{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6RASYPHO7UT6FTWBAKNPXDV3TE","short_pith_number":"pith:6RASYPHO","canonical_record":{"source":{"id":"2603.02719","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-03T08:16:44Z","cross_cats_sorted":[],"title_canon_sha256":"5e02b3714c0b0fb9b21434dc387c6521ff0d270d6dba06fe3ddeb9f511df5d91","abstract_canon_sha256":"ea305a5cea27fb3d5703ffed1c72aee4ca1dbc2475c67d50f32bc61297b262a6"},"schema_version":"1.0"},"canonical_sha256":"f4412c3ceefd27e2cec1029afb8ebb99229ab5b4e87a300eb7a30a76661d46b4","source":{"kind":"arxiv","id":"2603.02719","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.02719","created_at":"2026-05-25T02:01:16Z"},{"alias_kind":"arxiv_version","alias_value":"2603.02719v4","created_at":"2026-05-25T02:01:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.02719","created_at":"2026-05-25T02:01:16Z"},{"alias_kind":"pith_short_12","alias_value":"6RASYPHO7UT6","created_at":"2026-05-25T02:01:16Z"},{"alias_kind":"pith_short_16","alias_value":"6RASYPHO7UT6FTWB","created_at":"2026-05-25T02:01:16Z"},{"alias_kind":"pith_short_8","alias_value":"6RASYPHO","created_at":"2026-05-25T02:01:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6RASYPHO7UT6FTWBAKNPXDV3TE","target":"record","payload":{"canonical_record":{"source":{"id":"2603.02719","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-03T08:16:44Z","cross_cats_sorted":[],"title_canon_sha256":"5e02b3714c0b0fb9b21434dc387c6521ff0d270d6dba06fe3ddeb9f511df5d91","abstract_canon_sha256":"ea305a5cea27fb3d5703ffed1c72aee4ca1dbc2475c67d50f32bc61297b262a6"},"schema_version":"1.0"},"canonical_sha256":"f4412c3ceefd27e2cec1029afb8ebb99229ab5b4e87a300eb7a30a76661d46b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:16.410959Z","signature_b64":"HGhLfeSFSPqHGEr8E0pPlFs/yK6En8IdnGr8Jy9t4I02qsReYO8TmV3wpacRwCLF7VJ1ceT6mMtngEInPYDFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4412c3ceefd27e2cec1029afb8ebb99229ab5b4e87a300eb7a30a76661d46b4","last_reissued_at":"2026-05-25T02:01:16.410236Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:16.410236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.02719","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:01:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D1NRbIZgtxuMz2wCcZeE665bUdGBgYcuDp7CkLfln9NedcCB97T26deBsZ+uD+gbj9KpAq4KKB++7HOumjGZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T00:23:33.438085Z"},"content_sha256":"98eeabfa2f0562f352cf98a4a75d40eb549bd44eee01f5315074ed9cd8e3757d","schema_version":"1.0","event_id":"sha256:98eeabfa2f0562f352cf98a4a75d40eb549bd44eee01f5315074ed9cd8e3757d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6RASYPHO7UT6FTWBAKNPXDV3TE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Empirical Analysis of Calibration and Selective Prediction in Multimodal Clinical Condition Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Selective prediction degrades performance in multimodal clinical condition classification due to class-dependent miscalibration.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Farah E. Shamout, L. Juli\\'an Lechuga L\\'opez, Tim G. J. Rudner","submitted_at":"2026-03-03T08:16:44Z","abstract_excerpt":"As artificial intelligence systems move toward clinical deployment, ensuring reliable prediction behavior is fundamental for safety-critical decision-making tasks. One proposed safeguard is selective prediction, where models can defer uncertain predictions to human experts for review. In this work, we empirically evaluate the reliability of uncertainty-based selective prediction in multilabel clinical condition classification using multimodal ICU data. Across a range of state-of-the-art unimodal and multimodal models, we find that selective prediction can substantially degrade performance desp"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"selective prediction can substantially degrade performance despite strong standard evaluation metrics. This failure is driven by severe class-dependent miscalibration, whereby models assign high uncertainty to correct predictions and low uncertainty to incorrect ones, particularly for underrepresented clinical conditions.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that the tested unimodal and multimodal models and the specific ICU dataset splits are representative enough to generalize the miscalibration failure mode to broader clinical deployment scenarios.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Selective prediction degrades performance in multimodal clinical condition classification due to class-dependent miscalibration that assigns high uncertainty to correct predictions and low uncertainty to incorrect ones.