{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:V3SUKDRSZRB4RYHO36JGBAJHDR","short_pith_number":"pith:V3SUKDRS","schema_version":"1.0","canonical_sha256":"aee5450e32cc43c8e0eedf926081271c74cb40488ef7233a5dababa30f261bca","source":{"kind":"arxiv","id":"2204.10152","version":1},"attestation_state":"computed","paper":{"title":"Features of Explainability: How users understand counterfactual and causal explanations for categorical and continuous features in XAI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Greta Warren, Mark T Keane, Ruth M J Byrne","submitted_at":"2022-04-21T15:01:09Z","abstract_excerpt":"Counterfactual explanations are increasingly used to address interpretability, recourse, and bias in AI decisions. However, we do not know how well counterfactual explanations help users to understand a systems decisions, since no large scale user studies have compared their efficacy to other sorts of explanations such as causal explanations (which have a longer track record of use in rule based and decision tree models). It is also unknown whether counterfactual explanations are equally effective for categorical as for continuous features, although current methods assume they do. Hence, in a "},"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":"2204.10152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2022-04-21T15:01:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae3f7bee2a384eec2cb699567c11aed26ea6587dec72534c8c6203ae23aa1bb9","abstract_canon_sha256":"12d240d305a39a045120682ab27cdb435d2165c5d45acb4d445fea286edf6060"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:11.101742Z","signature_b64":"xZsgaaiJk+XAQRTMlXJUaV4HuA9hCSO/d1E3i3VFK7Vp58hcaXaeUCS8gvDeIMpj3qGwY+OMZoQcaenmWlDdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aee5450e32cc43c8e0eedf926081271c74cb40488ef7233a5dababa30f261bca","last_reissued_at":"2026-07-05T05:57:11.101233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:11.101233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Features of Explainability: How users understand counterfactual and causal explanations for categorical and continuous features in XAI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Greta Warren, Mark T Keane, Ruth M J Byrne","submitted_at":"2022-04-21T15:01:09Z","abstract_excerpt":"Counterfactual explanations are increasingly used to address interpretability, recourse, and bias in AI decisions. However, we do not know how well counterfactual explanations help users to understand a systems decisions, since no large scale user studies have compared their efficacy to other sorts of explanations such as causal explanations (which have a longer track record of use in rule based and decision tree models). It is also unknown whether counterfactual explanations are equally effective for categorical as for continuous features, although current methods assume they do. Hence, in a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.10152","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/2204.10152/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":"2204.10152","created_at":"2026-07-05T05:57:11.101287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.10152v1","created_at":"2026-07-05T05:57:11.101287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.10152","created_at":"2026-07-05T05:57:11.101287+00:00"},{"alias_kind":"pith_short_12","alias_value":"V3SUKDRSZRB4","created_at":"2026-07-05T05:57:11.101287+00:00"},{"alias_kind":"pith_short_16","alias_value":"V3SUKDRSZRB4RYHO","created_at":"2026-07-05T05:57:11.101287+00:00"},{"alias_kind":"pith_short_8","alias_value":"V3SUKDRS","created_at":"2026-07-05T05:57:11.101287+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14207","citing_title":"What Should Explanations Contain? A Human-Centered Explanation Content Model for Local, Post-Hoc Explanations","ref_index":146,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V3SUKDRSZRB4RYHO36JGBAJHDR","json":"https://pith.science/pith/V3SUKDRSZRB4RYHO36JGBAJHDR.json","graph_json":"https://pith.science/api/pith-number/V3SUKDRSZRB4RYHO36JGBAJHDR/graph.json","events_json":"https://pith.science/api/pith-number/V3SUKDRSZRB4RYHO36JGBAJHDR/events.json","paper":"https://pith.science/paper/V3SUKDRS"},"agent_actions":{"view_html":"https://pith.science/pith/V3SUKDRSZRB4RYHO36JGBAJHDR","download_json":"https://pith.science/pith/V3SUKDRSZRB4RYHO36JGBAJHDR.json","view_paper":"https://pith.science/paper/V3SUKDRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.10152&json=true","fetch_graph":"https://pith.science/api/pith-number/V3SUKDRSZRB4RYHO36JGBAJHDR/graph.json","fetch_events":"https://pith.science/api/pith-number/V3SUKDRSZRB4RYHO36JGBAJHDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V3SUKDRSZRB4RYHO36JGBAJHDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V3SUKDRSZRB4RYHO36JGBAJHDR/action/storage_attestation","attest_author":"https://pith.science/pith/V3SUKDRSZRB4RYHO36JGBAJHDR/action/author_attestation","sign_citation":"https://pith.science/pith/V3SUKDRSZRB4RYHO36JGBAJHDR/action/citation_signature","submit_replication":"https://pith.science/pith/V3SUKDRSZRB4RYHO36JGBAJHDR/action/replication_record"}},"created_at":"2026-07-05T05:57:11.101287+00:00","updated_at":"2026-07-05T05:57:11.101287+00:00"}