{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5P3XAODDDFR6U7OKF6QV4NCDWE","short_pith_number":"pith:5P3XAODD","schema_version":"1.0","canonical_sha256":"ebf77038631963ea7dca2fa15e3443b1037a36bc9428086754d054e684b77e64","source":{"kind":"arxiv","id":"2404.05094","version":1},"attestation_state":"computed","paper":{"title":"Active Test-Time Adaptation: Theoretical Analyses and An Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Shuiwang Ji, Shurui Gui, Xiner Li","submitted_at":"2024-04-07T22:31:34Z","abstract_excerpt":"Test-time adaptation (TTA) addresses distribution shifts for streaming test data in unsupervised settings. Currently, most TTA methods can only deal with minor shifts and rely heavily on heuristic and empirical studies.\n  To advance TTA under domain shifts, we propose the novel problem setting of active test-time adaptation (ATTA) that integrates active learning within the fully TTA setting.\n  We provide a learning theory analysis, demonstrating that incorporating limited labeled test instances enhances overall performances across test domains with a theoretical guarantee. We also present a sa"},"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":"2404.05094","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-07T22:31:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8564512f713cb7fee27f4cab3c2d5261f9fa9136ee72212264209033b8ee6261","abstract_canon_sha256":"b3e05adb6dcfde3ec90e7631a45aa7669ebfad6cfb969120ee66ce92e1da9e22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:26.040060Z","signature_b64":"MFQ81JHrVWwPEL+IzMezn0kZ0hKOqlzG+BtPy8NuCKwwSIUY9fqrDp67lrO81xOrk9Mw0azniN24wfyaHqtbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebf77038631963ea7dca2fa15e3443b1037a36bc9428086754d054e684b77e64","last_reissued_at":"2026-07-05T08:05:26.039584Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:26.039584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Test-Time Adaptation: Theoretical Analyses and An Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Shuiwang Ji, Shurui Gui, Xiner Li","submitted_at":"2024-04-07T22:31:34Z","abstract_excerpt":"Test-time adaptation (TTA) addresses distribution shifts for streaming test data in unsupervised settings. Currently, most TTA methods can only deal with minor shifts and rely heavily on heuristic and empirical studies.\n  To advance TTA under domain shifts, we propose the novel problem setting of active test-time adaptation (ATTA) that integrates active learning within the fully TTA setting.\n  We provide a learning theory analysis, demonstrating that incorporating limited labeled test instances enhances overall performances across test domains with a theoretical guarantee. We also present a sa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05094","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/2404.05094/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":"2404.05094","created_at":"2026-07-05T08:05:26.039642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05094v1","created_at":"2026-07-05T08:05:26.039642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05094","created_at":"2026-07-05T08:05:26.039642+00:00"},{"alias_kind":"pith_short_12","alias_value":"5P3XAODDDFR6","created_at":"2026-07-05T08:05:26.039642+00:00"},{"alias_kind":"pith_short_16","alias_value":"5P3XAODDDFR6U7OK","created_at":"2026-07-05T08:05:26.039642+00:00"},{"alias_kind":"pith_short_8","alias_value":"5P3XAODD","created_at":"2026-07-05T08:05:26.039642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20029","citing_title":"Segmentation Assisted Incremental Test Time Adaptation in an Open World","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5P3XAODDDFR6U7OKF6QV4NCDWE","json":"https://pith.science/pith/5P3XAODDDFR6U7OKF6QV4NCDWE.json","graph_json":"https://pith.science/api/pith-number/5P3XAODDDFR6U7OKF6QV4NCDWE/graph.json","events_json":"https://pith.science/api/pith-number/5P3XAODDDFR6U7OKF6QV4NCDWE/events.json","paper":"https://pith.science/paper/5P3XAODD"},"agent_actions":{"view_html":"https://pith.science/pith/5P3XAODDDFR6U7OKF6QV4NCDWE","download_json":"https://pith.science/pith/5P3XAODDDFR6U7OKF6QV4NCDWE.json","view_paper":"https://pith.science/paper/5P3XAODD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05094&json=true","fetch_graph":"https://pith.science/api/pith-number/5P3XAODDDFR6U7OKF6QV4NCDWE/graph.json","fetch_events":"https://pith.science/api/pith-number/5P3XAODDDFR6U7OKF6QV4NCDWE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5P3XAODDDFR6U7OKF6QV4NCDWE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5P3XAODDDFR6U7OKF6QV4NCDWE/action/storage_attestation","attest_author":"https://pith.science/pith/5P3XAODDDFR6U7OKF6QV4NCDWE/action/author_attestation","sign_citation":"https://pith.science/pith/5P3XAODDDFR6U7OKF6QV4NCDWE/action/citation_signature","submit_replication":"https://pith.science/pith/5P3XAODDDFR6U7OKF6QV4NCDWE/action/replication_record"}},"created_at":"2026-07-05T08:05:26.039642+00:00","updated_at":"2026-07-05T08:05:26.039642+00:00"}