{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:EQ7KM3LBNCDSDIBO6Z53ZKAJ6W","short_pith_number":"pith:EQ7KM3LB","schema_version":"1.0","canonical_sha256":"243ea66d61688721a02ef67bbca809f58aa269dfa45ebcac0ed1912eb5f800da","source":{"kind":"arxiv","id":"1708.02949","version":3},"attestation_state":"computed","paper":{"title":"Classification without labels: Learning from mixed samples in high energy physics","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, Jesse Thaler","submitted_at":"2017-08-09T18:00:06Z","abstract_excerpt":"Modern machine learning techniques can be used to construct powerful models for difficult collider physics problems. In many applications, however, these models are trained on imperfect simulations due to a lack of truth-level information in the data, which risks the model learning artifacts of the simulation. In this paper, we introduce the paradigm of classification without labels (CWoLa) in which a classifier is trained to distinguish statistical mixtures of classes, which are common in collider physics. Crucially, neither individual labels nor class proportions are required, yet we prove t"},"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":"1708.02949","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"hep-ph","submitted_at":"2017-08-09T18:00:06Z","cross_cats_sorted":["hep-ex","stat.ML"],"title_canon_sha256":"5938ad87cee5d3abe42155d848cd685aba87536b16c005941a0d8b652b895097","abstract_canon_sha256":"d8ca478c5f01fe9bccac3617b0a5429acfa265121280170920aa74ec686980a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:16.544702Z","signature_b64":"eMGqsMBPlZO0CssEoB31Xs1pAADrm9Ga/fJI1xYQwOfEKCwSCSukmcVHgQBZugpHDd08I1Dtxntjo57YjVvmDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"243ea66d61688721a02ef67bbca809f58aa269dfa45ebcac0ed1912eb5f800da","last_reissued_at":"2026-05-18T00:30:16.544031Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:16.544031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Classification without labels: Learning from mixed samples in high energy physics","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, Jesse Thaler","submitted_at":"2017-08-09T18:00:06Z","abstract_excerpt":"Modern machine learning techniques can be used to construct powerful models for difficult collider physics problems. In many applications, however, these models are trained on imperfect simulations due to a lack of truth-level information in the data, which risks the model learning artifacts of the simulation. In this paper, we introduce the paradigm of classification without labels (CWoLa) in which a classifier is trained to distinguish statistical mixtures of classes, which are common in collider physics. Crucially, neither individual labels nor class proportions are required, yet we prove t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.02949","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":"1708.02949","created_at":"2026-05-18T00:30:16.544142+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.02949v3","created_at":"2026-05-18T00:30:16.544142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.02949","created_at":"2026-05-18T00:30:16.544142+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQ7KM3LBNCDS","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQ7KM3LBNCDSDIBO","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQ7KM3LB","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.07158","citing_title":"Weakly supervised machine learning for model-agnostic searches of new phenomena in the $\\gamma$-ray sky","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20965","citing_title":"Kitchen Sink Anomaly Detection","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQ7KM3LBNCDSDIBO6Z53ZKAJ6W","json":"https://pith.science/pith/EQ7KM3LBNCDSDIBO6Z53ZKAJ6W.json","graph_json":"https://pith.science/api/pith-number/EQ7KM3LBNCDSDIBO6Z53ZKAJ6W/graph.json","events_json":"https://pith.science/api/pith-number/EQ7KM3LBNCDSDIBO6Z53ZKAJ6W/events.json","paper":"https://pith.science/paper/EQ7KM3LB"},"agent_actions":{"view_html":"https://pith.science/pith/EQ7KM3LBNCDSDIBO6Z53ZKAJ6W","download_json":"https://pith.science/pith/EQ7KM3LBNCDSDIBO6Z53ZKAJ6W.json","view_paper":"https://pith.science/paper/EQ7KM3LB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.02949&json=true","fetch_graph":"https://pith.science/api/pith-number/EQ7KM3LBNCDSDIBO6Z53ZKAJ6W/graph.json","fetch_events":"https://pith.science/api/pith-number/EQ7KM3LBNCDSDIBO6Z53ZKAJ6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQ7KM3LBNCDSDIBO6Z53ZKAJ6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQ7KM3LBNCDSDIBO6Z53ZKAJ6W/action/storage_attestation","attest_author":"https://pith.science/pith/EQ7KM3LBNCDSDIBO6Z53ZKAJ6W/action/author_attestation","sign_citation":"https://pith.science/pith/EQ7KM3LBNCDSDIBO6Z53ZKAJ6W/action/citation_signature","submit_replication":"https://pith.science/pith/EQ7KM3LBNCDSDIBO6Z53ZKAJ6W/action/replication_record"}},"created_at":"2026-05-18T00:30:16.544142+00:00","updated_at":"2026-05-18T00:30:16.544142+00:00"}