{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MXN5FRIDRDPUDU6R5VQN5QURFP","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":"ef617cac811904ffde06dca80db35f0cad9eafca14cb129c8f52c8bfa27328af","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-12T07:56:47Z","title_canon_sha256":"038074cc466f1bdf5f1a973b5d72cefa10e2bfccb680d99ffbfcf39219ece8db"},"schema_version":"1.0","source":{"id":"2410.09421","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09421","created_at":"2026-07-05T09:22:22Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09421v2","created_at":"2026-07-05T09:22:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09421","created_at":"2026-07-05T09:22:22Z"},{"alias_kind":"pith_short_12","alias_value":"MXN5FRIDRDPU","created_at":"2026-07-05T09:22:22Z"},{"alias_kind":"pith_short_16","alias_value":"MXN5FRIDRDPUDU6R","created_at":"2026-07-05T09:22:22Z"},{"alias_kind":"pith_short_8","alias_value":"MXN5FRID","created_at":"2026-07-05T09:22:22Z"}],"graph_snapshots":[{"event_id":"sha256:0a68505d6bc07b56061df8e109220ab4898b7e69473bc47aa49087709e3968cb","target":"graph","created_at":"2026-07-05T09:22:22Z","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/2410.09421/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large vision-language models (LVLMs) evolve rapidly, the demand for high-quality and diverse data to align these models becomes increasingly crucial. However, the creation of such data with human supervision proves costly and time-intensive. In this paper, we investigate the efficacy of AI feedback to scale supervision for aligning LVLMs. We introduce VLFeedback, the first large-scale vision-language feedback dataset, comprising over 82K multi-modal instructions and comprehensive rationales generated by off-the-shelf models without human annotations. To evaluate the effectiveness of AI feed","authors_text":"Benyou Wang, Lei Li, Liang Chen, Lingpeng Kong, Mukai Li, Peiyi Wang, Qi Liu, Shunian Chen, Yazheng Yang, Zhihui Xie","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-12T07:56:47Z","title":"VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09421","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":"sha256:14068186cd1c972e8470b362a47495a4d96d66723bddbbeb9e196c58b242b2a4","target":"record","created_at":"2026-07-05T09:22:22Z","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":"ef617cac811904ffde06dca80db35f0cad9eafca14cb129c8f52c8bfa27328af","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-12T07:56:47Z","title_canon_sha256":"038074cc466f1bdf5f1a973b5d72cefa10e2bfccb680d99ffbfcf39219ece8db"},"schema_version":"1.0","source":{"id":"2410.09421","kind":"arxiv","version":2}},"canonical_sha256":"65dbd2c50388df41d3d1ed60dec2912bd86bc025d2691dcc82ed456e6d43ded2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65dbd2c50388df41d3d1ed60dec2912bd86bc025d2691dcc82ed456e6d43ded2","first_computed_at":"2026-07-05T09:22:22.731416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:22.731416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bws03f3uih2Y65oeA6GMwz++XL6ti/GXiSqra8ZHS8+EWBzomhtTuKdXufExUm05C48YpCbn6Ggg4WAgYRLaAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:22.731887Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.09421","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14068186cd1c972e8470b362a47495a4d96d66723bddbbeb9e196c58b242b2a4","sha256:0a68505d6bc07b56061df8e109220ab4898b7e69473bc47aa49087709e3968cb"],"state_sha256":"983a30f05b7226e2d2f3c90b436bb26b9db85fd0ed491065a6006b0b33a0e15d"}