{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M6RZEZAZMI2FOZ7D2WCSBRREDM","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":"09293db9f57895cfc3d92cb90e6ed229f77e3ab4d4e100ea1f4890623ce7f2f2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T18:55:30Z","title_canon_sha256":"11fb8b49b6334760245526a1574f127c6faebc2c92704932127d419f7dc0fa3b"},"schema_version":"1.0","source":{"id":"2502.14846","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14846","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14846v2","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14846","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_12","alias_value":"M6RZEZAZMI2F","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_16","alias_value":"M6RZEZAZMI2FOZ7D","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_8","alias_value":"M6RZEZAZ","created_at":"2026-07-05T11:06:28Z"}],"graph_snapshots":[{"event_id":"sha256:e66d3efc26735b16fa0e4d873f7633e00ccba779a5dee00f7a00774e417a0253","target":"graph","created_at":"2026-07-05T11:06:28Z","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/2502.14846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning about images with rich text, such as charts and documents, is a critical application of vision-language models (VLMs). However, VLMs often struggle in these domains due to the scarcity of diverse text-rich vision-language data. To address this challenge, we present CoSyn, a framework that leverages the coding capabilities of text-only large language models (LLMs) to automatically create synthetic text-rich multimodal data. Given input text describing a target domain (e.g., \"nutrition fact labels\"), CoSyn prompts an LLM to generate code (Python, HTML, LaTeX, etc.) for rendering synthe","authors_text":"Ajay Patel, Andrew Head, Aniruddha Kembhavi, Chris Callison-Burch, Christopher Clark, Luca Weihs, Mark Yatskar, Matt Deitke, Ranjay Krishna, Tanmay Gupta, Yue Yang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T18:55:30Z","title":"Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14846","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":"sha256:6d507d76ca44c367a54a6bc9e710458e389a72aff5a938c6bd85cd22a1981b24","target":"record","created_at":"2026-07-05T11:06:28Z","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":"09293db9f57895cfc3d92cb90e6ed229f77e3ab4d4e100ea1f4890623ce7f2f2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T18:55:30Z","title_canon_sha256":"11fb8b49b6334760245526a1574f127c6faebc2c92704932127d419f7dc0fa3b"},"schema_version":"1.0","source":{"id":"2502.14846","kind":"arxiv","version":2}},"canonical_sha256":"67a392641962345767e3d58520c6241b0159dafd92efce586feff664345b0512","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67a392641962345767e3d58520c6241b0159dafd92efce586feff664345b0512","first_computed_at":"2026-07-05T11:06:28.666129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:28.666129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ooh0F4zmoQTDXUdsrV1BBQJaoMAkVQQGptdxjTui5GTatS5N2eZWSsDfLknf9IIMjfcTqDwAO+1V113n5178CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:28.666649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14846","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d507d76ca44c367a54a6bc9e710458e389a72aff5a938c6bd85cd22a1981b24","sha256:e66d3efc26735b16fa0e4d873f7633e00ccba779a5dee00f7a00774e417a0253"],"state_sha256":"41873d12cc2fdf76ada844f374b6f638237123e3b2763c77e97945ddfd0be2f4"}