{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HMKOJ2KYSTJFZJOJMDOMHFZMJ5","short_pith_number":"pith:HMKOJ2KY","schema_version":"1.0","canonical_sha256":"3b14e4e95894d25ca5c960dcc3972c4f7a20efba8064401a3bf32a0f6dd5ed54","source":{"kind":"arxiv","id":"2003.04315","version":5},"attestation_state":"computed","paper":{"title":"LIMEADE: From AI Explanations to Advice Taking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Benjamin Charles Germain Lee, Daniel S. Weld, Doug Downey, Kyle Lo","submitted_at":"2020-03-09T18:00:00Z","abstract_excerpt":"Research in human-centered AI has shown the benefits of systems that can explain their predictions. Methods that allow an AI to take advice from humans in response to explanations are similarly useful. While both capabilities are well-developed for transparent learning models (e.g., linear models and GA$^2$Ms), and recent techniques (e.g., LIME and SHAP) can generate explanations for opaque models, little attention has been given to advice methods for opaque models. This paper introduces LIMEADE, the first general framework that translates both positive and negative advice (expressed using hig"},"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":"2003.04315","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-03-09T18:00:00Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"d1649e592258e46da7391f048a39ad894502d4a49bbd12f6f326ba73442bacf5","abstract_canon_sha256":"fddbd61612e6c3868cd9ad3c752fb90527e6af09df14fad31a67b88248fbc28c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:57.547995Z","signature_b64":"ZoJ2kRiTCUfL062RtIz65ih3V0RTC94RgTXXBaTo4SbOydlIK1P1SRfUs8b2Kyi6H67OiTm5nWld3qtKpzTxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b14e4e95894d25ca5c960dcc3972c4f7a20efba8064401a3bf32a0f6dd5ed54","last_reissued_at":"2026-07-05T05:33:57.547462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:57.547462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LIMEADE: From AI Explanations to Advice Taking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Benjamin Charles Germain Lee, Daniel S. Weld, Doug Downey, Kyle Lo","submitted_at":"2020-03-09T18:00:00Z","abstract_excerpt":"Research in human-centered AI has shown the benefits of systems that can explain their predictions. Methods that allow an AI to take advice from humans in response to explanations are similarly useful. While both capabilities are well-developed for transparent learning models (e.g., linear models and GA$^2$Ms), and recent techniques (e.g., LIME and SHAP) can generate explanations for opaque models, little attention has been given to advice methods for opaque models. This paper introduces LIMEADE, the first general framework that translates both positive and negative advice (expressed using hig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04315","kind":"arxiv","version":5},"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/2003.04315/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":"2003.04315","created_at":"2026-07-05T05:33:57.547543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.04315v5","created_at":"2026-07-05T05:33:57.547543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04315","created_at":"2026-07-05T05:33:57.547543+00:00"},{"alias_kind":"pith_short_12","alias_value":"HMKOJ2KYSTJF","created_at":"2026-07-05T05:33:57.547543+00:00"},{"alias_kind":"pith_short_16","alias_value":"HMKOJ2KYSTJFZJOJ","created_at":"2026-07-05T05:33:57.547543+00:00"},{"alias_kind":"pith_short_8","alias_value":"HMKOJ2KY","created_at":"2026-07-05T05:33:57.547543+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/HMKOJ2KYSTJFZJOJMDOMHFZMJ5","json":"https://pith.science/pith/HMKOJ2KYSTJFZJOJMDOMHFZMJ5.json","graph_json":"https://pith.science/api/pith-number/HMKOJ2KYSTJFZJOJMDOMHFZMJ5/graph.json","events_json":"https://pith.science/api/pith-number/HMKOJ2KYSTJFZJOJMDOMHFZMJ5/events.json","paper":"https://pith.science/paper/HMKOJ2KY"},"agent_actions":{"view_html":"https://pith.science/pith/HMKOJ2KYSTJFZJOJMDOMHFZMJ5","download_json":"https://pith.science/pith/HMKOJ2KYSTJFZJOJMDOMHFZMJ5.json","view_paper":"https://pith.science/paper/HMKOJ2KY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.04315&json=true","fetch_graph":"https://pith.science/api/pith-number/HMKOJ2KYSTJFZJOJMDOMHFZMJ5/graph.json","fetch_events":"https://pith.science/api/pith-number/HMKOJ2KYSTJFZJOJMDOMHFZMJ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HMKOJ2KYSTJFZJOJMDOMHFZMJ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HMKOJ2KYSTJFZJOJMDOMHFZMJ5/action/storage_attestation","attest_author":"https://pith.science/pith/HMKOJ2KYSTJFZJOJMDOMHFZMJ5/action/author_attestation","sign_citation":"https://pith.science/pith/HMKOJ2KYSTJFZJOJMDOMHFZMJ5/action/citation_signature","submit_replication":"https://pith.science/pith/HMKOJ2KYSTJFZJOJMDOMHFZMJ5/action/replication_record"}},"created_at":"2026-07-05T05:33:57.547543+00:00","updated_at":"2026-07-05T05:33:57.547543+00:00"}