRQO6SIEDWGUEX/action/storage_attestation","attest_author":"https://pith.science/pith/A6SMLW5MRP72SRQO6SIEDWGUEX/action/author_attestation","sign_citation":"https://pith.science/pith/A6SMLW5MRP72SRQO6SIEDWGUEX/action/citation_signature","submit_replication":"https://pith.science/pith/A6SMLW5MRP72SRQO6SIEDWGUEX/action/replication_record"}},"created_at":"2026-07-05T05:53:56.843658+00:00","updated_at":"2026-07-05T05:53:56.843658+00:00"}