{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:5U6NZTT4WXAV7R6LVWYZRS26HA","short_pith_number":"pith:5U6NZTT4","schema_version":"1.0","canonical_sha256":"ed3cdcce7cb5c15fc7cbadb198cb5e38008982d6ac9d2581853dcf3acf4da620","source":{"kind":"arxiv","id":"1205.2657","version":1},"attestation_state":"computed","paper":{"title":"Multilingual Topic Models for Unaligned Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"David Blei, Jordan Boyd-Graber","submitted_at":"2012-05-09T14:53:11Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1205.2657","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2012-05-09T14:53:11Z","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"title_canon_sha256":"8f4d3ff51ee1bb8e0616a2d9267c35c5377df775d09f26b6a585d529d058fccb","abstract_canon_sha256":"8c30ebe579cceafa0f334e5d0459fb521ceef45aefa9e8d9363228bd7acdf5e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:55:47.594345Z","signature_b64":"m1h/+Eqt837kbk1ylmTndMOOo6fejoygPLv6V0s+t/Q4FU7LgnF5Mc9M1HXUiBxmdcxwrkNH+/5s9ey5y4mmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed3cdcce7cb5c15fc7cbadb198cb5e38008982d6ac9d2581853dcf3acf4da620","last_reissued_at":"2026-05-18T03:55:47.593883Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:55:47.593883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilingual Topic Models for Unaligned Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"David Blei, Jordan Boyd-Graber","submitted_at":"2012-05-09T14:53:11Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.2657","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1205.2657","created_at":"2026-05-18T03:55:47.593950+00:00"},{"alias_kind":"arxiv_version","alias_value":"1205.2657v1","created_at":"2026-05-18T03:55:47.593950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.2657","created_at":"2026-05-18T03:55:47.593950+00:00"},{"alias_kind":"pith_short_12","alias_value":"5U6NZTT4WXAV","created_at":"2026-05-18T12:26:56.085431+00:00"},{"alias_kind":"pith_short_16","alias_value":"5U6NZTT4WXAV7R6L","created_at":"2026-05-18T12:26:56.085431+00:00"},{"alias_kind":"pith_short_8","alias_value":"5U6NZTT4","created_at":"2026-05-18T12:26:56.085431+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03299","citing_title":"LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language Models","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5U6NZTT4WXAV7R6LVWYZRS26HA","json":"https://pith.science/pith/5U6NZTT4WXAV7R6LVWYZRS26HA.json","graph_json":"https://pith.science/api/pith-number/5U6NZTT4WXAV7R6LVWYZRS26HA/graph.json","events_json":"https://pith.science/api/pith-number/5U6NZTT4WXAV7R6LVWYZRS26HA/events.json","paper":"https://pith.science/paper/5U6NZTT4"},"agent_actions":{"view_html":"https://pith.science/pith/5U6NZTT4WXAV7R6LVWYZRS26HA","download_json":"https://pith.science/pith/5U6NZTT4WXAV7R6LVWYZRS26HA.json","view_paper":"https://pith.science/paper/5U6NZTT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1205.2657&json=true","fetch_graph":"https://pith.science/api/pith-number/5U6NZTT4WXAV7R6LVWYZRS26HA/graph.json","fetch_events":"https://pith.science/api/pith-number/5U6NZTT4WXAV7R6LVWYZRS26HA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5U6NZTT4WXAV7R6LVWYZRS26HA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5U6NZTT4WXAV7R6LVWYZRS26HA/action/storage_attestation","attest_author":"https://pith.science/pith/5U6NZTT4WXAV7R6LVWYZRS26HA/action/author_attestation","sign_citation":"https://pith.science/pith/5U6NZTT4WXAV7R6LVWYZRS26HA/action/citation_signature","submit_replication":"https://pith.science/pith/5U6NZTT4WXAV7R6LVWYZRS26HA/action/replication_record"}},"created_at":"2026-05-18T03:55:47.593950+00:00","updated_at":"2026-05-18T03:55:47.593950+00:00"}