{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:L2QS5XBESY4ZKEQSNOJ5VV2P3N","short_pith_number":"pith:L2QS5XBE","canonical_record":{"source":{"id":"1712.00499","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-01T21:24:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"559734642a22781e08ad8e5a7339deed7202fdd1edcaa01d43b59f6e216487fa","abstract_canon_sha256":"b6a9194b459df23c627016f91882b2932e3b4388d0d029f172a960c626686133"},"schema_version":"1.0"},"canonical_sha256":"5ea12edc2496399512126b93dad74fdb6707b64d39f0fa1c29e6774b29247db8","source":{"kind":"arxiv","id":"1712.00499","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.00499","created_at":"2026-05-18T00:29:05Z"},{"alias_kind":"arxiv_version","alias_value":"1712.00499v1","created_at":"2026-05-18T00:29:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00499","created_at":"2026-05-18T00:29:05Z"},{"alias_kind":"pith_short_12","alias_value":"L2QS5XBESY4Z","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"L2QS5XBESY4ZKEQS","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"L2QS5XBE","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:L2QS5XBESY4ZKEQSNOJ5VV2P3N","target":"record","payload":{"canonical_record":{"source":{"id":"1712.00499","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-01T21:24:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"559734642a22781e08ad8e5a7339deed7202fdd1edcaa01d43b59f6e216487fa","abstract_canon_sha256":"b6a9194b459df23c627016f91882b2932e3b4388d0d029f172a960c626686133"},"schema_version":"1.0"},"canonical_sha256":"5ea12edc2496399512126b93dad74fdb6707b64d39f0fa1c29e6774b29247db8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:05.114885Z","signature_b64":"tCBe12oVguG94xfuOfr+bo0kiaozjvJQq3dpI+Sq0JAKQ9YBjlohXNJbDH+pDbeh6mTSCuIjbwqcPT71W2tpAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ea12edc2496399512126b93dad74fdb6707b64d39f0fa1c29e6774b29247db8","last_reissued_at":"2026-05-18T00:29:05.114284Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:05.114284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.00499","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":"2026-05-18T00:29:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CagGv/nzXjqj//kAXx38Ye7B86GfMORCeYGdOLzx+FOLhvKqtzRZRz31hgof6PDOYVjMK6RgwsKAZReGatchBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:55:11.997384Z"},"content_sha256":"141f82189af3c91d756a1ae32168c5f4b066a3eda5497ad4b29a3eae377cb4f9","schema_version":"1.0","event_id":"sha256:141f82189af3c91d756a1ae32168c5f4b066a3eda5497ad4b29a3eae377cb4f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:L2QS5XBESY4ZKEQSNOJ5VV2P3N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prediction-Constrained Topic Models for Antidepressant Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Erik B. Sudderth, Finale Doshi-Velez, Gabriel Hope, Leah Weiner, Michael C. Hughes, Roy H. Perlis, Thomas H. McCoy","submitted_at":"2017-12-01T21:24:26Z","abstract_excerpt":"Supervisory signals can help topic models discover low-dimensional data representations that are more interpretable for clinical tasks. We propose a framework for training supervised latent Dirichlet allocation that balances two goals: faithful generative explanations of high-dimensional data and accurate prediction of associated class labels. Existing approaches fail to balance these goals by not properly handling a fundamental asymmetry: the intended task is always predicting labels from data, not data from labels. Our new prediction-constrained objective trains models that predict labels fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00499","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":"2026-05-18T00:29:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h9ZNJghlW97Ut1pROr/+VQ0J100RarXf8WLgg9y55dsus9FPtydtm5Tpz3R7Ftcs3c0ZMjoFOhTgSCOQSBrTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:55:11.998095Z"},"content_sha256":"71062286bad05ee5c51ae3443cd1a0b65895de4b8565279b63b6cd9c361a03f5","schema_version":"1.0","event_id":"sha256:71062286bad05ee5c51ae3443cd1a0b65895de4b8565279b63b6cd9c361a03f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L2QS5XBESY4ZKEQSNOJ5VV2P3N/bundle.json","state_url":"https://pith.science