{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EE245KREQDRK7CRKOA6F63EY5X","short_pith_number":"pith:EE245KRE","canonical_record":{"source":{"id":"2503.14604","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T18:03:56Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f726deb9f8f7010eeea8883631ab05cad4e9143d91d0d681e4b89fe6249dfc6e","abstract_canon_sha256":"ef93352fbf72f3d478a20f0238e9ecb18997500f39475a23999a565e57edf9ff"},"schema_version":"1.0"},"canonical_sha256":"2135ceaa2480e2af8a2a703c5f6c98edc7ee6c63758a0d69326ecf2d6dbb7326","source":{"kind":"arxiv","id":"2503.14604","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.14604","created_at":"2026-07-05T11:12:29Z"},{"alias_kind":"arxiv_version","alias_value":"2503.14604v2","created_at":"2026-07-05T11:12:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14604","created_at":"2026-07-05T11:12:29Z"},{"alias_kind":"pith_short_12","alias_value":"EE245KREQDRK","created_at":"2026-07-05T11:12:29Z"},{"alias_kind":"pith_short_16","alias_value":"EE245KREQDRK7CRK","created_at":"2026-07-05T11:12:29Z"},{"alias_kind":"pith_short_8","alias_value":"EE245KRE","created_at":"2026-07-05T11:12:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EE245KREQDRK7CRKOA6F63EY5X","target":"record","payload":{"canonical_record":{"source":{"id":"2503.14604","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T18:03:56Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f726deb9f8f7010eeea8883631ab05cad4e9143d91d0d681e4b89fe6249dfc6e","abstract_canon_sha256":"ef93352fbf72f3d478a20f0238e9ecb18997500f39475a23999a565e57edf9ff"},"schema_version":"1.0"},"canonical_sha256":"2135ceaa2480e2af8a2a703c5f6c98edc7ee6c63758a0d69326ecf2d6dbb7326","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:29.535616Z","signature_b64":"4jfV6T3MKAAeTt3R+qhgLb2Xyg9A3E2ZNZbryNk1PBzOH86ywFVoZtl0iKUcWzlrKJcKcayT9eYCkq85ImmuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2135ceaa2480e2af8a2a703c5f6c98edc7ee6c63758a0d69326ecf2d6dbb7326","last_reissued_at":"2026-07-05T11:12:29.535037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:29.535037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.14604","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mFbHndUqU2qj897JAqrofE7Bm3+V+TSymxq9uhiQ1SWIfSnPe/9ygveebJZ4J4G9/S3kmdxNaJSZuzsqj9NkAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:13:17.133069Z"},"content_sha256":"d3d7ecf230bad9d06aeece1768efc4e89ec694d05acf939ca93e4c3ae227076d","schema_version":"1.0","event_id":"sha256:d3d7ecf230bad9d06aeece1768efc4e89ec694d05acf939ca93e4c3ae227076d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EE245KREQDRK7CRKOA6F63EY5X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future Perspectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Marcella Cornia, Rita Cucchiara, Sara Sarto","submitted_at":"2025-03-18T18:03:56Z","abstract_excerpt":"The evaluation of machine-generated image captions is a complex and evolving challenge. With the advent of Multimodal Large Language Models (MLLMs), image captioning has become a core task, increasing the need for robust and reliable evaluation metrics. This survey provides a comprehensive overview of advancements in image captioning evaluation, analyzing the evolution, strengths, and limitations of existing metrics. We assess these metrics across multiple dimensions, including correlation with human judgment, ranking accuracy, and sensitivity to hallucinations. Additionally, we explore the ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14604","kind":"arxiv","version":2},"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/2503.14604/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":"2026-07-05T11:12:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SyZc+FSSbTe8JQGGjAH9W3OJxeTwBri2y4V8XjpWerkok6um5xxLMki5/BruizZKcGvxVv8WJAGDKTUwCn4jBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:13:17.133573Z"},"content_sha256":"305289286ad7584efd2459db16dc75e06965e164fe01c3e09127e3480918e8bc","schema_version":"1.0","event_id":"sha256:305289286ad7584efd2459db16dc75e06965e164fe01c3e09127e3480918e8bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EE245KREQDRK7CRKOA6F63EY5X/bundle.json","state_url":"https://pith.science/pith/EE245KREQDRK7CRKOA6F63EY5X