{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:OWRVFG7XFN3EZG7OMIWDD7YYPC","short_pith_number":"pith:OWRVFG7X","canonical_record":{"source":{"id":"1606.09403","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2016-06-30T09:18:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0eb2b731ff19042ac36b9b66eaab7b8f29c964afcece7cd5fdeabec2c3aaccbf","abstract_canon_sha256":"48a2110566b9b9cb55693b439d3e4cec4822139e9da0eb51d7a3889c38f4ddc7"},"schema_version":"1.0"},"canonical_sha256":"75a3529bf72b764c9bee622c31ff18788b56d30ca3d952733255d4f8e7ca7893","source":{"kind":"arxiv","id":"1606.09403","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.09403","created_at":"2026-05-18T01:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"1606.09403v1","created_at":"2026-05-18T01:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.09403","created_at":"2026-05-18T01:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"OWRVFG7XFN3E","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OWRVFG7XFN3EZG7O","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OWRVFG7X","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:OWRVFG7XFN3EZG7OMIWDD7YYPC","target":"record","payload":{"canonical_record":{"source":{"id":"1606.09403","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2016-06-30T09:18:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0eb2b731ff19042ac36b9b66eaab7b8f29c964afcece7cd5fdeabec2c3aaccbf","abstract_canon_sha256":"48a2110566b9b9cb55693b439d3e4cec4822139e9da0eb51d7a3889c38f4ddc7"},"schema_version":"1.0"},"canonical_sha256":"75a3529bf72b764c9bee622c31ff18788b56d30ca3d952733255d4f8e7ca7893","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:40.514343Z","signature_b64":"oTN5ruxLGEARaTK1nIIS76D83T6dgUaYaeeTaWhjpVjUM9bRkOvBaSc3AFQPc+u2M08QB3gak2yY9vO4Caw3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75a3529bf72b764c9bee622c31ff18788b56d30ca3d952733255d4f8e7ca7893","last_reissued_at":"2026-05-18T01:11:40.513642Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:40.513642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.09403","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:11:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gE9eG5P7Bk/LobdBiwgZAOihwYr915uK7SP+vIVJK5Ig2/d9xlGIEj6H4gp59wphiBRuCABaj2UChHwPLIzNCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T19:11:35.125696Z"},"content_sha256":"c6838dd35e1fb4fe3b29bb7042c35f9abac21e2b37d3f8c542ee306b7b34c649","schema_version":"1.0","event_id":"sha256:c6838dd35e1fb4fe3b29bb7042c35f9abac21e2b37d3f8c542ee306b7b34c649"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:OWRVFG7XFN3EZG7OMIWDD7YYPC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Crosslingual Word Embeddings without Bilingual Corpora","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hiroshi Kanayama, Long Duong, Steven Bird, Tengfei Ma, Trevor Cohn","submitted_at":"2016-06-30T09:18:53Z","abstract_excerpt":"Crosslingual word embeddings represent lexical items from different languages in the same vector space, enabling transfer of NLP tools. However, previous attempts had expensive resource requirements, difficulty incorporating monolingual data or were unable to handle polysemy. We address these drawbacks in our method which takes advantage of a high coverage dictionary in an EM style training algorithm over monolingual corpora in two languages. Our model achieves state-of-the-art performance on bilingual lexicon induction task exceeding models using large bilingual corpora, and competitive resul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.09403","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:11:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5TAPdINe6kvkEb9AQnfFHlSicwIJ+D3iO6Q2uaF5Imc5tyY2O0P0Hd7aFYsHvbZLlMwgdMfqGfe0BK1u1EcFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T19:11:35.126249Z"},"content_sha256":"03345870c61a0b257160d60b6da99a6d1d921c3d2c408e45618d2d6f8c08e1bd","schema_version":"1.0","event_id":"sha256:03345870c61a0b257160d60b6da99a6d1d921c3d2c408e45618d2d6f8c08e1bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OWRVFG7XFN3EZG7OMIWDD7YYPC/bundle.json","state_url":"https://pith.science/pith/OWRVFG7