{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QYNUOZWJXHW4A364JHRLRA2MHF","short_pith_number":"pith:QYNUOZWJ","canonical_record":{"source":{"id":"2412.03665","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T19:01:06Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"810e7696945afd6b3ba4357a0fd027c70796d002923ebdd74987cf6a5572669b","abstract_canon_sha256":"03d42c7ae77c3ffcbf7895f3c0fbfadad45fa8fa8680e1a8830747512c06428e"},"schema_version":"1.0"},"canonical_sha256":"861b4766c9b9edc06fdc49e2b8834c3941c7ed8d200051d50620f16c9e03a3f6","source":{"kind":"arxiv","id":"2412.03665","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03665","created_at":"2026-07-05T09:44:39Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03665v1","created_at":"2026-07-05T09:44:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03665","created_at":"2026-07-05T09:44:39Z"},{"alias_kind":"pith_short_12","alias_value":"QYNUOZWJXHW4","created_at":"2026-07-05T09:44:39Z"},{"alias_kind":"pith_short_16","alias_value":"QYNUOZWJXHW4A364","created_at":"2026-07-05T09:44:39Z"},{"alias_kind":"pith_short_8","alias_value":"QYNUOZWJ","created_at":"2026-07-05T09:44:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QYNUOZWJXHW4A364JHRLRA2MHF","target":"record","payload":{"canonical_record":{"source":{"id":"2412.03665","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T19:01:06Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"810e7696945afd6b3ba4357a0fd027c70796d002923ebdd74987cf6a5572669b","abstract_canon_sha256":"03d42c7ae77c3ffcbf7895f3c0fbfadad45fa8fa8680e1a8830747512c06428e"},"schema_version":"1.0"},"canonical_sha256":"861b4766c9b9edc06fdc49e2b8834c3941c7ed8d200051d50620f16c9e03a3f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:39.652646Z","signature_b64":"STqvT25XrsSalNFjuLF8cWQmwLkpRwsyTZatxrBncLzf7btZ/0jqfhJk77aw+XJivIo7LWHG3tkd1mdpQ3GlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"861b4766c9b9edc06fdc49e2b8834c3941c7ed8d200051d50620f16c9e03a3f6","last_reissued_at":"2026-07-05T09:44:39.652151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:39.652151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.03665","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":"2026-07-05T09:44:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GgtjtpKpB1GpNYJfuhPP/aSH3Z6TdFqPQwer56UCaEiEaF6cRz5cODfOJjeoyDoyalGoIOakyKdS1rUdaeuvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:07:16.692406Z"},"content_sha256":"c327d9dc44a1d8f433131fc11ddb93858f35f91712b77a12c134b89ca1e395d1","schema_version":"1.0","event_id":"sha256:c327d9dc44a1d8f433131fc11ddb93858f35f91712b77a12c134b89ca1e395d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QYNUOZWJXHW4A364JHRLRA2MHF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Davide Bucciarelli, Lorenzo Baraldi, Marcella Cornia, Nicholas Moratelli, Rita Cucchiara","submitted_at":"2024-12-04T19:01:06Z","abstract_excerpt":"The task of image captioning demands an algorithm to generate natural language descriptions of visual inputs. Recent advancements have seen a convergence between image captioning research and the development of Large Language Models (LLMs) and Multimodal LLMs -- like GPT-4V and Gemini -- which extend the capabilities of text-only LLMs to multiple modalities. This paper investigates whether Multimodal LLMs can supplant traditional image captioning networks by evaluating their performance on various image description benchmarks. We explore both the zero-shot capabilities of these models and thei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03665","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/2412.03665/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":"2026-07-05T09:44:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mDXhrgWK2cifVymWkj+/dmQsFa8LaPucORvCwIiEprK3SWRvNhuR5h1y4k6ehT3Vn+bJQ0DKs47c1oRQ7FpXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:07:16.693073Z"},"content_sha256":"77b5be6e1a1fb5c446092829ddfd0736272c1bfa1015f1424dc1b9d5a0df0753","schema_version":"1.0","event_id":"sha256:77b5be6e1a1fb5c446092829ddfd0736272c1bfa1015f1424dc1b9d5a0df0753"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QYNUOZWJXHW4A364JHRLRA2MHF/bundle.json","state_url":"https://pith.science/pith/QYNUOZWJXHW4A364JHRLRA2MHF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QYNUOZWJXHW4A364JHRLRA2MHF/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":"2026-08-10T13:07:16Z","links":{"resolver":"https://pith.science/pith/QYNUOZWJXHW4A364JHRLRA2MHF","bundle":"https://pith.science/pith/QYNUOZWJXHW4A364JHRLRA2MHF/bundle.json","state":"https://pith.science/pith/QYNUOZWJXHW4A364JHRLRA2MHF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QYNUOZWJXHW4A364JHRLRA2MHF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QYNUOZWJXHW4A364JHRLRA2MHF","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":"03d42c7ae77c3ffcbf7895f3c0fbfadad45fa8fa8680e1a8830747512c06428e","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T19:01:06Z","title_canon_sha256":"810e7696945afd6b3ba4357a0fd027c70796d002923ebdd74987cf6a5572669b"},"schema_version":"1.0","source":{"id":"2412.03665","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03665","created_at":"2026-07-05T09:44:39Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03665v1","created_at":"2026-07-05T09:44:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03665","created_at":"2026-07-05T09:44:39Z"},{"alias_kind":"pith_short_12","alias_value":"QYNUOZWJXHW4","created_at":"2026-07-05T09:44:39Z"},{"alias_kind":"pith_short_16","alias_value":"QYNUOZWJXHW4A364","created_at":"2026-07-05T09:44:39Z"},{"alias_kind":"pith_short_8","alias_value":"QYNUOZWJ","created_at":"2026-07-05T09:44:39Z"}],"graph_snapshots":[{"event_id":"sha256:77b5be6e1a1fb5c446092829ddfd0736272c1bfa1015f1424dc1b9d5a0df0753","target":"graph","created_at":"2026-07-05T09:44:39Z","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/2412.03665/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The task of image captioning demands an algorithm to generate natural language descriptions of visual inputs. Recent advancements have seen a convergence between image captioning research and the development of Large Language Models (LLMs) and Multimodal LLMs -- like GPT-4V and Gemini -- which extend the capabilities of text-only LLMs to multiple modalities. This paper investigates whether Multimodal LLMs can supplant traditional image captioning networks by evaluating their performance on various image description benchmarks. We explore both the zero-shot capabilities of these models and thei","authors_text":"Davide Bucciarelli, Lorenzo Baraldi, Marcella Cornia, Nicholas Moratelli, Rita Cucchiara","cross_cats":["cs.AI","cs.CL","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T19:01:06Z","title":"Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03665","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:c327d9dc44a1d8f433131fc11ddb93858f35f91712b77a12c134b89ca1e395d1","target":"record","created_at":"2026-07-05T09:44:39Z","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":"03d42c7ae77c3ffcbf7895f3c0fbfadad45fa8fa8680e1a8830747512c06428e","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T19:01:06Z","title_canon_sha256":"810e7696945afd6b3ba4357a0fd027c70796d002923ebdd74987cf6a5572669b"},"schema_version":"1.0","source":{"id":"2412.03665","kind":"arxiv","version":1}},"canonical_sha256":"861b4766c9b9edc06fdc49e2b8834c3941c7ed8d200051d50620f16c9e03a3f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"861b4766c9b9edc06fdc49e2b8834c3941c7ed8d200051d50620f16c9e03a3f6","first_computed_at":"2026-07-05T09:44:39.652151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:39.652151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"STqvT25XrsSalNFjuLF8cWQmwLkpRwsyTZatxrBncLzf7btZ/0jqfhJk77aw+XJivIo7LWHG3tkd1mdpQ3GlBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:39.652646Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03665","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c327d9dc44a1d8f433131fc11ddb93858f35f91712b77a12c134b89ca1e395d1","sha256:77b5be6e1a1fb5c446092829ddfd0736272c1bfa1015f1424dc1b9d5a0df0753"],"state_sha256":"d57eaed806dc73ff48eca25e646a7307a8ba2bdafc608f5854f2f0758ba270c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pQLKSnIrbuw8ZfdNcWVD3Klg8aUZ/o0qQFcRIkVYRC+lkeLxXEVR1Um7JBCn6Od4B3FlaA5AVD9SjKo88ctjDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T13:07:16.713790Z","bundle_sha256":"f92e0fa7a76a2ff9b4adfba2564376d4801f1b3a22e0ef54400d84adec0d5168"}}