{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:A3LJHFP5GPUZRG7WFIZV4SYZH3","short_pith_number":"pith:A3LJHFP5","schema_version":"1.0","canonical_sha256":"06d69395fd33e9989bf62a335e4b193ed6db320c17644e72c91a0e54322255c5","source":{"kind":"arxiv","id":"2307.05356","version":1},"attestation_state":"computed","paper":{"title":"VisText: A Benchmark for Semantically Rich Chart Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.CV","authors_text":"Angie Boggust, Arvind Satyanarayan, Benny J. Tang","submitted_at":"2023-06-28T15:16:24Z","abstract_excerpt":"Captions that describe or explain charts help improve recall and comprehension of the depicted data and provide a more accessible medium for people with visual disabilities. However, current approaches for automatically generating such captions struggle to articulate the perceptual or cognitive features that are the hallmark of charts (e.g., complex trends and patterns). In response, we introduce VisText: a dataset of 12,441 pairs of charts and captions that describe the charts' construction, report key statistics, and identify perceptual and cognitive phenomena. In VisText, a chart is availab"},"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":"2307.05356","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-28T15:16:24Z","cross_cats_sorted":["cs.HC","cs.LG"],"title_canon_sha256":"a3b1e178286a2e8e7fb7bc6d9ae3dd37d2c1771e624842477b7ee913fd3fbd80","abstract_canon_sha256":"0d755f9088ff390add6ce0979f1f499e47220a7daf30238284a8056929124576"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:56.446749Z","signature_b64":"JDkMekM/yD03xLpkWPEtg+nA/QIXFNnJz8eqUIZwCJpQnZtQXT5slBWqzzIcsJg3y4I5IZO5CcLX/P7jyVXWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06d69395fd33e9989bf62a335e4b193ed6db320c17644e72c91a0e54322255c5","last_reissued_at":"2026-07-05T06:29:56.446222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:56.446222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisText: A Benchmark for Semantically Rich Chart Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.CV","authors_text":"Angie Boggust, Arvind Satyanarayan, Benny J. Tang","submitted_at":"2023-06-28T15:16:24Z","abstract_excerpt":"Captions that describe or explain charts help improve recall and comprehension of the depicted data and provide a more accessible medium for people with visual disabilities. However, current approaches for automatically generating such captions struggle to articulate the perceptual or cognitive features that are the hallmark of charts (e.g., complex trends and patterns). In response, we introduce VisText: a dataset of 12,441 pairs of charts and captions that describe the charts' construction, report key statistics, and identify perceptual and cognitive phenomena. In VisText, a chart is availab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05356","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/2307.05356/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":"2307.05356","created_at":"2026-07-05T06:29:56.446286+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.05356v1","created_at":"2026-07-05T06:29:56.446286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05356","created_at":"2026-07-05T06:29:56.446286+00:00"},{"alias_kind":"pith_short_12","alias_value":"A3LJHFP5GPUZ","created_at":"2026-07-05T06:29:56.446286+00:00"},{"alias_kind":"pith_short_16","alias_value":"A3LJHFP5GPUZRG7W","created_at":"2026-07-05T06:29:56.446286+00:00"},{"alias_kind":"pith_short_8","alias_value":"A3LJHFP5","created_at":"2026-07-05T06:29:56.446286+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27365","citing_title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27978","citing_title":"ABot-OCR Technical Report","ref_index":42,"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":60,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14164","citing_title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","ref_index":139,"is_internal_anchor":false},{"citing_arxiv_id":"2406.16860","citing_title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2305.03726","citing_title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","ref_index":80,"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":48,"is_internal_anchor":false},{"citing_arxiv_id":"2306.14565","citing_title":"Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":227,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A3LJHFP5GPUZRG7WFIZV4SYZH3","json":"https://pith.science/pith/A3LJHFP5GPUZRG7WFIZV4SYZH3.json","graph_json":"https://pith.science/api/pith-number/A3LJHFP5GPUZRG7WFIZV4SYZH3/graph.json","events_json":"https://pith.science/api/pith-number/A3LJHFP5GPUZRG7WFIZV4SYZH3/events.json","paper":"https://pith.science/paper/A3LJHFP5"},"agent_actions":{"view_html":"https://pith.science/pith/A3LJHFP5GPUZRG7WFIZV4SYZH3","download_json":"https://pith.science/pith/A3LJHFP5GPUZRG7WFIZV4SYZH3.json","view_paper":"https://pith.science/paper/A3LJHFP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.05356&json=true","fetch_graph":"https://pith.science/api/pith-number/A3LJHFP5GPUZRG7WFIZV4SYZH3/graph.json","fetch_events":"https://pith.science/api/pith-number/A3LJHFP5GPUZRG7WFIZV4SYZH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A3LJHFP5GPUZRG7WFIZV4SYZH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A3LJHFP5GPUZRG7WFIZV4SYZH3/action/storage_attestation","attest_author":"https://pith.science/pith/A3LJHFP5GPUZRG7WFIZV4SYZH3/action/author_attestation","sign_citation":"https://pith.science/pith/A3LJHFP5GPUZRG7WFIZV4SYZH3/action/citation_signature","submit_replication":"https://pith.science/pith/A3LJHFP5GPUZRG7WFIZV4SYZH3/action/replication_record"}},"created_at":"2026-07-05T06:29:56.446286+00:00","updated_at":"2026-07-05T06:29:56.446286+00:00"}