{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:R4MZT466Z2LTY26P4WVQINASCP","short_pith_number":"pith:R4MZT466","canonical_record":{"source":{"id":"1205.1053","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-04T03:14:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"740659d43fbfa01aa92d516a05b63ace5a3f06f03affec054e9f9c9f6e11f074","abstract_canon_sha256":"864bc81a5918d7201cdf2fc8e3caef292babe019ac0917e6bc9ed61482c28985"},"schema_version":"1.0"},"canonical_sha256":"8f1999f3dece973c6bcfe5ab04341213d19bc9deab06e529a2bc3a1903866da6","source":{"kind":"arxiv","id":"1205.1053","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1205.1053","created_at":"2026-05-18T03:56:12Z"},{"alias_kind":"arxiv_version","alias_value":"1205.1053v1","created_at":"2026-05-18T03:56:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.1053","created_at":"2026-05-18T03:56:12Z"},{"alias_kind":"pith_short_12","alias_value":"R4MZT466Z2LT","created_at":"2026-05-18T12:27:20Z"},{"alias_kind":"pith_short_16","alias_value":"R4MZT466Z2LTY26P","created_at":"2026-05-18T12:27:20Z"},{"alias_kind":"pith_short_8","alias_value":"R4MZT466","created_at":"2026-05-18T12:27:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:R4MZT466Z2LTY26P4WVQINASCP","target":"record","payload":{"canonical_record":{"source":{"id":"1205.1053","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-04T03:14:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"740659d43fbfa01aa92d516a05b63ace5a3f06f03affec054e9f9c9f6e11f074","abstract_canon_sha256":"864bc81a5918d7201cdf2fc8e3caef292babe019ac0917e6bc9ed61482c28985"},"schema_version":"1.0"},"canonical_sha256":"8f1999f3dece973c6bcfe5ab04341213d19bc9deab06e529a2bc3a1903866da6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:56:12.247890Z","signature_b64":"e2M23FMvO/y4hzge7GR5ogTkKxWYl5FEjVTKOu+Y0hioTPJZw/9jSMSXimFY4pwuWjOE2wuC1O1sGU2lE83kAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f1999f3dece973c6bcfe5ab04341213d19bc9deab06e529a2bc3a1903866da6","last_reissued_at":"2026-05-18T03:56:12.247373Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:56:12.247373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1205.1053","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":"2026-05-18T03:56:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9fEIPH8/1j3cZGi9iflaYLSGsQHKSQGt99zsYWukt/F8KaIWK6aran6zYAxUkWDsXHZxkMSwht6Yca8E0lEfAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T02:42:29.315222Z"},"content_sha256":"b66e79bac20f2c871a2e8c84868f4d49e501592a8f3e29137dd116e18f2fe0e2","schema_version":"1.0","event_id":"sha256:b66e79bac20f2c871a2e8c84868f4d49e501592a8f3e29137dd116e18f2fe0e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:R4MZT466Z2LTY26P4WVQINASCP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variable Selection for Latent Dirichlet Allocation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alice Oh, Dongwoo Kim, Yeonseung Chung","submitted_at":"2012-05-04T03:14:18Z","abstract_excerpt":"In latent Dirichlet allocation (LDA), topics are multinomial distributions over the entire vocabulary. However, the vocabulary usually contains many words that are not relevant in forming the topics. We adopt a variable selection method widely used in statistical modeling as a dimension reduction tool and combine it with LDA. In this variable selection model for LDA (vsLDA), topics are multinomial distributions over a subset of the vocabulary, and by excluding words that are not informative for finding the latent topic structure of the corpus, vsLDA finds topics that are more robust and discri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.1053","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":"2026-05-18T03:56:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zC6KiBaxFyG96E0jrZugd+bwAexxXqFW//YcqDR/To/vC7S8IhKVRSIFzSW6ploR/C4Wdd8YKusjNdQBXbjhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T02:42:29.315589Z"},"content_sha256":"d5e8fb369e2e3746dc32d3812dd7135b0b80e71fba0cef32a1dd682073dc69de","schema_version":"1.0","event_id":"sha256:d5e8fb369e2e3746dc32d3812dd7135b0b80e71fba0cef32a1dd682073dc69de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R4MZT466Z2LTY26P4WVQINASCP/bundle.json","state_url":"https://pith.