{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PBNW7KGWQSACQB3Y4QMGMV3N72","short_pith_number":"pith:PBNW7KGW","canonical_record":{"source":{"id":"2505.03788","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T19:19:21Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"985cd3e36edff4917d4c254e5168cabafd6813082ea36be164a1adf2706ea7a5","abstract_canon_sha256":"5b3e568ffeddcabc52e56fd3fb5269308f36bbee94a1ad429851d4752408689d"},"schema_version":"1.0"},"canonical_sha256":"785b6fa8d68480280778e41866576dfeb611d5f4cd83775b77ec1088bf86dd9e","source":{"kind":"arxiv","id":"2505.03788","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03788","created_at":"2026-07-05T10:59:31Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03788v1","created_at":"2026-07-05T10:59:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03788","created_at":"2026-07-05T10:59:31Z"},{"alias_kind":"pith_short_12","alias_value":"PBNW7KGWQSAC","created_at":"2026-07-05T10:59:31Z"},{"alias_kind":"pith_short_16","alias_value":"PBNW7KGWQSACQB3Y","created_at":"2026-07-05T10:59:31Z"},{"alias_kind":"pith_short_8","alias_value":"PBNW7KGW","created_at":"2026-07-05T10:59:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PBNW7KGWQSACQB3Y4QMGMV3N72","target":"record","payload":{"canonical_record":{"source":{"id":"2505.03788","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T19:19:21Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"985cd3e36edff4917d4c254e5168cabafd6813082ea36be164a1adf2706ea7a5","abstract_canon_sha256":"5b3e568ffeddcabc52e56fd3fb5269308f36bbee94a1ad429851d4752408689d"},"schema_version":"1.0"},"canonical_sha256":"785b6fa8d68480280778e41866576dfeb611d5f4cd83775b77ec1088bf86dd9e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:31.567438Z","signature_b64":"MU4kc5l4qVmFmh8Yma371ih7G4KPpYPj/HJ7q93w7xoGIrkttTgCMoSlvkpVzTbvd8M2iYCssHfCbJISVY1mCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"785b6fa8d68480280778e41866576dfeb611d5f4cd83775b77ec1088bf86dd9e","last_reissued_at":"2026-07-05T10:59:31.566909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:31.566909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.03788","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":"2026-07-05T10:59:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wdUYNq6yVW2rTaYEBGuwUWwxnhX2T9ASuZ3mUq5GNMa11xkOI2ig1cyMLsPFRt05hM7QlsiWbjyG3eM5ul8tDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T22:14:40.718862Z"},"content_sha256":"40ff5a6f69f64e06e27798fab8f48107fcaf03abbcb63c4454703a58420fd3ad","schema_version":"1.0","event_id":"sha256:40ff5a6f69f64e06e27798fab8f48107fcaf03abbcb63c4454703a58420fd3ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PBNW7KGWQSACQB3Y4QMGMV3N72","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Calibrating Uncertainty Quantification of Multi-Modal LLMs using Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Adam D. Cobb, Alexander M. Berenbeim, Anirban Roy, Brian Matejek, Colin Samplawski, Manoj Acharya, Nathaniel D. Bastian, Ramneet Kaur, Susmit Jha, Trilok Padhi","submitted_at":"2025-04-30T19:19:21Z","abstract_excerpt":"We introduce a novel approach for calibrating uncertainty quantification (UQ) tailored for multi-modal large language models (LLMs). Existing state-of-the-art UQ methods rely on consistency among multiple responses generated by the LLM on an input query under diverse settings. However, these approaches often report higher confidence in scenarios where the LLM is consistently incorrect. This leads to a poorly calibrated confidence with respect to accuracy. To address this, we leverage cross-modal consistency in addition to self-consistency to improve the calibration of the multi-modal models. S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03788","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/2505.03788/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":"2026-07-05T10:59:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rumo/iiyxkQHXfmb/YgL3ozjM3qdJuJGVqLKmD7uWsAIg0Ced5y4gYlmrTpcQDAtuxsWRX2cJ9+auvVy3DVuDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T22:14:40.719360Z"},"content_sha256":"8372ffbbeab7660a9689785dc38dd6809629d1ef8f9045169341a7d72f2917da","schema_version":"1.0","event_id":"sha256:8372ffbbeab7660a9689785dc38dd6809629d1ef8f9045169341a7d72f2917da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PBNW7KGWQSACQB3Y4QMGMV3N72/bundle.json","state_url":"https