{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HHYCJPY6RVMCLYH6ERWDATGR23","short_pith_number":"pith:HHYCJPY6","schema_version":"1.0","canonical_sha256":"39f024bf1e8d5825e0fe246c304cd1d6c92417fbd5a706e0fdf0a0b9cc658a22","source":{"kind":"arxiv","id":"2506.11493","version":1},"attestation_state":"computed","paper":{"title":"Preserving Clusters in Prompt Learning for Unsupervised Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Bui, Dinh Phung, Hoang Phan, Thanh-Toan Do, Trung Le, Tung-Long Vuong, Vy Vo","submitted_at":"2025-06-13T06:33:27Z","abstract_excerpt":"Recent approaches leveraging multi-modal pre-trained models like CLIP for Unsupervised Domain Adaptation (UDA) have shown significant promise in bridging domain gaps and improving generalization by utilizing rich semantic knowledge and robust visual representations learned through extensive pre-training on diverse image-text datasets. While these methods achieve state-of-the-art performance across benchmarks, much of the improvement stems from base pseudo-labels (CLIP zero-shot predictions) and self-training mechanisms. Thus, the training mechanism exhibits a key limitation wherein the visual "},"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":"2506.11493","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T06:33:27Z","cross_cats_sorted":[],"title_canon_sha256":"62f000eb6b8aba4c2eaabc7e39b9cc3104c07b50c77abea476ad1080d07799e2","abstract_canon_sha256":"a2bca6e73832f3df64c5e43207bfe48e529bd7faeea9af4178e63b796315ad37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:05.514390Z","signature_b64":"jaL07y7QMg3+p2CHS/p2lo28B+AyMbEt4eBvjHjxZHwC8igyxkASAMG/dMM9YcgbfpM3ZcPJWXD+m3Zu9yL4Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39f024bf1e8d5825e0fe246c304cd1d6c92417fbd5a706e0fdf0a0b9cc658a22","last_reissued_at":"2026-07-05T11:21:05.513881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:05.513881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preserving Clusters in Prompt Learning for Unsupervised Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Bui, Dinh Phung, Hoang Phan, Thanh-Toan Do, Trung Le, Tung-Long Vuong, Vy Vo","submitted_at":"2025-06-13T06:33:27Z","abstract_excerpt":"Recent approaches leveraging multi-modal pre-trained models like CLIP for Unsupervised Domain Adaptation (UDA) have shown significant promise in bridging domain gaps and improving generalization by utilizing rich semantic knowledge and robust visual representations learned through extensive pre-training on diverse image-text datasets. While these methods achieve state-of-the-art performance across benchmarks, much of the improvement stems from base pseudo-labels (CLIP zero-shot predictions) and self-training mechanisms. Thus, the training mechanism exhibits a key limitation wherein the visual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11493","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/2506.11493/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":"2506.11493","created_at":"2026-07-05T11:21:05.513955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11493v1","created_at":"2026-07-05T11:21:05.513955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11493","created_at":"2026-07-05T11:21:05.513955+00:00"},{"alias_kind":"pith_short_12","alias_value":"HHYCJPY6RVMC","created_at":"2026-07-05T11:21:05.513955+00:00"},{"alias_kind":"pith_short_16","alias_value":"HHYCJPY6RVMCLYH6","created_at":"2026-07-05T11:21:05.513955+00:00"},{"alias_kind":"pith_short_8","alias_value":"HHYCJPY6","created_at":"2026-07-05T11:21:05.513955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HHYCJPY6RVMCLYH6ERWDATGR23","json":"https://pith.science/pith/HHYCJPY6RVMCLYH6ERWDATGR23.json","graph_json":"https://pith.science/api/pith-number/HHYCJPY6RVMCLYH6ERWDATGR23/graph.json","events_json":"https://pith.science/api/pith-number/HHYCJPY6RVMCLYH6ERWDATGR23/events.json","paper":"https://pith.science/paper/HHYCJPY6"},"agent_actions":{"view_html":"https://pith.science/pith/HHYCJPY6RVMCLYH6ERWDATGR23","download_json":"https://pith.science/pith/HHYCJPY6RVMCLYH6ERWDATGR23.json","view_paper":"https://pith.science/paper/HHYCJPY6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11493&json=true","fetch_graph":"https://pith.science/api/pith-number/HHYCJPY6RVMCLYH6ERWDATGR23/graph.json","fetch_events":"https://pith.science/api/pith-number/HHYCJPY6RVMCLYH6ERWDATGR23/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HHYCJPY6RVMCLYH6ERWDATGR23/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HHYCJPY6RVMCLYH6ERWDATGR23/action/storage_attestation","attest_author":"https://pith.science/pith/HHYCJPY6RVMCLYH6ERWDATGR23/action/author_attestation","sign_citation":"https://pith.science/pith/HHYCJPY6RVMCLYH6ERWDATGR23/action/citation_signature","submit_replication":"https://pith.science/pith/HHYCJPY6RVMCLYH6ERWDATGR23/action/replication_record"}},"created_at":"2026-07-05T11:21:05.513955+00:00","updated_at":"2026-07-05T11:21:05.513955+00:00"}