{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VBUBZ3EC763BLJTST64UZMK5X4","short_pith_number":"pith:VBUBZ3EC","schema_version":"1.0","canonical_sha256":"a8681cec82ffb615a6729fb94cb15dbf004f1afcba64d818d0a448c4591c4745","source":{"kind":"arxiv","id":"1906.00117","version":1},"attestation_state":"computed","paper":{"title":"Model Agnostic Contrastive Explanations for Structured Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amit Dhurandhar, Avinash Balakrishnan, Karthikeyan Shanmugam, Pin-Yu Chen, Ruchir Puri, Tejaswini Pedapati","submitted_at":"2019-05-31T23:06:44Z","abstract_excerpt":"Recently, a method [7] was proposed to generate contrastive explanations for differentiable models such as deep neural networks, where one has complete access to the model. In this work, we propose a method, Model Agnostic Contrastive Explanations Method (MACEM), to generate contrastive explanations for \\emph{any} classification model where one is able to \\emph{only} query the class probabilities for a desired input. This allows us to generate contrastive explanations for not only neural networks, but models such as random forests, boosted trees and even arbitrary ensembles that are still amon"},"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":"1906.00117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T23:06:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4c176312b16c4ec17f888365efd25ddc2519b07d4c349c1e3408c9b84b6a57b3","abstract_canon_sha256":"d83156f9eb7225c6bfd8fbdda509d4b57366904e6ed199792752bfa0b24044d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:28.143665Z","signature_b64":"bUrU3Cl0pOzY/tUsI5MrPkoxPn29f9MD0rFyERm6MCzjYCFrmAuyyyXX0/L1GPodz445K82X153/BiiRAGn8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8681cec82ffb615a6729fb94cb15dbf004f1afcba64d818d0a448c4591c4745","last_reissued_at":"2026-05-17T23:44:28.143050Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:28.143050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model Agnostic Contrastive Explanations for Structured Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amit Dhurandhar, Avinash Balakrishnan, Karthikeyan Shanmugam, Pin-Yu Chen, Ruchir Puri, Tejaswini Pedapati","submitted_at":"2019-05-31T23:06:44Z","abstract_excerpt":"Recently, a method [7] was proposed to generate contrastive explanations for differentiable models such as deep neural networks, where one has complete access to the model. In this work, we propose a method, Model Agnostic Contrastive Explanations Method (MACEM), to generate contrastive explanations for \\emph{any} classification model where one is able to \\emph{only} query the class probabilities for a desired input. This allows us to generate contrastive explanations for not only neural networks, but models such as random forests, boosted trees and even arbitrary ensembles that are still amon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00117","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":"1906.00117","created_at":"2026-05-17T23:44:28.143127+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.00117v1","created_at":"2026-05-17T23:44:28.143127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00117","created_at":"2026-05-17T23:44:28.143127+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBUBZ3EC763B","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBUBZ3EC763BLJTS","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBUBZ3EC","created_at":"2026-05-18T12:33:30.264802+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/VBUBZ3EC763BLJTST64UZMK5X4","json":"https://pith.science/pith/VBUBZ3EC763BLJTST64UZMK5X4.json","graph_json":"https://pith.science/api/pith-number/VBUBZ3EC763BLJTST64UZMK5X4/graph.json","events_json":"https://pith.science/api/pith-number/VBUBZ3EC763BLJTST64UZMK5X4/events.json","paper":"https://pith.science/paper/VBUBZ3EC"},"agent_actions":{"view_html":"https://pith.science/pith/VBUBZ3EC763BLJTST64UZMK5X4","download_json":"https://pith.science/pith/VBUBZ3EC763BLJTST64UZMK5X4.json","view_paper":"https://pith.science/paper/VBUBZ3EC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.00117&json=true","fetch_graph":"https://pith.science/api/pith-number/VBUBZ3EC763BLJTST64UZMK5X4/graph.json","fetch_events":"https://pith.science/api/pith-number/VBUBZ3EC763BLJTST64UZMK5X4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBUBZ3EC763BLJTST64UZMK5X4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBUBZ3EC763BLJTST64UZMK5X4/action/storage_attestation","attest_author":"https://pith.science/pith/VBUBZ3EC763BLJTST64UZMK5X4/action/author_attestation","sign_citation":"https://pith.science/pith/VBUBZ3EC763BLJTST64UZMK5X4/action/citation_signature","submit_replication":"https://pith.science/pith/VBUBZ3EC763BLJTST64UZMK5X4/action/replication_record"}},"created_at":"2026-05-17T23:44:28.143127+00:00","updated_at":"2026-05-17T23:44:28.143127+00:00"}