XFN3EZG7OMIWDD7YYPC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OWRVFG7XFN3EZG7OMIWDD7YYPC/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":"2026-05-18T19:11:35Z","links":{"resolver":"https://pith.science/pith/OWRVFG7XFN3EZG7OMIWDD7YYPC","bundle":"https://pith.science/pith/OWRVFG7XFN3EZG7OMIWDD7YYPC/bundle.json","state":"https://pith.science/pith/OWRVFG7XFN3EZG7OMIWDD7YYPC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OWRVFG7XFN3EZG7OMIWDD7YYPC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:OWRVFG7XFN3EZG7OMIWDD7YYPC","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":"48a2110566b9b9cb55693b439d3e4cec4822139e9da0eb51d7a3889c38f4ddc7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2016-06-30T09:18:53Z","title_canon_sha256":"0eb2b731ff19042ac36b9b66eaab7b8f29c964afcece7cd5fdeabec2c3aaccbf"},"schema_version":"1.0","source":{"id":"1606.09403","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.09403","created_at":"2026-05-18T01:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"1606.09403v1","created_at":"2026-05-18T01:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.09403","created_at":"2026-05-18T01:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"OWRVFG7XFN3E","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OWRVFG7XFN3EZG7O","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OWRVFG7X","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:03345870c61a0b257160d60b6da99a6d1d921c3d2c408e45618d2d6f8c08e1bd","target":"graph","created_at":"2026-05-18T01:11:40Z","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":"Crosslingual word embeddings represent lexical items from different languages in the same vector space, enabling transfer of NLP tools. However, previous attempts had expensive resource requirements, difficulty incorporating monolingual data or were unable to handle polysemy. We address these drawbacks in our method which takes advantage of a high coverage dictionary in an EM style training algorithm over monolingual corpora in two languages. Our model achieves state-of-the-art performance on bilingual lexicon induction task exceeding models using large bilingual corpora, and competitive resul","authors_text":"Hiroshi Kanayama, Long Duong, Steven Bird, Tengfei Ma, Trevor Cohn","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2016-06-30T09:18:53Z","title":"Learning Crosslingual Word Embeddings without Bilingual Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.09403","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:c6838dd35e1fb4fe3b29bb7042c35f9abac21e2b37d3f8c542ee306b7b34c649","target":"record","created_at":"2026-05-18T01:11:40Z","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":"48a2110566b9b9cb55693b439d3e4cec4822139e9da0eb51d7a3889c38f4ddc7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2016-06-30T09:18:53Z","title_canon_sha256":"0eb2b731ff19042ac36b9b66eaab7b8f29c964afcece7cd5fdeabec2c3aaccbf"},"schema_version":"1.0","source":{"id":"1606.09403","kind":"arxiv","version":1}},"canonical_sha256":"75a3529bf72b764c9bee622c31ff18788b56d30ca3d952733255d4f8e7ca7893","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75a3529bf72b764c9bee622c31ff18788b56d30ca3d952733255d4f8e7ca7893","first_computed_at":"2026-05-18T01:11:40.513642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:11:40.513642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oTN5ruxLGEARaTK1nIIS76D83T6dgUaYaeeTaWhjpVjUM9bRkOvBaSc3AFQPc+u2M08QB3gak2yY9vO4Caw3Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:11:40.514343Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.09403","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6838dd35e1fb4fe3b29bb7042c35f9abac21e2b37d3f8c542ee306b7b34c649","sha256:03345870c61a0b257160d60b6da99a6d1d921c3d2c408e45618d2d6f8c08e1bd"],"state_sha256":"f7379c990ec5029c6543d21a93c27bf115e49e95749d302cfe6fade8512e5cce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HPtOw1ZYBnowW1P1pVa+DnettOryHFXz+N6l/7VELpcx4dNCDpt0Ap1q9zmdmyJx+9LTk/iZfdNQ6jOcAIa9Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-18T19:11:35.128044Z","bundle_sha256":"184fbf10313159302459cfc3a43f4ef27e0d961c2d940832ee6b091603b0e6ff"}}