{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HOE3P6CDQD7E3V4EPW753FZTH3","short_pith_number":"pith:HOE3P6CD","schema_version":"1.0","canonical_sha256":"3b89b7f84380fe4dd7847dbfdd97333ede5add7e29211a6e7e29abda7e5ceb2b","source":{"kind":"arxiv","id":"1907.02509","version":1},"attestation_state":"computed","paper":{"title":"On Validating, Repairing and Refining Heuristic ML Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LO"],"primary_cat":"cs.LG","authors_text":"Alexey Ignatiev, Joao Marques-Silva, Nina Narodytska","submitted_at":"2019-07-04T17:45:11Z","abstract_excerpt":"Recent years have witnessed a fast-growing interest in computing explanations for Machine Learning (ML) models predictions. For non-interpretable ML models, the most commonly used approaches for computing explanations are heuristic in nature. In contrast, recent work proposed rigorous approaches for computing explanations, which hold for a given ML model and prediction over the entire instance space. This paper extends earlier work to the case of boosted trees and assesses the quality of explanations obtained with state-of-the-art heuristic approaches. On most of the datasets considered, and f"},"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":"1907.02509","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-04T17:45:11Z","cross_cats_sorted":["cs.AI","cs.LO"],"title_canon_sha256":"fd5bbd6e22e6f3e78d0698fa63be8c4f5706cab40b87384bf52c11cf982e5131","abstract_canon_sha256":"38877142ea1f12e7145643310c986f0d2bb3ed0fe1a77d51d68016b975e8c6c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:28.365190Z","signature_b64":"yoodVElisSFzNjVhDvmBQg86YAq7wC6iRSa48w/e0ZuFNPSGWGwXQZtr1K8FFcyTuuDHhyly+Zq/OtiyfWZ9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b89b7f84380fe4dd7847dbfdd97333ede5add7e29211a6e7e29abda7e5ceb2b","last_reissued_at":"2026-05-17T23:41:28.364489Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:28.364489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Validating, Repairing and Refining Heuristic ML Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LO"],"primary_cat":"cs.LG","authors_text":"Alexey Ignatiev, Joao Marques-Silva, Nina Narodytska","submitted_at":"2019-07-04T17:45:11Z","abstract_excerpt":"Recent years have witnessed a fast-growing interest in computing explanations for Machine Learning (ML) models predictions. For non-interpretable ML models, the most commonly used approaches for computing explanations are heuristic in nature. In contrast, recent work proposed rigorous approaches for computing explanations, which hold for a given ML model and prediction over the entire instance space. This paper extends earlier work to the case of boosted trees and assesses the quality of explanations obtained with state-of-the-art heuristic approaches. On most of the datasets considered, and f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02509","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":""},"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":"1907.02509","created_at":"2026-05-17T23:41:28.364604+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.02509v1","created_at":"2026-05-17T23:41:28.364604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02509","created_at":"2026-05-17T23:41:28.364604+00:00"},{"alias_kind":"pith_short_12","alias_value":"HOE3P6CDQD7E","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"HOE3P6CDQD7E3V4E","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"HOE3P6CD","created_at":"2026-05-18T12:33:18.533446+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/HOE3P6CDQD7E3V4EPW753FZTH3","json":"https://pith.science/pith/HOE3P6CDQD7E3V4EPW753FZTH3.json","graph_json":"https://pith.science/api/pith-number/HOE3P6CDQD7E3V4EPW753FZTH3/graph.json","events_json":"https://pith.science/api/pith-number/HOE3P6CDQD7E3V4EPW753FZTH3/events.json","paper":"https://pith.science/paper/HOE3P6CD"},"agent_actions":{"view_html":"https://pith.science/pith/HOE3P6CDQD7E3V4EPW753FZTH3","download_json":"https://pith.science/pith/HOE3P6CDQD7E3V4EPW753FZTH3.json","view_paper":"https://pith.science/paper/HOE3P6CD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.02509&json=true","fetch_graph":"https://pith.science/api/pith-number/HOE3P6CDQD7E3V4EPW753FZTH3/graph.json","fetch_events":"https://pith.science/api/pith-number/HOE3P6CDQD7E3V4EPW753FZTH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HOE3P6CDQD7E3V4EPW753FZTH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HOE3P6CDQD7E3V4EPW753FZTH3/action/storage_attestation","attest_author":"https://pith.science/pith/HOE3P6CDQD7E3V4EPW753FZTH3/action/author_attestation","sign_citation":"https://pith.science/pith/HOE3P6CDQD7E3V4EPW753FZTH3/action/citation_signature","submit_replication":"https://pith.science/pith/HOE3P6CDQD7E3V4EPW753FZTH3/action/replication_record"}},"created_at":"2026-05-17T23:41:28.364604+00:00","updated_at":"2026-05-17T23:41:28.364604+00:00"}