{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EQFW27FNIMCNJKYK77LEY66C4M","short_pith_number":"pith:EQFW27FN","schema_version":"1.0","canonical_sha256":"240b6d7cad4304d4ab0affd64c7bc2e31d953d4ace057d1194e30ec0d12a276e","source":{"kind":"arxiv","id":"2002.06278","version":4},"attestation_state":"computed","paper":{"title":"Algorithmic Recourse: from Counterfactual Explanations to Interventions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir-Hossein Karimi, Bernhard Sch\\\"olkopf, Isabel Valera","submitted_at":"2020-02-14T22:49:42Z","abstract_excerpt":"As machine learning is increasingly used to inform consequential decision-making (e.g., pre-trial bail and loan approval), it becomes important to explain how the system arrived at its decision, and also suggest actions to achieve a favorable decision. Counterfactual explanations -- \"how the world would have (had) to be different for a desirable outcome to occur\" -- aim to satisfy these criteria. Existing works have primarily focused on designing algorithms to obtain counterfactual explanations for a wide range of settings. However, one of the main objectives of \"explanations as a means to hel"},"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":"2002.06278","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-14T22:49:42Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1b8d80ca95911db5db1adaf6500c3ed15690f60d05a63590643ce09f34a78d35","abstract_canon_sha256":"02909e96dba234c0896af58288e4a6c3dda50a32e33fb6c0f09735ffdf4de46f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:16.743822Z","signature_b64":"QtEq51nxANtH+aR6tCrNVclhDgGZY4dXAUG7fybNsN8dkwk6PmjeeAJONg0c3++OUElqe6JxquDMPytUn25wAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"240b6d7cad4304d4ab0affd64c7bc2e31d953d4ace057d1194e30ec0d12a276e","last_reissued_at":"2026-07-05T01:41:16.743412Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:16.743412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Algorithmic Recourse: from Counterfactual Explanations to Interventions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir-Hossein Karimi, Bernhard Sch\\\"olkopf, Isabel Valera","submitted_at":"2020-02-14T22:49:42Z","abstract_excerpt":"As machine learning is increasingly used to inform consequential decision-making (e.g., pre-trial bail and loan approval), it becomes important to explain how the system arrived at its decision, and also suggest actions to achieve a favorable decision. Counterfactual explanations -- \"how the world would have (had) to be different for a desirable outcome to occur\" -- aim to satisfy these criteria. Existing works have primarily focused on designing algorithms to obtain counterfactual explanations for a wide range of settings. However, one of the main objectives of \"explanations as a means to hel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06278","kind":"arxiv","version":4},"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/2002.06278/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":"2002.06278","created_at":"2026-07-05T01:41:16.743476+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.06278v4","created_at":"2026-07-05T01:41:16.743476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06278","created_at":"2026-07-05T01:41:16.743476+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQFW27FNIMCN","created_at":"2026-07-05T01:41:16.743476+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQFW27FNIMCNJKYK","created_at":"2026-07-05T01:41:16.743476+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQFW27FN","created_at":"2026-07-05T01:41:16.743476+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00884","citing_title":"An Explainable Gaussian Process Auto-encoder for Tabular Data","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQFW27FNIMCNJKYK77LEY66C4M","json":"https://pith.science/pith/EQFW27FNIMCNJKYK77LEY66C4M.json","graph_json":"https://pith.science/api/pith-number/EQFW27FNIMCNJKYK77LEY66C4M/graph.json","events_json":"https://pith.science/api/pith-number/EQFW27FNIMCNJKYK77LEY66C4M/events.json","paper":"https://pith.science/paper/EQFW27FN"},"agent_actions":{"view_html":"https://pith.science/pith/EQFW27FNIMCNJKYK77LEY66C4M","download_json":"https://pith.science/pith/EQFW27FNIMCNJKYK77LEY66C4M.json","view_paper":"https://pith.science/paper/EQFW27FN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.06278&json=true","fetch_graph":"https://pith.science/api/pith-number/EQFW27FNIMCNJKYK77LEY66C4M/graph.json","fetch_events":"https://pith.science/api/pith-number/EQFW27FNIMCNJKYK77LEY66C4M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQFW27FNIMCNJKYK77LEY66C4M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQFW27FNIMCNJKYK77LEY66C4M/action/storage_attestation","attest_author":"https://pith.science/pith/EQFW27FNIMCNJKYK77LEY66C4M/action/author_attestation","sign_citation":"https://pith.science/pith/EQFW27FNIMCNJKYK77LEY66C4M/action/citation_signature","submit_replication":"https://pith.science/pith/EQFW27FNIMCNJKYK77LEY66C4M/action/replication_record"}},"created_at":"2026-07-05T01:41:16.743476+00:00","updated_at":"2026-07-05T01:41:16.743476+00:00"}