{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FGOXEEPY7TENK4IIIZ7JPYS2D6","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":"8adadc865aa4c8b532fc41d0168c961fb7c2810868b0ff61443d71f739fb9ee1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T10:35:53Z","title_canon_sha256":"4ef3febf8e191d0d94453bab411883709160618480850bce67a8599406d2b426"},"schema_version":"1.0","source":{"id":"2407.08374","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08374","created_at":"2026-07-05T09:21:06Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08374v3","created_at":"2026-07-05T09:21:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08374","created_at":"2026-07-05T09:21:06Z"},{"alias_kind":"pith_short_12","alias_value":"FGOXEEPY7TEN","created_at":"2026-07-05T09:21:06Z"},{"alias_kind":"pith_short_16","alias_value":"FGOXEEPY7TENK4II","created_at":"2026-07-05T09:21:06Z"},{"alias_kind":"pith_short_8","alias_value":"FGOXEEPY","created_at":"2026-07-05T09:21:06Z"}],"graph_snapshots":[{"event_id":"sha256:b63a5ee9df529900c59c8739869de769daa814c10b5a2fb04a7a7d2b9d9ff327","target":"graph","created_at":"2026-07-05T09:21:06Z","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/2407.08374/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient fine-tuning of vision-language models (VLMs) like CLIP for specific downstream tasks is gaining significant attention. Previous works primarily focus on prompt learning to adapt the CLIP into a variety of downstream tasks, however, suffering from task overfitting when fine-tuned on a small data set. In this paper, we introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization, while a self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs","authors_text":"Dong Zhao, Elisa Ricci, Jinlong Li, Lin Ma, Nicu Sebe, Zequn Jie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T10:35:53Z","title":"Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08374","kind":"arxiv","version":3},"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":"sha256:7e0280ab1121fe6bef051ca4182916668382eee4ab044931d93f5a38a9277a7b","target":"record","created_at":"2026-07-05T09:21:06Z","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":"8adadc865aa4c8b532fc41d0168c961fb7c2810868b0ff61443d71f739fb9ee1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T10:35:53Z","title_canon_sha256":"4ef3febf8e191d0d94453bab411883709160618480850bce67a8599406d2b426"},"schema_version":"1.0","source":{"id":"2407.08374","kind":"arxiv","version":3}},"canonical_sha256":"299d7211f8fcc8d57108467e97e25a1f8e7cfb1d12899239b2c5ec4a3deca385","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"299d7211f8fcc8d57108467e97e25a1f8e7cfb1d12899239b2c5ec4a3deca385","first_computed_at":"2026-07-05T09:21:06.492840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:06.492840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a8BNvG/FJQoI63fVgFWgGG7MpMTXKo8Kewvz6ldrXM5jM8HzjFcligvAKjafwh4YT2WTXdOmJJpDppVxFK47Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:06.493347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.08374","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e0280ab1121fe6bef051ca4182916668382eee4ab044931d93f5a38a9277a7b","sha256:b63a5ee9df529900c59c8739869de769daa814c10b5a2fb04a7a7d2b9d9ff327"],"state_sha256":"760c61957e8513ba93fb7a80f930f5b07fe396210dcf308bb09533845fea38e6"}