{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:553RH6Z5RENUDJAQLIE3ASWGAG","short_pith_number":"pith:553RH6Z5","schema_version":"1.0","canonical_sha256":"ef7713fb3d891b41a4105a09b04ac6018d3ccde4bc527454580eac190f017f86","source":{"kind":"arxiv","id":"2203.06486","version":3},"attestation_state":"computed","paper":{"title":"Chart-to-Text: A Large-Scale Benchmark for Chart Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Masry, Enamul Hoque, Megh Thakkar, Rixie Tiffany Ko Leong, Shafiq Joty, Shankar Kantharaj, Xiang Lin","submitted_at":"2022-03-12T17:01:38Z","abstract_excerpt":"Charts are commonly used for exploring data and communicating insights. Generating natural language summaries from charts can be very helpful for people in inferring key insights that would otherwise require a lot of cognitive and perceptual efforts. We present Chart-to-text, a large-scale benchmark with two datasets and a total of 44,096 charts covering a wide range of topics and chart types. We explain the dataset construction process and analyze the datasets. We also introduce a number of state-of-the-art neural models as baselines that utilize image captioning and data-to-text generation t"},"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":"2203.06486","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-12T17:01:38Z","cross_cats_sorted":[],"title_canon_sha256":"90ff3c17cc099e8effd4e4e877aa19a0c6484508e92e937d0dcd44811e3f002d","abstract_canon_sha256":"2aa37824f88bf6e2c999b411be771ef8646022b539986c7cdd4f2e39286da390"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:42.219282Z","signature_b64":"iuzcbXhahVJqZI3M2W+GjMK4pv8TrZa8UA9XYUUORTj38D/k/pDP95eNB/TEvqOmw1ov3SoM2FowchPbhrT9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef7713fb3d891b41a4105a09b04ac6018d3ccde4bc527454580eac190f017f86","last_reissued_at":"2026-07-05T04:14:42.218858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:42.218858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chart-to-Text: A Large-Scale Benchmark for Chart Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Masry, Enamul Hoque, Megh Thakkar, Rixie Tiffany Ko Leong, Shafiq Joty, Shankar Kantharaj, Xiang Lin","submitted_at":"2022-03-12T17:01:38Z","abstract_excerpt":"Charts are commonly used for exploring data and communicating insights. Generating natural language summaries from charts can be very helpful for people in inferring key insights that would otherwise require a lot of cognitive and perceptual efforts. We present Chart-to-text, a large-scale benchmark with two datasets and a total of 44,096 charts covering a wide range of topics and chart types. We explain the dataset construction process and analyze the datasets. We also introduce a number of state-of-the-art neural models as baselines that utilize image captioning and data-to-text generation t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06486","kind":"arxiv","version":3},"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/2203.06486/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":"2203.06486","created_at":"2026-07-05T04:14:42.218909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.06486v3","created_at":"2026-07-05T04:14:42.218909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06486","created_at":"2026-07-05T04:14:42.218909+00:00"},{"alias_kind":"pith_short_12","alias_value":"553RH6Z5RENU","created_at":"2026-07-05T04:14:42.218909+00:00"},{"alias_kind":"pith_short_16","alias_value":"553RH6Z5RENUDJAQ","created_at":"2026-07-05T04:14:42.218909+00:00"},{"alias_kind":"pith_short_8","alias_value":"553RH6Z5","created_at":"2026-07-05T04:14:42.218909+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27978","citing_title":"ABot-OCR Technical Report","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2504.09925","citing_title":"FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2603.24326","citing_title":"Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/553RH6Z5RENUDJAQLIE3ASWGAG","json":"https://pith.science/pith/553RH6Z5RENUDJAQLIE3ASWGAG.json","graph_json":"https://pith.science/api/pith-number/553RH6Z5RENUDJAQLIE3ASWGAG/graph.json","events_json":"https://pith.science/api/pith-number/553RH6Z5RENUDJAQLIE3ASWGAG/events.json","paper":"https://pith.science/paper/553RH6Z5"},"agent_actions":{"view_html":"https://pith.science/pith/553RH6Z5RENUDJAQLIE3ASWGAG","download_json":"https://pith.science/pith/553RH6Z5RENUDJAQLIE3ASWGAG.json","view_paper":"https://pith.science/paper/553RH6Z5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.06486&json=true","fetch_graph":"https://pith.science/api/pith-number/553RH6Z5RENUDJAQLIE3ASWGAG/graph.json","fetch_events":"https://pith.science/api/pith-number/553RH6Z5RENUDJAQLIE3ASWGAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/553RH6Z5RENUDJAQLIE3ASWGAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/553RH6Z5RENUDJAQLIE3ASWGAG/action/storage_attestation","attest_author":"https://pith.science/pith/553RH6Z5RENUDJAQLIE3ASWGAG/action/author_attestation","sign_citation":"https://pith.science/pith/553RH6Z5RENUDJAQLIE3ASWGAG/action/citation_signature","submit_replication":"https://pith.science/pith/553RH6Z5RENUDJAQLIE3ASWGAG/action/replication_record"}},"created_at":"2026-07-05T04:14:42.218909+00:00","updated_at":"2026-07-05T04:14:42.218909+00:00"}