{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:P2YJ5Z5YS335ZJ7C6CENUN6AK3","short_pith_number":"pith:P2YJ5Z5Y","schema_version":"1.0","canonical_sha256":"7eb09ee7b896f7dca7e2f088da37c056f821f644d36d0c1935a3ccd6cdec77fe","source":{"kind":"arxiv","id":"1801.10158","version":2},"attestation_state":"computed","paper":{"title":"Learning to Classify from Impure Samples with High-Dimensional Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["hep-ex","stat.ML"],"primary_cat":"hep-ph","authors_text":"Benjamin Nachman, Eric M. Metodiev, Matthew D. Schwartz, Patrick T. Komiske","submitted_at":"2018-01-30T19:00:00Z","abstract_excerpt":"A persistent challenge in practical classification tasks is that labeled training sets are not always available. In particle physics, this challenge is surmounted by the use of simulations. These simulations accurately reproduce most features of data, but cannot be trusted to capture all of the complex correlations exploitable by modern machine learning methods. Recent work in weakly supervised learning has shown that simple, low-dimensional classifiers can be trained using only the impure mixtures present in data. Here, we demonstrate that complex, high-dimensional classifiers can also be tra"},"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":"1801.10158","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"hep-ph","submitted_at":"2018-01-30T19:00:00Z","cross_cats_sorted":["hep-ex","stat.ML"],"title_canon_sha256":"1e19feed8cd699c3ea06dd81a8ab3e5c986cbd0c9e159e28655a61106214e192","abstract_canon_sha256":"4c818d72164b95b2c2bb45e6bce282ee44c07fe9ad2174f3404dac30ab65fe21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:03.057724Z","signature_b64":"yvBrsXE3nJQEQKLb0ww3+DQ+BtL4MUKDt7O1y2lv22s7vPXJkrT+kladZcLXGvphKzp/7yp3i6D9W4dKNLMsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7eb09ee7b896f7dca7e2f088da37c056f821f644d36d0c1935a3ccd6cdec77fe","last_reissued_at":"2026-05-18T00:10:03.057111Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:03.057111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Classify from Impure Samples with High-Dimensional Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["hep-ex","stat.ML"],"primary_cat":"hep-ph","authors_text":"Benjamin Nachman, Eric M. Metodiev, Matthew D. Schwartz, Patrick T. Komiske","submitted_at":"2018-01-30T19:00:00Z","abstract_excerpt":"A persistent challenge in practical classification tasks is that labeled training sets are not always available. In particle physics, this challenge is surmounted by the use of simulations. These simulations accurately reproduce most features of data, but cannot be trusted to capture all of the complex correlations exploitable by modern machine learning methods. Recent work in weakly supervised learning has shown that simple, low-dimensional classifiers can be trained using only the impure mixtures present in data. Here, we demonstrate that complex, high-dimensional classifiers can also be tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.10158","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":"1801.10158","created_at":"2026-05-18T00:10:03.057194+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.10158v2","created_at":"2026-05-18T00:10:03.057194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.10158","created_at":"2026-05-18T00:10:03.057194+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2YJ5Z5YS335","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2YJ5Z5YS335ZJ7C","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2YJ5Z5Y","created_at":"2026-05-18T12:32:43.782077+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/P2YJ5Z5YS335ZJ7C6CENUN6AK3","json":"https://pith.science/pith/P2YJ5Z5YS335ZJ7C6CENUN6AK3.json","graph_json":"https://pith.science/api/pith-number/P2YJ5Z5YS335ZJ7C6CENUN6AK3/graph.json","events_json":"https://pith.science/api/pith-number/P2YJ5Z5YS335ZJ7C6CENUN6AK3/events.json","paper":"https://pith.science/paper/P2YJ5Z5Y"},"agent_actions":{"view_html":"https://pith.science/pith/P2YJ5Z5YS335ZJ7C6CENUN6AK3","download_json":"https://pith.science/pith/P2YJ5Z5YS335ZJ7C6CENUN6AK3.json","view_paper":"https://pith.science/paper/P2YJ5Z5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.10158&json=true","fetch_graph":"https://pith.science/api/pith-number/P2YJ5Z5YS335ZJ7C6CENUN6AK3/graph.json","fetch_events":"https://pith.science/api/pith-number/P2YJ5Z5YS335ZJ7C6CENUN6AK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2YJ5Z5YS335ZJ7C6CENUN6AK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2YJ5Z5YS335ZJ7C6CENUN6AK3/action/storage_attestation","attest_author":"https://pith.science/pith/P2YJ5Z5YS335ZJ7C6CENUN6AK3/action/author_attestation","sign_citation":"https://pith.science/pith/P2YJ5Z5YS335ZJ7C6CENUN6AK3/action/citation_signature","submit_replication":"https://pith.science/pith/P2YJ5Z5YS335ZJ7C6CENUN6AK3/action/replication_record"}},"created_at":"2026-05-18T00:10:03.057194+00:00","updated_at":"2026-05-18T00:10:03.057194+00:00"}