{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3WBREGZIJMCSUGBCUZZCAFKJGK","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":"294a4d8d1a1cb175790584f6de9a71469bcd70262fa1b52dbfcce5fb970e4099","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T02:21:30Z","title_canon_sha256":"2e2f6a3d7b80c3a72a5c484a93a922ec06c892ec7509e2dd5e8fd96dbe5ff088"},"schema_version":"1.0","source":{"id":"2403.00231","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00231","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00231v3","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00231","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_12","alias_value":"3WBREGZIJMCS","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_16","alias_value":"3WBREGZIJMCSUGBC","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_8","alias_value":"3WBREGZI","created_at":"2026-07-05T08:26:20Z"}],"graph_snapshots":[{"event_id":"sha256:6f5780075cd74699fc5ccb327996210cef792ac4bd50dda3f9155536b7c4cfc3","target":"graph","created_at":"2026-07-05T08:26:20Z","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/2403.00231/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large vision-language models (LVLMs) excel across diverse tasks involving concrete images from natural scenes. However, their ability to interpret abstract figures, such as geometry shapes and scientific plots, remains limited due to a scarcity of training datasets in scientific domains. To fill this gap, we introduce Multimodal ArXiv, consisting of ArXivCap and ArXivQA, for enhancing LVLMs scientific comprehension. ArXivCap is a figure-caption dataset comprising 6.4M images and 3.9M captions, sourced from 572K ArXiv papers spanning various scientific domains. Drawing from ArXivCap, we introdu","authors_text":"Lei Li, Lingpeng Kong, Peiyi Wang, Qi Liu, Runxin Xu, Xiachong Feng, Yuqi Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T02:21:30Z","title":"Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00231","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:c254edb08b8fd2a0b6502c406ddcc1df6fe3254c9d15b403e68f65a055d55549","target":"record","created_at":"2026-07-05T08:26:20Z","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":"294a4d8d1a1cb175790584f6de9a71469bcd70262fa1b52dbfcce5fb970e4099","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T02:21:30Z","title_canon_sha256":"2e2f6a3d7b80c3a72a5c484a93a922ec06c892ec7509e2dd5e8fd96dbe5ff088"},"schema_version":"1.0","source":{"id":"2403.00231","kind":"arxiv","version":3}},"canonical_sha256":"dd83121b284b052a1822a6722015493285e29805ead275e305953603c439dfe8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd83121b284b052a1822a6722015493285e29805ead275e305953603c439dfe8","first_computed_at":"2026-07-05T08:26:20.870790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:20.870790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GbshuBQPUFYVBKH9h4ANELqnwsr6adbAHbK5xCGpwh82yZnFSb1Ujx8TEs1vPx3hj5CSjoz9/xi8ht0SJ99zDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:20.871260Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.00231","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c254edb08b8fd2a0b6502c406ddcc1df6fe3254c9d15b403e68f65a055d55549","sha256:6f5780075cd74699fc5ccb327996210cef792ac4bd50dda3f9155536b7c4cfc3"],"state_sha256":"f5fdc37bae4f64020a19a06e9e5d09ecc5903c78f265b3bc4ca92ad19e06db8d"}