science/pith/R4MZT466Z2LTY26P4WVQINASCP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R4MZT466Z2LTY26P4WVQINASCP/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":"2026-06-04T02:42:29Z","links":{"resolver":"https://pith.science/pith/R4MZT466Z2LTY26P4WVQINASCP","bundle":"https://pith.science/pith/R4MZT466Z2LTY26P4WVQINASCP/bundle.json","state":"https://pith.science/pith/R4MZT466Z2LTY26P4WVQINASCP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R4MZT466Z2LTY26P4WVQINASCP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:R4MZT466Z2LTY26P4WVQINASCP","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":"864bc81a5918d7201cdf2fc8e3caef292babe019ac0917e6bc9ed61482c28985","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-04T03:14:18Z","title_canon_sha256":"740659d43fbfa01aa92d516a05b63ace5a3f06f03affec054e9f9c9f6e11f074"},"schema_version":"1.0","source":{"id":"1205.1053","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1205.1053","created_at":"2026-05-18T03:56:12Z"},{"alias_kind":"arxiv_version","alias_value":"1205.1053v1","created_at":"2026-05-18T03:56:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.1053","created_at":"2026-05-18T03:56:12Z"},{"alias_kind":"pith_short_12","alias_value":"R4MZT466Z2LT","created_at":"2026-05-18T12:27:20Z"},{"alias_kind":"pith_short_16","alias_value":"R4MZT466Z2LTY26P","created_at":"2026-05-18T12:27:20Z"},{"alias_kind":"pith_short_8","alias_value":"R4MZT466","created_at":"2026-05-18T12:27:20Z"}],"graph_snapshots":[{"event_id":"sha256:d5e8fb369e2e3746dc32d3812dd7135b0b80e71fba0cef32a1dd682073dc69de","target":"graph","created_at":"2026-05-18T03:56:12Z","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":"In latent Dirichlet allocation (LDA), topics are multinomial distributions over the entire vocabulary. However, the vocabulary usually contains many words that are not relevant in forming the topics. We adopt a variable selection method widely used in statistical modeling as a dimension reduction tool and combine it with LDA. In this variable selection model for LDA (vsLDA), topics are multinomial distributions over a subset of the vocabulary, and by excluding words that are not informative for finding the latent topic structure of the corpus, vsLDA finds topics that are more robust and discri","authors_text":"Alice Oh, Dongwoo Kim, Yeonseung Chung","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-04T03:14:18Z","title":"Variable Selection for Latent Dirichlet Allocation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.1053","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:b66e79bac20f2c871a2e8c84868f4d49e501592a8f3e29137dd116e18f2fe0e2","target":"record","created_at":"2026-05-18T03:56:12Z","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":"864bc81a5918d7201cdf2fc8e3caef292babe019ac0917e6bc9ed61482c28985","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-04T03:14:18Z","title_canon_sha256":"740659d43fbfa01aa92d516a05b63ace5a3f06f03affec054e9f9c9f6e11f074"},"schema_version":"1.0","source":{"id":"1205.1053","kind":"arxiv","version":1}},"canonical_sha256":"8f1999f3dece973c6bcfe5ab04341213d19bc9deab06e529a2bc3a1903866da6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f1999f3dece973c6bcfe5ab04341213d19bc9deab06e529a2bc3a1903866da6","first_computed_at":"2026-05-18T03:56:12.247373Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:56:12.247373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e2M23FMvO/y4hzge7GR5ogTkKxWYl5FEjVTKOu+Y0hioTPJZw/9jSMSXimFY4pwuWjOE2wuC1O1sGU2lE83kAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:56:12.247890Z","signed_message":"canonical_sha256_bytes"},"source_id":"1205.1053","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b66e79bac20f2c871a2e8c84868f4d49e501592a8f3e29137dd116e18f2fe0e2","sha256:d5e8fb369e2e3746dc32d3812dd7135b0b80e71fba0cef32a1dd682073dc69de"],"state_sha256":"6608a479289bc83ff942be12fe19dde5b2f0a3633c5ce4b39226b6bc5117beaf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HvG/sYWHvw9fOZ5XoXf7PYccalUHMXYD6elOuAc6T4qvZ7tcFN3IB1i5NCA5EaEFqcpwn7aW3MmWz3fJR+SfCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T02:42:29.317470Z","bundle_sha256":"0c481a538151d6c47dd4e16e46217e1967ae9ac56b8786e53e68ba567de71387"}}