{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4FXFKKHFFMTVVNRIMC3FWJBTEB","short_pith_number":"pith:4FXFKKHF","schema_version":"1.0","canonical_sha256":"e16e5528e52b275ab62860b65b2433205e9be973170090b3cb2724dba2c86f66","source":{"kind":"arxiv","id":"1811.05245","version":2},"attestation_state":"computed","paper":{"title":"Interpretable Credit Application Predictions With Counterfactual Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chan Le Van, Farbod Kamiab, Freddy Lecue, Luca Costabello, Paul Sweeney, Rory Mc Grath, Zhao Shen","submitted_at":"2018-11-13T12:12:57Z","abstract_excerpt":"We predict credit applications with off-the-shelf, interchangeable black-box classifiers and we explain single predictions with counterfactual explanations. Counterfactual explanations expose the minimal changes required on the input data to obtain a different result e.g., approved vs rejected application. Despite their effectiveness, counterfactuals are mainly designed for changing an undesired outcome of a prediction i.e. loan rejected. Counterfactuals, however, can be difficult to interpret, especially when a high number of features are involved in the explanation. Our contribution is two-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":"1811.05245","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-13T12:12:57Z","cross_cats_sorted":[],"title_canon_sha256":"707f14243044e17f6eef6ab107603d10fa9bac44d20810a9ad1b0755bec0b8fa","abstract_canon_sha256":"bc8393e01541105585687527bf1f5d27020f7e92b8994bf55ab7d0ee8215cab8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:34.594882Z","signature_b64":"Iqfq8c4UTkrcmDmCh4G5W/j/NtRrgSCeh4DrEz+iAqiNSm60EDOWejnDhlwQbAV+f5kR6I/XJzFCfhXEfHiLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e16e5528e52b275ab62860b65b2433205e9be973170090b3cb2724dba2c86f66","last_reissued_at":"2026-05-18T00:00:34.594390Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:34.594390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Credit Application Predictions With Counterfactual Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chan Le Van, Farbod Kamiab, Freddy Lecue, Luca Costabello, Paul Sweeney, Rory Mc Grath, Zhao Shen","submitted_at":"2018-11-13T12:12:57Z","abstract_excerpt":"We predict credit applications with off-the-shelf, interchangeable black-box classifiers and we explain single predictions with counterfactual explanations. Counterfactual explanations expose the minimal changes required on the input data to obtain a different result e.g., approved vs rejected application. Despite their effectiveness, counterfactuals are mainly designed for changing an undesired outcome of a prediction i.e. loan rejected. Counterfactuals, however, can be difficult to interpret, especially when a high number of features are involved in the explanation. Our contribution is two-f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05245","kind":"arxiv","version":2},"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":"1811.05245","created_at":"2026-05-18T00:00:34.594493+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.05245v2","created_at":"2026-05-18T00:00:34.594493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05245","created_at":"2026-05-18T00:00:34.594493+00:00"},{"alias_kind":"pith_short_12","alias_value":"4FXFKKHFFMTV","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4FXFKKHFFMTVVNRI","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4FXFKKHF","created_at":"2026-05-18T12:32:05.422762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2407.11089","citing_title":"Explainable bank failure prediction models: Counterfactual explanations to reduce the failure risk","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4FXFKKHFFMTVVNRIMC3FWJBTEB","json":"https://pith.science/pith/4FXFKKHFFMTVVNRIMC3FWJBTEB.json","graph_json":"https://pith.science/api/pith-number/4FXFKKHFFMTVVNRIMC3FWJBTEB/graph.json","events_json":"https://pith.science/api/pith-number/4FXFKKHFFMTVVNRIMC3FWJBTEB/events.json","paper":"https://pith.science/paper/4FXFKKHF"},"agent_actions":{"view_html":"https://pith.science/pith/4FXFKKHFFMTVVNRIMC3FWJBTEB","download_json":"https://pith.science/pith/4FXFKKHFFMTVVNRIMC3FWJBTEB.json","view_paper":"https://pith.science/paper/4FXFKKHF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.05245&json=true","fetch_graph":"https://pith.science/api/pith-number/4FXFKKHFFMTVVNRIMC3FWJBTEB/graph.json","fetch_events":"https://pith.science/api/pith-number/4FXFKKHFFMTVVNRIMC3FWJBTEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4FXFKKHFFMTVVNRIMC3FWJBTEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4FXFKKHFFMTVVNRIMC3FWJBTEB/action/storage_attestation","attest_author":"https://pith.science/pith/4FXFKKHFFMTVVNRIMC3FWJBTEB/action/author_attestation","sign_citation":"https://pith.science/pith/4FXFKKHFFMTVVNRIMC3FWJBTEB/action/citation_signature","submit_replication":"https://pith.science/pith/4FXFKKHFFMTVVNRIMC3FWJBTEB/action/replication_record"}},"created_at":"2026-05-18T00:00:34.594493+00:00","updated_at":"2026-05-18T00:00:34.594493+00:00"}