/pith/L2QS5XBESY4ZKEQSNOJ5VV2P3N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L2QS5XBESY4ZKEQSNOJ5VV2P3N/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":"2026-05-27T02:55:11Z","links":{"resolver":"https://pith.science/pith/L2QS5XBESY4ZKEQSNOJ5VV2P3N","bundle":"https://pith.science/pith/L2QS5XBESY4ZKEQSNOJ5VV2P3N/bundle.json","state":"https://pith.science/pith/L2QS5XBESY4ZKEQSNOJ5VV2P3N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L2QS5XBESY4ZKEQSNOJ5VV2P3N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:L2QS5XBESY4ZKEQSNOJ5VV2P3N","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":"b6a9194b459df23c627016f91882b2932e3b4388d0d029f172a960c626686133","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-01T21:24:26Z","title_canon_sha256":"559734642a22781e08ad8e5a7339deed7202fdd1edcaa01d43b59f6e216487fa"},"schema_version":"1.0","source":{"id":"1712.00499","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.00499","created_at":"2026-05-18T00:29:05Z"},{"alias_kind":"arxiv_version","alias_value":"1712.00499v1","created_at":"2026-05-18T00:29:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00499","created_at":"2026-05-18T00:29:05Z"},{"alias_kind":"pith_short_12","alias_value":"L2QS5XBESY4Z","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"L2QS5XBESY4ZKEQS","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"L2QS5XBE","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:71062286bad05ee5c51ae3443cd1a0b65895de4b8565279b63b6cd9c361a03f5","target":"graph","created_at":"2026-05-18T00:29:05Z","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 can help topic models discover low-dimensional data representations that are more interpretable for clinical tasks. We propose a framework for training supervised latent Dirichlet allocation that balances two goals: faithful generative explanations of high-dimensional data and accurate prediction of associated class labels. Existing approaches fail to balance these goals by not properly handling a fundamental asymmetry: the intended task is always predicting labels from data, not data from labels. Our new prediction-constrained objective trains models that predict labels fr","authors_text":"Erik B. Sudderth, Finale Doshi-Velez, Gabriel Hope, Leah Weiner, Michael C. Hughes, Roy H. Perlis, Thomas H. McCoy","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-01T21:24:26Z","title":"Prediction-Constrained Topic Models for Antidepressant Recommendation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00499","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":"sha256:141f82189af3c91d756a1ae32168c5f4b066a3eda5497ad4b29a3eae377cb4f9","target":"record","created_at":"2026-05-18T00:29:05Z","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":"b6a9194b459df23c627016f91882b2932e3b4388d0d029f172a960c626686133","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-01T21:24:26Z","title_canon_sha256":"559734642a22781e08ad8e5a7339deed7202fdd1edcaa01d43b59f6e216487fa"},"schema_version":"1.0","source":{"id":"1712.00499","kind":"arxiv","version":1}},"canonical_sha256":"5ea12edc2496399512126b93dad74fdb6707b64d39f0fa1c29e6774b29247db8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ea12edc2496399512126b93dad74fdb6707b64d39f0fa1c29e6774b29247db8","first_computed_at":"2026-05-18T00:29:05.114284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:05.114284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tCBe12oVguG94xfuOfr+bo0kiaozjvJQq3dpI+Sq0JAKQ9YBjlohXNJbDH+pDbeh6mTSCuIjbwqcPT71W2tpAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:05.114885Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.00499","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:141f82189af3c91d756a1ae32168c5f4b066a3eda5497ad4b29a3eae377cb4f9","sha256:71062286bad05ee5c51ae3443cd1a0b65895de4b8565279b63b6cd9c361a03f5"],"state_sha256":"4f8b97a537006c7ac9b2ab8de7d634b436fb6832149d573b959582a67973d5e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7H2Ti6tazXEd547u5/t5opIxwoy8tUcCxBh4PK3V2h0zaNEeddOp6tO018w2apE2x5jKLi4s2j5QC0nTb/B9DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T02:55:12.002305Z","bundle_sha256":"2b901c08d716909868b76fa52c1ed3d1b9b9669accf5d536662c57e0fad9288f"}}