{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KEFOJBKEUAPCZJRJZZB4UJLEFZ","short_pith_number":"pith:KEFOJBKE","schema_version":"1.0","canonical_sha256":"510ae48544a01e2ca629ce43ca25642e6f829298d637b8da39b9f45170f2a2e1","source":{"kind":"arxiv","id":"2310.15405","version":1},"attestation_state":"computed","paper":{"title":"GPT-4 as an Effective Zero-Shot Evaluator for Scientific Figure Captions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chieh-Yang Huang, C. Lee Giles, Ryan Rossi, Sungchul Kim, Ting-Hao K. Huang, Ting-Yao Hsu","submitted_at":"2023-10-23T23:24:57Z","abstract_excerpt":"There is growing interest in systems that generate captions for scientific figures. However, assessing these systems output poses a significant challenge. Human evaluation requires academic expertise and is costly, while automatic evaluation depends on often low-quality author-written captions. This paper investigates using large language models (LLMs) as a cost-effective, reference-free method for evaluating figure captions. We first constructed SCICAP-EVAL, a human evaluation dataset that contains human judgments for 3,600 scientific figure captions, both original and machine-made, for 600 a"},"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":"2310.15405","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T23:24:57Z","cross_cats_sorted":[],"title_canon_sha256":"79b97233e1358de983f83032566cd38349ad91a31a08771683b1d34af84b9aef","abstract_canon_sha256":"367e46ea808ba2655d31777d8a2f12a4cfc78aaa0e090823ceb27e3f55f94ac2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:25.521908Z","signature_b64":"lSvSfonruP2Zp7Hfm4cyQaGaJm+ShoAdEgmWZeEF8O8La8xVSmQWu9WJz5JnagVGd9gMVy09wEnSWvyZGU3LAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"510ae48544a01e2ca629ce43ca25642e6f829298d637b8da39b9f45170f2a2e1","last_reissued_at":"2026-07-05T07:04:25.521454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:25.521454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPT-4 as an Effective Zero-Shot Evaluator for Scientific Figure Captions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chieh-Yang Huang, C. Lee Giles, Ryan Rossi, Sungchul Kim, Ting-Hao K. Huang, Ting-Yao Hsu","submitted_at":"2023-10-23T23:24:57Z","abstract_excerpt":"There is growing interest in systems that generate captions for scientific figures. However, assessing these systems output poses a significant challenge. Human evaluation requires academic expertise and is costly, while automatic evaluation depends on often low-quality author-written captions. This paper investigates using large language models (LLMs) as a cost-effective, reference-free method for evaluating figure captions. We first constructed SCICAP-EVAL, a human evaluation dataset that contains human judgments for 3,600 scientific figure captions, both original and machine-made, for 600 a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15405","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/2310.15405/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":"2310.15405","created_at":"2026-07-05T07:04:25.521504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15405v1","created_at":"2026-07-05T07:04:25.521504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15405","created_at":"2026-07-05T07:04:25.521504+00:00"},{"alias_kind":"pith_short_12","alias_value":"KEFOJBKEUAPC","created_at":"2026-07-05T07:04:25.521504+00:00"},{"alias_kind":"pith_short_16","alias_value":"KEFOJBKEUAPCZJRJ","created_at":"2026-07-05T07:04:25.521504+00:00"},{"alias_kind":"pith_short_8","alias_value":"KEFOJBKE","created_at":"2026-07-05T07:04:25.521504+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/KEFOJBKEUAPCZJRJZZB4UJLEFZ","json":"https://pith.science/pith/KEFOJBKEUAPCZJRJZZB4UJLEFZ.json","graph_json":"https://pith.science/api/pith-number/KEFOJBKEUAPCZJRJZZB4UJLEFZ/graph.json","events_json":"https://pith.science/api/pith-number/KEFOJBKEUAPCZJRJZZB4UJLEFZ/events.json","paper":"https://pith.science/paper/KEFOJBKE"},"agent_actions":{"view_html":"https://pith.science/pith/KEFOJBKEUAPCZJRJZZB4UJLEFZ","download_json":"https://pith.science/pith/KEFOJBKEUAPCZJRJZZB4UJLEFZ.json","view_paper":"https://pith.science/paper/KEFOJBKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15405&json=true","fetch_graph":"https://pith.science/api/pith-number/KEFOJBKEUAPCZJRJZZB4UJLEFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/KEFOJBKEUAPCZJRJZZB4UJLEFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KEFOJBKEUAPCZJRJZZB4UJLEFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KEFOJBKEUAPCZJRJZZB4UJLEFZ/action/storage_attestation","attest_author":"https://pith.science/pith/KEFOJBKEUAPCZJRJZZB4UJLEFZ/action/author_attestation","sign_citation":"https://pith.science/pith/KEFOJBKEUAPCZJRJZZB4UJLEFZ/action/citation_signature","submit_replication":"https://pith.science/pith/KEFOJBKEUAPCZJRJZZB4UJLEFZ/action/replication_record"}},"created_at":"2026-07-05T07:04:25.521504+00:00","updated_at":"2026-07-05T07:04:25.521504+00:00"}