{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:26X3L5VOJ545NOEZQPZY2IPART","short_pith_number":"pith:26X3L5VO","schema_version":"1.0","canonical_sha256":"d7afb5f6ae4f79d6b89983f38d21e08cc5d3a31bc54b5276204534f28ebb4ac4","source":{"kind":"arxiv","id":"2507.01627","version":1},"attestation_state":"computed","paper":{"title":"Chart Question Answering from Real-World Analytical Narratives","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aidan Slingsby, Jo Wood, Maeve Hutchinson, Pranava Madhyastha, Radu Jianu","submitted_at":"2025-07-02T11:58:04Z","abstract_excerpt":"We present a new dataset for chart question answering (CQA) constructed from visualization notebooks. The dataset features real-world, multi-view charts paired with natural language questions grounded in analytical narratives. Unlike prior benchmarks, our data reflects ecologically valid reasoning workflows. Benchmarking state-of-the-art multimodal large language models reveals a significant performance gap, with GPT-4.1 achieving an accuracy of 69.3%, underscoring the challenges posed by this more authentic CQA setting."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.01627","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T11:58:04Z","cross_cats_sorted":[],"title_canon_sha256":"fcb5a987592430997d5b01d7e79fce3de781235e329f476fb217518c110b4c4a","abstract_canon_sha256":"d00684c92e233d746f6a1a7536b3029d711fa34643079c5cd42d7e3e739dd081"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:52.158841Z","signature_b64":"V5Zu9FGLysVGucufgwkAnOvJHiip3SK8CbCmK1c1ILoUWutEDJjmQ74h7txncyEPsEP2v5DHX9yl+mOZPZXTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7afb5f6ae4f79d6b89983f38d21e08cc5d3a31bc54b5276204534f28ebb4ac4","last_reissued_at":"2026-07-05T11:30:52.158360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:52.158360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chart Question Answering from Real-World Analytical Narratives","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aidan Slingsby, Jo Wood, Maeve Hutchinson, Pranava Madhyastha, Radu Jianu","submitted_at":"2025-07-02T11:58:04Z","abstract_excerpt":"We present a new dataset for chart question answering (CQA) constructed from visualization notebooks. The dataset features real-world, multi-view charts paired with natural language questions grounded in analytical narratives. Unlike prior benchmarks, our data reflects ecologically valid reasoning workflows. Benchmarking state-of-the-art multimodal large language models reveals a significant performance gap, with GPT-4.1 achieving an accuracy of 69.3%, underscoring the challenges posed by this more authentic CQA setting."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01627","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.01627/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.01627","created_at":"2026-07-05T11:30:52.158421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01627v1","created_at":"2026-07-05T11:30:52.158421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01627","created_at":"2026-07-05T11:30:52.158421+00:00"},{"alias_kind":"pith_short_12","alias_value":"26X3L5VOJ545","created_at":"2026-07-05T11:30:52.158421+00:00"},{"alias_kind":"pith_short_16","alias_value":"26X3L5VOJ545NOEZ","created_at":"2026-07-05T11:30:52.158421+00:00"},{"alias_kind":"pith_short_8","alias_value":"26X3L5VO","created_at":"2026-07-05T11:30:52.158421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/26X3L5VOJ545NOEZQPZY2IPART","json":"https://pith.science/pith/26X3L5VOJ545NOEZQPZY2IPART.json","graph_json":"https://pith.science/api/pith-number/26X3L5VOJ545NOEZQPZY2IPART/graph.json","events_json":"https://pith.science/api/pith-number/26X3L5VOJ545NOEZQPZY2IPART/events.json","paper":"https://pith.science/paper/26X3L5VO"},"agent_actions":{"view_html":"https://pith.science/pith/26X3L5VOJ545NOEZQPZY2IPART","download_json":"https://pith.science/pith/26X3L5VOJ545NOEZQPZY2IPART.json","view_paper":"https://pith.science/paper/26X3L5VO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01627&json=true","fetch_graph":"https://pith.science/api/pith-number/26X3L5VOJ545NOEZQPZY2IPART/graph.json","fetch_events":"https://pith.science/api/pith-number/26X3L5VOJ545NOEZQPZY2IPART/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26X3L5VOJ545NOEZQPZY2IPART/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26X3L5VOJ545NOEZQPZY2IPART/action/storage_attestation","attest_author":"https://pith.science/pith/26X3L5VOJ545NOEZQPZY2IPART/action/author_attestation","sign_citation":"https://pith.science/pith/26X3L5VOJ545NOEZQPZY2IPART/action/citation_signature","submit_replication":"https://pith.science/pith/26X3L5VOJ545NOEZQPZY2IPART/action/replication_record"}},"created_at":"2026-07-05T11:30:52.158421+00:00","updated_at":"2026-07-05T11:30:52.158421+00:00"}