{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MI25ZGKS2ND6VNHIDHQBRICTX6","short_pith_number":"pith:MI25ZGKS","canonical_record":{"source":{"id":"2412.14660","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T09:10:07Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","stat.ML"],"title_canon_sha256":"ee079953289a7ba14ec5303ab2763ea8a08c6d6c79603f5a3f28f6266f76b7d3","abstract_canon_sha256":"7101144636022915e57bb6680a606a9e4924bb5e97709eb0944b20732741a7c8"},"schema_version":"1.0"},"canonical_sha256":"6235dc9952d347eab4e819e018a053bfa77243eba398881e95634a8abfb116de","source":{"kind":"arxiv","id":"2412.14660","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14660","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14660v2","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14660","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"pith_short_12","alias_value":"MI25ZGKS2ND6","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"pith_short_16","alias_value":"MI25ZGKS2ND6VNHI","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"pith_short_8","alias_value":"MI25ZGKS","created_at":"2026-07-05T09:54:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MI25ZGKS2ND6VNHIDHQBRICTX6","target":"record","payload":{"canonical_record":{"source":{"id":"2412.14660","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T09:10:07Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","stat.ML"],"title_canon_sha256":"ee079953289a7ba14ec5303ab2763ea8a08c6d6c79603f5a3f28f6266f76b7d3","abstract_canon_sha256":"7101144636022915e57bb6680a606a9e4924bb5e97709eb0944b20732741a7c8"},"schema_version":"1.0"},"canonical_sha256":"6235dc9952d347eab4e819e018a053bfa77243eba398881e95634a8abfb116de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:06.919950Z","signature_b64":"ZkfReMs1G+sgpFjwq5EEcgawRZLTCJr0psFuE52239vXPsnWw6/Vo5ObhL01ErVKFsXqJDJhWiwxOGYOU1LnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6235dc9952d347eab4e819e018a053bfa77243eba398881e95634a8abfb116de","last_reissued_at":"2026-07-05T09:54:06.919393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:06.919393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.14660","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":"2026-07-05T09:54:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fa3/Vpy+OjXV9iq+r6lnjKGn3Nju2H7F1HrsC16GI2Gg582XlxIGF94XDZ8mYGNQxz6oC+vxJZPVFt//ZXDqAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:15:57.730856Z"},"content_sha256":"26a01b853a708171882856886ba94de348f8a636a56ca9040d14cb58f12605b8","schema_version":"1.0","event_id":"sha256:26a01b853a708171882856886ba94de348f8a636a56ca9040d14cb58f12605b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MI25ZGKS2ND6VNHIDHQBRICTX6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unveiling Uncertainty: A Deep Dive into Calibration and Performance of Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Guande He, Richang Hong, Wenbo Hu, Zheng Zhang, Zhijie Deng, Zijun Chen","submitted_at":"2024-12-19T09:10:07Z","abstract_excerpt":"Multimodal large language models (MLLMs) combine visual and textual data for tasks such as image captioning and visual question answering. Proper uncertainty calibration is crucial, yet challenging, for reliable use in areas like healthcare and autonomous driving. This paper investigates representative MLLMs, focusing on their calibration across various scenarios, including before and after visual fine-tuning, as well as before and after multimodal training of the base LLMs. We observed miscalibration in their performance, and at the same time, no significant differences in calibration across "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14660","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/2412.14660/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":"2026-07-05T09:54:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ed4cwatA1vTQO/LcR1jwXx0jzbHlRDQ2Mpl+R6Bxf0ZEQov3s23yGontFRRGEzpH/iOBDPB3xsKnu4g9aU0wBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:15:57.731806Z"},"content_sha256":"69180a93e3b245f56c185321fd78efb53e1c6769e3d08a5b393382005d8a210d","schema_version":"1.0","event_id":"sha256:69180a93e3b245f56c185321fd78efb53e1c6769e3d08a5b393382005d8a210d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MI25ZGKS2ND6VNHIDHQBRICTX