{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GFLOF46FU76FMQUHCA6ONBVQPU","short_pith_number":"pith:GFLOF46F","schema_version":"1.0","canonical_sha256":"3156e2f3c5a7fc564287103ce686b07d319c47b79ef462aed79b9da3c516088b","source":{"kind":"arxiv","id":"2505.13118","version":1},"attestation_state":"computed","paper":{"title":"Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Agathe Fernandes Machado (UQAM), Arthur Charpentier (UQAM), Ewen Gallic (AMSE), IID), Marouane Il Idrissi (UQAM","submitted_at":"2025-05-19T13:49:05Z","abstract_excerpt":"Cooperative game theory methods, notably Shapley values, have significantly enhanced machine learning (ML) interpretability. However, existing explainable AI (XAI) frameworks mainly attribute average model predictions, overlooking predictive uncertainty. This work addresses that gap by proposing a novel, model-agnostic uncertainty attribution (UA) method grounded in conformal prediction (CP). By defining cooperative games where CP interval properties-such as width and bounds-serve as value functions, we systematically attribute predictive uncertainty to input features. Extending beyond the tra"},"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":false},"canonical_record":{"source":{"id":"2505.13118","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T13:49:05Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"22df5eb759bf86c2571a189e6ca53df4c7b8b7d3b0b666daebff99ec46393dc9","abstract_canon_sha256":"b60c278cf5d9257508abfc83c48ff55720e466dcd1b72a6ecbc8fe5164147aaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:25.448746Z","signature_b64":"eyGxKZgJRttpq8169MSsEORJ2FwvykGCM3e4G0I0YEhbbuVjgLda4BeIIrJ0tVnOYrXt0xnnOVuQekQzP+thAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3156e2f3c5a7fc564287103ce686b07d319c47b79ef462aed79b9da3c516088b","last_reissued_at":"2026-07-05T11:05:25.448273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:25.448273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Agathe Fernandes Machado (UQAM), Arthur Charpentier (UQAM), Ewen Gallic (AMSE), IID), Marouane Il Idrissi (UQAM","submitted_at":"2025-05-19T13:49:05Z","abstract_excerpt":"Cooperative game theory methods, notably Shapley values, have significantly enhanced machine learning (ML) interpretability. However, existing explainable AI (XAI) frameworks mainly attribute average model predictions, overlooking predictive uncertainty. This work addresses that gap by proposing a novel, model-agnostic uncertainty attribution (UA) method grounded in conformal prediction (CP). By defining cooperative games where CP interval properties-such as width and bounds-serve as value functions, we systematically attribute predictive uncertainty to input features. Extending beyond the tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13118","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/2505.13118/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.13118","created_at":"2026-07-05T11:05:25.448344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13118v1","created_at":"2026-07-05T11:05:25.448344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13118","created_at":"2026-07-05T11:05:25.448344+00:00"},{"alias_kind":"pith_short_12","alias_value":"GFLOF46FU76F","created_at":"2026-07-05T11:05:25.448344+00:00"},{"alias_kind":"pith_short_16","alias_value":"GFLOF46FU76FMQUH","created_at":"2026-07-05T11:05:25.448344+00:00"},{"alias_kind":"pith_short_8","alias_value":"GFLOF46F","created_at":"2026-07-05T11:05:25.448344+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14240","citing_title":"Interpretable and Explainable Surrogate Modeling for Simulations: A State-of-the-Art Survey and Perspectives on Explainable AI for Decision-Making","ref_index":124,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GFLOF46FU76FMQUHCA6ONBVQPU","json":"https://pith.science/pith/GFLOF46FU76FMQUHCA6ONBVQPU.json","graph_json":"https://pith.science/api/pith-number/GFLOF46FU76FMQUHCA6ONBVQPU/graph.json","events_json":"https://pith.science/api/pith-number/GFLOF46FU76FMQUHCA6ONBVQPU/events.json","paper":"https://pith.science/paper/GFLOF46F"},"agent_actions":{"view_html":"https://pith.science/pith/GFLOF46FU76FMQUHCA6ONBVQPU","download_json":"https://pith.science/pith/GFLOF46FU76FMQUHCA6ONBVQPU.json","view_paper":"https://pith.science/paper/GFLOF46F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13118&json=true","fetch_graph":"https://pith.science/api/pith-number/GFLOF46FU76FMQUHCA6ONBVQPU/graph.json","fetch_events":"https://pith.science/api/pith-number/GFLOF46FU76FMQUHCA6ONBVQPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GFLOF46FU76FMQUHCA6ONBVQPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GFLOF46FU76FMQUHCA6ONBVQPU/action/storage_attestation","attest_author":"https://pith.science/pith/GFLOF46FU76FMQUHCA6ONBVQPU/action/author_attestation","sign_citation":"https://pith.science/pith/GFLOF46FU76FMQUHCA6ONBVQPU/action/citation_signature","submit_replication":"https://pith.science/pith/GFLOF46FU76FMQUHCA6ONBVQPU/action/replication_record"}},"created_at":"2026-07-05T11:05:25.448344+00:00","updated_at":"2026-07-05T11:05:25.448344+00:00"}