{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CLF42EWQSQJVSV3QNOGLI5HBJ2","short_pith_number":"pith:CLF42EWQ","schema_version":"1.0","canonical_sha256":"12cbcd12d094135957706b8cb474e14eaf5ea22c4364a0c4024564f7ecc71086","source":{"kind":"arxiv","id":"2307.07489","version":1},"attestation_state":"computed","paper":{"title":"PseudoCal: A Source-Free Approach to Unsupervised Uncertainty Calibration in Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chuan-Sheng Foo, Dapeng Hu, Jian Liang, Xinchao Wang","submitted_at":"2023-07-14T17:21:41Z","abstract_excerpt":"Unsupervised domain adaptation (UDA) has witnessed remarkable advancements in improving the accuracy of models for unlabeled target domains. However, the calibration of predictive uncertainty in the target domain, a crucial aspect of the safe deployment of UDA models, has received limited attention. The conventional in-domain calibration method, \\textit{temperature scaling} (TempScal), encounters challenges due to domain distribution shifts and the absence of labeled target domain data. Recent approaches have employed importance-weighting techniques to estimate the target-optimal temperature b"},"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":"2307.07489","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-14T17:21:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"90b772dd1519141e6685ba1eaa62f6e8391c8ec2ad1f187582a8d7458d8192fc","abstract_canon_sha256":"a72ee7ae952db78b3f46a46f706860defc929c6c2f091aa02852d0664db27030"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:56.344137Z","signature_b64":"4yy0nGyqYZ59AsKAdwboB443ifz5WRJex/IiYGSPEp7i1DJzop49tXcFWvJsbxkGEVkOpwE5qoWC2jAHuab/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12cbcd12d094135957706b8cb474e14eaf5ea22c4364a0c4024564f7ecc71086","last_reissued_at":"2026-07-05T06:30:56.343557Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:56.343557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PseudoCal: A Source-Free Approach to Unsupervised Uncertainty Calibration in Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chuan-Sheng Foo, Dapeng Hu, Jian Liang, Xinchao Wang","submitted_at":"2023-07-14T17:21:41Z","abstract_excerpt":"Unsupervised domain adaptation (UDA) has witnessed remarkable advancements in improving the accuracy of models for unlabeled target domains. However, the calibration of predictive uncertainty in the target domain, a crucial aspect of the safe deployment of UDA models, has received limited attention. The conventional in-domain calibration method, \\textit{temperature scaling} (TempScal), encounters challenges due to domain distribution shifts and the absence of labeled target domain data. Recent approaches have employed importance-weighting techniques to estimate the target-optimal temperature b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07489","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/2307.07489/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":"2307.07489","created_at":"2026-07-05T06:30:56.343630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.07489v1","created_at":"2026-07-05T06:30:56.343630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07489","created_at":"2026-07-05T06:30:56.343630+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLF42EWQSQJV","created_at":"2026-07-05T06:30:56.343630+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLF42EWQSQJVSV3Q","created_at":"2026-07-05T06:30:56.343630+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLF42EWQ","created_at":"2026-07-05T06:30:56.343630+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/CLF42EWQSQJVSV3QNOGLI5HBJ2","json":"https://pith.science/pith/CLF42EWQSQJVSV3QNOGLI5HBJ2.json","graph_json":"https://pith.science/api/pith-number/CLF42EWQSQJVSV3QNOGLI5HBJ2/graph.json","events_json":"https://pith.science/api/pith-number/CLF42EWQSQJVSV3QNOGLI5HBJ2/events.json","paper":"https://pith.science/paper/CLF42EWQ"},"agent_actions":{"view_html":"https://pith.science/pith/CLF42EWQSQJVSV3QNOGLI5HBJ2","download_json":"https://pith.science/pith/CLF42EWQSQJVSV3QNOGLI5HBJ2.json","view_paper":"https://pith.science/paper/CLF42EWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.07489&json=true","fetch_graph":"https://pith.science/api/pith-number/CLF42EWQSQJVSV3QNOGLI5HBJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/CLF42EWQSQJVSV3QNOGLI5HBJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLF42EWQSQJVSV3QNOGLI5HBJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLF42EWQSQJVSV3QNOGLI5HBJ2/action/storage_attestation","attest_author":"https://pith.science/pith/CLF42EWQSQJVSV3QNOGLI5HBJ2/action/author_attestation","sign_citation":"https://pith.science/pith/CLF42EWQSQJVSV3QNOGLI5HBJ2/action/citation_signature","submit_replication":"https://pith.science/pith/CLF42EWQSQJVSV3QNOGLI5HBJ2/action/replication_record"}},"created_at":"2026-07-05T06:30:56.343630+00:00","updated_at":"2026-07-05T06:30:56.343630+00:00"}