{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3S3KQ4S67QSABTZIYTI2CJBZC3","short_pith_number":"pith:3S3KQ4S6","schema_version":"1.0","canonical_sha256":"dcb6a8725efc2400cf28c4d1a1243916cba6fbb3a947921a218b722e512d8b92","source":{"kind":"arxiv","id":"2408.01382","version":3},"attestation_state":"computed","paper":{"title":"Explaining a probabilistic prediction on the simplex with Shapley compositions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Jean-Fran\\c{c}ois Bonastre, Miquel Perell\\'o-Nieto, Paul-Gauthier No\\'e, Peter Flach","submitted_at":"2024-08-02T16:40:58Z","abstract_excerpt":"Originating in game theory, Shapley values are widely used for explaining a machine learning model's prediction by quantifying the contribution of each feature's value to the prediction. This requires a scalar prediction as in binary classification, whereas a multiclass probabilistic prediction is a discrete probability distribution, living on a multidimensional simplex. In such a multiclass setting the Shapley values are typically computed separately on each class in a one-vs-rest manner, ignoring the compositional nature of the output distribution. In this paper, we introduce Shapley composi"},"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":"2408.01382","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-02T16:40:58Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"754985c00799ea8f1f393ae3c3baab4db3ce71c2ad77d1c14b3e60b402b18332","abstract_canon_sha256":"a2ba07c0c45fcaecd8bb2066fa67fd24413446f69e9b517e0d667fdb624640be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:25.896760Z","signature_b64":"noCs4Zsn2RFE+L15tfWOfU5BJoI30NN5P2HAhaNxBeRCsQZl6s1XskKnIlGHpmiUfWgtg4/6H7aYjawM3zfEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcb6a8725efc2400cf28c4d1a1243916cba6fbb3a947921a218b722e512d8b92","last_reissued_at":"2026-06-04T01:08:25.895771Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:25.895771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explaining a probabilistic prediction on the simplex with Shapley compositions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Jean-Fran\\c{c}ois Bonastre, Miquel Perell\\'o-Nieto, Paul-Gauthier No\\'e, Peter Flach","submitted_at":"2024-08-02T16:40:58Z","abstract_excerpt":"Originating in game theory, Shapley values are widely used for explaining a machine learning model's prediction by quantifying the contribution of each feature's value to the prediction. This requires a scalar prediction as in binary classification, whereas a multiclass probabilistic prediction is a discrete probability distribution, living on a multidimensional simplex. In such a multiclass setting the Shapley values are typically computed separately on each class in a one-vs-rest manner, ignoring the compositional nature of the output distribution. In this paper, we introduce Shapley composi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01382","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/2408.01382/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":"2408.01382","created_at":"2026-06-04T01:08:25.895917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.01382v3","created_at":"2026-06-04T01:08:25.895917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01382","created_at":"2026-06-04T01:08:25.895917+00:00"},{"alias_kind":"pith_short_12","alias_value":"3S3KQ4S67QSA","created_at":"2026-06-04T01:08:25.895917+00:00"},{"alias_kind":"pith_short_16","alias_value":"3S3KQ4S67QSABTZI","created_at":"2026-06-04T01:08:25.895917+00:00"},{"alias_kind":"pith_short_8","alias_value":"3S3KQ4S6","created_at":"2026-06-04T01:08:25.895917+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3S3KQ4S67QSABTZIYTI2CJBZC3","json":"https://pith.science/pith/3S3KQ4S67QSABTZIYTI2CJBZC3.json","graph_json":"https://pith.science/api/pith-number/3S3KQ4S67QSABTZIYTI2CJBZC3/graph.json","events_json":"https://pith.science/api/pith-number/3S3KQ4S67QSABTZIYTI2CJBZC3/events.json","paper":"https://pith.science/paper/3S3KQ4S6"},"agent_actions":{"view_html":"https://pith.science/pith/3S3KQ4S67QSABTZIYTI2CJBZC3","download_json":"https://pith.science/pith/3S3KQ4S67QSABTZIYTI2CJBZC3.json","view_paper":"https://pith.science/paper/3S3KQ4S6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.01382&json=true","fetch_graph":"https://pith.science/api/pith-number/3S3KQ4S67QSABTZIYTI2CJBZC3/graph.json","fetch_events":"https://pith.science/api/pith-number/3S3KQ4S67QSABTZIYTI2CJBZC3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3S3KQ4S67QSABTZIYTI2CJBZC3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3S3KQ4S67QSABTZIYTI2CJBZC3/action/storage_attestation","attest_author":"https://pith.science/pith/3S3KQ4S67QSABTZIYTI2CJBZC3/action/author_attestation","sign_citation":"https://pith.science/pith/3S3KQ4S67QSABTZIYTI2CJBZC3/action/citation_signature","submit_replication":"https://pith.science/pith/3S3KQ4S67QSABTZIYTI2CJBZC3/action/replication_record"}},"created_at":"2026-06-04T01:08:25.895917+00:00","updated_at":"2026-06-04T01:08:25.895917+00:00"}