{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EDTII4PLMETRQZSLHXTPOYHWJV","short_pith_number":"pith:EDTII4PL","schema_version":"1.0","canonical_sha256":"20e68471eb612718664b3de6f760f64d464ae8b2a814759240cace7970a992b6","source":{"kind":"arxiv","id":"2308.09139","version":2},"attestation_state":"computed","paper":{"title":"The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alessandro Conti, Elisa Ricci, Giacomo Zara, Paolo Rota, St\\'ephane Lathuili\\`ere, Subhankar Roy","submitted_at":"2023-08-17T18:12:05Z","abstract_excerpt":"Source-Free Video Unsupervised Domain Adaptation (SFVUDA) task consists in adapting an action recognition model, trained on a labelled source dataset, to an unlabelled target dataset, without accessing the actual source data. The previous approaches have attempted to address SFVUDA by leveraging self-supervision (e.g., enforcing temporal consistency) derived from the target data itself. In this work, we take an orthogonal approach by exploiting \"web-supervision\" from Large Language-Vision Models (LLVMs), driven by the rationale that LLVMs contain a rich world prior surprisingly robust to domai"},"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":"2308.09139","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-17T18:12:05Z","cross_cats_sorted":[],"title_canon_sha256":"0cbc7dcb81e4d58ac655ce19feb8489c20141acbf7b195333e40efe79174e05a","abstract_canon_sha256":"7b2df24853b31d73868112a5d25e0e1dbbc625325e0ddf3827ba17bb954c38f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:25.657619Z","signature_b64":"jrKnM+guhZugY5/Mkr/mBljD47DB+olMEzDiOC8ipwEio3Whm5wnOsgJyiDEB/IwZysJa05QPoxyLsAF9KgRDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20e68471eb612718664b3de6f760f64d464ae8b2a814759240cace7970a992b6","last_reissued_at":"2026-07-05T06:43:25.656932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:25.656932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alessandro Conti, Elisa Ricci, Giacomo Zara, Paolo Rota, St\\'ephane Lathuili\\`ere, Subhankar Roy","submitted_at":"2023-08-17T18:12:05Z","abstract_excerpt":"Source-Free Video Unsupervised Domain Adaptation (SFVUDA) task consists in adapting an action recognition model, trained on a labelled source dataset, to an unlabelled target dataset, without accessing the actual source data. The previous approaches have attempted to address SFVUDA by leveraging self-supervision (e.g., enforcing temporal consistency) derived from the target data itself. In this work, we take an orthogonal approach by exploiting \"web-supervision\" from Large Language-Vision Models (LLVMs), driven by the rationale that LLVMs contain a rich world prior surprisingly robust to domai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09139","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/2308.09139/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":"2308.09139","created_at":"2026-07-05T06:43:25.657024+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.09139v2","created_at":"2026-07-05T06:43:25.657024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09139","created_at":"2026-07-05T06:43:25.657024+00:00"},{"alias_kind":"pith_short_12","alias_value":"EDTII4PLMETR","created_at":"2026-07-05T06:43:25.657024+00:00"},{"alias_kind":"pith_short_16","alias_value":"EDTII4PLMETRQZSL","created_at":"2026-07-05T06:43:25.657024+00:00"},{"alias_kind":"pith_short_8","alias_value":"EDTII4PL","created_at":"2026-07-05T06:43:25.657024+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/EDTII4PLMETRQZSLHXTPOYHWJV","json":"https://pith.science/pith/EDTII4PLMETRQZSLHXTPOYHWJV.json","graph_json":"https://pith.science/api/pith-number/EDTII4PLMETRQZSLHXTPOYHWJV/graph.json","events_json":"https://pith.science/api/pith-number/EDTII4PLMETRQZSLHXTPOYHWJV/events.json","paper":"https://pith.science/paper/EDTII4PL"},"agent_actions":{"view_html":"https://pith.science/pith/EDTII4PLMETRQZSLHXTPOYHWJV","download_json":"https://pith.science/pith/EDTII4PLMETRQZSLHXTPOYHWJV.json","view_paper":"https://pith.science/paper/EDTII4PL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.09139&json=true","fetch_graph":"https://pith.science/api/pith-number/EDTII4PLMETRQZSLHXTPOYHWJV/graph.json","fetch_events":"https://pith.science/api/pith-number/EDTII4PLMETRQZSLHXTPOYHWJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EDTII4PLMETRQZSLHXTPOYHWJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EDTII4PLMETRQZSLHXTPOYHWJV/action/storage_attestation","attest_author":"https://pith.science/pith/EDTII4PLMETRQZSLHXTPOYHWJV/action/author_attestation","sign_citation":"https://pith.science/pith/EDTII4PLMETRQZSLHXTPOYHWJV/action/citation_signature","submit_replication":"https://pith.science/pith/EDTII4PLMETRQZSLHXTPOYHWJV/action/replication_record"}},"created_at":"2026-07-05T06:43:25.657024+00:00","updated_at":"2026-07-05T06:43:25.657024+00:00"}