{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2YSYRW2X53IC4V7WPDUUEYM7Z3","short_pith_number":"pith:2YSYRW2X","schema_version":"1.0","canonical_sha256":"d62588db57eed02e57f678e942619fcee3b7825ba4ef3b896445d062f6a130f7","source":{"kind":"arxiv","id":"2205.07774","version":1},"attestation_state":"computed","paper":{"title":"Gradient-based Counterfactual Explanations using Tractable Probabilistic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kristian Kersting, Xiaoting Shao","submitted_at":"2022-05-16T16:05:43Z","abstract_excerpt":"Counterfactual examples are an appealing class of post-hoc explanations for machine learning models. Given input $x$ of class $y_1$, its counterfactual is a contrastive example $x^\\prime$ of another class $y_0$. Current approaches primarily solve this task by a complex optimization: define an objective function based on the loss of the counterfactual outcome $y_0$ with hard or soft constraints, then optimize this function as a black-box. This \"deep learning\" approach, however, is rather slow, sometimes tricky, and may result in unrealistic counterfactual examples. In this work, we propose a no"},"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":"2205.07774","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-16T16:05:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"32d256b4706016655454543a066f13c897b6c8e09f423491ae2832d3759898cf","abstract_canon_sha256":"6ea145908ad4f8c554b05e5f63f4133f95ab9fd2b3f9397bf824c447299902c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:23:32.084982Z","signature_b64":"PyrP0lhZnHQ2+TaO9ofyw4A877azY6NmU9wXqizI2/en7i0fsuDbIPYoMRGabIKKbjud8f0+2WcwF5VxYgyKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d62588db57eed02e57f678e942619fcee3b7825ba4ef3b896445d062f6a130f7","last_reissued_at":"2026-07-05T04:23:32.084580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:23:32.084580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient-based Counterfactual Explanations using Tractable Probabilistic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kristian Kersting, Xiaoting Shao","submitted_at":"2022-05-16T16:05:43Z","abstract_excerpt":"Counterfactual examples are an appealing class of post-hoc explanations for machine learning models. Given input $x$ of class $y_1$, its counterfactual is a contrastive example $x^\\prime$ of another class $y_0$. Current approaches primarily solve this task by a complex optimization: define an objective function based on the loss of the counterfactual outcome $y_0$ with hard or soft constraints, then optimize this function as a black-box. This \"deep learning\" approach, however, is rather slow, sometimes tricky, and may result in unrealistic counterfactual examples. In this work, we propose a no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.07774","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/2205.07774/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":"2205.07774","created_at":"2026-07-05T04:23:32.084639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.07774v1","created_at":"2026-07-05T04:23:32.084639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.07774","created_at":"2026-07-05T04:23:32.084639+00:00"},{"alias_kind":"pith_short_12","alias_value":"2YSYRW2X53IC","created_at":"2026-07-05T04:23:32.084639+00:00"},{"alias_kind":"pith_short_16","alias_value":"2YSYRW2X53IC4V7W","created_at":"2026-07-05T04:23:32.084639+00:00"},{"alias_kind":"pith_short_8","alias_value":"2YSYRW2X","created_at":"2026-07-05T04:23:32.084639+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10455","citing_title":"RealAC: A Domain-Agnostic Framework for Realistic and Actionable Counterfactual Explanations","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2YSYRW2X53IC4V7WPDUUEYM7Z3","json":"https://pith.science/pith/2YSYRW2X53IC4V7WPDUUEYM7Z3.json","graph_json":"https://pith.science/api/pith-number/2YSYRW2X53IC4V7WPDUUEYM7Z3/graph.json","events_json":"https://pith.science/api/pith-number/2YSYRW2X53IC4V7WPDUUEYM7Z3/events.json","paper":"https://pith.science/paper/2YSYRW2X"},"agent_actions":{"view_html":"https://pith.science/pith/2YSYRW2X53IC4V7WPDUUEYM7Z3","download_json":"https://pith.science/pith/2YSYRW2X53IC4V7WPDUUEYM7Z3.json","view_paper":"https://pith.science/paper/2YSYRW2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.07774&json=true","fetch_graph":"https://pith.science/api/pith-number/2YSYRW2X53IC4V7WPDUUEYM7Z3/graph.json","fetch_events":"https://pith.science/api/pith-number/2YSYRW2X53IC4V7WPDUUEYM7Z3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2YSYRW2X53IC4V7WPDUUEYM7Z3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2YSYRW2X53IC4V7WPDUUEYM7Z3/action/storage_attestation","attest_author":"https://pith.science/pith/2YSYRW2X53IC4V7WPDUUEYM7Z3/action/author_attestation","sign_citation":"https://pith.science/pith/2YSYRW2X53IC4V7WPDUUEYM7Z3/action/citation_signature","submit_replication":"https://pith.science/pith/2YSYRW2X53IC4V7WPDUUEYM7Z3/action/replication_record"}},"created_at":"2026-07-05T04:23:32.084639+00:00","updated_at":"2026-07-05T04:23:32.084639+00:00"}