{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LSTSHLPVJL7WVCIWWQMJ4IQIV4","short_pith_number":"pith:LSTSHLPV","schema_version":"1.0","canonical_sha256":"5ca723adf54aff6a8916b4189e2208af1bce8f500e99f12702e19ec27f78bf1e","source":{"kind":"arxiv","id":"2108.12560","version":1},"attestation_state":"computed","paper":{"title":"QACE: Asking Questions to Evaluate an Image Caption","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Franck Dernoncourt, Hwanhee Lee, Kyomin Jung, Seunghyun Yoon, Thomas Scialom","submitted_at":"2021-08-28T03:04:28Z","abstract_excerpt":"In this paper, we propose QACE, a new metric based on Question Answering for Caption Evaluation. QACE generates questions on the evaluated caption and checks its content by asking the questions on either the reference caption or the source image. We first develop QACE-Ref that compares the answers of the evaluated caption to its reference, and report competitive results with the state-of-the-art metrics. To go further, we propose QACE-Img, which asks the questions directly on the image, instead of reference. A Visual-QA system is necessary for QACE-Img. Unfortunately, the standard VQA models 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":"2108.12560","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-28T03:04:28Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4f2a35361322adb8d0746faca13ba97d812313c33b7d58f17767c8f43318efc1","abstract_canon_sha256":"bb4c913f8641406db841c486c35bfd2e5da7ebd49b9737d012b4b8f58e062e0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:09:33.393777Z","signature_b64":"f8sWOm6SN7iomdqE07JiS9z1QUarOEXRt050acEAhHn1+lVu6feOuzxfEXK2naFNMc0fmKZIy6GMrn5k4l7GDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ca723adf54aff6a8916b4189e2208af1bce8f500e99f12702e19ec27f78bf1e","last_reissued_at":"2026-07-05T03:09:33.393297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:09:33.393297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QACE: Asking Questions to Evaluate an Image Caption","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Franck Dernoncourt, Hwanhee Lee, Kyomin Jung, Seunghyun Yoon, Thomas Scialom","submitted_at":"2021-08-28T03:04:28Z","abstract_excerpt":"In this paper, we propose QACE, a new metric based on Question Answering for Caption Evaluation. QACE generates questions on the evaluated caption and checks its content by asking the questions on either the reference caption or the source image. We first develop QACE-Ref that compares the answers of the evaluated caption to its reference, and report competitive results with the state-of-the-art metrics. To go further, we propose QACE-Img, which asks the questions directly on the image, instead of reference. A Visual-QA system is necessary for QACE-Img. Unfortunately, the standard VQA models a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.12560","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/2108.12560/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":"2108.12560","created_at":"2026-07-05T03:09:33.393363+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.12560v1","created_at":"2026-07-05T03:09:33.393363+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.12560","created_at":"2026-07-05T03:09:33.393363+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSTSHLPVJL7W","created_at":"2026-07-05T03:09:33.393363+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSTSHLPVJL7WVCIW","created_at":"2026-07-05T03:09:33.393363+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSTSHLPV","created_at":"2026-07-05T03:09:33.393363+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/LSTSHLPVJL7WVCIWWQMJ4IQIV4","json":"https://pith.science/pith/LSTSHLPVJL7WVCIWWQMJ4IQIV4.json","graph_json":"https://pith.science/api/pith-number/LSTSHLPVJL7WVCIWWQMJ4IQIV4/graph.json","events_json":"https://pith.science/api/pith-number/LSTSHLPVJL7WVCIWWQMJ4IQIV4/events.json","paper":"https://pith.science/paper/LSTSHLPV"},"agent_actions":{"view_html":"https://pith.science/pith/LSTSHLPVJL7WVCIWWQMJ4IQIV4","download_json":"https://pith.science/pith/LSTSHLPVJL7WVCIWWQMJ4IQIV4.json","view_paper":"https://pith.science/paper/LSTSHLPV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.12560&json=true","fetch_graph":"https://pith.science/api/pith-number/LSTSHLPVJL7WVCIWWQMJ4IQIV4/graph.json","fetch_events":"https://pith.science/api/pith-number/LSTSHLPVJL7WVCIWWQMJ4IQIV4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSTSHLPVJL7WVCIWWQMJ4IQIV4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSTSHLPVJL7WVCIWWQMJ4IQIV4/action/storage_attestation","attest_author":"https://pith.science/pith/LSTSHLPVJL7WVCIWWQMJ4IQIV4/action/author_attestation","sign_citation":"https://pith.science/pith/LSTSHLPVJL7WVCIWWQMJ4IQIV4/action/citation_signature","submit_replication":"https://pith.science/pith/LSTSHLPVJL7WVCIWWQMJ4IQIV4/action/replication_record"}},"created_at":"2026-07-05T03:09:33.393363+00:00","updated_at":"2026-07-05T03:09:33.393363+00:00"}