{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SBWR6XBWL3GZSTPTORNIH6RDNL","short_pith_number":"pith:SBWR6XBW","schema_version":"1.0","canonical_sha256":"906d1f5c365ecd994df3745a83fa236aff9cd8b83a834ec476bfdb4315567f7a","source":{"kind":"arxiv","id":"2508.05547","version":1},"attestation_state":"computed","paper":{"title":"Adapting Vision-Language Models Without Labels: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Eleni Chatzi, Hao Dong, Jian Liang, Lijun Sheng, Olga Fink, Ran He","submitted_at":"2025-08-07T16:27:37Z","abstract_excerpt":"Vision-Language Models (VLMs) have demonstrated remarkable generalization capabilities across a wide range of tasks. However, their performance often remains suboptimal when directly applied to specific downstream scenarios without task-specific adaptation. To enhance their utility while preserving data efficiency, recent research has increasingly focused on unsupervised adaptation methods that do not rely on labeled data. Despite the growing interest in this area, there remains a lack of a unified, task-oriented survey dedicated to unsupervised VLM adaptation. To bridge this gap, we present a"},"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":"2508.05547","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-07T16:27:37Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"6e89570b3267aae211e11290f905da0de3bacce746ffc39eca9bcfa5842cbe4a","abstract_canon_sha256":"0e39c012d74fd4276d70162399e8543d37d1c051fb7f551cb99980a43b56a126"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:15.231886Z","signature_b64":"n+Hm+MiPHEwY0+3yktEmxLVx3XgvitlH5i+5wLfWQedskfAxthu8Z8Rb4jV+ak5EsErxmz5okngN1xkatDxqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"906d1f5c365ecd994df3745a83fa236aff9cd8b83a834ec476bfdb4315567f7a","last_reissued_at":"2026-07-05T11:50:15.231348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:15.231348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapting Vision-Language Models Without Labels: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Eleni Chatzi, Hao Dong, Jian Liang, Lijun Sheng, Olga Fink, Ran He","submitted_at":"2025-08-07T16:27:37Z","abstract_excerpt":"Vision-Language Models (VLMs) have demonstrated remarkable generalization capabilities across a wide range of tasks. However, their performance often remains suboptimal when directly applied to specific downstream scenarios without task-specific adaptation. To enhance their utility while preserving data efficiency, recent research has increasingly focused on unsupervised adaptation methods that do not rely on labeled data. Despite the growing interest in this area, there remains a lack of a unified, task-oriented survey dedicated to unsupervised VLM adaptation. To bridge this gap, we present a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05547","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/2508.05547/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":"2508.05547","created_at":"2026-07-05T11:50:15.231428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.05547v1","created_at":"2026-07-05T11:50:15.231428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05547","created_at":"2026-07-05T11:50:15.231428+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBWR6XBWL3GZ","created_at":"2026-07-05T11:50:15.231428+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBWR6XBWL3GZSTPT","created_at":"2026-07-05T11:50:15.231428+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBWR6XBW","created_at":"2026-07-05T11:50:15.231428+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28719","citing_title":"ComMem: Complementary Memory Systems for Test-Time Adaptation of Vision-Language Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12325","citing_title":"VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12325","citing_title":"VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SBWR6XBWL3GZSTPTORNIH6RDNL","json":"https://pith.science/pith/SBWR6XBWL3GZSTPTORNIH6RDNL.json","graph_json":"https://pith.science/api/pith-number/SBWR6XBWL3GZSTPTORNIH6RDNL/graph.json","events_json":"https://pith.science/api/pith-number/SBWR6XBWL3GZSTPTORNIH6RDNL/events.json","paper":"https://pith.science/paper/SBWR6XBW"},"agent_actions":{"view_html":"https://pith.science/pith/SBWR6XBWL3GZSTPTORNIH6RDNL","download_json":"https://pith.science/pith/SBWR6XBWL3GZSTPTORNIH6RDNL.json","view_paper":"https://pith.science/paper/SBWR6XBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.05547&json=true","fetch_graph":"https://pith.science/api/pith-number/SBWR6XBWL3GZSTPTORNIH6RDNL/graph.json","fetch_events":"https://pith.science/api/pith-number/SBWR6XBWL3GZSTPTORNIH6RDNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBWR6XBWL3GZSTPTORNIH6RDNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBWR6XBWL3GZSTPTORNIH6RDNL/action/storage_attestation","attest_author":"https://pith.science/pith/SBWR6XBWL3GZSTPTORNIH6RDNL/action/author_attestation","sign_citation":"https://pith.science/pith/SBWR6XBWL3GZSTPTORNIH6RDNL/action/citation_signature","submit_replication":"https://pith.science/pith/SBWR6XBWL3GZSTPTORNIH6RDNL/action/replication_record"}},"created_at":"2026-07-05T11:50:15.231428+00:00","updated_at":"2026-07-05T11:50:15.231428+00:00"}