{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BZP4HTLTPOJFWXYR35PQTHFD42","short_pith_number":"pith:BZP4HTLT","schema_version":"1.0","canonical_sha256":"0e5fc3cd737b925b5f11df5f099ca3e690f0410705c61f8c4a99714009b97d53","source":{"kind":"arxiv","id":"2101.10123","version":1},"attestation_state":"computed","paper":{"title":"Conditional Generative Models for Counterfactual Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arnaud Van Looveren, Giovanni Vacanti, Janis Klaise, Oliver Cobb","submitted_at":"2021-01-25T14:31:13Z","abstract_excerpt":"Counterfactual instances offer human-interpretable insight into the local behaviour of machine learning models. We propose a general framework to generate sparse, in-distribution counterfactual model explanations which match a desired target prediction with a conditional generative model, allowing batches of counterfactual instances to be generated with a single forward pass. The method is flexible with respect to the type of generative model used as well as the task of the underlying predictive model. This allows straightforward application of the framework to different modalities such as ima"},"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":"2101.10123","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-25T14:31:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c8c4d8ae8fc95cd394eb4b0e5c521ada0a796743cd91b205a905085e7fec7925","abstract_canon_sha256":"5f647a5658e4024cca2400a42a6d16a107094d6bf60711cd6a743dfd28f1f345"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:09:25.974951Z","signature_b64":"embdE9YAAyH0b1Gt4zgjar8nyfI42Dmt3OAMX/SyWXZ3mQMHa9DC+6FI3fFHLhsCAo9kXKQe4uveeky+zb0yBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e5fc3cd737b925b5f11df5f099ca3e690f0410705c61f8c4a99714009b97d53","last_reissued_at":"2026-07-05T02:09:25.974553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:09:25.974553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditional Generative Models for Counterfactual Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arnaud Van Looveren, Giovanni Vacanti, Janis Klaise, Oliver Cobb","submitted_at":"2021-01-25T14:31:13Z","abstract_excerpt":"Counterfactual instances offer human-interpretable insight into the local behaviour of machine learning models. We propose a general framework to generate sparse, in-distribution counterfactual model explanations which match a desired target prediction with a conditional generative model, allowing batches of counterfactual instances to be generated with a single forward pass. The method is flexible with respect to the type of generative model used as well as the task of the underlying predictive model. This allows straightforward application of the framework to different modalities such as ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.10123","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/2101.10123/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":"2101.10123","created_at":"2026-07-05T02:09:25.974603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.10123v1","created_at":"2026-07-05T02:09:25.974603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.10123","created_at":"2026-07-05T02:09:25.974603+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZP4HTLTPOJF","created_at":"2026-07-05T02:09:25.974603+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZP4HTLTPOJFWXYR","created_at":"2026-07-05T02:09:25.974603+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZP4HTLT","created_at":"2026-07-05T02:09:25.974603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01838","citing_title":"Adaptive Group-Based Counterfactual Explanations for Time-Series Rehabilitation Data","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06561","citing_title":"Optimal Counterfactual Search in Tree Ensembles: A Study Across Modeling and Solution Paradigms","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BZP4HTLTPOJFWXYR35PQTHFD42","json":"https://pith.science/pith/BZP4HTLTPOJFWXYR35PQTHFD42.json","graph_json":"https://pith.science/api/pith-number/BZP4HTLTPOJFWXYR35PQTHFD42/graph.json","events_json":"https://pith.science/api/pith-number/BZP4HTLTPOJFWXYR35PQTHFD42/events.json","paper":"https://pith.science/paper/BZP4HTLT"},"agent_actions":{"view_html":"https://pith.science/pith/BZP4HTLTPOJFWXYR35PQTHFD42","download_json":"https://pith.science/pith/BZP4HTLTPOJFWXYR35PQTHFD42.json","view_paper":"https://pith.science/paper/BZP4HTLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.10123&json=true","fetch_graph":"https://pith.science/api/pith-number/BZP4HTLTPOJFWXYR35PQTHFD42/graph.json","fetch_events":"https://pith.science/api/pith-number/BZP4HTLTPOJFWXYR35PQTHFD42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZP4HTLTPOJFWXYR35PQTHFD42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZP4HTLTPOJFWXYR35PQTHFD42/action/storage_attestation","attest_author":"https://pith.science/pith/BZP4HTLTPOJFWXYR35PQTHFD42/action/author_attestation","sign_citation":"https://pith.science/pith/BZP4HTLTPOJFWXYR35PQTHFD42/action/citation_signature","submit_replication":"https://pith.science/pith/BZP4HTLTPOJFWXYR35PQTHFD42/action/replication_record"}},"created_at":"2026-07-05T02:09:25.974603+00:00","updated_at":"2026-07-05T02:09:25.974603+00:00"}