{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WYCNYPCFYQOKT4QKRRXGQTTY4Y","short_pith_number":"pith:WYCNYPCF","schema_version":"1.0","canonical_sha256":"b604dc3c45c41ca9f20a8c6e684e78e6363c9fe14e3bfeac2325cb04c194379a","source":{"kind":"arxiv","id":"2405.16417","version":2},"attestation_state":"computed","paper":{"title":"CRoFT: Robust Fine-Tuning with Concurrent Optimization for OOD Generalization and Open-Set OOD Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenghu Zhou, Lin Zhu, Nanyang Ye, Qinying Gu, Xinbing Wang, Yifeng Yang","submitted_at":"2024-05-26T03:28:59Z","abstract_excerpt":"Recent vision-language pre-trained models (VL-PTMs) have shown remarkable success in open-vocabulary tasks. However, downstream use cases often involve further fine-tuning of VL-PTMs, which may distort their general knowledge and impair their ability to handle distribution shifts. In real-world scenarios, machine learning systems inevitably encounter both covariate shifts (e.g., changes in image styles) and semantic shifts (e.g., test-time unseen classes). This highlights the importance of enhancing out-of-distribution (OOD) generalization on covariate shifts and simultaneously detecting seman"},"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":"2405.16417","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-26T03:28:59Z","cross_cats_sorted":[],"title_canon_sha256":"f3d2eace0bde8379127a4f565de3acb3426a0ed8c31993a1ca1dee5b9940f7ed","abstract_canon_sha256":"cae4747b755a4871b3a84765638b0efa239eb4c12b0ad4723eeab41f75bdd39c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:32.231536Z","signature_b64":"pdX6g3KyIGqdrm6lAngTINa4ek6QGxvTHRYFsYPeX/YnttkXfS7qAAd0mQnG4n8ANc4tdIn8odsO8FeQipZdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b604dc3c45c41ca9f20a8c6e684e78e6363c9fe14e3bfeac2325cb04c194379a","last_reissued_at":"2026-05-27T01:05:32.230982Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:32.230982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CRoFT: Robust Fine-Tuning with Concurrent Optimization for OOD Generalization and Open-Set OOD Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenghu Zhou, Lin Zhu, Nanyang Ye, Qinying Gu, Xinbing Wang, Yifeng Yang","submitted_at":"2024-05-26T03:28:59Z","abstract_excerpt":"Recent vision-language pre-trained models (VL-PTMs) have shown remarkable success in open-vocabulary tasks. However, downstream use cases often involve further fine-tuning of VL-PTMs, which may distort their general knowledge and impair their ability to handle distribution shifts. In real-world scenarios, machine learning systems inevitably encounter both covariate shifts (e.g., changes in image styles) and semantic shifts (e.g., test-time unseen classes). This highlights the importance of enhancing out-of-distribution (OOD) generalization on covariate shifts and simultaneously detecting seman"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16417","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/2405.16417/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":"2405.16417","created_at":"2026-05-27T01:05:32.231046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16417v2","created_at":"2026-05-27T01:05:32.231046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16417","created_at":"2026-05-27T01:05:32.231046+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYCNYPCFYQOK","created_at":"2026-05-27T01:05:32.231046+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYCNYPCFYQOKT4QK","created_at":"2026-05-27T01:05:32.231046+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYCNYPCF","created_at":"2026-05-27T01:05:32.231046+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/WYCNYPCFYQOKT4QKRRXGQTTY4Y","json":"https://pith.science/pith/WYCNYPCFYQOKT4QKRRXGQTTY4Y.json","graph_json":"https://pith.science/api/pith-number/WYCNYPCFYQOKT4QKRRXGQTTY4Y/graph.json","events_json":"https://pith.science/api/pith-number/WYCNYPCFYQOKT4QKRRXGQTTY4Y/events.json","paper":"https://pith.science/paper/WYCNYPCF"},"agent_actions":{"view_html":"https://pith.science/pith/WYCNYPCFYQOKT4QKRRXGQTTY4Y","download_json":"https://pith.science/pith/WYCNYPCFYQOKT4QKRRXGQTTY4Y.json","view_paper":"https://pith.science/paper/WYCNYPCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16417&json=true","fetch_graph":"https://pith.science/api/pith-number/WYCNYPCFYQOKT4QKRRXGQTTY4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/WYCNYPCFYQOKT4QKRRXGQTTY4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYCNYPCFYQOKT4QKRRXGQTTY4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYCNYPCFYQOKT4QKRRXGQTTY4Y/action/storage_attestation","attest_author":"https://pith.science/pith/WYCNYPCFYQOKT4QKRRXGQTTY4Y/action/author_attestation","sign_citation":"https://pith.science/pith/WYCNYPCFYQOKT4QKRRXGQTTY4Y/action/citation_signature","submit_replication":"https://pith.science/pith/WYCNYPCFYQOKT4QKRRXGQTTY4Y/action/replication_record"}},"created_at":"2026-05-27T01:05:32.231046+00:00","updated_at":"2026-05-27T01:05:32.231046+00:00"}