{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Y4FWQVEPWNS6FFPWMAUTRCDPHU","short_pith_number":"pith:Y4FWQVEP","schema_version":"1.0","canonical_sha256":"c70b68548fb365e295f6602938886f3d1f6ee0db2f1e0c5ee6f0ce8f60b24a20","source":{"kind":"arxiv","id":"2308.08810","version":1},"attestation_state":"computed","paper":{"title":"Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaegul Choo, Seunghan Yang, Sunghyun Park, Sungrack Yun","submitted_at":"2023-08-17T06:37:37Z","abstract_excerpt":"Test-time adaptation (TTA) aims to adapt a pre-trained model to the target domain in a batch-by-batch manner during inference. While label distributions often exhibit imbalances in real-world scenarios, most previous TTA approaches typically assume that both source and target domain datasets have balanced label distribution. Due to the fact that certain classes appear more frequently in certain domains (e.g., buildings in cities, trees in forests), it is natural that the label distribution shifts as the domain changes. However, we discover that the majority of existing TTA methods fail to addr"},"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":"2308.08810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-17T06:37:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ddb0ad73924f9bfc0b2ae4f57d6f7f4e0677e3b7c30bc5101d9ebde5958e86b8","abstract_canon_sha256":"7cfd389defae7872147acc40a287bd808383f035fd29e619e55c71a6ce5c3938"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:11.900692Z","signature_b64":"FR4P3OecTtgdEkX+GdO/i6MF8AcpKqgKi3o37MslVgQVWw3iz71BcVdqNOtfsj94xGRgvIUAYEdtU1aWoqK9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c70b68548fb365e295f6602938886f3d1f6ee0db2f1e0c5ee6f0ce8f60b24a20","last_reissued_at":"2026-07-05T06:42:11.900276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:11.900276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaegul Choo, Seunghan Yang, Sunghyun Park, Sungrack Yun","submitted_at":"2023-08-17T06:37:37Z","abstract_excerpt":"Test-time adaptation (TTA) aims to adapt a pre-trained model to the target domain in a batch-by-batch manner during inference. While label distributions often exhibit imbalances in real-world scenarios, most previous TTA approaches typically assume that both source and target domain datasets have balanced label distribution. Due to the fact that certain classes appear more frequently in certain domains (e.g., buildings in cities, trees in forests), it is natural that the label distribution shifts as the domain changes. However, we discover that the majority of existing TTA methods fail to addr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.08810","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/2308.08810/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":"2308.08810","created_at":"2026-07-05T06:42:11.900342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.08810v1","created_at":"2026-07-05T06:42:11.900342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.08810","created_at":"2026-07-05T06:42:11.900342+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y4FWQVEPWNS6","created_at":"2026-07-05T06:42:11.900342+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y4FWQVEPWNS6FFPW","created_at":"2026-07-05T06:42:11.900342+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y4FWQVEP","created_at":"2026-07-05T06:42:11.900342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15204","citing_title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y4FWQVEPWNS6FFPWMAUTRCDPHU","json":"https://pith.science/pith/Y4FWQVEPWNS6FFPWMAUTRCDPHU.json","graph_json":"https://pith.science/api/pith-number/Y4FWQVEPWNS6FFPWMAUTRCDPHU/graph.json","events_json":"https://pith.science/api/pith-number/Y4FWQVEPWNS6FFPWMAUTRCDPHU/events.json","paper":"https://pith.science/paper/Y4FWQVEP"},"agent_actions":{"view_html":"https://pith.science/pith/Y4FWQVEPWNS6FFPWMAUTRCDPHU","download_json":"https://pith.science/pith/Y4FWQVEPWNS6FFPWMAUTRCDPHU.json","view_paper":"https://pith.science/paper/Y4FWQVEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.08810&json=true","fetch_graph":"https://pith.science/api/pith-number/Y4FWQVEPWNS6FFPWMAUTRCDPHU/graph.json","fetch_events":"https://pith.science/api/pith-number/Y4FWQVEPWNS6FFPWMAUTRCDPHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y4FWQVEPWNS6FFPWMAUTRCDPHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y4FWQVEPWNS6FFPWMAUTRCDPHU/action/storage_attestation","attest_author":"https://pith.science/pith/Y4FWQVEPWNS6FFPWMAUTRCDPHU/action/author_attestation","sign_citation":"https://pith.science/pith/Y4FWQVEPWNS6FFPWMAUTRCDPHU/action/citation_signature","submit_replication":"https://pith.science/pith/Y4FWQVEPWNS6FFPWMAUTRCDPHU/action/replication_record"}},"created_at":"2026-07-05T06:42:11.900342+00:00","updated_at":"2026-07-05T06:42:11.900342+00:00"}