{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FFVBKFWJV6JMQBI47QIN67RI5L","short_pith_number":"pith:FFVBKFWJ","schema_version":"1.0","canonical_sha256":"296a1516c9af92c8051cfc10df7e28eac3109a1740a91ff8d61bbc3faf21b3e2","source":{"kind":"arxiv","id":"2410.15430","version":2},"attestation_state":"computed","paper":{"title":"BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Chen, Hang Guo, Jinpeng Wang, Shu-Tao Xia, Tao Dai, Taolin Zhang","submitted_at":"2024-10-20T15:58:43Z","abstract_excerpt":"Adaptation of pretrained vision-language models such as CLIP to various downstream tasks have raised great interest in recent researches. Previous works have proposed a variety of test-time adaptation (TTA) methods to achieve strong generalization without any knowledge of the target domain. However, existing training-required TTA approaches like TPT necessitate entropy minimization that involves large computational overhead, while training-free methods like TDA overlook the potential for information mining from the test samples themselves. In this paper, we break down the design of existing po"},"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":"2410.15430","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-20T15:58:43Z","cross_cats_sorted":[],"title_canon_sha256":"84e41bc22b4edde61082a34638a233f8b3aae8c8035cfef847db3bbbc2ef97ab","abstract_canon_sha256":"e46d0ace9efea0d31b6628221a0eed163be78bcfa384335bed6fcfe2268a0191"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:02.638994Z","signature_b64":"KpnzWII6iT7avlELcBETdThZovJZ8twQn/jQL0V9JrzGRKEeHGGjlXAZkKxSxY2EyTTbiCAFrQywPEp5vktfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"296a1516c9af92c8051cfc10df7e28eac3109a1740a91ff8d61bbc3faf21b3e2","last_reissued_at":"2026-07-05T09:25:02.638495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:02.638495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Chen, Hang Guo, Jinpeng Wang, Shu-Tao Xia, Tao Dai, Taolin Zhang","submitted_at":"2024-10-20T15:58:43Z","abstract_excerpt":"Adaptation of pretrained vision-language models such as CLIP to various downstream tasks have raised great interest in recent researches. Previous works have proposed a variety of test-time adaptation (TTA) methods to achieve strong generalization without any knowledge of the target domain. However, existing training-required TTA approaches like TPT necessitate entropy minimization that involves large computational overhead, while training-free methods like TDA overlook the potential for information mining from the test samples themselves. In this paper, we break down the design of existing po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15430","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/2410.15430/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":"2410.15430","created_at":"2026-07-05T09:25:02.638567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.15430v2","created_at":"2026-07-05T09:25:02.638567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15430","created_at":"2026-07-05T09:25:02.638567+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFVBKFWJV6JM","created_at":"2026-07-05T09:25:02.638567+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFVBKFWJV6JMQBI4","created_at":"2026-07-05T09:25:02.638567+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFVBKFWJ","created_at":"2026-07-05T09:25:02.638567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.02671","citing_title":"Test-Time Distillation for Continual Model Adaptation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10421","citing_title":"Neural Collapse in Test-Time Adaptation","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FFVBKFWJV6JMQBI47QIN67RI5L","json":"https://pith.science/pith/FFVBKFWJV6JMQBI47QIN67RI5L.json","graph_json":"https://pith.science/api/pith-number/FFVBKFWJV6JMQBI47QIN67RI5L/graph.json","events_json":"https://pith.science/api/pith-number/FFVBKFWJV6JMQBI47QIN67RI5L/events.json","paper":"https://pith.science/paper/FFVBKFWJ"},"agent_actions":{"view_html":"https://pith.science/pith/FFVBKFWJV6JMQBI47QIN67RI5L","download_json":"https://pith.science/pith/FFVBKFWJV6JMQBI47QIN67RI5L.json","view_paper":"https://pith.science/paper/FFVBKFWJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.15430&json=true","fetch_graph":"https://pith.science/api/pith-number/FFVBKFWJV6JMQBI47QIN67RI5L/graph.json","fetch_events":"https://pith.science/api/pith-number/FFVBKFWJV6JMQBI47QIN67RI5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFVBKFWJV6JMQBI47QIN67RI5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFVBKFWJV6JMQBI47QIN67RI5L/action/storage_attestation","attest_author":"https://pith.science/pith/FFVBKFWJV6JMQBI47QIN67RI5L/action/author_attestation","sign_citation":"https://pith.science/pith/FFVBKFWJV6JMQBI47QIN67RI5L/action/citation_signature","submit_replication":"https://pith.science/pith/FFVBKFWJV6JMQBI47QIN67RI5L/action/replication_record"}},"created_at":"2026-07-05T09:25:02.638567+00:00","updated_at":"2026-07-05T09:25:02.638567+00:00"}