{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:47CY66C6VUNJKCYKINFI6GWLF3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0b2c99506d6ecf47fedc8621efadc4415e235b4f56d35ff386772dd8e4fa6c67","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T06:57:48Z","title_canon_sha256":"854c4f972cbd60d51e1969f138e214700644d21f78a79552fe65b70c0d595e3d"},"schema_version":"1.0","source":{"id":"2401.15914","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.15914","created_at":"2026-07-05T08:08:20Z"},{"alias_kind":"arxiv_version","alias_value":"2401.15914v2","created_at":"2026-07-05T08:08:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15914","created_at":"2026-07-05T08:08:20Z"},{"alias_kind":"pith_short_12","alias_value":"47CY66C6VUNJ","created_at":"2026-07-05T08:08:20Z"},{"alias_kind":"pith_short_16","alias_value":"47CY66C6VUNJKCYK","created_at":"2026-07-05T08:08:20Z"},{"alias_kind":"pith_short_8","alias_value":"47CY66C6","created_at":"2026-07-05T08:08:20Z"}],"graph_snapshots":[{"event_id":"sha256:56d5ae67b817f4e5027516c5035c9cce04d8075fc5d031541adb5e6f22e2000d","target":"graph","created_at":"2026-07-05T08:08:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.15914/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing vision-language models exhibit strong generalization on a variety of visual domains and tasks. However, such models mainly perform zero-shot recognition in a closed-set manner, and thus struggle to handle open-domain visual concepts by design. There are recent finetuning methods, such as prompt learning, that not only study the discrimination between in-distribution (ID) and out-of-distribution (OOD) samples, but also show some improvements in both ID and OOD accuracies. In this paper, we first demonstrate that vision-language models, after long enough finetuning but without proper re","authors_text":"Chen Huang, Hanlin Goh, Josh Susskind, Yuhang Zang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T06:57:48Z","title":"Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15914","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8e0b67fe1f1345c3b45ce0e9e44dd70d598b221f6f46bb15d7ee02b8a13ad9fb","target":"record","created_at":"2026-07-05T08:08:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0b2c99506d6ecf47fedc8621efadc4415e235b4f56d35ff386772dd8e4fa6c67","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T06:57:48Z","title_canon_sha256":"854c4f972cbd60d51e1969f138e214700644d21f78a79552fe65b70c0d595e3d"},"schema_version":"1.0","source":{"id":"2401.15914","kind":"arxiv","version":2}},"canonical_sha256":"e7c58f785ead1a950b0a434a8f1acb2ec73810d021750a639525071aaa94a118","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7c58f785ead1a950b0a434a8f1acb2ec73810d021750a639525071aaa94a118","first_computed_at":"2026-07-05T08:08:20.483823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:20.483823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q8TmoOWrIzNXONLivxH5zDcMeYC9LSyVxrDXCsYWVO93jxVI1gK5ovCQ+gbemzRbdzUxtK3MvB52eOQL1SLQDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:20.484303Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.15914","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e0b67fe1f1345c3b45ce0e9e44dd70d598b221f6f46bb15d7ee02b8a13ad9fb","sha256:56d5ae67b817f4e5027516c5035c9cce04d8075fc5d031541adb5e6f22e2000d"],"state_sha256":"59cbb69d0137ffed99ecc6ee6edec5e7f636a268186b2fa0fa4af22be6f10306"}