{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:YD6BK5C63ON522RRNJ3WXIZKKF","short_pith_number":"pith:YD6BK5C6","canonical_record":{"source":{"id":"1612.01678","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-06T06:07:55Z","cross_cats_sorted":[],"title_canon_sha256":"23e688275eb384afc859bd3844b17c6ef9feec1b3a80b4e05b89aafbfe412579","abstract_canon_sha256":"566f7766098ac18d069e2cf6665cbf281a68e9f60586b4d525f3b3c56a960567"},"schema_version":"1.0"},"canonical_sha256":"c0fc15745edb9bdd6a316a776ba32a5149b03e5edbe8560b5aa075d4f02de341","source":{"kind":"arxiv","id":"1612.01678","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.01678","created_at":"2026-05-18T00:55:47Z"},{"alias_kind":"arxiv_version","alias_value":"1612.01678v1","created_at":"2026-05-18T00:55:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.01678","created_at":"2026-05-18T00:55:47Z"},{"alias_kind":"pith_short_12","alias_value":"YD6BK5C63ON5","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"YD6BK5C63ON522RR","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"YD6BK5C6","created_at":"2026-05-18T12:30:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:YD6BK5C63ON522RRNJ3WXIZKKF","target":"record","payload":{"canonical_record":{"source":{"id":"1612.01678","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-06T06:07:55Z","cross_cats_sorted":[],"title_canon_sha256":"23e688275eb384afc859bd3844b17c6ef9feec1b3a80b4e05b89aafbfe412579","abstract_canon_sha256":"566f7766098ac18d069e2cf6665cbf281a68e9f60586b4d525f3b3c56a960567"},"schema_version":"1.0"},"canonical_sha256":"c0fc15745edb9bdd6a316a776ba32a5149b03e5edbe8560b5aa075d4f02de341","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:47.866241Z","signature_b64":"yqE8WQsAFbliU2erGJbi3u+z+N9YM+YkeJRmX9LuxuCSJU0fI+Q6I91145nIWWCTti3xIvdILkNHClZSVbluDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0fc15745edb9bdd6a316a776ba32a5149b03e5edbe8560b5aa075d4f02de341","last_reissued_at":"2026-05-18T00:55:47.865597Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:47.865597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.01678","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":"2026-05-18T00:55:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SFTssrkBs6QS8B2YCfYga9a4ldl1AaxwCJfmiGuNEb13M3uoPkTbPr31+vMPuOtIbMJmCbSXQO1T6tTd8+ZUAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T23:30:42.023363Z"},"content_sha256":"54b0b23cad2e3113c72b16c665a0fb4dc2f93e5b853cdfafe8c74a4322091ad4","schema_version":"1.0","event_id":"sha256:54b0b23cad2e3113c72b16c665a0fb4dc2f93e5b853cdfafe8c74a4322091ad4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:YD6BK5C63ON522RRNJ3WXIZKKF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Supervised topic models for clinical interpretability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Finale Doshi-Velez, Huseyin Melih Elibol, Michael C. Hughes, Roy Perlis, Thomas McCoy","submitted_at":"2016-12-06T06:07:55Z","abstract_excerpt":"Supervised topic models can help clinical researchers find interpretable cooccurence patterns in count data that are relevant for diagnostics. However, standard formulations of supervised Latent Dirichlet Allocation have two problems. First, when documents have many more words than labels, the influence of the labels will be negligible. Second, due to conditional independence assumptions in the graphical model the impact of supervised labels on the learned topic-word probabilities is often minimal, leading to poor predictions on heldout data. We investigate penalized optimization methods for t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.01678","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":"2026-05-18T00:55:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NJYxyijorDK99HIo0PSO6IK2RIe+zTlvRG2vixL/Ex6qsb1FZ5GBSS356qJCsUbZDpGmRkFOvCeQljDnYAhAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T23:30:42.024025Z"},"content_sha256":"aa8643dab013ee0702bf278abc67c713e8817c530ab59e7ecb88bd66968b30c8","schema_version":"1.0","event_id":"sha256:aa8643dab013ee0702bf278abc67c713e8817c530ab59e7ecb88bd66968b30c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YD6BK5C63ON522RRNJ3WXIZKKF/bundle.json","state_url":"https://pith.science