{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YCGZTW3EFN52R3RXGAUFGY4RDD","short_pith_number":"pith:YCGZTW3E","schema_version":"1.0","canonical_sha256":"c08d99db642b7ba8ee37302853639118c23956c341bf807fcf2b980e5facd1a1","source":{"kind":"arxiv","id":"2506.24016","version":1},"attestation_state":"computed","paper":{"title":"EXPERT: An Explainable Image Captioning Evaluation Metric with Structured Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Hyunjong Kim, Jongheon Jeong, Sangyeop Kim, Sungzoon Cho, Yeongjae Cho","submitted_at":"2025-06-30T16:20:51Z","abstract_excerpt":"Recent advances in large language models and vision-language models have led to growing interest in explainable evaluation metrics for image captioning. However, these metrics generate explanations without standardized criteria, and the overall quality of the generated explanations remains unverified. In this paper, we propose EXPERT, a reference-free evaluation metric that provides structured explanations based on three fundamental criteria: fluency, relevance, and descriptiveness. By constructing large-scale datasets of high-quality structured explanations, we develop a two-stage evaluation "},"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":"2506.24016","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-30T16:20:51Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"db940c3c7c95800f3b07888a5ff8f9bf3dcf2fb924074b3ce931863da4a286cb","abstract_canon_sha256":"ff05b77bd8bad8e58a020d7dc1dabea999cbff2038d5f6ebed8835818aa9dcc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:31.745914Z","signature_b64":"4m0n99WoI7DsYSaNdjUg/JU1UVEcJ/xwoARmMHxOP5TF633EHoD0WJx5Dxyg3DlYoKeRPhinoEMYQFfDtz4lAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c08d99db642b7ba8ee37302853639118c23956c341bf807fcf2b980e5facd1a1","last_reissued_at":"2026-07-05T11:29:31.745404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:31.745404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EXPERT: An Explainable Image Captioning Evaluation Metric with Structured Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Hyunjong Kim, Jongheon Jeong, Sangyeop Kim, Sungzoon Cho, Yeongjae Cho","submitted_at":"2025-06-30T16:20:51Z","abstract_excerpt":"Recent advances in large language models and vision-language models have led to growing interest in explainable evaluation metrics for image captioning. However, these metrics generate explanations without standardized criteria, and the overall quality of the generated explanations remains unverified. In this paper, we propose EXPERT, a reference-free evaluation metric that provides structured explanations based on three fundamental criteria: fluency, relevance, and descriptiveness. By constructing large-scale datasets of high-quality structured explanations, we develop a two-stage evaluation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.24016","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/2506.24016/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":"2506.24016","created_at":"2026-07-05T11:29:31.745472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.24016v1","created_at":"2026-07-05T11:29:31.745472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.24016","created_at":"2026-07-05T11:29:31.745472+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCGZTW3EFN52","created_at":"2026-07-05T11:29:31.745472+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCGZTW3EFN52R3RX","created_at":"2026-07-05T11:29:31.745472+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCGZTW3E","created_at":"2026-07-05T11:29:31.745472+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/YCGZTW3EFN52R3RXGAUFGY4RDD","json":"https://pith.science/pith/YCGZTW3EFN52R3RXGAUFGY4RDD.json","graph_json":"https://pith.science/api/pith-number/YCGZTW3EFN52R3RXGAUFGY4RDD/graph.json","events_json":"https://pith.science/api/pith-number/YCGZTW3EFN52R3RXGAUFGY4RDD/events.json","paper":"https://pith.science/paper/YCGZTW3E"},"agent_actions":{"view_html":"https://pith.science/pith/YCGZTW3EFN52R3RXGAUFGY4RDD","download_json":"https://pith.science/pith/YCGZTW3EFN52R3RXGAUFGY4RDD.json","view_paper":"https://pith.science/paper/YCGZTW3E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.24016&json=true","fetch_graph":"https://pith.science/api/pith-number/YCGZTW3EFN52R3RXGAUFGY4RDD/graph.json","fetch_events":"https://pith.science/api/pith-number/YCGZTW3EFN52R3RXGAUFGY4RDD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCGZTW3EFN52R3RXGAUFGY4RDD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCGZTW3EFN52R3RXGAUFGY4RDD/action/storage_attestation","attest_author":"https://pith.science/pith/YCGZTW3EFN52R3RXGAUFGY4RDD/action/author_attestation","sign_citation":"https://pith.science/pith/YCGZTW3EFN52R3RXGAUFGY4RDD/action/citation_signature","submit_replication":"https://pith.science/pith/YCGZTW3EFN52R3RXGAUFGY4RDD/action/replication_record"}},"created_at":"2026-07-05T11:29:31.745472+00:00","updated_at":"2026-07-05T11:29:31.745472+00:00"}