{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:67DHYZFE4Q4HMUHUOZ2O2RR5EF","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":"e58fa82023f00ea1eb37cfbc729a31329a88292dc7e8f93afb98dc6e08152045","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-16T16:21:17Z","title_canon_sha256":"c65d74f24d6f5ee26a58e33f27b20d970201b2e7a5323be3e585af3919fa5e01"},"schema_version":"1.0","source":{"id":"2004.07737","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.07737","created_at":"2026-07-05T02:12:41Z"},{"alias_kind":"arxiv_version","alias_value":"2004.07737v2","created_at":"2026-07-05T02:12:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.07737","created_at":"2026-07-05T02:12:41Z"},{"alias_kind":"pith_short_12","alias_value":"67DHYZFE4Q4H","created_at":"2026-07-05T02:12:41Z"},{"alias_kind":"pith_short_16","alias_value":"67DHYZFE4Q4HMUHU","created_at":"2026-07-05T02:12:41Z"},{"alias_kind":"pith_short_8","alias_value":"67DHYZFE","created_at":"2026-07-05T02:12:41Z"}],"graph_snapshots":[{"event_id":"sha256:8014090930e9944d38b0da2c47226f0d100609138027e2f436db78723122338f","target":"graph","created_at":"2026-07-05T02:12:41Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.07737/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many data sets (e.g., reviews, forums, news, etc.) exist parallelly in multiple languages. They all cover the same content, but the linguistic differences make it impossible to use traditional, bag-of-word-based topic models. Models have to be either single-language or suffer from a huge, but extremely sparse vocabulary. Both issues can be addressed by transfer learning. In this paper, we introduce a zero-shot cross-lingual topic model. Our model learns topics on one language (here, English), and predicts them for unseen documents in different languages (here, Italian, French, German, and Port","authors_text":"Debora Nozza, Dirk Hovy, Elisabetta Fersini, Federico Bianchi, Silvia Terragni","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-16T16:21:17Z","title":"Cross-lingual Contextualized Topic Models with Zero-shot Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.07737","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":"sha256:9bdebd2c87c323bff2e3da5842a45bc87a3db88619be56e5aad4b647c822dbd7","target":"record","created_at":"2026-07-05T02:12:41Z","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":"e58fa82023f00ea1eb37cfbc729a31329a88292dc7e8f93afb98dc6e08152045","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-16T16:21:17Z","title_canon_sha256":"c65d74f24d6f5ee26a58e33f27b20d970201b2e7a5323be3e585af3919fa5e01"},"schema_version":"1.0","source":{"id":"2004.07737","kind":"arxiv","version":2}},"canonical_sha256":"f7c67c64a4e4387650f47674ed463d216e58d2955d18cc734c3ba0bb94086e6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7c67c64a4e4387650f47674ed463d216e58d2955d18cc734c3ba0bb94086e6e","first_computed_at":"2026-07-05T02:12:41.129955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:12:41.129955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h+2Z8hx7ShTdGrOC1Ob17zMmFrDu0hrNaYGRggOz6QbIrXeWug37AXv5t1JQEt5RvrPWzwk4cszaworhGtqtCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:12:41.130445Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.07737","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9bdebd2c87c323bff2e3da5842a45bc87a3db88619be56e5aad4b647c822dbd7","sha256:8014090930e9944d38b0da2c47226f0d100609138027e2f436db78723122338f"],"state_sha256":"6e25a41cc5aa584b4a74dd7c7501faf4e5a5dc82c489c8e18b46707dd67be76f"}