/pith/YD6BK5C63ON522RRNJ3WXIZKKF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YD6BK5C63ON522RRNJ3WXIZKKF/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":"2026-05-27T23:30:42Z","links":{"resolver":"https://pith.science/pith/YD6BK5C63ON522RRNJ3WXIZKKF","bundle":"https://pith.science/pith/YD6BK5C63ON522RRNJ3WXIZKKF/bundle.json","state":"https://pith.science/pith/YD6BK5C63ON522RRNJ3WXIZKKF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YD6BK5C63ON522RRNJ3WXIZKKF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:YD6BK5C63ON522RRNJ3WXIZKKF","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":"566f7766098ac18d069e2cf6665cbf281a68e9f60586b4d525f3b3c56a960567","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-06T06:07:55Z","title_canon_sha256":"23e688275eb384afc859bd3844b17c6ef9feec1b3a80b4e05b89aafbfe412579"},"schema_version":"1.0","source":{"id":"1612.01678","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.01678","created_at":"2026-05-18T00:55:47Z"},{"alias_kind":"arxiv_version","alias_value":"1612.01678v1","created_at":"2026-05-18T00:55:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.01678","created_at":"2026-05-18T00:55:47Z"},{"alias_kind":"pith_short_12","alias_value":"YD6BK5C63ON5","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"YD6BK5C63ON522RR","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"YD6BK5C6","created_at":"2026-05-18T12:30:53Z"}],"graph_snapshots":[{"event_id":"sha256:aa8643dab013ee0702bf278abc67c713e8817c530ab59e7ecb88bd66968b30c8","target":"graph","created_at":"2026-05-18T00:55:47Z","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":"Supervised topic models can help clinical researchers find interpretable cooccurence patterns in count data that are relevant for diagnostics. However, standard formulations of supervised Latent Dirichlet Allocation have two problems. First, when documents have many more words than labels, the influence of the labels will be negligible. Second, due to conditional independence assumptions in the graphical model the impact of supervised labels on the learned topic-word probabilities is often minimal, leading to poor predictions on heldout data. We investigate penalized optimization methods for t","authors_text":"Finale Doshi-Velez, Huseyin Melih Elibol, Michael C. Hughes, Roy Perlis, Thomas McCoy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-06T06:07:55Z","title":"Supervised topic models for clinical interpretability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.01678","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":"sha256:54b0b23cad2e3113c72b16c665a0fb4dc2f93e5b853cdfafe8c74a4322091ad4","target":"record","created_at":"2026-05-18T00:55:47Z","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":"566f7766098ac18d069e2cf6665cbf281a68e9f60586b4d525f3b3c56a960567","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-06T06:07:55Z","title_canon_sha256":"23e688275eb384afc859bd3844b17c6ef9feec1b3a80b4e05b89aafbfe412579"},"schema_version":"1.0","source":{"id":"1612.01678","kind":"arxiv","version":1}},"canonical_sha256":"c0fc15745edb9bdd6a316a776ba32a5149b03e5edbe8560b5aa075d4f02de341","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0fc15745edb9bdd6a316a776ba32a5149b03e5edbe8560b5aa075d4f02de341","first_computed_at":"2026-05-18T00:55:47.865597Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:55:47.865597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yqE8WQsAFbliU2erGJbi3u+z+N9YM+YkeJRmX9LuxuCSJU0fI+Q6I91145nIWWCTti3xIvdILkNHClZSVbluDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:55:47.866241Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.01678","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54b0b23cad2e3113c72b16c665a0fb4dc2f93e5b853cdfafe8c74a4322091ad4","sha256:aa8643dab013ee0702bf278abc67c713e8817c530ab59e7ecb88bd66968b30c8"],"state_sha256":"379edf8bf7c5d245560c1487b8138582be1041d9898a3593a2dc07b78b57a8f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7oIy3SwyXX4D6sLqJtYdkxl8CsksHHPaJhCZ+Uv4IakzK8XUH3leD0BYgFJRn2kXaN2/ZD+yZLRbkBvmZTyZDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T23:30:42.027690Z","bundle_sha256":"8f14da3ab6b810dab80cfcc437a02d3908bb596456534e1f67bbe0797f9e3899"}}