{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6RASYPHO7UT6FTWBAKNPXDV3TE","short_pith_number":"pith:6RASYPHO","schema_version":"1.0","canonical_sha256":"f4412c3ceefd27e2cec1029afb8ebb99229ab5b4e87a300eb7a30a76661d46b4","source":{"kind":"arxiv","id":"2603.02719","version":4},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2603.02719","created_at":"2026-05-25T02:01:16.410358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.02719v4","created_at":"2026-05-25T02:01:16.410358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.02719","created_at":"2026-05-25T02:01:16.410358+00:00"},{"alias_kind":"pith_short_12","alias_value":"6RASYPHO7UT6","created_at":"2026-05-25T02:01:16.410358+00:00"},{"alias_kind":"pith_short_16","alias_value":"6RASYPHO7UT6FTWB","created_at":"2026-05-25T02:01:16.410358+00:00"},{"alias_kind":"pith_short_8","alias_value":"6RASYPHO","created_at":"2026-05-25T02:01:16.410358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6RASYPHO7UT6FTWBAKNPXDV3TE","json":"https://pith.science/pith/6RASYPHO7UT6FTWBAKNPXDV3TE.json","graph_json":"https://pith.science/api/pith-number/6RASYPHO7UT6FTWBAKNPXDV3TE/graph.json","events_json":"https://pith.science/api/pith-number/6RASYPHO7UT6FTWBAKNPXDV3TE/events.json","paper":"https://pith.science/paper/6RASYPHO"},"agent_actions":{"view_html":"https://pith.science/pith/6RASYPHO7UT6FTWBAKNPXDV3TE","download_json":"https://pith.science/pith/6RASYPHO7UT6FTWBAKNPXDV3TE.json","view_paper":"https://pith.science/paper/6RASYPHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.02719&json=true","fetch_graph":"https://pith.science/api/pith-number/6RASYPHO7UT6FTWBAKNPXDV3TE/graph.json","fetch_events":"https://pith.science/api/pith-number/6RASYPHO7UT6FTWBAKNPXDV3TE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6RASYPHO7UT6FTWBAKNPXDV3TE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6RASYPHO7UT6FTWBAKNPXDV3TE/action/storage_attestation","attest_author":"https://pith.science/pith/6RASYPHO7UT6FTWBAKNPXDV3TE/action/author_attestation","sign_citation":"https://pith.science/pith/6RASYPHO7UT6FTWBAKNPXDV3TE/action/citation_signature","submit_replication":"https://pith.science/pith/6RASYPHO7UT6FTWBAKNPXDV3TE/action/replication_record"}},"created_at":"2026-05-25T02:01:16.410358+00:00","updated_at":"2026-05-25T02:01:16.410358+00:00"}