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Selective prediction degrades performance in multimodal clinical condition classification due to class-dependent miscalibration.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"facc65be53f068b0b2c03ac239f1c93aa09a1c003ee33e31d115b666ef5950e7"},"source":{"id":"2603.02719","kind":"arxiv","version":4},"verdict":{"id":"4de4ad46-b29d-43af-aa5a-77ee3c29c9b7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T16:37:55.521039Z","strongest_claim":"selective prediction can substantially degrade performance despite strong standard evaluation metrics. This failure is driven by severe class-dependent miscalibration, whereby models assign high uncertainty to correct predictions and low uncertainty to incorrect ones, particularly for underrepresented clinical conditions.","one_line_summary":"Selective prediction degrades performance in multimodal clinical condition classification due to class-dependent miscalibration that assigns high uncertainty to correct predictions and low uncertainty to incorrect ones.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that the tested unimodal and multimodal models and the specific ICU dataset splits are representative enough to generalize the miscalibration failure mode to broader clinical deployment scenarios.","pith_extraction_headline":"Selective prediction degrades performance in multimodal clinical condition classification due to class-dependent miscalibration."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.02719/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":2,"snapshot_sha256":"827e4d79f4d02844342a709227af034737b21c21aa3e60147cb640f5a4e39f26"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"4de4ad46-b29d-43af-aa5a-77ee3c29c9b7"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:01:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oIqRLjlrV3sbhE7DbrXTddlc4tLRHHE4ToiwQMg1jFzxSXk+tpVlR2cv2hw8AwZSYHlrI/WjJUkiKjFb/32+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T00:23:33.438554Z"},"content_sha256":"e54ab28c6072e58f71da13eb7b5ee2a8978914484f342ccfdd7da92dab2aef1a","schema_version":"1.0","event_id":"sha256:e54ab28c6072e58f71da13eb7b5ee2a8978914484f342ccfdd7da92dab2aef1a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6RASYPHO7UT6FTWBAKNPXDV3TE/bundle.json","state_url":"https://pith.science/pith/6RASYPHO7UT6FTWBAKNPXDV3TE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6RASYPHO7UT6FTWBAKNPXDV3TE/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":"2026-06-09T00:23:33Z","links":{"resolver":"https://pith.science/pith/6RASYPHO7UT6FTWBAKNPXDV3TE","bundle":"https://pith.science/pith/6RASYPHO7UT6FTWBAKNPXDV3TE/bundle.json","state":"https://pith.science/pith/6RASYPHO7UT6FTWBAKNPXDV3TE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6RASYPHO7UT6FTWBAKNPXDV3TE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6RASYPHO7UT6FTWBAKNPXDV3TE","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":"ea305a5cea27fb3d5703ffed1c72aee4ca1dbc2475c67d50f32bc61297b262a6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-03T08:16:44Z","title_canon_sha256":"5e02b3714c0b0fb9b21434dc387c6521ff0d270d6dba06fe3ddeb9f511df5d91"},"schema_version":"1.0","source":{"id":"2603.02719","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.02719","created_at":"2026-05-25T02:01:16Z"},{"alias_kind":"arxiv_version","alias_value":"2603.02719v4","created_at":"2026-05-25T02:01:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.02719","created_at":"2026-05-25T02:01:16Z"},{"alias_kind":"pith_short_12","alias_value":"6RASYPHO7UT6","created_at":"2026-05-25T02:01:16Z"},{"alias_kind":"pith_short_16","alias_value":"6RASYPHO7UT6FTWB","created_at":"2026-05-25T02:01:16Z"},{"alias_kind":"pith_short_8","alias_value":"6RASYPHO","created_at":"2026-05-25T02:01:16Z"}],"graph_snapshots":[{"event_id":"sha256:e54ab28c6072e58f71da13eb7b5ee2a8978914484f342ccfdd7da92dab2aef1a","target":"graph","created_at":"2026-05-25T02:01:16Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"selective prediction can substantially degrade performance despite strong standard evaluation metrics. This failure is driven by severe class-dependent miscalibration, whereby models assign high uncertainty to correct predictions and low uncertainty to incorrect ones, particularly for underrepresented clinical conditions."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the tested unimodal and multimodal models and the specific ICU dataset splits are representative enough to generalize the miscalibration failure mode to broader clinical deployment scenarios."