{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LVXHARPWTONQXE6XOGUTNP6BN3","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":"797afbede17c21eff2d9d734c8dd4ea3daedc184dbff51af1f9f4431c69be4fb","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T14:39:40Z","title_canon_sha256":"6d46389c2f5f0f0ef708cb3b87700ea20e36c7c267dbd9a5552fa7f46644999c"},"schema_version":"1.0","source":{"id":"2407.16526","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16526","created_at":"2026-07-05T08:47:34Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16526v1","created_at":"2026-07-05T08:47:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16526","created_at":"2026-07-05T08:47:34Z"},{"alias_kind":"pith_short_12","alias_value":"LVXHARPWTONQ","created_at":"2026-07-05T08:47:34Z"},{"alias_kind":"pith_short_16","alias_value":"LVXHARPWTONQXE6X","created_at":"2026-07-05T08:47:34Z"},{"alias_kind":"pith_short_8","alias_value":"LVXHARPW","created_at":"2026-07-05T08:47:34Z"}],"graph_snapshots":[{"event_id":"sha256:6a84ab878e2907267cdb8cdda8f62a53f52755473790eab36bac41794643cc5d","target":"graph","created_at":"2026-07-05T08:47:34Z","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/2407.16526/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision language models (VLMs) demonstrate impressive capabilities in visual question answering and image captioning, acting as a crucial link between visual and language models. However, existing open-source VLMs heavily rely on pretrained and frozen vision encoders (such as CLIP). Despite CLIP's robustness across diverse domains, it still exhibits non-negligible image understanding errors. These errors propagate to the VLM responses, resulting in sub-optimal performance. In our work, we propose an efficient and robust method for updating vision encoders within VLMs. Our approach selectively a","authors_text":"Aristeidis Panos, Daniel Olmeda Reino, Rahaf Aljundi, Richard E Turner","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T14:39:40Z","title":"Imperfect Vision Encoders: Efficient and Robust Tuning for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16526","kind":"arxiv","version":1},"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":"sha256:531504bab986676147145c319de397b8dc631e1856ba61b00f18c3785e431db9","target":"record","created_at":"2026-07-05T08:47:34Z","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":"797afbede17c21eff2d9d734c8dd4ea3daedc184dbff51af1f9f4431c69be4fb","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T14:39:40Z","title_canon_sha256":"6d46389c2f5f0f0ef708cb3b87700ea20e36c7c267dbd9a5552fa7f46644999c"},"schema_version":"1.0","source":{"id":"2407.16526","kind":"arxiv","version":1}},"canonical_sha256":"5d6e7045f69b9b0b93d771a936bfc16ee534b1fcf1d3d07adf06aea06bc60ea1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d6e7045f69b9b0b93d771a936bfc16ee534b1fcf1d3d07adf06aea06bc60ea1","first_computed_at":"2026-07-05T08:47:34.705113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:47:34.705113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tlsb1kLN2LEDXXV69QhIvDKH3oXRevcY0l5V4nfbtLhAhGpvqNlXJpoA/qF+9gP73xFC9ZrnjA1Ktoj65gXqAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:47:34.705633Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.16526","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:531504bab986676147145c319de397b8dc631e1856ba61b00f18c3785e431db9","sha256:6a84ab878e2907267cdb8cdda8f62a53f52755473790eab36bac41794643cc5d"],"state_sha256":"440331db216572a208f2c7d9dac40b68d6fc3a216ba9044e434eaf617ce3aca3"}