{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QUGJNYC4C7HE6DDXTUUK5C5BAD","short_pith_number":"pith:QUGJNYC4","canonical_record":{"source":{"id":"2406.06004","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T03:57:39Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"906146551595da96b55887c4491afcc025a16aec18a46bb4e8e09b7576b5d09f","abstract_canon_sha256":"3801ada259485ed2a181ffbdcb315b7956003bcc94f64898235575fdb0c0ab23"},"schema_version":"1.0"},"canonical_sha256":"850c96e05c17ce4f0c779d28ae8ba100c2b0d0fe226ba60d7c53d8f573ba5b20","source":{"kind":"arxiv","id":"2406.06004","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06004","created_at":"2026-07-05T08:29:36Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06004v1","created_at":"2026-07-05T08:29:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06004","created_at":"2026-07-05T08:29:36Z"},{"alias_kind":"pith_short_12","alias_value":"QUGJNYC4C7HE","created_at":"2026-07-05T08:29:36Z"},{"alias_kind":"pith_short_16","alias_value":"QUGJNYC4C7HE6DDX","created_at":"2026-07-05T08:29:36Z"},{"alias_kind":"pith_short_8","alias_value":"QUGJNYC4","created_at":"2026-07-05T08:29:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QUGJNYC4C7HE6DDXTUUK5C5BAD","target":"record","payload":{"canonical_record":{"source":{"id":"2406.06004","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T03:57:39Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"906146551595da96b55887c4491afcc025a16aec18a46bb4e8e09b7576b5d09f","abstract_canon_sha256":"3801ada259485ed2a181ffbdcb315b7956003bcc94f64898235575fdb0c0ab23"},"schema_version":"1.0"},"canonical_sha256":"850c96e05c17ce4f0c779d28ae8ba100c2b0d0fe226ba60d7c53d8f573ba5b20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:36.329905Z","signature_b64":"xU4pNtCre0lW9pzemS+q/iDouJDjfnPVSySshyjM5N9gl/l25V4mIk+ciCyQj4h5GLHlLKkUU495qzZtBzvHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"850c96e05c17ce4f0c779d28ae8ba100c2b0d0fe226ba60d7c53d8f573ba5b20","last_reissued_at":"2026-07-05T08:29:36.329529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:36.329529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.06004","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":"2026-07-05T08:29:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O1I0Gmdg7dk1B/6DP2XoJadHekwxXo5T+Z6joAoTRxU6rbCtJBV/JWMljQ5dP9LQVoP9Lr18dETKT3YyPVpGCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:15:13.850487Z"},"content_sha256":"da38856f2c99cdc3449a41a2dc325f94127c1cffdf41a9b875b7d5769859ed79","schema_version":"1.0","event_id":"sha256:da38856f2c99cdc3449a41a2dc325f94127c1cffdf41a9b875b7d5769859ed79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QUGJNYC4C7HE6DDXTUUK5C5BAD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FLEUR: An Explainable Reference-Free Evaluation Metric for Image Captioning Using a Large Multimodal Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Imseong Park, Myungjoo Kang, Yebin Lee","submitted_at":"2024-06-10T03:57:39Z","abstract_excerpt":"Most existing image captioning evaluation metrics focus on assigning a single numerical score to a caption by comparing it with reference captions. However, these methods do not provide an explanation for the assigned score. Moreover, reference captions are expensive to acquire. In this paper, we propose FLEUR, an explainable reference-free metric to introduce explainability into image captioning evaluation metrics. By leveraging a large multimodal model, FLEUR can evaluate the caption against the image without the need for reference captions, and provide the explanation for the assigned score"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06004","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/2406.06004/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":"2026-07-05T08:29:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D/AMDTmwInvt6J0DtiKGK5TdAQ3+sMNtHZrQnB2cyz6enSL7I8joPW4YLjjR7AyiIiKEyfjDSDj3AnMPTNp2BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:15:13.851359Z"},"content_sha256":"b2524d7a2dc8b4d2cb1b9fa03b86829545fce4c3910503c6f635ebad3d4d3d96","schema_version":"1.0","event_id":"sha256:b2524d7a2dc8b4d2cb1b9fa03b86829545fce4c3910503c6f635ebad3d4d3d96"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QUGJNYC4C7HE6DDXTUUK5C5BAD/bundle.json","state_url":"https