{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7NLWGLNTVQJOQSCTNE7INL5GWV","short_pith_number":"pith:7NLWGLNT","schema_version":"1.0","canonical_sha256":"fb57632db3ac12e84853693e86afa6b558913b7b2ca9854edd85a67663857ca8","source":{"kind":"arxiv","id":"2306.03491","version":1},"attestation_state":"computed","paper":{"title":"SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hideki Tanaka, Naoaki Okazaki, Raj Dabre, Zhishen Yang","submitted_at":"2023-06-06T08:16:16Z","abstract_excerpt":"In scholarly documents, figures provide a straightforward way of communicating scientific findings to readers. Automating figure caption generation helps move model understandings of scientific documents beyond text and will help authors write informative captions that facilitate communicating scientific findings. Unlike previous studies, we reframe scientific figure captioning as a knowledge-augmented image captioning task that models need to utilize knowledge embedded across modalities for caption generation. To this end, we extended the large-scale SciCap dataset~\\cite{hsu-etal-2021-scicap-"},"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":"2306.03491","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-06T08:16:16Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"de2c1bf2b52268f072bd68a21f5d9c44ac299e9a844a4b16680efc67e7fec9ea","abstract_canon_sha256":"1ed92a1ce3c02e2394950ea790d0aeed43b3155a98d5900c904baf3a000f81bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:58.687230Z","signature_b64":"XUaiA649+wYkd7PXbcRTGXk/URAUVbrmk5yV1YfCx1w3rP6u+eLly/bTdec2O4SRFHF9Kv+tWjR2hehgzYO3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb57632db3ac12e84853693e86afa6b558913b7b2ca9854edd85a67663857ca8","last_reissued_at":"2026-07-05T06:17:58.686833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:58.686833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hideki Tanaka, Naoaki Okazaki, Raj Dabre, Zhishen Yang","submitted_at":"2023-06-06T08:16:16Z","abstract_excerpt":"In scholarly documents, figures provide a straightforward way of communicating scientific findings to readers. Automating figure caption generation helps move model understandings of scientific documents beyond text and will help authors write informative captions that facilitate communicating scientific findings. Unlike previous studies, we reframe scientific figure captioning as a knowledge-augmented image captioning task that models need to utilize knowledge embedded across modalities for caption generation. To this end, we extended the large-scale SciCap dataset~\\cite{hsu-etal-2021-scicap-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03491","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/2306.03491/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":"2306.03491","created_at":"2026-07-05T06:17:58.686887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.03491v1","created_at":"2026-07-05T06:17:58.686887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03491","created_at":"2026-07-05T06:17:58.686887+00:00"},{"alias_kind":"pith_short_12","alias_value":"7NLWGLNTVQJO","created_at":"2026-07-05T06:17:58.686887+00:00"},{"alias_kind":"pith_short_16","alias_value":"7NLWGLNTVQJOQSCT","created_at":"2026-07-05T06:17:58.686887+00:00"},{"alias_kind":"pith_short_8","alias_value":"7NLWGLNT","created_at":"2026-07-05T06:17:58.686887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04172","citing_title":"GENFIG1: Visual Summaries of Scholarly Work as a Challenge for Vision-Language Models","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7NLWGLNTVQJOQSCTNE7INL5GWV","json":"https://pith.science/pith/7NLWGLNTVQJOQSCTNE7INL5GWV.json","graph_json":"https://pith.science/api/pith-number/7NLWGLNTVQJOQSCTNE7INL5GWV/graph.json","events_json":"https://pith.science/api/pith-number/7NLWGLNTVQJOQSCTNE7INL5GWV/events.json","paper":"https://pith.science/paper/7NLWGLNT"},"agent_actions":{"view_html":"https://pith.science/pith/7NLWGLNTVQJOQSCTNE7INL5GWV","download_json":"https://pith.science/pith/7NLWGLNTVQJOQSCTNE7INL5GWV.json","view_paper":"https://pith.science/paper/7NLWGLNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.03491&json=true","fetch_graph":"https://pith.science/api/pith-number/7NLWGLNTVQJOQSCTNE7INL5GWV/graph.json","fetch_events":"https://pith.science/api/pith-number/7NLWGLNTVQJOQSCTNE7INL5GWV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7NLWGLNTVQJOQSCTNE7INL5GWV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7NLWGLNTVQJOQSCTNE7INL5GWV/action/storage_attestation","attest_author":"https://pith.science/pith/7NLWGLNTVQJOQSCTNE7INL5GWV/action/author_attestation","sign_citation":"https://pith.science/pith/7NLWGLNTVQJOQSCTNE7INL5GWV/action/citation_signature","submit_replication":"https://pith.science/pith/7NLWGLNTVQJOQSCTNE7INL5GWV/action/replication_record"}},"created_at":"2026-07-05T06:17:58.686887+00:00","updated_at":"2026-07-05T06:17:58.686887+00:00"}