{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:7UUBQQ5RN6VRF6PY3VDXUXYGYO","short_pith_number":"pith:7UUBQQ5R","schema_version":"1.0","canonical_sha256":"fd281843b16fab12f9f8dd477a5f06c3b21c873ff47debdd41b740cd98ec7723","source":{"kind":"arxiv","id":"1309.6392","version":2},"attestation_state":"computed","paper":{"title":"Peeking Inside the Black Box: Visualizing Statistical Learning with Plots of Individual Conditional Expectation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Adam Kapelner, Alex Goldstein, Emil Pitkin, Justin Bleich","submitted_at":"2013-09-25T03:34:37Z","abstract_excerpt":"This article presents Individual Conditional Expectation (ICE) plots, a tool for visualizing the model estimated by any supervised learning algorithm. Classical partial dependence plots (PDPs) help visualize the average partial relationship between the predicted response and one or more features. In the presence of substantial interaction effects, the partial response relationship can be heterogeneous. Thus, an average curve, such as the PDP, can obfuscate the complexity of the modeled relationship. Accordingly, ICE plots refine the partial dependence plot by graphing the functional relationsh"},"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":"1309.6392","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2013-09-25T03:34:37Z","cross_cats_sorted":[],"title_canon_sha256":"bd4a3eb5c84742cccd7bf110f67339b9f30ee137060e97420f4dcf2320275b25","abstract_canon_sha256":"a9a7de15a9b50631e0f82d21637c6706984f3931125eae4b3c98379181e8e356"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:55:58.873037Z","signature_b64":"TTXTAbqgHZ3IUDRs8FnGXkfqwm04eU9/EFyw0N7u+ToidwR5rzUK/S0fBmez0dKWKKUlj2KQYWmy1OBD2jESDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd281843b16fab12f9f8dd477a5f06c3b21c873ff47debdd41b740cd98ec7723","last_reissued_at":"2026-05-18T02:55:58.872660Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:55:58.872660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Peeking Inside the Black Box: Visualizing Statistical Learning with Plots of Individual Conditional Expectation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Adam Kapelner, Alex Goldstein, Emil Pitkin, Justin Bleich","submitted_at":"2013-09-25T03:34:37Z","abstract_excerpt":"This article presents Individual Conditional Expectation (ICE) plots, a tool for visualizing the model estimated by any supervised learning algorithm. Classical partial dependence plots (PDPs) help visualize the average partial relationship between the predicted response and one or more features. In the presence of substantial interaction effects, the partial response relationship can be heterogeneous. Thus, an average curve, such as the PDP, can obfuscate the complexity of the modeled relationship. Accordingly, ICE plots refine the partial dependence plot by graphing the functional relationsh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1309.6392","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":""},"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":"1309.6392","created_at":"2026-05-18T02:55:58.872714+00:00"},{"alias_kind":"arxiv_version","alias_value":"1309.6392v2","created_at":"2026-05-18T02:55:58.872714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1309.6392","created_at":"2026-05-18T02:55:58.872714+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UUBQQ5RN6VR","created_at":"2026-05-18T12:27:38.830355+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UUBQQ5RN6VRF6PY","created_at":"2026-05-18T12:27:38.830355+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UUBQQ5R","created_at":"2026-05-18T12:27:38.830355+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2402.16391","citing_title":"Industry Practitioners Perspectives on AI Model Quality: Perceptions, Challenges, and Solutions","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12350","citing_title":"A New Technique for AI Explainability using Feature Association Map","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12350","citing_title":"A New Technique for AI Explainability using Feature Association Map","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12350","citing_title":"A New Technique for AI Explainability using Feature Association Map","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7UUBQQ5RN6VRF6PY3VDXUXYGYO","json":"https://pith.science/pith/7UUBQQ5RN6VRF6PY3VDXUXYGYO.json","graph_json":"https://pith.science/api/pith-number/7UUBQQ5RN6VRF6PY3VDXUXYGYO/graph.json","events_json":"https://pith.science/api/pith-number/7UUBQQ5RN6VRF6PY3VDXUXYGYO/events.json","paper":"https://pith.science/paper/7UUBQQ5R"},"agent_actions":{"view_html":"https://pith.science/pith/7UUBQQ5RN6VRF6PY3VDXUXYGYO","download_json":"https://pith.science/pith/7UUBQQ5RN6VRF6PY3VDXUXYGYO.json","view_paper":"https://pith.science/paper/7UUBQQ5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1309.6392&json=true","fetch_graph":"https://pith.science/api/pith-number/7UUBQQ5RN6VRF6PY3VDXUXYGYO/graph.json","fetch_events":"https://pith.science/api/pith-number/7UUBQQ5RN6VRF6PY3VDXUXYGYO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UUBQQ5RN6VRF6PY3VDXUXYGYO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UUBQQ5RN6VRF6PY3VDXUXYGYO/action/storage_attestation","attest_author":"https://pith.science/pith/7UUBQQ5RN6VRF6PY3VDXUXYGYO/action/author_attestation","sign_citation":"https://pith.science/pith/7UUBQQ5RN6VRF6PY3VDXUXYGYO/action/citation_signature","submit_replication":"https://pith.science/pith/7UUBQQ5RN6VRF6PY3VDXUXYGYO/action/replication_record"}},"created_at":"2026-05-18T02:55:58.872714+00:00","updated_at":"2026-05-18T02:55:58.872714+00:00"}