{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FEVCAORPAOEYNF2ZDKP7WLY4ZF","short_pith_number":"pith:FEVCAORP","schema_version":"1.0","canonical_sha256":"292a203a2f03898697591a9ffb2f1cc95b0ae5949b980a11d009c9c9f968055a","source":{"kind":"arxiv","id":"2508.02180","version":1},"attestation_state":"computed","paper":{"title":"Test-Time Model Adaptation for Quantized Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guohao Chen, Hui Luo, Mingkui Tan, Renjie Chen, Shuaicheng Niu, Shuhai Zhang, Wei Luo, Yifan Yang, Zeshuai Deng","submitted_at":"2025-08-04T08:24:19Z","abstract_excerpt":"Quantizing deep models prior to deployment is a widely adopted technique to speed up inference for various real-time applications, such as autonomous driving. However, quantized models often suffer from severe performance degradation in dynamic environments with potential domain shifts and this degradation is significantly more pronounced compared with their full-precision counterparts, as shown by our theoretical and empirical illustrations. To address the domain shift problem, test-time adaptation (TTA) has emerged as an effective solution by enabling models to learn adaptively from test dat"},"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":"2508.02180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-04T08:24:19Z","cross_cats_sorted":[],"title_canon_sha256":"8aa6332a1b71ddf0db01a4417a9bd5f06ba8d0c4763f43a53208b3cc4f99b72e","abstract_canon_sha256":"16e9bde8831149c100d54ac5a8249fa5311b82bf4f4687bdc30964274999a87c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:09.813375Z","signature_b64":"Irr6eob/96vHqeAuBUepSVBkeizGelAJzkVeLdMbwzgMBr1A8pG6THL6e40FQKaocCcHz5HaYZqRpREOmRzGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"292a203a2f03898697591a9ffb2f1cc95b0ae5949b980a11d009c9c9f968055a","last_reissued_at":"2026-07-05T11:48:09.812841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:09.812841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Test-Time Model Adaptation for Quantized Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guohao Chen, Hui Luo, Mingkui Tan, Renjie Chen, Shuaicheng Niu, Shuhai Zhang, Wei Luo, Yifan Yang, Zeshuai Deng","submitted_at":"2025-08-04T08:24:19Z","abstract_excerpt":"Quantizing deep models prior to deployment is a widely adopted technique to speed up inference for various real-time applications, such as autonomous driving. However, quantized models often suffer from severe performance degradation in dynamic environments with potential domain shifts and this degradation is significantly more pronounced compared with their full-precision counterparts, as shown by our theoretical and empirical illustrations. To address the domain shift problem, test-time adaptation (TTA) has emerged as an effective solution by enabling models to learn adaptively from test dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02180","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/2508.02180/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":"2508.02180","created_at":"2026-07-05T11:48:09.812898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.02180v1","created_at":"2026-07-05T11:48:09.812898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02180","created_at":"2026-07-05T11:48:09.812898+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEVCAORPAOEY","created_at":"2026-07-05T11:48:09.812898+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEVCAORPAOEYNF2Z","created_at":"2026-07-05T11:48:09.812898+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEVCAORP","created_at":"2026-07-05T11:48:09.812898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.23183","citing_title":"ZeroSiam: An Efficient Asymmetry for Test-Time Entropy Optimization without Collapse","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18867","citing_title":"EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FEVCAORPAOEYNF2ZDKP7WLY4ZF","json":"https://pith.science/pith/FEVCAORPAOEYNF2ZDKP7WLY4ZF.json","graph_json":"https://pith.science/api/pith-number/FEVCAORPAOEYNF2ZDKP7WLY4ZF/graph.json","events_json":"https://pith.science/api/pith-number/FEVCAORPAOEYNF2ZDKP7WLY4ZF/events.json","paper":"https://pith.science/paper/FEVCAORP"},"agent_actions":{"view_html":"https://pith.science/pith/FEVCAORPAOEYNF2ZDKP7WLY4ZF","download_json":"https://pith.science/pith/FEVCAORPAOEYNF2ZDKP7WLY4ZF.json","view_paper":"https://pith.science/paper/FEVCAORP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.02180&json=true","fetch_graph":"https://pith.science/api/pith-number/FEVCAORPAOEYNF2ZDKP7WLY4ZF/graph.json","fetch_events":"https://pith.science/api/pith-number/FEVCAORPAOEYNF2ZDKP7WLY4ZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEVCAORPAOEYNF2ZDKP7WLY4ZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEVCAORPAOEYNF2ZDKP7WLY4ZF/action/storage_attestation","attest_author":"https://pith.science/pith/FEVCAORPAOEYNF2ZDKP7WLY4ZF/action/author_attestation","sign_citation":"https://pith.science/pith/FEVCAORPAOEYNF2ZDKP7WLY4ZF/action/citation_signature","submit_replication":"https://pith.science/pith/FEVCAORPAOEYNF2ZDKP7WLY4ZF/action/replication_record"}},"created_at":"2026-07-05T11:48:09.812898+00:00","updated_at":"2026-07-05T11:48:09.812898+00:00"}