{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:D6HB3XGKWMHPWGN345OTQLF33O","short_pith_number":"pith:D6HB3XGK","schema_version":"1.0","canonical_sha256":"1f8e1ddccab30efb19bbe75d382cbbdba47fa0174a0e2b8977d6f706b1813e81","source":{"kind":"arxiv","id":"1707.07341","version":1},"attestation_state":"computed","paper":{"title":"Prediction-Constrained Training for Semi-Supervised Mixture and Topic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Erik B. Sudderth, Finale Doshi-Velez, Gabriel Hope, Leah Weiner, Michael C. Hughes, Roy H. Perlis, Thomas H. McCoy Jr.","submitted_at":"2017-07-23T20:19:06Z","abstract_excerpt":"Supervisory signals have the potential to make low-dimensional data representations, like those learned by mixture and topic models, more interpretable and useful. We propose a framework for training latent variable models that explicitly balances two goals: recovery of faithful generative explanations of high-dimensional data, and accurate prediction of associated semantic labels. Existing approaches fail to achieve these goals due to an incomplete treatment of a fundamental asymmetry: the intended application is always predicting labels from data, not data from labels. Our prediction-constra"},"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":"1707.07341","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-23T20:19:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e72bd64caa9b1aee710166078d981da2a0e9a1d2c17e576844ebd77785b5b1e5","abstract_canon_sha256":"a1f25045c86aedd873a9322d764a72919faad72551742bf387595c3fa1177998"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:43.759933Z","signature_b64":"uelC3GcJTQgLWm86aoxljV0KCohSibJSDSYI6njk4wvC/YnXRvmENktveF9FOeRrILQM9KuBQ6wpRTevMdO8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f8e1ddccab30efb19bbe75d382cbbdba47fa0174a0e2b8977d6f706b1813e81","last_reissued_at":"2026-05-18T00:30:43.759486Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:43.759486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prediction-Constrained Training for Semi-Supervised Mixture and Topic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Erik B. Sudderth, Finale Doshi-Velez, Gabriel Hope, Leah Weiner, Michael C. Hughes, Roy H. Perlis, Thomas H. McCoy Jr.","submitted_at":"2017-07-23T20:19:06Z","abstract_excerpt":"Supervisory signals have the potential to make low-dimensional data representations, like those learned by mixture and topic models, more interpretable and useful. We propose a framework for training latent variable models that explicitly balances two goals: recovery of faithful generative explanations of high-dimensional data, and accurate prediction of associated semantic labels. Existing approaches fail to achieve these goals due to an incomplete treatment of a fundamental asymmetry: the intended application is always predicting labels from data, not data from labels. Our prediction-constra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.07341","kind":"arxiv","version":1},"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":"1707.07341","created_at":"2026-05-18T00:30:43.759564+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.07341v1","created_at":"2026-05-18T00:30:43.759564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.07341","created_at":"2026-05-18T00:30:43.759564+00:00"},{"alias_kind":"pith_short_12","alias_value":"D6HB3XGKWMHP","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"D6HB3XGKWMHPWGN3","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"D6HB3XGK","created_at":"2026-05-18T12:31:10.602751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02112","citing_title":"An adaptive variance estimator for relative sparsity","ref_index":236,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D6HB3XGKWMHPWGN345OTQLF33O","json":"https://pith.science/pith/D6HB3XGKWMHPWGN345OTQLF33O.json","graph_json":"https://pith.science/api/pith-number/D6HB3XGKWMHPWGN345OTQLF33O/graph.json","events_json":"https://pith.science/api/pith-number/D6HB3XGKWMHPWGN345OTQLF33O/events.json","paper":"https://pith.science/paper/D6HB3XGK"},"agent_actions":{"view_html":"https://pith.science/pith/D6HB3XGKWMHPWGN345OTQLF33O","download_json":"https://pith.science/pith/D6HB3XGKWMHPWGN345OTQLF33O.json","view_paper":"https://pith.science/paper/D6HB3XGK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.07341&json=true","fetch_graph":"https://pith.science/api/pith-number/D6HB3XGKWMHPWGN345OTQLF33O/graph.json","fetch_events":"https://pith.science/api/pith-number/D6HB3XGKWMHPWGN345OTQLF33O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D6HB3XGKWMHPWGN345OTQLF33O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D6HB3XGKWMHPWGN345OTQLF33O/action/storage_attestation","attest_author":"https://pith.science/pith/D6HB3XGKWMHPWGN345OTQLF33O/action/author_attestation","sign_citation":"https://pith.science/pith/D6HB3XGKWMHPWGN345OTQLF33O/action/citation_signature","submit_replication":"https://pith.science/pith/D6HB3XGKWMHPWGN345OTQLF33O/action/replication_record"}},"created_at":"2026-05-18T00:30:43.759564+00:00","updated_at":"2026-05-18T00:30:43.759564+00:00"}