{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:67DHYZFE4Q4HMUHUOZ2O2RR5EF","short_pith_number":"pith:67DHYZFE","canonical_record":{"source":{"id":"2004.07737","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-16T16:21:17Z","cross_cats_sorted":[],"title_canon_sha256":"c65d74f24d6f5ee26a58e33f27b20d970201b2e7a5323be3e585af3919fa5e01","abstract_canon_sha256":"e58fa82023f00ea1eb37cfbc729a31329a88292dc7e8f93afb98dc6e08152045"},"schema_version":"1.0"},"canonical_sha256":"f7c67c64a4e4387650f47674ed463d216e58d2955d18cc734c3ba0bb94086e6e","source":{"kind":"arxiv","id":"2004.07737","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:67DHYZFE4Q4HMUHUOZ2O2RR5EF","target":"record","payload":{"canonical_record":{"source":{"id":"2004.07737","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-16T16:21:17Z","cross_cats_sorted":[],"title_canon_sha256":"c65d74f24d6f5ee26a58e33f27b20d970201b2e7a5323be3e585af3919fa5e01","abstract_canon_sha256":"e58fa82023f00ea1eb37cfbc729a31329a88292dc7e8f93afb98dc6e08152045"},"schema_version":"1.0"},"canonical_sha256":"f7c67c64a4e4387650f47674ed463d216e58d2955d18cc734c3ba0bb94086e6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:12:41.130445Z","signature_b64":"h+2Z8hx7ShTdGrOC1Ob17zMmFrDu0hrNaYGRggOz6QbIrXeWug37AXv5t1JQEt5RvrPWzwk4cszaworhGtqtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7c67c64a4e4387650f47674ed463d216e58d2955d18cc734c3ba0bb94086e6e","last_reissued_at":"2026-07-05T02:12:41.129955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:12:41.129955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.07737","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:12:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4LLnG02w/GgI/cbG3rTdcvCIXcXkwh35L02y27LdxoW7QNIVPu3s16ToXdvuMBL2P+SHB/JwAuoTp4CDOY3nCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:05:20.066082Z"},"content_sha256":"9bdebd2c87c323bff2e3da5842a45bc87a3db88619be56e5aad4b647c822dbd7","schema_version":"1.0","event_id":"sha256:9bdebd2c87c323bff2e3da5842a45bc87a3db88619be56e5aad4b647c822dbd7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:67DHYZFE4Q4HMUHUOZ2O2RR5EF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-lingual Contextualized Topic Models with Zero-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Debora Nozza, Dirk Hovy, Elisabetta Fersini, Federico Bianchi, Silvia Terragni","submitted_at":"2020-04-16T16:21:17Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.07737","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.07737/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:12:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rdAxJiP+7UhqmmLTx9eReGEeazEOk3XCJGYcHLFjYIzyfB967ENoTmY6xaHiYVcBVXzfsLu9amA28FkOm31yDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:05:20.066509Z"},"content_sha256":"8014090930e9944d38b0da2c47226f0d100609138027e2f436db78723122338f","schema_version":"1.0","event_id":"sha256:8014090930e9944d38b0da2c47226f0d100609138027e2f436db78723122338f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/67DHYZFE4Q4HMUHUOZ2O2RR5EF/bundle.json","state_url":"https://pith.science/pith/67DHYZFE4Q4HMUHUOZ2O2RR5EF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/67DHYZFE4Q4HMUHUOZ2O2RR5EF/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":"2026-07-09T04:05:20Z","links":{"resolver":"https://pith.science/pith/67DHYZFE4Q4HMUHUOZ2O2RR5EF","bundle":"https://pith.science/pith/67DHYZFE4Q4HMUHUOZ2O2RR5EF/bundle.json","state":"https://pith.science/pith/67DHYZFE4Q4HMUHUOZ2O2RR5EF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/67DHYZFE4Q4HMUHUOZ2O2RR5EF/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LFI4bfxkGBomMrrLI70Re53VSaJJtbyjJIM4BPDn6lrnLiKQXmBqZKzEqOw+29f/AHFh4v6AxuH7F5uTmkesBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T04:05:20.068501Z","bundle_sha256":"2df50fa9ecdee6d8e5ba9a08737bd53cca976865fe8bb9b7029c638f69d23d7b"}}