{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RIKW4I4WC4FMETK3KMCSTEUZ3L","short_pith_number":"pith:RIKW4I4W","schema_version":"1.0","canonical_sha256":"8a156e2396170ac24d5b5305299299dac382cdcd77665379b5fe8ec9b25d40d2","source":{"kind":"arxiv","id":"2202.12512","version":1},"attestation_state":"computed","paper":{"title":"MUC-driven Feature Importance Measurement and Adversarial Analysis for Random Forest","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jianqi Shi, Shengchao Qin, Shucen Ma, Yanhong Huang, Zhe Hou","submitted_at":"2022-02-25T06:15:47Z","abstract_excerpt":"The broad adoption of Machine Learning (ML) in security-critical fields demands the explainability of the approach. However, the research on understanding ML models, such as Random Forest (RF), is still in its infant stage. In this work, we leverage formal methods and logical reasoning to develop a novel model-specific method for explaining the prediction of RF. Our approach is centered around Minimal Unsatisfiable Cores (MUC) and provides a comprehensive solution for feature importance, covering local and global aspects, and adversarial sample analysis. Experimental results on several dataset"},"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":"2202.12512","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-25T06:15:47Z","cross_cats_sorted":[],"title_canon_sha256":"98de2e249acd7fb39455d8dd447d3c3f33678d8767af8bcdce8f7753ca67fb94","abstract_canon_sha256":"acd0ec482fa1e0a4e63d33ce0393ead991ab735c36a5726de1e3ea143c99a069"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:00:05.221658Z","signature_b64":"PHM6ABkyAv49c/c7pZpkjLlSw52WrmiZ1GoWdcX09xIEeAnkDkkHJMfJ3bPBtxqGobpLC9OkFBygaL/GQONaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a156e2396170ac24d5b5305299299dac382cdcd77665379b5fe8ec9b25d40d2","last_reissued_at":"2026-07-05T04:00:05.221200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:00:05.221200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MUC-driven Feature Importance Measurement and Adversarial Analysis for Random Forest","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jianqi Shi, Shengchao Qin, Shucen Ma, Yanhong Huang, Zhe Hou","submitted_at":"2022-02-25T06:15:47Z","abstract_excerpt":"The broad adoption of Machine Learning (ML) in security-critical fields demands the explainability of the approach. However, the research on understanding ML models, such as Random Forest (RF), is still in its infant stage. In this work, we leverage formal methods and logical reasoning to develop a novel model-specific method for explaining the prediction of RF. Our approach is centered around Minimal Unsatisfiable Cores (MUC) and provides a comprehensive solution for feature importance, covering local and global aspects, and adversarial sample analysis. Experimental results on several dataset"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.12512","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/2202.12512/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":"2202.12512","created_at":"2026-07-05T04:00:05.221258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.12512v1","created_at":"2026-07-05T04:00:05.221258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.12512","created_at":"2026-07-05T04:00:05.221258+00:00"},{"alias_kind":"pith_short_12","alias_value":"RIKW4I4WC4FM","created_at":"2026-07-05T04:00:05.221258+00:00"},{"alias_kind":"pith_short_16","alias_value":"RIKW4I4WC4FMETK3","created_at":"2026-07-05T04:00:05.221258+00:00"},{"alias_kind":"pith_short_8","alias_value":"RIKW4I4W","created_at":"2026-07-05T04:00:05.221258+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/RIKW4I4WC4FMETK3KMCSTEUZ3L","json":"https://pith.science/pith/RIKW4I4WC4FMETK3KMCSTEUZ3L.json","graph_json":"https://pith.science/api/pith-number/RIKW4I4WC4FMETK3KMCSTEUZ3L/graph.json","events_json":"https://pith.science/api/pith-number/RIKW4I4WC4FMETK3KMCSTEUZ3L/events.json","paper":"https://pith.science/paper/RIKW4I4W"},"agent_actions":{"view_html":"https://pith.science/pith/RIKW4I4WC4FMETK3KMCSTEUZ3L","download_json":"https://pith.science/pith/RIKW4I4WC4FMETK3KMCSTEUZ3L.json","view_paper":"https://pith.science/paper/RIKW4I4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.12512&json=true","fetch_graph":"https://pith.science/api/pith-number/RIKW4I4WC4FMETK3KMCSTEUZ3L/graph.json","fetch_events":"https://pith.science/api/pith-number/RIKW4I4WC4FMETK3KMCSTEUZ3L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RIKW4I4WC4FMETK3KMCSTEUZ3L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RIKW4I4WC4FMETK3KMCSTEUZ3L/action/storage_attestation","attest_author":"https://pith.science/pith/RIKW4I4WC4FMETK3KMCSTEUZ3L/action/author_attestation","sign_citation":"https://pith.science/pith/RIKW4I4WC4FMETK3KMCSTEUZ3L/action/citation_signature","submit_replication":"https://pith.science/pith/RIKW4I4WC4FMETK3KMCSTEUZ3L/action/replication_record"}},"created_at":"2026-07-05T04:00:05.221258+00:00","updated_at":"2026-07-05T04:00:05.221258+00:00"}