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EE245KREQDRK7CRKOA6F63EY5X/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":"2026-08-06T08:13:17Z","links":{"resolver":"https://pith.science/pith/EE245KREQDRK7CRKOA6F63EY5X","bundle":"https://pith.science/pith/EE245KREQDRK7CRKOA6F63EY5X/bundle.json","state":"https://pith.science/pith/EE245KREQDRK7CRKOA6F63EY5X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EE245KREQDRK7CRKOA6F63EY5X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EE245KREQDRK7CRKOA6F63EY5X","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":"ef93352fbf72f3d478a20f0238e9ecb18997500f39475a23999a565e57edf9ff","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T18:03:56Z","title_canon_sha256":"f726deb9f8f7010eeea8883631ab05cad4e9143d91d0d681e4b89fe6249dfc6e"},"schema_version":"1.0","source":{"id":"2503.14604","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.14604","created_at":"2026-07-05T11:12:29Z"},{"alias_kind":"arxiv_version","alias_value":"2503.14604v2","created_at":"2026-07-05T11:12:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14604","created_at":"2026-07-05T11:12:29Z"},{"alias_kind":"pith_short_12","alias_value":"EE245KREQDRK","created_at":"2026-07-05T11:12:29Z"},{"alias_kind":"pith_short_16","alias_value":"EE245KREQDRK7CRK","created_at":"2026-07-05T11:12:29Z"},{"alias_kind":"pith_short_8","alias_value":"EE245KRE","created_at":"2026-07-05T11:12:29Z"}],"graph_snapshots":[{"event_id":"sha256:305289286ad7584efd2459db16dc75e06965e164fe01c3e09127e3480918e8bc","target":"graph","created_at":"2026-07-05T11:12:29Z","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/2503.14604/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The evaluation of machine-generated image captions is a complex and evolving challenge. With the advent of Multimodal Large Language Models (MLLMs), image captioning has become a core task, increasing the need for robust and reliable evaluation metrics. This survey provides a comprehensive overview of advancements in image captioning evaluation, analyzing the evolution, strengths, and limitations of existing metrics. We assess these metrics across multiple dimensions, including correlation with human judgment, ranking accuracy, and sensitivity to hallucinations. Additionally, we explore the ch","authors_text":"Marcella Cornia, Rita Cucchiara, Sara Sarto","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T18:03:56Z","title":"Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future Perspectives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14604","kind":"arxiv","version":2},"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:d3d7ecf230bad9d06aeece1768efc4e89ec694d05acf939ca93e4c3ae227076d","target":"record","created_at":"2026-07-05T11:12:29Z","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":"ef93352fbf72f3d478a20f0238e9ecb18997500f39475a23999a565e57edf9ff","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T18:03:56Z","title_canon_sha256":"f726deb9f8f7010eeea8883631ab05cad4e9143d91d0d681e4b89fe6249dfc6e"},"schema_version":"1.0","source":{"id":"2503.14604","kind":"arxiv","version":2}},"canonical_sha256":"2135ceaa2480e2af8a2a703c5f6c98edc7ee6c63758a0d69326ecf2d6dbb7326","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2135ceaa2480e2af8a2a703c5f6c98edc7ee6c63758a0d69326ecf2d6dbb7326","first_computed_at":"2026-07-05T11:12:29.535037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:29.535037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4jfV6T3MKAAeTt3R+qhgLb2Xyg9A3E2ZNZbryNk1PBzOH86ywFVoZtl0iKUcWzlrKJcKcayT9eYCkq85ImmuCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:29.535616Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.14604","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3d7ecf230bad9d06aeece1768efc4e89ec694d05acf939ca93e4c3ae227076d","sha256:305289286ad7584efd2459db16dc75e06965e164fe01c3e09127e3480918e8bc"],"state_sha256":"a293c5adae67298ec3d83fc372298b5b36e5d85b69b5e60c90f99ce887d9b161"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uNoXKTb8Rn8wo+R9dpSlNi4W9mEsnKSuayJZGrI48u0814tY5uNaUQuJDORN9p/X7xKpu6mK+xu8HRfOrLHIDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:13:17.137063Z","bundle_sha256":"913d980efe1ca6dad74805e1e0b2a7c6dbb5684a9be33226b92c1d201332f7b6"}}