{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:5U6NZTT4WXAV7R6LVWYZRS26HA","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":"8c30ebe579cceafa0f334e5d0459fb521ceef45aefa9e8d9363228bd7acdf5e7","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2012-05-09T14:53:11Z","title_canon_sha256":"8f4d3ff51ee1bb8e0616a2d9267c35c5377df775d09f26b6a585d529d058fccb"},"schema_version":"1.0","source":{"id":"1205.2657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1205.2657","created_at":"2026-05-18T03:55:47Z"},{"alias_kind":"arxiv_version","alias_value":"1205.2657v1","created_at":"2026-05-18T03:55:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.2657","created_at":"2026-05-18T03:55:47Z"},{"alias_kind":"pith_short_12","alias_value":"5U6NZTT4WXAV","created_at":"2026-05-18T12:26:56Z"},{"alias_kind":"pith_short_16","alias_value":"5U6NZTT4WXAV7R6L","created_at":"2026-05-18T12:26:56Z"},{"alias_kind":"pith_short_8","alias_value":"5U6NZTT4","created_at":"2026-05-18T12:26:56Z"}],"graph_snapshots":[{"event_id":"sha256:1184cb2b289c6de4f0e49959bf8a21ced3cbdad64f05797533850b725cbbb820","target":"graph","created_at":"2026-05-18T03:55:47Z","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":"We develop the multilingual topic model for unaligned text (MuTo), a probabilistic model of text that is designed to analyze corpora composed of documents in two languages. From these documents, MuTo uses stochastic EM to simultaneously discover both a matching between the languages and multilingual latent topics. We demonstrate that MuTo is able to find shared topics on real-world multilingual corpora, successfully pairing related documents across languages. MuTo provides a new framework for creating multilingual topic models without needing carefully curated parallel corpora and allows appli","authors_text":"David Blei, Jordan Boyd-Graber","cross_cats":["cs.IR","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2012-05-09T14:53:11Z","title":"Multilingual Topic Models for Unaligned Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.2657","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":"sha256:3e6c5441190349a80b8dd5c3c3a1d9e94faefa5fb58a49bc7446b12623a1ff1c","target":"record","created_at":"2026-05-18T03:55:47Z","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":"8c30ebe579cceafa0f334e5d0459fb521ceef45aefa9e8d9363228bd7acdf5e7","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2012-05-09T14:53:11Z","title_canon_sha256":"8f4d3ff51ee1bb8e0616a2d9267c35c5377df775d09f26b6a585d529d058fccb"},"schema_version":"1.0","source":{"id":"1205.2657","kind":"arxiv","version":1}},"canonical_sha256":"ed3cdcce7cb5c15fc7cbadb198cb5e38008982d6ac9d2581853dcf3acf4da620","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed3cdcce7cb5c15fc7cbadb198cb5e38008982d6ac9d2581853dcf3acf4da620","first_computed_at":"2026-05-18T03:55:47.593883Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:55:47.593883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m1h/+Eqt837kbk1ylmTndMOOo6fejoygPLv6V0s+t/Q4FU7LgnF5Mc9M1HXUiBxmdcxwrkNH+/5s9ey5y4mmBw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:55:47.594345Z","signed_message":"canonical_sha256_bytes"},"source_id":"1205.2657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e6c5441190349a80b8dd5c3c3a1d9e94faefa5fb58a49bc7446b12623a1ff1c","sha256:1184cb2b289c6de4f0e49959bf8a21ced3cbdad64f05797533850b725cbbb820"],"state_sha256":"8f2ec12d2b246db328e71606affd1cb82cc23a870220115db5f90527bb6d9021"}