{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BFLV43RX3SXZWYEWKJLHJMBCGH","short_pith_number":"pith:BFLV43RX","schema_version":"1.0","canonical_sha256":"09575e6e37dcaf9b6096525674b02231c258796c96472becbdcdf37ec5efe4ae","source":{"kind":"arxiv","id":"2406.02609","version":2},"attestation_state":"computed","paper":{"title":"Less is More: Pseudo-Label Filtering for Continual Test-Time Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenggong Ni, Fan Lyu, Fuyuan Hu, Jiayao Tan, Liang Wang, Shaochuang Zhao, Tingliang Feng, Zhang Zhang","submitted_at":"2024-06-03T04:09:36Z","abstract_excerpt":"Continual Test-Time Adaptation (CTTA) aims to adapt a pre-trained model to a sequence of target domains during the test phase without accessing the source data. To adapt to unlabeled data from unknown domains, existing methods rely on constructing pseudo-labels for all samples and updating the model through self-training. However, these pseudo-labels often involve noise, leading to insufficient adaptation. To improve the quality of pseudo-labels, we propose a pseudo-label selection method for CTTA, called Pseudo Labeling Filter (PLF). The key idea of PLF is to keep selecting appropriate thresh"},"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":"2406.02609","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T04:09:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"052cf81ea2ff865c91a3a8c2bf30b71ecbc211834dae1861a2cb7f85dfd6d73c","abstract_canon_sha256":"715298fa4b1d173b9395dfc26083ebb2be4eaf322c0f91f17de1c0571b6986ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:10.430166Z","signature_b64":"vDrQTrO1pGhu9yZS0YaYBBG12adXrY5XFsfjSp8J6uWz1XWs/iPmiHhFAg7x7XPfP9/FQ++CHNbdV2AyXvOgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09575e6e37dcaf9b6096525674b02231c258796c96472becbdcdf37ec5efe4ae","last_reissued_at":"2026-07-05T08:43:10.429736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:10.429736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Less is More: Pseudo-Label Filtering for Continual Test-Time Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenggong Ni, Fan Lyu, Fuyuan Hu, Jiayao Tan, Liang Wang, Shaochuang Zhao, Tingliang Feng, Zhang Zhang","submitted_at":"2024-06-03T04:09:36Z","abstract_excerpt":"Continual Test-Time Adaptation (CTTA) aims to adapt a pre-trained model to a sequence of target domains during the test phase without accessing the source data. To adapt to unlabeled data from unknown domains, existing methods rely on constructing pseudo-labels for all samples and updating the model through self-training. However, these pseudo-labels often involve noise, leading to insufficient adaptation. To improve the quality of pseudo-labels, we propose a pseudo-label selection method for CTTA, called Pseudo Labeling Filter (PLF). The key idea of PLF is to keep selecting appropriate thresh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02609","kind":"arxiv","version":2},"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/2406.02609/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":"2406.02609","created_at":"2026-07-05T08:43:10.429793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02609v2","created_at":"2026-07-05T08:43:10.429793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02609","created_at":"2026-07-05T08:43:10.429793+00:00"},{"alias_kind":"pith_short_12","alias_value":"BFLV43RX3SXZ","created_at":"2026-07-05T08:43:10.429793+00:00"},{"alias_kind":"pith_short_16","alias_value":"BFLV43RX3SXZWYEW","created_at":"2026-07-05T08:43:10.429793+00:00"},{"alias_kind":"pith_short_8","alias_value":"BFLV43RX","created_at":"2026-07-05T08:43:10.429793+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08164","citing_title":"Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BFLV43RX3SXZWYEWKJLHJMBCGH","json":"https://pith.science/pith/BFLV43RX3SXZWYEWKJLHJMBCGH.json","graph_json":"https://pith.science/api/pith-number/BFLV43RX3SXZWYEWKJLHJMBCGH/graph.json","events_json":"https://pith.science/api/pith-number/BFLV43RX3SXZWYEWKJLHJMBCGH/events.json","paper":"https://pith.science/paper/BFLV43RX"},"agent_actions":{"view_html":"https://pith.science/pith/BFLV43RX3SXZWYEWKJLHJMBCGH","download_json":"https://pith.science/pith/BFLV43RX3SXZWYEWKJLHJMBCGH.json","view_paper":"https://pith.science/paper/BFLV43RX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02609&json=true","fetch_graph":"https://pith.science/api/pith-number/BFLV43RX3SXZWYEWKJLHJMBCGH/graph.json","fetch_events":"https://pith.science/api/pith-number/BFLV43RX3SXZWYEWKJLHJMBCGH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BFLV43RX3SXZWYEWKJLHJMBCGH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BFLV43RX3SXZWYEWKJLHJMBCGH/action/storage_attestation","attest_author":"https://pith.science/pith/BFLV43RX3SXZWYEWKJLHJMBCGH/action/author_attestation","sign_citation":"https://pith.science/pith/BFLV43RX3SXZWYEWKJLHJMBCGH/action/citation_signature","submit_replication":"https://pith.science/pith/BFLV43RX3SXZWYEWKJLHJMBCGH/action/replication_record"}},"created_at":"2026-07-05T08:43:10.429793+00:00","updated_at":"2026-07-05T08:43:10.429793+00:00"}