{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:LSTSHLPVJL7WVCIWWQMJ4IQIV4","short_pith_number":"pith:LSTSHLPV","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"},"canonical_sha256":"5ca723adf54aff6a8916b4189e2208af1bce8f500e99f12702e19ec27f78bf1e","source":{"kind":"arxiv","id":"2108.12560","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.12560","created_at":"2026-07-05T03:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"2108.12560v1","created_at":"2026-07-05T03:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.12560","created_at":"2026-07-05T03:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"LSTSHLPVJL7W","created_at":"2026-07-05T03:09:33Z"},{"alias_kind":"pith_short_16","alias_value":"LSTSHLPVJL7WVCIW","created_at":"2026-07-05T03:09:33Z"},{"alias_kind":"pith_short_8","alias_value":"LSTSHLPV","created_at":"2026-07-05T03:09:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:LSTSHLPVJL7WVCIWWQMJ4IQIV4","target":"record","payload":{"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"},"canonical_sha256":"5ca723adf54aff6a8916b4189e2208af1bce8f500e99f12702e19ec27f78bf1e","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"},"source_kind":"arxiv","source_id":"2108.12560","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:09:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+wYqJ1/+QxSq51I4LUEB/YKlrWXLFlJRcId9iimvFi6CPbzZjqmeaLK2xlwu3a+ZKOFLXuPHE5PPFD/CCs1hCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T21:51:49.050087Z"},"content_sha256":"7358bc0f6dd14847e69f1ced829590810022adbe0bbd5529b444f5dca9a7dfaf","schema_version":"1.0","event_id":"sha256:7358bc0f6dd14847e69f1ced829590810022adbe0bbd5529b444f5dca9a7dfaf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:LSTSHLPVJL7WVCIWWQMJ4IQIV4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:09:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jQHW5TamXTYn9IxQOjKOruRW/2Y1iozAamCrZ/QNZ/ylCe+2Jg+/HrenD9upwmZ9IqRV5KSVndo8QWorNjp6AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T21:51:49.050477Z"},"content_sha256":"e0c1c5c4fc84ae819c66f705e0a904e152d5d80513a1a6ca6cdcfbe61845afd1","schema_version":"1.0","event_id":"sha256:e0c1c5c4fc84ae819c66f705e0a904e152d5d80513a1a6ca6cdcfbe61845afd1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LSTSHLPVJL7WVCIWWQMJ4IQIV4/bundle.json","state_url":"https://pith.science/pith/LSTSHLPVJL7WVCIWWQMJ4IQIV4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LSTSHLPVJL7WVCIWWQMJ4IQIV4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-16T21:51:49Z","links":{"resolver":"https://pith.science/pith/LSTSHLPVJL7WVCIWWQMJ4IQIV4","bundle":"https://pith.science/pith/LSTSHLPVJL7WVCIWWQMJ4IQIV4/bundle.json","state":"https://pith.science/pith/LSTSHLPVJL7WVCIWWQMJ4IQIV4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LSTSHLPVJL7WVCIWWQMJ4IQIV4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LSTSHLPVJL7WVCIWWQMJ4IQIV4","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":"bb4c913f8641406db841c486c35bfd2e5da7ebd49b9737d012b4b8f58e062e0f","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-28T03:04:28Z","title_canon_sha256":"4f2a35361322adb8d0746faca13ba97d812313c33b7d58f17767c8f43318efc1"},"schema_version":"1.0","source":{"id":"2108.12560","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.12560","created_at":"2026-07-05T03:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"2108.12560v1","created_at":"2026-07-05T03:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.12560","created_at":"2026-07-05T03:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"LSTSHLPVJL7W","created_at":"2026-07-05T03:09:33Z"},{"alias_kind":"pith_short_16","alias_value":"LSTSHLPVJL7WVCIW","created_at":"2026-07-05T03:09:33Z"},{"alias_kind":"pith_short_8","alias_value":"LSTSHLPV","created_at":"2026-07-05T03:09:33Z"}],"graph_snapshots":[{"event_id":"sha256:e0c1c5c4fc84ae819c66f705e0a904e152d5d80513a1a6ca6cdcfbe61845afd1","target":"graph","created_at":"2026-07-05T03:09:33Z","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/2108.12560/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Franck Dernoncourt, Hwanhee Lee, Kyomin Jung, Seunghyun Yoon, Thomas Scialom","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-28T03:04:28Z","title":"QACE: Asking Questions to Evaluate an Image Caption"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.12560","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":"sha256:7358bc0f6dd14847e69f1ced829590810022adbe0bbd5529b444f5dca9a7dfaf","target":"record","created_at":"2026-07-05T03:09:33Z","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":"bb4c913f8641406db841c486c35bfd2e5da7ebd49b9737d012b4b8f58e062e0f","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-28T03:04:28Z","title_canon_sha256":"4f2a35361322adb8d0746faca13ba97d812313c33b7d58f17767c8f43318efc1"},"schema_version":"1.0","source":{"id":"2108.12560","kind":"arxiv","version":1}},"canonical_sha256":"5ca723adf54aff6a8916b4189e2208af1bce8f500e99f12702e19ec27f78bf1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ca723adf54aff6a8916b4189e2208af1bce8f500e99f12702e19ec27f78bf1e","first_computed_at":"2026-07-05T03:09:33.393297Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:09:33.393297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f8sWOm6SN7iomdqE07JiS9z1QUarOEXRt050acEAhHn1+lVu6feOuzxfEXK2naFNMc0fmKZIy6GMrn5k4l7GDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:09:33.393777Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.12560","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7358bc0f6dd14847e69f1ced829590810022adbe0bbd5529b444f5dca9a7dfaf","sha256:e0c1c5c4fc84ae819c66f705e0a904e152d5d80513a1a6ca6cdcfbe61845afd1"],"state_sha256":"d25cd6d39d8a12d437106c863ffe4c26d477d18ae1e3e141a94fad55e9e038b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1nf84AW9Hy7uRTG/zynoAcAg9Y4l2L+EnPzXjEKzFHluF8WyB5Osdk6lb0L8mWcW1Sxu3qgsp104nCSHyQ5MAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T21:51:49.052673Z","bundle_sha256":"af759fa0d267e91b8a211d6b184b835ad21209ad25151cfb5345956bb1f3205c"}}