{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FMZIMESY3CP6SW7AKKIFTR6IMG","short_pith_number":"pith:FMZIMESY","canonical_record":{"source":{"id":"2407.18589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-26T08:24:30Z","cross_cats_sorted":[],"title_canon_sha256":"999c11f09667c1bb9970d0c765a3f54333e881d74b372b92d946635592d184ed","abstract_canon_sha256":"dacd7ae50e4659b8482771b468a9d83127b5c1f63788ad1bcd871e0542e66a2c"},"schema_version":"1.0"},"canonical_sha256":"2b32861258d89fe95be0529059c7c8619021b3b38b224d2c1b5eecc9d658e245","source":{"kind":"arxiv","id":"2407.18589","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18589","created_at":"2026-07-05T08:48:52Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18589v1","created_at":"2026-07-05T08:48:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18589","created_at":"2026-07-05T08:48:52Z"},{"alias_kind":"pith_short_12","alias_value":"FMZIMESY3CP6","created_at":"2026-07-05T08:48:52Z"},{"alias_kind":"pith_short_16","alias_value":"FMZIMESY3CP6SW7A","created_at":"2026-07-05T08:48:52Z"},{"alias_kind":"pith_short_8","alias_value":"FMZIMESY","created_at":"2026-07-05T08:48:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FMZIMESY3CP6SW7AKKIFTR6IMG","target":"record","payload":{"canonical_record":{"source":{"id":"2407.18589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-26T08:24:30Z","cross_cats_sorted":[],"title_canon_sha256":"999c11f09667c1bb9970d0c765a3f54333e881d74b372b92d946635592d184ed","abstract_canon_sha256":"dacd7ae50e4659b8482771b468a9d83127b5c1f63788ad1bcd871e0542e66a2c"},"schema_version":"1.0"},"canonical_sha256":"2b32861258d89fe95be0529059c7c8619021b3b38b224d2c1b5eecc9d658e245","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:52.005910Z","signature_b64":"Rf5aFJr3W86qAl+WtgQER83tsLrYxvhqj0OQpgw4/6K3jQ0zsoNKwxX/Zlq0BylqvHVr8GW4F1xIckvoZCAKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b32861258d89fe95be0529059c7c8619021b3b38b224d2c1b5eecc9d658e245","last_reissued_at":"2026-07-05T08:48:52.005477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:52.005477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.18589","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":"2026-07-05T08:48:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wY+WvEBnvq2+lHTF334YSnhZwpO6Dn1zLBvAnYdTknM/WiKPKojzYbyKp8v9VvEOkwTX8ul10YMmwcmQESnYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T09:36:59.153241Z"},"content_sha256":"dcf71a80eaebfa2b37af9cf455bd7544f7861d3d7be8cc496c25080342000220","schema_version":"1.0","event_id":"sha256:dcf71a80eaebfa2b37af9cf455bd7544f7861d3d7be8cc496c25080342000220"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FMZIMESY3CP6SW7AKKIFTR6IMG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HICEScore: A Hierarchical Metric for Image Captioning Evaluation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Chen, Hao Zhang, Jianqiao Sun, Tiansheng Wen, Yan Xie, Yudi Su, Zequn Zeng, Zhengjue Wang","submitted_at":"2024-07-26T08:24:30Z","abstract_excerpt":"Image captioning evaluation metrics can be divided into two categories, reference-based metrics and reference-free metrics. However, reference-based approaches may struggle to evaluate descriptive captions with abundant visual details produced by advanced multimodal large language models, due to their heavy reliance on limited human-annotated references. In contrast, previous reference-free metrics have been proven effective via CLIP cross-modality similarity. Nonetheless, CLIP-based metrics, constrained by their solution of global image-text compatibility, often have a deficiency in detecting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18589","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/2407.18589/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":"2026-07-05T08:48:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZP4HIHeq3Jk1TLkYFfvRLnZkIDh0PeLsJq2SQikQxxzrK2gXrTAtDR57Vdv9e7pmAOypTRXAIzOfAWbuNrzmDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T09:36:59.153626Z"},"content_sha256":"58937ac09aeffac9357caa3868fefe3d89079e51f604081e7a39cd9fef0cfa03","schema_version":"1.0","event_id":"sha256:58937ac09aeffac9357caa3868fefe3d89079e51f604081e7a39cd9fef0cfa03"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FMZIMESY3CP6SW7AKKIFTR6IMG/bundle.json","state_url