{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LDYST4ZSU37XE7QYOMXU32LH2U","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":"2e16402b3d921cd1ffc8789a782e57533d2903751f488c5743cb305229a2cf42","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T17:50:11Z","title_canon_sha256":"531199deafb8a1268646384aee85acfaf187cb6d1e2becffe6e48f68c2d96309"},"schema_version":"1.0","source":{"id":"2406.18521","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18521","created_at":"2026-07-05T08:37:10Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18521v1","created_at":"2026-07-05T08:37:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18521","created_at":"2026-07-05T08:37:10Z"},{"alias_kind":"pith_short_12","alias_value":"LDYST4ZSU37X","created_at":"2026-07-05T08:37:10Z"},{"alias_kind":"pith_short_16","alias_value":"LDYST4ZSU37XE7QY","created_at":"2026-07-05T08:37:10Z"},{"alias_kind":"pith_short_8","alias_value":"LDYST4ZS","created_at":"2026-07-05T08:37:10Z"}],"graph_snapshots":[{"event_id":"sha256:11e8c5f29c6a9f3cae4884d9b54c083fcd6e6978e679103956bd3b46f7affc15","target":"graph","created_at":"2026-07-05T08:37:10Z","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/2406.18521/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chart understanding plays a pivotal role when applying Multimodal Large Language Models (MLLMs) to real-world tasks such as analyzing scientific papers or financial reports. However, existing datasets often focus on oversimplified and homogeneous charts with template-based questions, leading to an over-optimistic measure of progress. We demonstrate that although open-source models can appear to outperform strong proprietary models on these benchmarks, a simple stress test with slightly different charts or questions can deteriorate performance by up to 34.5%. In this work, we propose CharXiv, a","authors_text":"Alexis Chevalier, Danqi Chen, Haotian Liu, Howard Chen, Kaiqu Liang, Luxi He, Mengzhou Xia, Richard Zhu, Sadhika Malladi, Sanjeev Arora, Xindi Wu, Yitao Liu, Zirui Wang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T17:50:11Z","title":"CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18521","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":"sha256:673085f747a45c0b8449d02ee815a24baf853d0a4416434d4dc459d0e4abb48d","target":"record","created_at":"2026-07-05T08:37:10Z","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":"2e16402b3d921cd1ffc8789a782e57533d2903751f488c5743cb305229a2cf42","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T17:50:11Z","title_canon_sha256":"531199deafb8a1268646384aee85acfaf187cb6d1e2becffe6e48f68c2d96309"},"schema_version":"1.0","source":{"id":"2406.18521","kind":"arxiv","version":1}},"canonical_sha256":"58f129f332a6ff727e18732f4de967d51b9af2284ff86d3f30a5ced5e884e24b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58f129f332a6ff727e18732f4de967d51b9af2284ff86d3f30a5ced5e884e24b","first_computed_at":"2026-07-05T08:37:10.697105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:10.697105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ifCg2hU7u7Wgq3nFzzbw/e3+g7JXbWVPc7EDqowMws6H+rQVb+LLQb03eSff61CJdOEYH8HvkSyXnPimZAKsAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:10.697604Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.18521","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:673085f747a45c0b8449d02ee815a24baf853d0a4416434d4dc459d0e4abb48d","sha256:11e8c5f29c6a9f3cae4884d9b54c083fcd6e6978e679103956bd3b46f7affc15"],"state_sha256":"c9aaa8e803edbc6e39a48c4ce4656f17e1b639fe992f8ad7e6afbb5e3ae2f9f3"}