://pith.science/pith/PBNW7KGWQSACQB3Y4QMGMV3N72/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PBNW7KGWQSACQB3Y4QMGMV3N72/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":"2026-08-20T22:14:40Z","links":{"resolver":"https://pith.science/pith/PBNW7KGWQSACQB3Y4QMGMV3N72","bundle":"https://pith.science/pith/PBNW7KGWQSACQB3Y4QMGMV3N72/bundle.json","state":"https://pith.science/pith/PBNW7KGWQSACQB3Y4QMGMV3N72/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PBNW7KGWQSACQB3Y4QMGMV3N72/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PBNW7KGWQSACQB3Y4QMGMV3N72","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":"5b3e568ffeddcabc52e56fd3fb5269308f36bbee94a1ad429851d4752408689d","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T19:19:21Z","title_canon_sha256":"985cd3e36edff4917d4c254e5168cabafd6813082ea36be164a1adf2706ea7a5"},"schema_version":"1.0","source":{"id":"2505.03788","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03788","created_at":"2026-07-05T10:59:31Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03788v1","created_at":"2026-07-05T10:59:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03788","created_at":"2026-07-05T10:59:31Z"},{"alias_kind":"pith_short_12","alias_value":"PBNW7KGWQSAC","created_at":"2026-07-05T10:59:31Z"},{"alias_kind":"pith_short_16","alias_value":"PBNW7KGWQSACQB3Y","created_at":"2026-07-05T10:59:31Z"},{"alias_kind":"pith_short_8","alias_value":"PBNW7KGW","created_at":"2026-07-05T10:59:31Z"}],"graph_snapshots":[{"event_id":"sha256:8372ffbbeab7660a9689785dc38dd6809629d1ef8f9045169341a7d72f2917da","target":"graph","created_at":"2026-07-05T10:59:31Z","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/2505.03788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a novel approach for calibrating uncertainty quantification (UQ) tailored for multi-modal large language models (LLMs). Existing state-of-the-art UQ methods rely on consistency among multiple responses generated by the LLM on an input query under diverse settings. However, these approaches often report higher confidence in scenarios where the LLM is consistently incorrect. This leads to a poorly calibrated confidence with respect to accuracy. To address this, we leverage cross-modal consistency in addition to self-consistency to improve the calibration of the multi-modal models. S","authors_text":"Adam D. Cobb, Alexander M. Berenbeim, Anirban Roy, Brian Matejek, Colin Samplawski, Manoj Acharya, Nathaniel D. Bastian, Ramneet Kaur, Susmit Jha, Trilok Padhi","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T19:19:21Z","title":"Calibrating Uncertainty Quantification of Multi-Modal LLMs using Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03788","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":"sha256:40ff5a6f69f64e06e27798fab8f48107fcaf03abbcb63c4454703a58420fd3ad","target":"record","created_at":"2026-07-05T10:59:31Z","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":"5b3e568ffeddcabc52e56fd3fb5269308f36bbee94a1ad429851d4752408689d","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T19:19:21Z","title_canon_sha256":"985cd3e36edff4917d4c254e5168cabafd6813082ea36be164a1adf2706ea7a5"},"schema_version":"1.0","source":{"id":"2505.03788","kind":"arxiv","version":1}},"canonical_sha256":"785b6fa8d68480280778e41866576dfeb611d5f4cd83775b77ec1088bf86dd9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"785b6fa8d68480280778e41866576dfeb611d5f4cd83775b77ec1088bf86dd9e","first_computed_at":"2026-07-05T10:59:31.566909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:31.566909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MU4kc5l4qVmFmh8Yma371ih7G4KPpYPj/HJ7q93w7xoGIrkttTgCMoSlvkpVzTbvd8M2iYCssHfCbJISVY1mCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:31.567438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03788","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40ff5a6f69f64e06e27798fab8f48107fcaf03abbcb63c4454703a58420fd3ad","sha256:8372ffbbeab7660a9689785dc38dd6809629d1ef8f9045169341a7d72f2917da"],"state_sha256":"3b6eb043fdcda03a0b5059e9a8b75e79797a34430b0c7533995dbf6868e7d021"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J6howxHc6Ra19A2OZTwTGSfPxp/AzLcPIgeLo1nGr8KJxBFkdwCVuYXfd+Z6gMEAh1uTXUGAjcNbQEYLwVLxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T22:14:40.723115Z","bundle_sha256":"115b2e6da55617394cbc0b1941083e1d87968eaf45305747be3ef4aefcf00edc"}}