":"https://pith.science/pith/FMZIMESY3CP6SW7AKKIFTR6IMG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FMZIMESY3CP6SW7AKKIFTR6IMG/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":"2026-07-06T09:36:59Z","links":{"resolver":"https://pith.science/pith/FMZIMESY3CP6SW7AKKIFTR6IMG","bundle":"https://pith.science/pith/FMZIMESY3CP6SW7AKKIFTR6IMG/bundle.json","state":"https://pith.science/pith/FMZIMESY3CP6SW7AKKIFTR6IMG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FMZIMESY3CP6SW7AKKIFTR6IMG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FMZIMESY3CP6SW7AKKIFTR6IMG","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":"dacd7ae50e4659b8482771b468a9d83127b5c1f63788ad1bcd871e0542e66a2c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-26T08:24:30Z","title_canon_sha256":"999c11f09667c1bb9970d0c765a3f54333e881d74b372b92d946635592d184ed"},"schema_version":"1.0","source":{"id":"2407.18589","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18589","created_at":"2026-07-05T08:48:52Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18589v1","created_at":"2026-07-05T08:48:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18589","created_at":"2026-07-05T08:48:52Z"},{"alias_kind":"pith_short_12","alias_value":"FMZIMESY3CP6","created_at":"2026-07-05T08:48:52Z"},{"alias_kind":"pith_short_16","alias_value":"FMZIMESY3CP6SW7A","created_at":"2026-07-05T08:48:52Z"},{"alias_kind":"pith_short_8","alias_value":"FMZIMESY","created_at":"2026-07-05T08:48:52Z"}],"graph_snapshots":[{"event_id":"sha256:58937ac09aeffac9357caa3868fefe3d89079e51f604081e7a39cd9fef0cfa03","target":"graph","created_at":"2026-07-05T08:48:52Z","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/2407.18589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning evaluation metrics can be divided into two categories, reference-based metrics and reference-free metrics. However, reference-based approaches may struggle to evaluate descriptive captions with abundant visual details produced by advanced multimodal large language models, due to their heavy reliance on limited human-annotated references. In contrast, previous reference-free metrics have been proven effective via CLIP cross-modality similarity. Nonetheless, CLIP-based metrics, constrained by their solution of global image-text compatibility, often have a deficiency in detecting","authors_text":"Bo Chen, Hao Zhang, Jianqiao Sun, Tiansheng Wen, Yan Xie, Yudi Su, Zequn Zeng, Zhengjue Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-26T08:24:30Z","title":"HICEScore: A Hierarchical Metric for Image Captioning Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18589","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:dcf71a80eaebfa2b37af9cf455bd7544f7861d3d7be8cc496c25080342000220","target":"record","created_at":"2026-07-05T08:48:52Z","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":"dacd7ae50e4659b8482771b468a9d83127b5c1f63788ad1bcd871e0542e66a2c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-26T08:24:30Z","title_canon_sha256":"999c11f09667c1bb9970d0c765a3f54333e881d74b372b92d946635592d184ed"},"schema_version":"1.0","source":{"id":"2407.18589","kind":"arxiv","version":1}},"canonical_sha256":"2b32861258d89fe95be0529059c7c8619021b3b38b224d2c1b5eecc9d658e245","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b32861258d89fe95be0529059c7c8619021b3b38b224d2c1b5eecc9d658e245","first_computed_at":"2026-07-05T08:48:52.005477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:52.005477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rf5aFJr3W86qAl+WtgQER83tsLrYxvhqj0OQpgw4/6K3jQ0zsoNKwxX/Zlq0BylqvHVr8GW4F1xIckvoZCAKDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:52.005910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.18589","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcf71a80eaebfa2b37af9cf455bd7544f7861d3d7be8cc496c25080342000220","sha256:58937ac09aeffac9357caa3868fefe3d89079e51f604081e7a39cd9fef0cfa03"],"state_sha256":"f7cd424824901197f08546dc1ee665acd25b873bf1aae0b5d4ceb4a25482b8fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7bSpAD/lYC9N9JK3mCOVVCZPIPcd5Z2dRAOs6uKfNzl3PloslcVKbnNnKcJJLvHWrVJae97yAaI2JZzEMLbyCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T09:36:59.155747Z","bundle_sha256":"00d9c2fe5ed75abafaa89ce223134cecfbf12a0546946deded085490e23afd0f"}}