{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YH2UJUCFWU4TEGQDM5BX4LIXGR","short_pith_number":"pith:YH2UJUCF","schema_version":"1.0","canonical_sha256":"c1f544d045b539321a0367437e2d1734613f1b63aa294da8d25657a5d54e3993","source":{"kind":"arxiv","id":"2201.01044","version":2},"attestation_state":"computed","paper":{"title":"McXai: Local model-agnostic explanation as two games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Likun Fang, Michael Beigl, Michael Hefenbrock, Nicole Schaal, Till Riedel, Yexu Zhou, Yiran Huang","submitted_at":"2022-01-04T09:02:48Z","abstract_excerpt":"To this day, a variety of approaches for providing local interpretability of black-box machine learning models have been introduced. Unfortunately, all of these methods suffer from one or more of the following deficiencies: They are either difficult to understand themselves, they work on a per-feature basis and ignore the dependencies between features and/or they only focus on those features asserting the decision made by the model. To address these points, this work introduces a reinforcement learning-based approach called Monte Carlo tree search for eXplainable Artificial Intelligent (McXai)"},"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":"2201.01044","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-04T09:02:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f6be71179f4a3c9379d1dcd710e0af5f394d751144ec12a992293b674bef774c","abstract_canon_sha256":"cf7256d66289563332818c74b16b955b77d900f30ebcc474cd268cd5604ca835"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:22.331518Z","signature_b64":"3g4TNlmnJwfnxc0nlFBO+L1mgLqDb//U8r+IVqWhNyqI3lojK+PaCScs15BUjwwbwJ1Q7SwO7w6t1RKrcLs4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1f544d045b539321a0367437e2d1734613f1b63aa294da8d25657a5d54e3993","last_reissued_at":"2026-07-05T04:02:22.330985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:22.330985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"McXai: Local model-agnostic explanation as two games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Likun Fang, Michael Beigl, Michael Hefenbrock, Nicole Schaal, Till Riedel, Yexu Zhou, Yiran Huang","submitted_at":"2022-01-04T09:02:48Z","abstract_excerpt":"To this day, a variety of approaches for providing local interpretability of black-box machine learning models have been introduced. Unfortunately, all of these methods suffer from one or more of the following deficiencies: They are either difficult to understand themselves, they work on a per-feature basis and ignore the dependencies between features and/or they only focus on those features asserting the decision made by the model. To address these points, this work introduces a reinforcement learning-based approach called Monte Carlo tree search for eXplainable Artificial Intelligent (McXai)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01044","kind":"arxiv","version":2},"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/2201.01044/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":"2201.01044","created_at":"2026-07-05T04:02:22.331046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.01044v2","created_at":"2026-07-05T04:02:22.331046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01044","created_at":"2026-07-05T04:02:22.331046+00:00"},{"alias_kind":"pith_short_12","alias_value":"YH2UJUCFWU4T","created_at":"2026-07-05T04:02:22.331046+00:00"},{"alias_kind":"pith_short_16","alias_value":"YH2UJUCFWU4TEGQD","created_at":"2026-07-05T04:02:22.331046+00:00"},{"alias_kind":"pith_short_8","alias_value":"YH2UJUCF","created_at":"2026-07-05T04:02:22.331046+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/YH2UJUCFWU4TEGQDM5BX4LIXGR","json":"https://pith.science/pith/YH2UJUCFWU4TEGQDM5BX4LIXGR.json","graph_json":"https://pith.science/api/pith-number/YH2UJUCFWU4TEGQDM5BX4LIXGR/graph.json","events_json":"https://pith.science/api/pith-number/YH2UJUCFWU4TEGQDM5BX4LIXGR/events.json","paper":"https://pith.science/paper/YH2UJUCF"},"agent_actions":{"view_html":"https://pith.science/pith/YH2UJUCFWU4TEGQDM5BX4LIXGR","download_json":"https://pith.science/pith/YH2UJUCFWU4TEGQDM5BX4LIXGR.json","view_paper":"https://pith.science/paper/YH2UJUCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.01044&json=true","fetch_graph":"https://pith.science/api/pith-number/YH2UJUCFWU4TEGQDM5BX4LIXGR/graph.json","fetch_events":"https://pith.science/api/pith-number/YH2UJUCFWU4TEGQDM5BX4LIXGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YH2UJUCFWU4TEGQDM5BX4LIXGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YH2UJUCFWU4TEGQDM5BX4LIXGR/action/storage_attestation","attest_author":"https://pith.science/pith/YH2UJUCFWU4TEGQDM5BX4LIXGR/action/author_attestation","sign_citation":"https://pith.science/pith/YH2UJUCFWU4TEGQDM5BX4LIXGR/action/citation_signature","submit_replication":"https://pith.science/pith/YH2UJUCFWU4TEGQDM5BX4LIXGR/action/replication_record"}},"created_at":"2026-07-05T04:02:22.331046+00:00","updated_at":"2026-07-05T04:02:22.331046+00:00"}