6/bundle.json","state_url":"https://pith.science/pith/MI25ZGKS2ND6VNHIDHQBRICTX6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MI25ZGKS2ND6VNHIDHQBRICTX6/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":"2026-08-07T05:15:57Z","links":{"resolver":"https://pith.science/pith/MI25ZGKS2ND6VNHIDHQBRICTX6","bundle":"https://pith.science/pith/MI25ZGKS2ND6VNHIDHQBRICTX6/bundle.json","state":"https://pith.science/pith/MI25ZGKS2ND6VNHIDHQBRICTX6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MI25ZGKS2ND6VNHIDHQBRICTX6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MI25ZGKS2ND6VNHIDHQBRICTX6","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":"7101144636022915e57bb6680a606a9e4924bb5e97709eb0944b20732741a7c8","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T09:10:07Z","title_canon_sha256":"ee079953289a7ba14ec5303ab2763ea8a08c6d6c79603f5a3f28f6266f76b7d3"},"schema_version":"1.0","source":{"id":"2412.14660","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14660","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14660v2","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14660","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"pith_short_12","alias_value":"MI25ZGKS2ND6","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"pith_short_16","alias_value":"MI25ZGKS2ND6VNHI","created_at":"2026-07-05T09:54:06Z"},{"alias_kind":"pith_short_8","alias_value":"MI25ZGKS","created_at":"2026-07-05T09:54:06Z"}],"graph_snapshots":[{"event_id":"sha256:69180a93e3b245f56c185321fd78efb53e1c6769e3d08a5b393382005d8a210d","target":"graph","created_at":"2026-07-05T09:54:06Z","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/2412.14660/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) combine visual and textual data for tasks such as image captioning and visual question answering. Proper uncertainty calibration is crucial, yet challenging, for reliable use in areas like healthcare and autonomous driving. This paper investigates representative MLLMs, focusing on their calibration across various scenarios, including before and after visual fine-tuning, as well as before and after multimodal training of the base LLMs. We observed miscalibration in their performance, and at the same time, no significant differences in calibration across ","authors_text":"Guande He, Richang Hong, Wenbo Hu, Zheng Zhang, Zhijie Deng, Zijun Chen","cross_cats":["cs.AI","cs.CL","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T09:10:07Z","title":"Unveiling Uncertainty: A Deep Dive into Calibration and Performance of Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14660","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":"sha256:26a01b853a708171882856886ba94de348f8a636a56ca9040d14cb58f12605b8","target":"record","created_at":"2026-07-05T09:54:06Z","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":"7101144636022915e57bb6680a606a9e4924bb5e97709eb0944b20732741a7c8","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T09:10:07Z","title_canon_sha256":"ee079953289a7ba14ec5303ab2763ea8a08c6d6c79603f5a3f28f6266f76b7d3"},"schema_version":"1.0","source":{"id":"2412.14660","kind":"arxiv","version":2}},"canonical_sha256":"6235dc9952d347eab4e819e018a053bfa77243eba398881e95634a8abfb116de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6235dc9952d347eab4e819e018a053bfa77243eba398881e95634a8abfb116de","first_computed_at":"2026-07-05T09:54:06.919393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:06.919393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZkfReMs1G+sgpFjwq5EEcgawRZLTCJr0psFuE52239vXPsnWw6/Vo5ObhL01ErVKFsXqJDJhWiwxOGYOU1LnCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:06.919950Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14660","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26a01b853a708171882856886ba94de348f8a636a56ca9040d14cb58f12605b8","sha256:69180a93e3b245f56c185321fd78efb53e1c6769e3d08a5b393382005d8a210d"],"state_sha256":"b3e78f9d42c6358564b550d8280955260549e39375c036efb0fcdb6066b3b690"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xWS/KHdO3WgVtEptDv9GWFK7yRQbyl9xm08YPhf7yJoYyvaVzlb1XtLEdk5qGuotkVhYgh3w1ew/WuL+ZOuwBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T05:15:57.738396Z","bundle_sha256":"9d35800674f5f6905117ce38a972ef90b14b47371875c32bf3ae7a1ad7cabf81"}}