{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O3XKW67UCX2ZFRAU4ISRJO76NU","short_pith_number":"pith:O3XKW67U","schema_version":"1.0","canonical_sha256":"76eeab7bf415f592c414e22514bbfe6d1d60eb1e235dacc0084e723807681123","source":{"kind":"arxiv","id":"2410.04253","version":2},"attestation_state":"computed","paper":{"title":"Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Amanda E. Paluch, Finale Doshi-Velez, Krzysztof Z. Gajos, Siddharth Swaroop, Zana Bu\\c{c}inca","submitted_at":"2024-10-05T18:21:04Z","abstract_excerpt":"People's decision-making abilities often fail to improve or may even erode when they rely on AI for decision-support, even when the AI provides informative explanations. We argue this is partly because people intuitively seek contrastive explanations, which clarify the difference between the AI's decision and their own reasoning, while most AI systems offer \"unilateral\" explanations that justify the AI's decision but do not account for users' thinking. To align human-AI knowledge on decision tasks, we introduce a framework for generating human-centered contrastive explanations that explain the"},"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":"2410.04253","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-10-05T18:21:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a7712d0dcb1c9a5ac296c2fb2adbf7366405303c0f586712be0b96bebb33fda4","abstract_canon_sha256":"41b4880dd122a5379414924b6d3a6f2a31afb69f8b483bcf7bb0c05667a0424d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:11.244706Z","signature_b64":"/cyZaMmR8WE2MBH7vgfzgDKIzbB2/G5TnbLcAKpNUNUn/n8WzNNswppTttgqLJxxtnUBjzUecJqflIHYvyWDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76eeab7bf415f592c414e22514bbfe6d1d60eb1e235dacc0084e723807681123","last_reissued_at":"2026-07-05T10:34:11.244123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:11.244123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Amanda E. Paluch, Finale Doshi-Velez, Krzysztof Z. Gajos, Siddharth Swaroop, Zana Bu\\c{c}inca","submitted_at":"2024-10-05T18:21:04Z","abstract_excerpt":"People's decision-making abilities often fail to improve or may even erode when they rely on AI for decision-support, even when the AI provides informative explanations. We argue this is partly because people intuitively seek contrastive explanations, which clarify the difference between the AI's decision and their own reasoning, while most AI systems offer \"unilateral\" explanations that justify the AI's decision but do not account for users' thinking. To align human-AI knowledge on decision tasks, we introduce a framework for generating human-centered contrastive explanations that explain the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04253","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.04253/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":"2410.04253","created_at":"2026-07-05T10:34:11.244192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04253v2","created_at":"2026-07-05T10:34:11.244192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04253","created_at":"2026-07-05T10:34:11.244192+00:00"},{"alias_kind":"pith_short_12","alias_value":"O3XKW67UCX2Z","created_at":"2026-07-05T10:34:11.244192+00:00"},{"alias_kind":"pith_short_16","alias_value":"O3XKW67UCX2ZFRAU","created_at":"2026-07-05T10:34:11.244192+00:00"},{"alias_kind":"pith_short_8","alias_value":"O3XKW67U","created_at":"2026-07-05T10:34:11.244192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.08583","citing_title":"An Empirical Examination of the Evaluative AI Framework","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O3XKW67UCX2ZFRAU4ISRJO76NU","json":"https://pith.science/pith/O3XKW67UCX2ZFRAU4ISRJO76NU.json","graph_json":"https://pith.science/api/pith-number/O3XKW67UCX2ZFRAU4ISRJO76NU/graph.json","events_json":"https://pith.science/api/pith-number/O3XKW67UCX2ZFRAU4ISRJO76NU/events.json","paper":"https://pith.science/paper/O3XKW67U"},"agent_actions":{"view_html":"https://pith.science/pith/O3XKW67UCX2ZFRAU4ISRJO76NU","download_json":"https://pith.science/pith/O3XKW67UCX2ZFRAU4ISRJO76NU.json","view_paper":"https://pith.science/paper/O3XKW67U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04253&json=true","fetch_graph":"https://pith.science/api/pith-number/O3XKW67UCX2ZFRAU4ISRJO76NU/graph.json","fetch_events":"https://pith.science/api/pith-number/O3XKW67UCX2ZFRAU4ISRJO76NU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O3XKW67UCX2ZFRAU4ISRJO76NU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O3XKW67UCX2ZFRAU4ISRJO76NU/action/storage_attestation","attest_author":"https://pith.science/pith/O3XKW67UCX2ZFRAU4ISRJO76NU/action/author_attestation","sign_citation":"https://pith.science/pith/O3XKW67UCX2ZFRAU4ISRJO76NU/action/citation_signature","submit_replication":"https://pith.science/pith/O3XKW67UCX2ZFRAU4ISRJO76NU/action/replication_record"}},"created_at":"2026-07-05T10:34:11.244192+00:00","updated_at":"2026-07-05T10:34:11.244192+00:00"}