{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:D6HB3XGKWMHPWGN345OTQLF33O","short_pith_number":"pith:D6HB3XGK","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"},"canonical_sha256":"1f8e1ddccab30efb19bbe75d382cbbdba47fa0174a0e2b8977d6f706b1813e81","source":{"kind":"arxiv","id":"1707.07341","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.07341","created_at":"2026-05-18T00:30:43Z"},{"alias_kind":"arxiv_version","alias_value":"1707.07341v1","created_at":"2026-05-18T00:30:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.07341","created_at":"2026-05-18T00:30:43Z"},{"alias_kind":"pith_short_12","alias_value":"D6HB3XGKWMHP","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"D6HB3XGKWMHPWGN3","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"D6HB3XGK","created_at":"2026-05-18T12:31:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:D6HB3XGKWMHPWGN345OTQLF33O","target":"record","payload":{"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"},"canonical_sha256":"1f8e1ddccab30efb19bbe75d382cbbdba47fa0174a0e2b8977d6f706b1813e81","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"},"source_kind":"arxiv","source_id":"1707.07341","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:30:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pp25eMU0eXKtaN30hKa++XmaZzJtcZM6TAk3vYSwE+jf995oERTvPPsvRqBpGPnoGLMKilfvHpkEWzrjUhE/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:49:11.928734Z"},"content_sha256":"524d362e7119404a3758eb4f3b85ec6e540ebddbb2a8c3765c82a4e68f2dbd88","schema_version":"1.0","event_id":"sha256:524d362e7119404a3758eb4f3b85ec6e540ebddbb2a8c3765c82a4e68f2dbd88"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:D6HB3XGKWMHPWGN345OTQLF33O","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:30:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t0suw9qJc7vjlpX54Ys7H6YS2D+ENZwk9p0CrkfEjy2x8YUuD1F7d2jqUO9DPuTZHdHrtpOoyfHJyWClJUw6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:49:11.929477Z"},"content_sha256":"df740506724991d7af64ce4738e1e7244bb9a2b53f64ef3f9f1dce4f0ab6a39f","schema_version":"1.0","event_id":"sha256:df740506724991d7af64ce4738e1e7244bb9a2b53f64ef3f9f1dce4f0ab6a39f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D6HB3XGKWMHPWGN345OTQLF33O/bundle.json","state_url":"https://pith.science/pith/D6HB3XGKWMHPWGN345OTQLF33O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D6HB3XGKWMHPWGN345OTQLF33O/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T02:49:11Z","links":{"resolver":"https://pith.science/pith/D6HB3XGKWMHPWGN345OTQLF33O","bundle":"https://pith.science/pith/D6HB3XGKWMHPWGN345OTQLF33O/bundle.json","state":"https://pith.science/pith/D6HB3XGKWMHPWGN345OTQLF33O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D6HB3XGKWMHPWGN345OTQLF33O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:D6HB3XGKWMHPWGN345OTQLF33O","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a1f25045c86aedd873a9322d764a72919faad72551742bf387595c3fa1177998","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-23T20:19:06Z","title_canon_sha256":"e72bd64caa9b1aee710166078d981da2a0e9a1d2c17e576844ebd77785b5b1e5"},"schema_version":"1.0","source":{"id":"1707.07341","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.07341","created_at":"2026-05-18T00:30:43Z"},{"alias_kind":"arxiv_version","alias_value":"1707.07341v1","created_at":"2026-05-18T00:30:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.07341","created_at":"2026-05-18T00:30:43Z"},{"alias_kind":"pith_short_12","alias_value":"D6HB3XGKWMHP","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"D6HB3XGKWMHPWGN3","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"D6HB3XGK","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:df740506724991d7af64ce4738e1e7244bb9a2b53f64ef3f9f1dce4f0ab6a39f","target":"graph","created_at":"2026-05-18T00:30:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Erik B. Sudderth, Finale Doshi-Velez, Gabriel Hope, Leah Weiner, Michael C. Hughes, Roy H. Perlis, Thomas H. McCoy Jr.","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-23T20:19:06Z","title":"Prediction-Constrained Training for Semi-Supervised Mixture and Topic Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.07341","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:524d362e7119404a3758eb4f3b85ec6e540ebddbb2a8c3765c82a4e68f2dbd88","target":"record","created_at":"2026-05-18T00:30:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a1f25045c86aedd873a9322d764a72919faad72551742bf387595c3fa1177998","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-23T20:19:06Z","title_canon_sha256":"e72bd64caa9b1aee710166078d981da2a0e9a1d2c17e576844ebd77785b5b1e5"},"schema_version":"1.0","source":{"id":"1707.07341","kind":"arxiv","version":1}},"canonical_sha256":"1f8e1ddccab30efb19bbe75d382cbbdba47fa0174a0e2b8977d6f706b1813e81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f8e1ddccab30efb19bbe75d382cbbdba47fa0174a0e2b8977d6f706b1813e81","first_computed_at":"2026-05-18T00:30:43.759486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:43.759486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uelC3GcJTQgLWm86aoxljV0KCohSibJSDSYI6njk4wvC/YnXRvmENktveF9FOeRrILQM9KuBQ6wpRTevMdO8BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:43.759933Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.07341","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:524d362e7119404a3758eb4f3b85ec6e540ebddbb2a8c3765c82a4e68f2dbd88","sha256:df740506724991d7af64ce4738e1e7244bb9a2b53f64ef3f9f1dce4f0ab6a39f"],"state_sha256":"fa188d1c08226924eab7b130be47fee32c346244c502aec105d4fd75195c2fd1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OIWjIEJi0yFLz+ikAJxkA9B0xI0UvMyrQG1QX7AT6ehM2eBrQ2ZRIRoZ+SsNN6c7wgxfxUJ8SO/7fkq5S/UfCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T02:49:11.933189Z","bundle_sha256":"769d256060fb213b30eb28ecc88b7ec7c77e0a3bcca22e6607ee1e34376e1730"}}