{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B5FY6GXNA442BINYN3KCQYZSQW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"79e49917b128d1a47db9d13255cff3f155458676ed34bf15f1df6b0c7f58e7d3","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T21:49:21Z","title_canon_sha256":"9b7d13690c69b4db4f48bf7fb5c985816b4fd4f08beadfd9956b3df1db3bec76"},"schema_version":"1.0","source":{"id":"2407.11008","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11008","created_at":"2026-07-05T08:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11008v1","created_at":"2026-07-05T08:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11008","created_at":"2026-07-05T08:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"B5FY6GXNA442","created_at":"2026-07-05T08:44:16Z"},{"alias_kind":"pith_short_16","alias_value":"B5FY6GXNA442BINY","created_at":"2026-07-05T08:44:16Z"},{"alias_kind":"pith_short_8","alias_value":"B5FY6GXN","created_at":"2026-07-05T08:44:16Z"}],"graph_snapshots":[{"event_id":"sha256:94ad179a3b8761bb042273374be629033fd4a9c1348ab2bc3a7bc59b072e6950","target":"graph","created_at":"2026-07-05T08:44:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.11008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kevin Liu, Stanley Cao","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T21:49:21Z","title":"Figuring out Figures: Using Textual References to Caption Scientific Figures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11008","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c84a8d73768c8d02aa8e8c0947a5b71cb5c26e28fc2af6c5f7ef542e8218c042","target":"record","created_at":"2026-07-05T08:44:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"79e49917b128d1a47db9d13255cff3f155458676ed34bf15f1df6b0c7f58e7d3","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T21:49:21Z","title_canon_sha256":"9b7d13690c69b4db4f48bf7fb5c985816b4fd4f08beadfd9956b3df1db3bec76"},"schema_version":"1.0","source":{"id":"2407.11008","kind":"arxiv","version":1}},"canonical_sha256":"0f4b8f1aed0739a0a1b86ed42863328580a6cd8d1d71040311170de79d557b26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f4b8f1aed0739a0a1b86ed42863328580a6cd8d1d71040311170de79d557b26","first_computed_at":"2026-07-05T08:44:16.940776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:16.940776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"st0KcsHqhPtJVrQdzVZL8TvMY5undUFx1BCHGBAov4mh4P/51kQhhGQ5GbCmaykXgSkStt6ivA00wvuTCwHmAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:16.941275Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.11008","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c84a8d73768c8d02aa8e8c0947a5b71cb5c26e28fc2af6c5f7ef542e8218c042","sha256:94ad179a3b8761bb042273374be629033fd4a9c1348ab2bc3a7bc59b072e6950"],"state_sha256":"3867161d32a05f6ac785324e32677ee900fb1e886b256411e454623b621c3376"}