{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QM5MHGVWNJJOLM64VJUPSZSIO4","short_pith_number":"pith:QM5MHGVW","schema_version":"1.0","canonical_sha256":"833ac39ab66a52e5b3dcaa68f9664877224a2e5a72783231ae79bfc8c234ba82","source":{"kind":"arxiv","id":"2505.18514","version":1},"attestation_state":"computed","paper":{"title":"Test-Time Adaptation with Binary Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jinwoo Shin, Junsu Kim, Sorn Chottananurak, Sung-Ju Lee, Taeckyung Lee, Taesik Gong","submitted_at":"2025-05-24T05:24:10Z","abstract_excerpt":"Deep learning models perform poorly when domain shifts exist between training and test data. Test-time adaptation (TTA) is a paradigm to mitigate this issue by adapting pre-trained models using only unlabeled test samples. However, existing TTA methods can fail under severe domain shifts, while recent active TTA approaches requiring full-class labels are impractical due to high labeling costs. To address this issue, we introduce a new setting of TTA with binary feedback. This setting uses a few binary feedback inputs from annotators to indicate whether model predictions are correct, thereby si"},"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":"2505.18514","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T05:24:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3adcaf23ac122051fdde8be5d81cf14e4a6cbde5b6c531d1d2e9a9e0ad1337f8","abstract_canon_sha256":"fe2e24112b72ae7d2e09dff5354c70f6ff92e1afb8ac41309c6fc4ac7386c177"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:47.587386Z","signature_b64":"KoAZC26ARP3RqY/8ebLn8WB/Ct5h9gdjb5nI+I34/AvLNoRr/l1bROxH5g3/FUgso3EkdMd4P6VEB0kDNNH3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"833ac39ab66a52e5b3dcaa68f9664877224a2e5a72783231ae79bfc8c234ba82","last_reissued_at":"2026-07-05T11:08:47.586964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:47.586964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Test-Time Adaptation with Binary Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jinwoo Shin, Junsu Kim, Sorn Chottananurak, Sung-Ju Lee, Taeckyung Lee, Taesik Gong","submitted_at":"2025-05-24T05:24:10Z","abstract_excerpt":"Deep learning models perform poorly when domain shifts exist between training and test data. Test-time adaptation (TTA) is a paradigm to mitigate this issue by adapting pre-trained models using only unlabeled test samples. However, existing TTA methods can fail under severe domain shifts, while recent active TTA approaches requiring full-class labels are impractical due to high labeling costs. To address this issue, we introduce a new setting of TTA with binary feedback. This setting uses a few binary feedback inputs from annotators to indicate whether model predictions are correct, thereby si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18514","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/2505.18514/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":"2505.18514","created_at":"2026-07-05T11:08:47.587020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18514v1","created_at":"2026-07-05T11:08:47.587020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18514","created_at":"2026-07-05T11:08:47.587020+00:00"},{"alias_kind":"pith_short_12","alias_value":"QM5MHGVWNJJO","created_at":"2026-07-05T11:08:47.587020+00:00"},{"alias_kind":"pith_short_16","alias_value":"QM5MHGVWNJJOLM64","created_at":"2026-07-05T11:08:47.587020+00:00"},{"alias_kind":"pith_short_8","alias_value":"QM5MHGVW","created_at":"2026-07-05T11:08:47.587020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18107","citing_title":"Test-Time Perturbation Learning with Delayed Feedback for Vision-Language-Action Models","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QM5MHGVWNJJOLM64VJUPSZSIO4","json":"https://pith.science/pith/QM5MHGVWNJJOLM64VJUPSZSIO4.json","graph_json":"https://pith.science/api/pith-number/QM5MHGVWNJJOLM64VJUPSZSIO4/graph.json","events_json":"https://pith.science/api/pith-number/QM5MHGVWNJJOLM64VJUPSZSIO4/events.json","paper":"https://pith.science/paper/QM5MHGVW"},"agent_actions":{"view_html":"https://pith.science/pith/QM5MHGVWNJJOLM64VJUPSZSIO4","download_json":"https://pith.science/pith/QM5MHGVWNJJOLM64VJUPSZSIO4.json","view_paper":"https://pith.science/paper/QM5MHGVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18514&json=true","fetch_graph":"https://pith.science/api/pith-number/QM5MHGVWNJJOLM64VJUPSZSIO4/graph.json","fetch_events":"https://pith.science/api/pith-number/QM5MHGVWNJJOLM64VJUPSZSIO4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QM5MHGVWNJJOLM64VJUPSZSIO4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QM5MHGVWNJJOLM64VJUPSZSIO4/action/storage_attestation","attest_author":"https://pith.science/pith/QM5MHGVWNJJOLM64VJUPSZSIO4/action/author_attestation","sign_citation":"https://pith.science/pith/QM5MHGVWNJJOLM64VJUPSZSIO4/action/citation_signature","submit_replication":"https://pith.science/pith/QM5MHGVWNJJOLM64VJUPSZSIO4/action/replication_record"}},"created_at":"2026-07-05T11:08:47.587020+00:00","updated_at":"2026-07-05T11:08:47.587020+00:00"}