://pith.science/pith/QUGJNYC4C7HE6DDXTUUK5C5BAD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QUGJNYC4C7HE6DDXTUUK5C5BAD/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":"2026-08-03T22:15:13Z","links":{"resolver":"https://pith.science/pith/QUGJNYC4C7HE6DDXTUUK5C5BAD","bundle":"https://pith.science/pith/QUGJNYC4C7HE6DDXTUUK5C5BAD/bundle.json","state":"https://pith.science/pith/QUGJNYC4C7HE6DDXTUUK5C5BAD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QUGJNYC4C7HE6DDXTUUK5C5BAD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QUGJNYC4C7HE6DDXTUUK5C5BAD","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":"3801ada259485ed2a181ffbdcb315b7956003bcc94f64898235575fdb0c0ab23","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T03:57:39Z","title_canon_sha256":"906146551595da96b55887c4491afcc025a16aec18a46bb4e8e09b7576b5d09f"},"schema_version":"1.0","source":{"id":"2406.06004","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06004","created_at":"2026-07-05T08:29:36Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06004v1","created_at":"2026-07-05T08:29:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06004","created_at":"2026-07-05T08:29:36Z"},{"alias_kind":"pith_short_12","alias_value":"QUGJNYC4C7HE","created_at":"2026-07-05T08:29:36Z"},{"alias_kind":"pith_short_16","alias_value":"QUGJNYC4C7HE6DDX","created_at":"2026-07-05T08:29:36Z"},{"alias_kind":"pith_short_8","alias_value":"QUGJNYC4","created_at":"2026-07-05T08:29:36Z"}],"graph_snapshots":[{"event_id":"sha256:b2524d7a2dc8b4d2cb1b9fa03b86829545fce4c3910503c6f635ebad3d4d3d96","target":"graph","created_at":"2026-07-05T08:29:36Z","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/2406.06004/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most existing image captioning evaluation metrics focus on assigning a single numerical score to a caption by comparing it with reference captions. However, these methods do not provide an explanation for the assigned score. Moreover, reference captions are expensive to acquire. In this paper, we propose FLEUR, an explainable reference-free metric to introduce explainability into image captioning evaluation metrics. By leveraging a large multimodal model, FLEUR can evaluate the caption against the image without the need for reference captions, and provide the explanation for the assigned score","authors_text":"Imseong Park, Myungjoo Kang, Yebin Lee","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T03:57:39Z","title":"FLEUR: An Explainable Reference-Free Evaluation Metric for Image Captioning Using a Large Multimodal Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06004","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:da38856f2c99cdc3449a41a2dc325f94127c1cffdf41a9b875b7d5769859ed79","target":"record","created_at":"2026-07-05T08:29:36Z","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":"3801ada259485ed2a181ffbdcb315b7956003bcc94f64898235575fdb0c0ab23","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T03:57:39Z","title_canon_sha256":"906146551595da96b55887c4491afcc025a16aec18a46bb4e8e09b7576b5d09f"},"schema_version":"1.0","source":{"id":"2406.06004","kind":"arxiv","version":1}},"canonical_sha256":"850c96e05c17ce4f0c779d28ae8ba100c2b0d0fe226ba60d7c53d8f573ba5b20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"850c96e05c17ce4f0c779d28ae8ba100c2b0d0fe226ba60d7c53d8f573ba5b20","first_computed_at":"2026-07-05T08:29:36.329529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:36.329529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xU4pNtCre0lW9pzemS+q/iDouJDjfnPVSySshyjM5N9gl/l25V4mIk+ciCyQj4h5GLHlLKkUU495qzZtBzvHCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:36.329905Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06004","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da38856f2c99cdc3449a41a2dc325f94127c1cffdf41a9b875b7d5769859ed79","sha256:b2524d7a2dc8b4d2cb1b9fa03b86829545fce4c3910503c6f635ebad3d4d3d96"],"state_sha256":"6d9e19995c372071e75039e0a5eaebb48f22f680e5c14059730399f3a0609b8b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dxq1ycmCRrPUd437iLhGTiNNLrgbJMYsDp9BfhrvTeHbVYCm1QOLm2POoQ9W5+o6tscR3dJJR9TFjzliceIGBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:15:13.857123Z","bundle_sha256":"1b3187f836b3022461c81cf68cdc642c68f1b1e4e33a75b9a17f99f2d87539fb"}}