{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6YEGRA5IID3AE2C7IBHPOAQNCK","short_pith_number":"pith:6YEGRA5I","schema_version":"1.0","canonical_sha256":"f6086883a840f602685f404ef7020d12ba5fc68a73224287c54216d5f78c3e5d","source":{"kind":"arxiv","id":"2308.12367","version":3},"attestation_state":"computed","paper":{"title":"SafeAR: Safe Algorithmic Recourse by Risk-Aware Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haochen Wu, Shubham Sharma, Sriram Gopalakrishnan, Sunandita Patra","submitted_at":"2023-08-23T18:12:11Z","abstract_excerpt":"With the growing use of machine learning (ML) models in critical domains such as finance and healthcare, the need to offer recourse for those adversely affected by the decisions of ML models has become more important; individuals ought to be provided with recommendations on actions to take for improving their situation and thus receiving a favorable decision. Prior work on sequential algorithmic recourse -- which recommends a series of changes -- focuses on action feasibility and uses the proximity of feature changes to determine action costs. However, the uncertainties of feature changes and "},"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":"2308.12367","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-23T18:12:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"322e248ab75615dcadf999930a2d27a783f9218b54231bd1472985759b27195e","abstract_canon_sha256":"f7e5c4108111e316ff01e1bbc25af6ac23f51a71feb80842f0c13d1dfd7ed8af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:21.159420Z","signature_b64":"wzTbE0RkJIXNrrdJxpnerX9IKDzP8tHvT75Nu/VSlX2ynp9G12zmK0HdaxD2exvc1T9NYY+z//wOodUbKZseAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6086883a840f602685f404ef7020d12ba5fc68a73224287c54216d5f78c3e5d","last_reissued_at":"2026-07-05T08:02:21.158914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:21.158914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SafeAR: Safe Algorithmic Recourse by Risk-Aware Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haochen Wu, Shubham Sharma, Sriram Gopalakrishnan, Sunandita Patra","submitted_at":"2023-08-23T18:12:11Z","abstract_excerpt":"With the growing use of machine learning (ML) models in critical domains such as finance and healthcare, the need to offer recourse for those adversely affected by the decisions of ML models has become more important; individuals ought to be provided with recommendations on actions to take for improving their situation and thus receiving a favorable decision. Prior work on sequential algorithmic recourse -- which recommends a series of changes -- focuses on action feasibility and uses the proximity of feature changes to determine action costs. However, the uncertainties of feature changes and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12367","kind":"arxiv","version":3},"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/2308.12367/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":"2308.12367","created_at":"2026-07-05T08:02:21.158968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.12367v3","created_at":"2026-07-05T08:02:21.158968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12367","created_at":"2026-07-05T08:02:21.158968+00:00"},{"alias_kind":"pith_short_12","alias_value":"6YEGRA5IID3A","created_at":"2026-07-05T08:02:21.158968+00:00"},{"alias_kind":"pith_short_16","alias_value":"6YEGRA5IID3AE2C7","created_at":"2026-07-05T08:02:21.158968+00:00"},{"alias_kind":"pith_short_8","alias_value":"6YEGRA5I","created_at":"2026-07-05T08:02:21.158968+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/6YEGRA5IID3AE2C7IBHPOAQNCK","json":"https://pith.science/pith/6YEGRA5IID3AE2C7IBHPOAQNCK.json","graph_json":"https://pith.science/api/pith-number/6YEGRA5IID3AE2C7IBHPOAQNCK/graph.json","events_json":"https://pith.science/api/pith-number/6YEGRA5IID3AE2C7IBHPOAQNCK/events.json","paper":"https://pith.science/paper/6YEGRA5I"},"agent_actions":{"view_html":"https://pith.science/pith/6YEGRA5IID3AE2C7IBHPOAQNCK","download_json":"https://pith.science/pith/6YEGRA5IID3AE2C7IBHPOAQNCK.json","view_paper":"https://pith.science/paper/6YEGRA5I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.12367&json=true","fetch_graph":"https://pith.science/api/pith-number/6YEGRA5IID3AE2C7IBHPOAQNCK/graph.json","fetch_events":"https://pith.science/api/pith-number/6YEGRA5IID3AE2C7IBHPOAQNCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6YEGRA5IID3AE2C7IBHPOAQNCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6YEGRA5IID3AE2C7IBHPOAQNCK/action/storage_attestation","attest_author":"https://pith.science/pith/6YEGRA5IID3AE2C7IBHPOAQNCK/action/author_attestation","sign_citation":"https://pith.science/pith/6YEGRA5IID3AE2C7IBHPOAQNCK/action/citation_signature","submit_replication":"https://pith.science/pith/6YEGRA5IID3AE2C7IBHPOAQNCK/action/replication_record"}},"created_at":"2026-07-05T08:02:21.158968+00:00","updated_at":"2026-07-05T08:02:21.158968+00:00"}