{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ZDAIZ7L2MTEQXCGIPRBA2EY2J5","short_pith_number":"pith:ZDAIZ7L2","schema_version":"1.0","canonical_sha256":"c8c08cfd7a64c90b88c87c420d131a4f411a13ab551bbd49d35bcd4dce345935","source":{"kind":"arxiv","id":"1610.09064","version":3},"attestation_state":"computed","paper":{"title":"Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ece Kamar, Eric Horvitz, Himabindu Lakkaraju, Rich Caruana","submitted_at":"2016-10-28T02:55:14Z","abstract_excerpt":"Predictive models deployed in the real world may assign incorrect labels to instances with high confidence. Such errors or unknown unknowns are rooted in model incompleteness, and typically arise because of the mismatch between training data and the cases encountered at test time. As the models are blind to such errors, input from an oracle is needed to identify these failures. In this paper, we formulate and address the problem of informed discovery of unknown unknowns of any given predictive model where unknown unknowns occur due to systematic biases in the training data. We propose a model-"},"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":"1610.09064","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-10-28T02:55:14Z","cross_cats_sorted":[],"title_canon_sha256":"697fa311d60c6e5fa554337bb83dfb702f00d6c9c8fc4bcb746aa89479dd6573","abstract_canon_sha256":"14124f8a1eecdb5fc89101e154d3c93f8db5c161d47d64055e0064cddcc5e966"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:20.428371Z","signature_b64":"VOn4QPr2GibGqyfLJWpSZwWJGGKRLOoiIE9oAIs6D+3LX2ndk9Dgawe42K+RhutB9sdiWgW3mom5WidfVds5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8c08cfd7a64c90b88c87c420d131a4f411a13ab551bbd49d35bcd4dce345935","last_reissued_at":"2026-05-18T00:55:20.427671Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:20.427671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ece Kamar, Eric Horvitz, Himabindu Lakkaraju, Rich Caruana","submitted_at":"2016-10-28T02:55:14Z","abstract_excerpt":"Predictive models deployed in the real world may assign incorrect labels to instances with high confidence. Such errors or unknown unknowns are rooted in model incompleteness, and typically arise because of the mismatch between training data and the cases encountered at test time. As the models are blind to such errors, input from an oracle is needed to identify these failures. In this paper, we formulate and address the problem of informed discovery of unknown unknowns of any given predictive model where unknown unknowns occur due to systematic biases in the training data. We propose a model-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.09064","kind":"arxiv","version":3},"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":"1610.09064","created_at":"2026-05-18T00:55:20.427765+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.09064v3","created_at":"2026-05-18T00:55:20.427765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.09064","created_at":"2026-05-18T00:55:20.427765+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDAIZ7L2MTEQ","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDAIZ7L2MTEQXCGI","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDAIZ7L2","created_at":"2026-05-18T12:30:53.716459+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/ZDAIZ7L2MTEQXCGIPRBA2EY2J5","json":"https://pith.science/pith/ZDAIZ7L2MTEQXCGIPRBA2EY2J5.json","graph_json":"https://pith.science/api/pith-number/ZDAIZ7L2MTEQXCGIPRBA2EY2J5/graph.json","events_json":"https://pith.science/api/pith-number/ZDAIZ7L2MTEQXCGIPRBA2EY2J5/events.json","paper":"https://pith.science/paper/ZDAIZ7L2"},"agent_actions":{"view_html":"https://pith.science/pith/ZDAIZ7L2MTEQXCGIPRBA2EY2J5","download_json":"https://pith.science/pith/ZDAIZ7L2MTEQXCGIPRBA2EY2J5.json","view_paper":"https://pith.science/paper/ZDAIZ7L2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.09064&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDAIZ7L2MTEQXCGIPRBA2EY2J5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDAIZ7L2MTEQXCGIPRBA2EY2J5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDAIZ7L2MTEQXCGIPRBA2EY2J5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDAIZ7L2MTEQXCGIPRBA2EY2J5/action/storage_attestation","attest_author":"https://pith.science/pith/ZDAIZ7L2MTEQXCGIPRBA2EY2J5/action/author_attestation","sign_citation":"https://pith.science/pith/ZDAIZ7L2MTEQXCGIPRBA2EY2J5/action/citation_signature","submit_replication":"https://pith.science/pith/ZDAIZ7L2MTEQXCGIPRBA2EY2J5/action/replication_record"}},"created_at":"2026-05-18T00:55:20.427765+00:00","updated_at":"2026-05-18T00:55:20.427765+00:00"}