{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:M3SJQVI4MDNAHOKWFEGIE5U2HK","short_pith_number":"pith:M3SJQVI4","canonical_record":{"source":{"id":"2506.23298","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2025-06-29T15:37:17Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"51e45b0c2df514a65cd5b0d3fb3a795166eb5e822b5256fff02491761ad77265","abstract_canon_sha256":"340984524a69dd0577f96a4de9086e213fae544d4147914a0e99e6f6f8bcc513"},"schema_version":"1.0"},"canonical_sha256":"66e498551c60da03b956290c82769a3a853d39c3f7850fb4704a6b9d59ee74b9","source":{"kind":"arxiv","id":"2506.23298","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23298","created_at":"2026-07-05T11:39:55Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23298v3","created_at":"2026-07-05T11:39:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23298","created_at":"2026-07-05T11:39:55Z"},{"alias_kind":"pith_short_12","alias_value":"M3SJQVI4MDNA","created_at":"2026-07-05T11:39:55Z"},{"alias_kind":"pith_short_16","alias_value":"M3SJQVI4MDNAHOKW","created_at":"2026-07-05T11:39:55Z"},{"alias_kind":"pith_short_8","alias_value":"M3SJQVI4","created_at":"2026-07-05T11:39:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:M3SJQVI4MDNAHOKWFEGIE5U2HK","target":"record","payload":{"canonical_record":{"source":{"id":"2506.23298","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2025-06-29T15:37:17Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"51e45b0c2df514a65cd5b0d3fb3a795166eb5e822b5256fff02491761ad77265","abstract_canon_sha256":"340984524a69dd0577f96a4de9086e213fae544d4147914a0e99e6f6f8bcc513"},"schema_version":"1.0"},"canonical_sha256":"66e498551c60da03b956290c82769a3a853d39c3f7850fb4704a6b9d59ee74b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:55.709924Z","signature_b64":"MP1gikWfAPiAS34NW66yoV1+K+GdCjRmQhQ7dxQEb63ga9TyNvINYQnEDtZyYS4S+FMDJAsBpLap75vT7RKTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66e498551c60da03b956290c82769a3a853d39c3f7850fb4704a6b9d59ee74b9","last_reissued_at":"2026-07-05T11:39:55.709467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:55.709467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.23298","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:39:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oKfCmkKa9zqbS9kMvhWBITujkRa5d5FXgeVx1DI6IQxoMtgpsR3YYapQzVIVlZlt0fs6TP4P1ukfb3WAJe2ICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:59:23.161688Z"},"content_sha256":"415fc0ef1b37216e3966a41d2978fb2d69ed2bdb327ed8ed245035b53c352aa8","schema_version":"1.0","event_id":"sha256:415fc0ef1b37216e3966a41d2978fb2d69ed2bdb327ed8ed245035b53c352aa8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:M3SJQVI4MDNAHOKWFEGIE5U2HK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exposing and Mitigating Calibration Biases and Demographic Unfairness in MLLM Few-Shot In-Context Learning for Medical Image Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"eess.IV","authors_text":"Hengguan Huang, Justin Szeto, Mingyang Li, Tal Arbel, Xing Shen","submitted_at":"2025-06-29T15:37:17Z","abstract_excerpt":"Multimodal large language models (MLLMs) have enormous potential to perform few-shot in-context learning in the context of medical image analysis. However, safe deployment of these models into real-world clinical practice requires an in-depth analysis of the accuracies of their predictions, and their associated calibration errors, particularly across different demographic subgroups. In this work, we present the first investigation into the calibration biases and demographic unfairness of MLLMs' predictions and confidence scores in few-shot in-context learning for medical image classification. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23298","kind":"arxiv","version":3},"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/2506.23298/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":"2026-07-05T11:39:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uUsQcIyhq4k2O8/v/m1SqwvVZffyeuoRyNU+ME5VjUiTDWgzSOU1dOVZiULcE+SFbLW6VoO4w4XbxC+/vZJsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:59:23.162287Z"},"content_sha256":"bb6afe1854f81d7019545c10cf8b5cc008d0f364023821edd7540be770c00438","schema_version":"1.0","event_id":"sha256:bb6afe1854f81d7019545c10cf8b5cc008d0f364023821edd7540be770c00438"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M3SJQVI4MDNAHOKWFEGIE5U2HK/bundle.json","state