{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DDG7WADQ6QUWVH5K3EIF2DPUPT","short_pith_number":"pith:DDG7WADQ","schema_version":"1.0","canonical_sha256":"18cdfb0070f4296a9faad9105d0df47ce3fe30e038bb9320ae11c96efb91e34a","source":{"kind":"arxiv","id":"2002.04202","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Rationales to Improve Human Task Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Devleena Das, Sonia Chernova","submitted_at":"2020-02-11T04:51:35Z","abstract_excerpt":"Machine learning (ML) systems across many application areas are increasingly demonstrating performance that is beyond that of humans. In response to the proliferation of such models, the field of Explainable AI (XAI) has sought to develop techniques that enhance the transparency and interpretability of machine learning methods. In this work, we consider a question not previously explored within the XAI and ML communities: Given a computational system whose performance exceeds that of its human user, can explainable AI capabilities be leveraged to improve the performance of the human? We study "},"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":"2002.04202","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2020-02-11T04:51:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9bc2860171082884e6dc3541a5104bef52a7c4582eeebea17549066cd53ef4eb","abstract_canon_sha256":"201c2f541b16093be82768e0fa6d58919f4a2147a86ea8f5b72606ec19b3247a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:39:43.153996Z","signature_b64":"UO84TWS23S9OTMEWVnjf5+uL8QB/hIlmMoFpuCgLa/UBAm7RNP3MUi6v5LsDUrsua/ExPtqw452qBASKQIauAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18cdfb0070f4296a9faad9105d0df47ce3fe30e038bb9320ae11c96efb91e34a","last_reissued_at":"2026-07-05T00:39:43.153519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:39:43.153519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Rationales to Improve Human Task Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Devleena Das, Sonia Chernova","submitted_at":"2020-02-11T04:51:35Z","abstract_excerpt":"Machine learning (ML) systems across many application areas are increasingly demonstrating performance that is beyond that of humans. In response to the proliferation of such models, the field of Explainable AI (XAI) has sought to develop techniques that enhance the transparency and interpretability of machine learning methods. In this work, we consider a question not previously explored within the XAI and ML communities: Given a computational system whose performance exceeds that of its human user, can explainable AI capabilities be leveraged to improve the performance of the human? We study "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.04202","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/2002.04202/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":"2002.04202","created_at":"2026-07-05T00:39:43.153573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.04202v1","created_at":"2026-07-05T00:39:43.153573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.04202","created_at":"2026-07-05T00:39:43.153573+00:00"},{"alias_kind":"pith_short_12","alias_value":"DDG7WADQ6QUW","created_at":"2026-07-05T00:39:43.153573+00:00"},{"alias_kind":"pith_short_16","alias_value":"DDG7WADQ6QUWVH5K","created_at":"2026-07-05T00:39:43.153573+00:00"},{"alias_kind":"pith_short_8","alias_value":"DDG7WADQ","created_at":"2026-07-05T00:39:43.153573+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/DDG7WADQ6QUWVH5K3EIF2DPUPT","json":"https://pith.science/pith/DDG7WADQ6QUWVH5K3EIF2DPUPT.json","graph_json":"https://pith.science/api/pith-number/DDG7WADQ6QUWVH5K3EIF2DPUPT/graph.json","events_json":"https://pith.science/api/pith-number/DDG7WADQ6QUWVH5K3EIF2DPUPT/events.json","paper":"https://pith.science/paper/DDG7WADQ"},"agent_actions":{"view_html":"https://pith.science/pith/DDG7WADQ6QUWVH5K3EIF2DPUPT","download_json":"https://pith.science/pith/DDG7WADQ6QUWVH5K3EIF2DPUPT.json","view_paper":"https://pith.science/paper/DDG7WADQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.04202&json=true","fetch_graph":"https://pith.science/api/pith-number/DDG7WADQ6QUWVH5K3EIF2DPUPT/graph.json","fetch_events":"https://pith.science/api/pith-number/DDG7WADQ6QUWVH5K3EIF2DPUPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DDG7WADQ6QUWVH5K3EIF2DPUPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DDG7WADQ6QUWVH5K3EIF2DPUPT/action/storage_attestation","attest_author":"https://pith.science/pith/DDG7WADQ6QUWVH5K3EIF2DPUPT/action/author_attestation","sign_citation":"https://pith.science/pith/DDG7WADQ6QUWVH5K3EIF2DPUPT/action/citation_signature","submit_replication":"https://pith.science/pith/DDG7WADQ6QUWVH5K3EIF2DPUPT/action/replication_record"}},"created_at":"2026-07-05T00:39:43.153573+00:00","updated_at":"2026-07-05T00:39:43.153573+00:00"}