{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UG2H5OBKZH655BOFB5LRH2QTJU","short_pith_number":"pith:UG2H5OBK","schema_version":"1.0","canonical_sha256":"a1b47eb82ac9fdde85c50f5713ea134d383a2efcf0af785f0b96e394ea6bc4e1","source":{"kind":"arxiv","id":"2412.17606","version":1},"attestation_state":"computed","paper":{"title":"SBS Figures: Pre-training Figure QA from Stage-by-Stage Synthesized Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kuniaki Saito, Risa Shinoda, Shohei Tanaka, Tosho Hirasawa, Yoshitaka Ushiku","submitted_at":"2024-12-23T14:25:33Z","abstract_excerpt":"Building a large-scale figure QA dataset requires a considerable amount of work, from gathering and selecting figures to extracting attributes like text, numbers, and colors, and generating QAs. Although recent developments in LLMs have led to efforts to synthesize figures, most of these focus primarily on QA generation. Additionally, creating figures directly using LLMs often encounters issues such as code errors, similar-looking figures, and repetitive content in figures. To address this issue, we present SBSFigures (Stage-by-Stage Synthetic Figures), a dataset for pre-training figure QA. Ou"},"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":"2412.17606","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-23T14:25:33Z","cross_cats_sorted":[],"title_canon_sha256":"83a66ce0d446e906bc9d4dde9ce0b79dde4a544728cb1ff5fcbf13ad3f91f57a","abstract_canon_sha256":"de7bcb1920bcb3e6c67286e714d1248d2485ba8fcd3de53a616ce1675f37e608"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:24.876358Z","signature_b64":"GdtNoTqw0i6BYZ2WyWmQKeNK+RWTZzU4/tconSraO53MfkIX2/L2UtxlH4CYpNW+JFxVGMbXlHW8CMf8UqoUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1b47eb82ac9fdde85c50f5713ea134d383a2efcf0af785f0b96e394ea6bc4e1","last_reissued_at":"2026-07-05T09:53:24.875914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:24.875914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SBS Figures: Pre-training Figure QA from Stage-by-Stage Synthesized Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kuniaki Saito, Risa Shinoda, Shohei Tanaka, Tosho Hirasawa, Yoshitaka Ushiku","submitted_at":"2024-12-23T14:25:33Z","abstract_excerpt":"Building a large-scale figure QA dataset requires a considerable amount of work, from gathering and selecting figures to extracting attributes like text, numbers, and colors, and generating QAs. Although recent developments in LLMs have led to efforts to synthesize figures, most of these focus primarily on QA generation. Additionally, creating figures directly using LLMs often encounters issues such as code errors, similar-looking figures, and repetitive content in figures. To address this issue, we present SBSFigures (Stage-by-Stage Synthetic Figures), a dataset for pre-training figure QA. Ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17606","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/2412.17606/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":"2412.17606","created_at":"2026-07-05T09:53:24.875979+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17606v1","created_at":"2026-07-05T09:53:24.875979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17606","created_at":"2026-07-05T09:53:24.875979+00:00"},{"alias_kind":"pith_short_12","alias_value":"UG2H5OBKZH65","created_at":"2026-07-05T09:53:24.875979+00:00"},{"alias_kind":"pith_short_16","alias_value":"UG2H5OBKZH655BOF","created_at":"2026-07-05T09:53:24.875979+00:00"},{"alias_kind":"pith_short_8","alias_value":"UG2H5OBK","created_at":"2026-07-05T09:53:24.875979+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28551","citing_title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","ref_index":260,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28551","citing_title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","ref_index":260,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UG2H5OBKZH655BOFB5LRH2QTJU","json":"https://pith.science/pith/UG2H5OBKZH655BOFB5LRH2QTJU.json","graph_json":"https://pith.science/api/pith-number/UG2H5OBKZH655BOFB5LRH2QTJU/graph.json","events_json":"https://pith.science/api/pith-number/UG2H5OBKZH655BOFB5LRH2QTJU/events.json","paper":"https://pith.science/paper/UG2H5OBK"},"agent_actions":{"view_html":"https://pith.science/pith/UG2H5OBKZH655BOFB5LRH2QTJU","download_json":"https://pith.science/pith/UG2H5OBKZH655BOFB5LRH2QTJU.json","view_paper":"https://pith.science/paper/UG2H5OBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17606&json=true","fetch_graph":"https://pith.science/api/pith-number/UG2H5OBKZH655BOFB5LRH2QTJU/graph.json","fetch_events":"https://pith.science/api/pith-number/UG2H5OBKZH655BOFB5LRH2QTJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UG2H5OBKZH655BOFB5LRH2QTJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UG2H5OBKZH655BOFB5LRH2QTJU/action/storage_attestation","attest_author":"https://pith.science/pith/UG2H5OBKZH655BOFB5LRH2QTJU/action/author_attestation","sign_citation":"https://pith.science/pith/UG2H5OBKZH655BOFB5LRH2QTJU/action/citation_signature","submit_replication":"https://pith.science/pith/UG2H5OBKZH655BOFB5LRH2QTJU/action/replication_record"}},"created_at":"2026-07-05T09:53:24.875979+00:00","updated_at":"2026-07-05T09:53:24.875979+00:00"}