{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B5FY6GXNA442BINYN3KCQYZSQW","short_pith_number":"pith:B5FY6GXN","schema_version":"1.0","canonical_sha256":"0f4b8f1aed0739a0a1b86ed42863328580a6cd8d1d71040311170de79d557b26","source":{"kind":"arxiv","id":"2407.11008","version":1},"attestation_state":"computed","paper":{"title":"Figuring out Figures: Using Textual References to Caption Scientific Figures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Kevin Liu, Stanley Cao","submitted_at":"2024-06-25T21:49:21Z","abstract_excerpt":"Figures are essential channels for densely communicating complex ideas in scientific papers. Previous work in automatically generating figure captions has been largely unsuccessful and has defaulted to using single-layer LSTMs, which no longer achieve state-of-the-art performance. In our work, we use the SciCap datasets curated by Hsu et al. and use a variant of a CLIP+GPT-2 encoder-decoder model with cross-attention to generate captions conditioned on the image. Furthermore, we augment our training pipeline by creating a new dataset MetaSciCap that incorporates textual metadata from the origi"},"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":"2407.11008","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T21:49:21Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"9b7d13690c69b4db4f48bf7fb5c985816b4fd4f08beadfd9956b3df1db3bec76","abstract_canon_sha256":"79e49917b128d1a47db9d13255cff3f155458676ed34bf15f1df6b0c7f58e7d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:16.941275Z","signature_b64":"st0KcsHqhPtJVrQdzVZL8TvMY5undUFx1BCHGBAov4mh4P/51kQhhGQ5GbCmaykXgSkStt6ivA00wvuTCwHmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f4b8f1aed0739a0a1b86ed42863328580a6cd8d1d71040311170de79d557b26","last_reissued_at":"2026-07-05T08:44:16.940776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:16.940776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Figuring out Figures: Using Textual References to Caption Scientific Figures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Kevin Liu, Stanley Cao","submitted_at":"2024-06-25T21:49:21Z","abstract_excerpt":"Figures are essential channels for densely communicating complex ideas in scientific papers. Previous work in automatically generating figure captions has been largely unsuccessful and has defaulted to using single-layer LSTMs, which no longer achieve state-of-the-art performance. In our work, we use the SciCap datasets curated by Hsu et al. and use a variant of a CLIP+GPT-2 encoder-decoder model with cross-attention to generate captions conditioned on the image. Furthermore, we augment our training pipeline by creating a new dataset MetaSciCap that incorporates textual metadata from the origi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11008","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/2407.11008/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":"2407.11008","created_at":"2026-07-05T08:44:16.940841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11008v1","created_at":"2026-07-05T08:44:16.940841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11008","created_at":"2026-07-05T08:44:16.940841+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5FY6GXNA442","created_at":"2026-07-05T08:44:16.940841+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5FY6GXNA442BINY","created_at":"2026-07-05T08:44:16.940841+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5FY6GXN","created_at":"2026-07-05T08:44:16.940841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B5FY6GXNA442BINYN3KCQYZSQW","json":"https://pith.science/pith/B5FY6GXNA442BINYN3KCQYZSQW.json","graph_json":"https://pith.science/api/pith-number/B5FY6GXNA442BINYN3KCQYZSQW/graph.json","events_json":"https://pith.science/api/pith-number/B5FY6GXNA442BINYN3KCQYZSQW/events.json","paper":"https://pith.science/paper/B5FY6GXN"},"agent_actions":{"view_html":"https://pith.science/pith/B5FY6GXNA442BINYN3KCQYZSQW","download_json":"https://pith.science/pith/B5FY6GXNA442BINYN3KCQYZSQW.json","view_paper":"https://pith.science/paper/B5FY6GXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11008&json=true","fetch_graph":"https://pith.science/api/pith-number/B5FY6GXNA442BINYN3KCQYZSQW/graph.json","fetch_events":"https://pith.science/api/pith-number/B5FY6GXNA442BINYN3KCQYZSQW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5FY6GXNA442BINYN3KCQYZSQW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5FY6GXNA442BINYN3KCQYZSQW/action/storage_attestation","attest_author":"https://pith.science/pith/B5FY6GXNA442BINYN3KCQYZSQW/action/author_attestation","sign_citation":"https://pith.science/pith/B5FY6GXNA442BINYN3KCQYZSQW/action/citation_signature","submit_replication":"https://pith.science/pith/B5FY6GXNA442BINYN3KCQYZSQW/action/replication_record"}},"created_at":"2026-07-05T08:44:16.940841+00:00","updated_at":"2026-07-05T08:44:16.940841+00:00"}