{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KEFOJBKEUAPCZJRJZZB4UJLEFZ","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":"367e46ea808ba2655d31777d8a2f12a4cfc78aaa0e090823ceb27e3f55f94ac2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T23:24:57Z","title_canon_sha256":"79b97233e1358de983f83032566cd38349ad91a31a08771683b1d34af84b9aef"},"schema_version":"1.0","source":{"id":"2310.15405","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15405","created_at":"2026-07-05T07:04:25Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15405v1","created_at":"2026-07-05T07:04:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15405","created_at":"2026-07-05T07:04:25Z"},{"alias_kind":"pith_short_12","alias_value":"KEFOJBKEUAPC","created_at":"2026-07-05T07:04:25Z"},{"alias_kind":"pith_short_16","alias_value":"KEFOJBKEUAPCZJRJ","created_at":"2026-07-05T07:04:25Z"},{"alias_kind":"pith_short_8","alias_value":"KEFOJBKE","created_at":"2026-07-05T07:04:25Z"}],"graph_snapshots":[{"event_id":"sha256:70c43100d74fcbf1b0d8ec0956942aba122cfb2f8a619a84c7d7648ef09e7ebc","target":"graph","created_at":"2026-07-05T07:04:25Z","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/2310.15405/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chieh-Yang Huang, C. Lee Giles, Ryan Rossi, Sungchul Kim, Ting-Hao K. Huang, Ting-Yao Hsu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T23:24:57Z","title":"GPT-4 as an Effective Zero-Shot Evaluator for Scientific Figure Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15405","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":"sha256:6b8e365281c7c350ee927834cdb229d3fc6f3864fe5d1ec31b7a1e7faccd2894","target":"record","created_at":"2026-07-05T07:04:25Z","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":"367e46ea808ba2655d31777d8a2f12a4cfc78aaa0e090823ceb27e3f55f94ac2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T23:24:57Z","title_canon_sha256":"79b97233e1358de983f83032566cd38349ad91a31a08771683b1d34af84b9aef"},"schema_version":"1.0","source":{"id":"2310.15405","kind":"arxiv","version":1}},"canonical_sha256":"510ae48544a01e2ca629ce43ca25642e6f829298d637b8da39b9f45170f2a2e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"510ae48544a01e2ca629ce43ca25642e6f829298d637b8da39b9f45170f2a2e1","first_computed_at":"2026-07-05T07:04:25.521454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:25.521454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lSvSfonruP2Zp7Hfm4cyQaGaJm+ShoAdEgmWZeEF8O8La8xVSmQWu9WJz5JnagVGd9gMVy09wEnSWvyZGU3LAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:25.521908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.15405","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b8e365281c7c350ee927834cdb229d3fc6f3864fe5d1ec31b7a1e7faccd2894","sha256:70c43100d74fcbf1b0d8ec0956942aba122cfb2f8a619a84c7d7648ef09e7ebc"],"state_sha256":"087036022210002f2674e8ed0a03026d32ae4bd30edab8c5983ad3efe2ee2f1e"}