_url":"https://pith.science/pith/M3SJQVI4MDNAHOKWFEGIE5U2HK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M3SJQVI4MDNAHOKWFEGIE5U2HK/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":"2026-08-15T18:59:23Z","links":{"resolver":"https://pith.science/pith/M3SJQVI4MDNAHOKWFEGIE5U2HK","bundle":"https://pith.science/pith/M3SJQVI4MDNAHOKWFEGIE5U2HK/bundle.json","state":"https://pith.science/pith/M3SJQVI4MDNAHOKWFEGIE5U2HK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M3SJQVI4MDNAHOKWFEGIE5U2HK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M3SJQVI4MDNAHOKWFEGIE5U2HK","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":"340984524a69dd0577f96a4de9086e213fae544d4147914a0e99e6f6f8bcc513","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2025-06-29T15:37:17Z","title_canon_sha256":"51e45b0c2df514a65cd5b0d3fb3a795166eb5e822b5256fff02491761ad77265"},"schema_version":"1.0","source":{"id":"2506.23298","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23298","created_at":"2026-07-05T11:39:55Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23298v3","created_at":"2026-07-05T11:39:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23298","created_at":"2026-07-05T11:39:55Z"},{"alias_kind":"pith_short_12","alias_value":"M3SJQVI4MDNA","created_at":"2026-07-05T11:39:55Z"},{"alias_kind":"pith_short_16","alias_value":"M3SJQVI4MDNAHOKW","created_at":"2026-07-05T11:39:55Z"},{"alias_kind":"pith_short_8","alias_value":"M3SJQVI4","created_at":"2026-07-05T11:39:55Z"}],"graph_snapshots":[{"event_id":"sha256:bb6afe1854f81d7019545c10cf8b5cc008d0f364023821edd7540be770c00438","target":"graph","created_at":"2026-07-05T11:39:55Z","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/2506.23298/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have enormous potential to perform few-shot in-context learning in the context of medical image analysis. However, safe deployment of these models into real-world clinical practice requires an in-depth analysis of the accuracies of their predictions, and their associated calibration errors, particularly across different demographic subgroups. In this work, we present the first investigation into the calibration biases and demographic unfairness of MLLMs' predictions and confidence scores in few-shot in-context learning for medical image classification. ","authors_text":"Hengguan Huang, Justin Szeto, Mingyang Li, Tal Arbel, Xing Shen","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2025-06-29T15:37:17Z","title":"Exposing and Mitigating Calibration Biases and Demographic Unfairness in MLLM Few-Shot In-Context Learning for Medical Image Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23298","kind":"arxiv","version":3},"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":"sha256:415fc0ef1b37216e3966a41d2978fb2d69ed2bdb327ed8ed245035b53c352aa8","target":"record","created_at":"2026-07-05T11:39:55Z","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":"340984524a69dd0577f96a4de9086e213fae544d4147914a0e99e6f6f8bcc513","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2025-06-29T15:37:17Z","title_canon_sha256":"51e45b0c2df514a65cd5b0d3fb3a795166eb5e822b5256fff02491761ad77265"},"schema_version":"1.0","source":{"id":"2506.23298","kind":"arxiv","version":3}},"canonical_sha256":"66e498551c60da03b956290c82769a3a853d39c3f7850fb4704a6b9d59ee74b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66e498551c60da03b956290c82769a3a853d39c3f7850fb4704a6b9d59ee74b9","first_computed_at":"2026-07-05T11:39:55.709467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:55.709467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MP1gikWfAPiAS34NW66yoV1+K+GdCjRmQhQ7dxQEb63ga9TyNvINYQnEDtZyYS4S+FMDJAsBpLap75vT7RKTBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:55.709924Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23298","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:415fc0ef1b37216e3966a41d2978fb2d69ed2bdb327ed8ed245035b53c352aa8","sha256:bb6afe1854f81d7019545c10cf8b5cc008d0f364023821edd7540be770c00438"],"state_sha256":"4ba94687738d99cb915c32670fbd6ce5f5cc54d65a2c8ffb451d86c0a8bb3842"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hArUSSPx3PvSARkx8uc4Mc4m6kOy7N3ftdvjGhW7oRPQpDIOjTEzJWz85JZVDslG4VZ1dLL6RnU8SpNcCglJAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T18:59:23.167294Z","bundle_sha256":"3713857ad9fe6efdbef44e6d8e7fea2374ea25f44aa283046a7d1af502d65f1f"}}