{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GKVNJSP6YC3ESMEPXEQSNFWATK","short_pith_number":"pith:GKVNJSP6","schema_version":"1.0","canonical_sha256":"32aad4c9fec0b649308fb9212696c09a911b47a3cd3fcc44fe1cad3d57373fdf","source":{"kind":"arxiv","id":"2110.11624","version":2},"attestation_state":"computed","paper":{"title":"SciCap: Generating Captions for Scientific Figures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"C. Lee Giles, Ting-Hao 'Kenneth' Huang, Ting-Yao Hsu","submitted_at":"2021-10-22T07:10:41Z","abstract_excerpt":"Researchers use figures to communicate rich, complex information in scientific papers. The captions of these figures are critical to conveying effective messages. However, low-quality figure captions commonly occur in scientific articles and may decrease understanding. In this paper, we propose an end-to-end neural framework to automatically generate informative, high-quality captions for scientific figures. To this end, we introduce SCICAP, a large-scale figure-caption dataset based on computer science arXiv papers published between 2010 and 2020. After pre-processing - including figure-type "},"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":"2110.11624","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-22T07:10:41Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"f3c6cdeb698ccb6e887bb081145687556a9c16bcb4738a6ceadbe0ccc9df4a34","abstract_canon_sha256":"337c92b77ef8eb424728a67a6f157611bdbd23c1a917c8004dcd985e9402ac30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:18.939186Z","signature_b64":"9DLXXnlEdIWywz9xS1z9UIJGcmO0rMsLPE9AZOlhvgmiHVgHaYS3GWwE+pWGRRcB0H0Aya0enmrDs+1LNsysAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32aad4c9fec0b649308fb9212696c09a911b47a3cd3fcc44fe1cad3d57373fdf","last_reissued_at":"2026-07-05T03:25:18.938815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:18.938815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciCap: Generating Captions for Scientific Figures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"C. Lee Giles, Ting-Hao 'Kenneth' Huang, Ting-Yao Hsu","submitted_at":"2021-10-22T07:10:41Z","abstract_excerpt":"Researchers use figures to communicate rich, complex information in scientific papers. The captions of these figures are critical to conveying effective messages. However, low-quality figure captions commonly occur in scientific articles and may decrease understanding. In this paper, we propose an end-to-end neural framework to automatically generate informative, high-quality captions for scientific figures. To this end, we introduce SCICAP, a large-scale figure-caption dataset based on computer science arXiv papers published between 2010 and 2020. After pre-processing - including figure-type "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.11624","kind":"arxiv","version":2},"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/2110.11624/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":"2110.11624","created_at":"2026-07-05T03:25:18.938881+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.11624v2","created_at":"2026-07-05T03:25:18.938881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.11624","created_at":"2026-07-05T03:25:18.938881+00:00"},{"alias_kind":"pith_short_12","alias_value":"GKVNJSP6YC3E","created_at":"2026-07-05T03:25:18.938881+00:00"},{"alias_kind":"pith_short_16","alias_value":"GKVNJSP6YC3ESMEP","created_at":"2026-07-05T03:25:18.938881+00:00"},{"alias_kind":"pith_short_8","alias_value":"GKVNJSP6","created_at":"2026-07-05T03:25:18.938881+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.00264","citing_title":"S1-MMAlign: A Large-Scale, Multi-Disciplinary Dataset for Scientific Figure-Text Understanding","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2412.03555","citing_title":"PaliGemma 2: A Family of Versatile VLMs for Transfer","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04172","citing_title":"GENFIG1: Visual Summaries of Scholarly Work as a Challenge for Vision-Language Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2407.07726","citing_title":"PaliGemma: A versatile 3B VLM for transfer","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2502.14786","citing_title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GKVNJSP6YC3ESMEPXEQSNFWATK","json":"https://pith.science/pith/GKVNJSP6YC3ESMEPXEQSNFWATK.json","graph_json":"https://pith.science/api/pith-number/GKVNJSP6YC3ESMEPXEQSNFWATK/graph.json","events_json":"https://pith.science/api/pith-number/GKVNJSP6YC3ESMEPXEQSNFWATK/events.json","paper":"https://pith.science/paper/GKVNJSP6"},"agent_actions":{"view_html":"https://pith.science/pith/GKVNJSP6YC3ESMEPXEQSNFWATK","download_json":"https://pith.science/pith/GKVNJSP6YC3ESMEPXEQSNFWATK.json","view_paper":"https://pith.science/paper/GKVNJSP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.11624&json=true","fetch_graph":"https://pith.science/api/pith-number/GKVNJSP6YC3ESMEPXEQSNFWATK/graph.json","fetch_events":"https://pith.science/api/pith-number/GKVNJSP6YC3ESMEPXEQSNFWATK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GKVNJSP6YC3ESMEPXEQSNFWATK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GKVNJSP6YC3ESMEPXEQSNFWATK/action/storage_attestation","attest_author":"https://pith.science/pith/GKVNJSP6YC3ESMEPXEQSNFWATK/action/author_attestation","sign_citation":"https://pith.science/pith/GKVNJSP6YC3ESMEPXEQSNFWATK/action/citation_signature","submit_replication":"https://pith.science/pith/GKVNJSP6YC3ESMEPXEQSNFWATK/action/replication_record"}},"created_at":"2026-07-05T03:25:18.938881+00:00","updated_at":"2026-07-05T03:25:18.938881+00:00"}