{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JOXEDJ3GDSO56UZ4E5HF2WALVH","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":"b9860f49ee77825cee7b0e7e3a2754e0be9925d5e88cabf96b47834674fbdf47","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-29T17:08:16Z","title_canon_sha256":"6951ae9cad2a196cd709fd2c49d51553a366a9588fac3c35f451f87304220ac4"},"schema_version":"1.0","source":{"id":"2306.17107","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17107","created_at":"2026-07-05T07:40:54Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17107v2","created_at":"2026-07-05T07:40:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17107","created_at":"2026-07-05T07:40:54Z"},{"alias_kind":"pith_short_12","alias_value":"JOXEDJ3GDSO5","created_at":"2026-07-05T07:40:54Z"},{"alias_kind":"pith_short_16","alias_value":"JOXEDJ3GDSO56UZ4","created_at":"2026-07-05T07:40:54Z"},{"alias_kind":"pith_short_8","alias_value":"JOXEDJ3G","created_at":"2026-07-05T07:40:54Z"}],"graph_snapshots":[{"event_id":"sha256:27db3bf01da2b606f6c2c87f1d03a871cbc009961e45dc4c848d4fc8b757be57","target":"graph","created_at":"2026-07-05T07:40:54Z","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/2306.17107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning unlocks the superior capability of Large Language Models (LLM) to interact with humans. Furthermore, recent instruction-following datasets include images as visual inputs, collecting responses for image-based instructions. However, visual instruction-tuned models cannot comprehend textual details within images well. This work enhances the current visual instruction tuning pipeline with text-rich images (e.g., movie posters, book covers, etc.). Specifically, we first use publicly available OCR tools to collect results on 422K text-rich images from the LAION dataset. Moreover,","authors_text":"Diyi Yang, Jiuxiang Gu, Nedim Lipka, Ruiyi Zhang, Tong Sun, Yanzhe Zhang, Yufan Zhou","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-29T17:08:16Z","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17107","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:dc497025c5e3131086bd09c6ba1f99ddfa08df452e9e0477bcb23c09bba92a0e","target":"record","created_at":"2026-07-05T07:40:54Z","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":"b9860f49ee77825cee7b0e7e3a2754e0be9925d5e88cabf96b47834674fbdf47","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-29T17:08:16Z","title_canon_sha256":"6951ae9cad2a196cd709fd2c49d51553a366a9588fac3c35f451f87304220ac4"},"schema_version":"1.0","source":{"id":"2306.17107","kind":"arxiv","version":2}},"canonical_sha256":"4bae41a7661c9ddf533c274e5d580ba9fecfd05477c11ac07991166ff0671c1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bae41a7661c9ddf533c274e5d580ba9fecfd05477c11ac07991166ff0671c1d","first_computed_at":"2026-07-05T07:40:54.754481Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:40:54.754481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qK2sR3vX8V4IMCc7H1oYAUap3RPcYmIxs1zvqLNwVQ2S5aw8NxlLZ5ZECEBkUMkqzC67TojFlWQkDTlNs8+3BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:40:54.754956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.17107","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc497025c5e3131086bd09c6ba1f99ddfa08df452e9e0477bcb23c09bba92a0e","sha256:27db3bf01da2b606f6c2c87f1d03a871cbc009961e45dc4c848d4fc8b757be57"],"state_sha256":"fb71c2126d7dd2806e9626e1b5e66e5bbcd82187b4602676393954a511573c8d"}