{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:SJ6XLD7EMKBUAPJWD3A6REO4TI","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":"e4db3a80239fb4431e8baedacecd45290c017bf91e9ab214086c2d15c8416127","cross_cats_sorted":["cs.CL","cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-01-22T21:47:48Z","title_canon_sha256":"483d6e5f1f35c672ebe595f9802970c49877195058379ea74aa9851145d81806"},"schema_version":"1.0","source":{"id":"1401.6169","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1401.6169","created_at":"2026-05-18T01:14:59Z"},{"alias_kind":"arxiv_version","alias_value":"1401.6169v2","created_at":"2026-05-18T01:14:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1401.6169","created_at":"2026-05-18T01:14:59Z"},{"alias_kind":"pith_short_12","alias_value":"SJ6XLD7EMKBU","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"SJ6XLD7EMKBUAPJW","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"SJ6XLD7E","created_at":"2026-05-18T12:28:49Z"}],"graph_snapshots":[{"event_id":"sha256:c693adaeeb62908490f8cf6200bbe2f4373285899c75375718c954b79383f938","target":"graph","created_at":"2026-05-18T01:14:59Z","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":"We propose a parsimonious topic model for text corpora. In related models such as Latent Dirichlet Allocation (LDA), all words are modeled topic-specifically, even though many words occur with similar frequencies across different topics. Our modeling determines salient words for each topic, which have topic-specific probabilities, with the rest explained by a universal shared model. Further, in LDA all topics are in principle present in every document. By contrast our model gives sparse topic representation, determining the (small) subset of relevant topics for each document. We derive a Bayes","authors_text":"David J. Miller, Hossein Soleimani","cross_cats":["cs.CL","cs.IR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-01-22T21:47:48Z","title":"Parsimonious Topic Models with Salient Word Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1401.6169","kind":"arxiv","version":2},"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":"sha256:28ba99e20e1970495c5c05de24f55d6fe282721e50b94ab55896faadc4bc0e1a","target":"record","created_at":"2026-05-18T01:14:59Z","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":"e4db3a80239fb4431e8baedacecd45290c017bf91e9ab214086c2d15c8416127","cross_cats_sorted":["cs.CL","cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-01-22T21:47:48Z","title_canon_sha256":"483d6e5f1f35c672ebe595f9802970c49877195058379ea74aa9851145d81806"},"schema_version":"1.0","source":{"id":"1401.6169","kind":"arxiv","version":2}},"canonical_sha256":"927d758fe46283403d361ec1e891dc9a1bde7a4d839d792670bde2009bdad85f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"927d758fe46283403d361ec1e891dc9a1bde7a4d839d792670bde2009bdad85f","first_computed_at":"2026-05-18T01:14:59.062204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:14:59.062204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IFfbSAOqfcS5Z9X5JPw8jYXWhe/E77fZCgrbFXoxvPKevzqR55PypZj06dbCAKiv3ETyUHDnC6EJlqd9VSSgCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:14:59.062653Z","signed_message":"canonical_sha256_bytes"},"source_id":"1401.6169","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28ba99e20e1970495c5c05de24f55d6fe282721e50b94ab55896faadc4bc0e1a","sha256:c693adaeeb62908490f8cf6200bbe2f4373285899c75375718c954b79383f938"],"state_sha256":"276ed867e3fcb0c57d492ec89a24785eb511489f969a0574ac766919b1ead159"}