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Selective prediction degrades performance in multimodal clinical condition classification due to class-dependent miscalibration that assigns high uncertainty to correct predictions and low uncertainty to incorrect ones."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Selective prediction degrades performance in multimodal clinical condition classification due to class-dependent miscalibration."}],"snapshot_sha256":"facc65be53f068b0b2c03ac239f1c93aa09a1c003ee33e31d115b666ef5950e7"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"827e4d79f4d02844342a709227af034737b21c21aa3e60147cb640f5a4e39f26"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.02719/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As artificial intelligence systems move toward clinical deployment, ensuring reliable prediction behavior is fundamental for safety-critical decision-making tasks. One proposed safeguard is selective prediction, where models can defer uncertain predictions to human experts for review. In this work, we empirically evaluate the reliability of uncertainty-based selective prediction in multilabel clinical condition classification using multimodal ICU data. Across a range of state-of-the-art unimodal and multimodal models, we find that selective prediction can substantially degrade performance desp","authors_text":"Farah E. Shamout, L. Juli\\'an Lechuga L\\'opez, Tim G. J. Rudner","cross_cats":[],"headline":"Selective prediction degrades performance in multimodal clinical condition classification due to class-dependent miscalibration.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-03T08:16:44Z","title":"An Empirical Analysis of Calibration and Selective Prediction in Multimodal Clinical Condition Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.02719","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-15T16:37:55.521039Z","id":"4de4ad46-b29d-43af-aa5a-77ee3c29c9b7","model_set":{"reader":"grok-4.3"},"one_line_summary":"Selective prediction degrades performance in multimodal clinical condition classification due to class-dependent miscalibration that assigns high uncertainty to correct predictions and low uncertainty to incorrect ones.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Selective prediction degrades performance in multimodal clinical condition classification due to class-dependent miscalibration.","strongest_claim":"selective prediction can substantially degrade performance despite strong standard evaluation metrics. This failure is driven by severe class-dependent miscalibration, whereby models assign high uncertainty to correct predictions and low uncertainty to incorrect ones, particularly for underrepresented clinical conditions.","weakest_assumption":"The assumption that the tested unimodal and multimodal models and the specific ICU dataset splits are representative enough to generalize the miscalibration failure mode to broader clinical deployment scenarios."}},"verdict_id":"4de4ad46-b29d-43af-aa5a-77ee3c29c9b7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:98eeabfa2f0562f352cf98a4a75d40eb549bd44eee01f5315074ed9cd8e3757d","target":"record","created_at":"2026-05-25T02:01:16Z","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":"ea305a5cea27fb3d5703ffed1c72aee4ca1dbc2475c67d50f32bc61297b262a6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-03T08:16:44Z","title_canon_sha256":"5e02b3714c0b0fb9b21434dc387c6521ff0d270d6dba06fe3ddeb9f511df5d91"},"schema_version":"1.0","source":{"id":"2603.02719","kind":"arxiv","version":4}},"canonical_sha256":"f4412c3ceefd27e2cec1029afb8ebb99229ab5b4e87a300eb7a30a76661d46b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4412c3ceefd27e2cec1029afb8ebb99229ab5b4e87a300eb7a30a76661d46b4","first_computed_at":"2026-05-25T02:01:16.410236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:16.410236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HGhLfeSFSPqHGEr8E0pPlFs/yK6En8IdnGr8Jy9t4I02qsReYO8TmV3wpacRwCLF7VJ1ceT6mMtngEInPYDFAQ==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:16.410959Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.02719","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98eeabfa2f0562f352cf98a4a75d40eb549bd44eee01f5315074ed9cd8e3757d","sha256:e54ab28c6072e58f71da13eb7b5ee2a8978914484f342ccfdd7da92dab2aef1a"],"state_sha256":"eba28d1f87a19c3211e6adc7c0969402a494518c37b516f07ac040b6e7940fee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gi58US8XhaUQJh/yn93Uc+4lbG+fIFOTKg+ZXW/KgMOaTZrmRyFfamg6KBlo/RbookIj6MEWk3umXPdIaPPGBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T00:23:33.440809Z","bundle_sha256":"2787c9623a94875677c7627e2e9182219ebef0bd17648da5af2417230496f2a8"}}