{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:2VHNNPUDYBTZ6OBBZ7KBJEQG2K","short_pith_number":"pith:2VHNNPUD","canonical_record":{"source":{"id":"1901.01577","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-06T17:29:24Z","cross_cats_sorted":[],"title_canon_sha256":"5682bb8d99203bd3e12666714c706418d81273e913dd6ef4eb746105cac2da43","abstract_canon_sha256":"3feb6eb65992d39a85d8f9ed4bd0f201923acb1ee5d849712b33bc8f751668d5"},"schema_version":"1.0"},"canonical_sha256":"d54ed6be83c0679f3821cfd4149206d2969c8c3abc6c6adbda900ff5d35627fd","source":{"kind":"arxiv","id":"1901.01577","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.01577","created_at":"2026-05-17T23:56:51Z"},{"alias_kind":"arxiv_version","alias_value":"1901.01577v1","created_at":"2026-05-17T23:56:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.01577","created_at":"2026-05-17T23:56:51Z"},{"alias_kind":"pith_short_12","alias_value":"2VHNNPUDYBTZ","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2VHNNPUDYBTZ6OBB","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2VHNNPUD","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:2VHNNPUDYBTZ6OBBZ7KBJEQG2K","target":"record","payload":{"canonical_record":{"source":{"id":"1901.01577","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-06T17:29:24Z","cross_cats_sorted":[],"title_canon_sha256":"5682bb8d99203bd3e12666714c706418d81273e913dd6ef4eb746105cac2da43","abstract_canon_sha256":"3feb6eb65992d39a85d8f9ed4bd0f201923acb1ee5d849712b33bc8f751668d5"},"schema_version":"1.0"},"canonical_sha256":"d54ed6be83c0679f3821cfd4149206d2969c8c3abc6c6adbda900ff5d35627fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:51.683037Z","signature_b64":"wCIkMVxlQv9NWhY1d9mOCuEASGsL/8ulUKL+n/FucuJkJwNWbuCvyfPVKInsWth9s3Y7k2n/vaxJAR4OypkWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d54ed6be83c0679f3821cfd4149206d2969c8c3abc6c6adbda900ff5d35627fd","last_reissued_at":"2026-05-17T23:56:51.682650Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:51.682650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.01577","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":"2026-05-17T23:56:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XjkAbgKh9kYSUZDYWN/OnnjWejiiDDCFIB5kRB9869LkVGOtGVIhngPV8KryeZGr6tyekw99NxJD+UmW9rVeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T18:56:34.255162Z"},"content_sha256":"749ed7894950c9ede7a459ca06a55c8b4663e4eb653a456dc9f2f94c8cff638c","schema_version":"1.0","event_id":"sha256:749ed7894950c9ede7a459ca06a55c8b4663e4eb653a456dc9f2f94c8cff638c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:2VHNNPUDYBTZ6OBBZ7KBJEQG2K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Training for Large Vocabulary Translation Using Sparse Lexicon and Word Classes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hermann Ney, Julian Schamper, Yunsu Kim","submitted_at":"2019-01-06T17:29:24Z","abstract_excerpt":"We address for the first time unsupervised training for a translation task with hundreds of thousands of vocabulary words. We scale up the expectation-maximization (EM) algorithm to learn a large translation table without any parallel text or seed lexicon. First, we solve the memory bottleneck and enforce the sparsity with a simple thresholding scheme for the lexicon. Second, we initialize the lexicon training with word classes, which efficiently boosts the performance. Our methods produced promising results on two large-scale unsupervised translation tasks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.01577","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":"2026-05-17T23:56:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JwQlf00aMfI5XgKigKj8hSLzRI9ypSqs/WGzB2ydIDOEoXOE5SSpV9NiiAxR7ptb4GEyp036X4r6awhTeJzdBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T18:56:34.255528Z"},"content_sha256":"e48ec11cb98c05a71359983e2cd0efe1199444c4bb29c6fc0818305d69b84a25","schema_version":"1.0","event_id":"sha256:e48ec11cb98c05a71359983e2cd0efe1199444c4bb29c6fc0818305d69b84a25"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2VHNNPUDYBTZ6OBBZ7KBJEQG2K/bundle.json","state_url":"https://pith.science/pith/2VHNNPUDYBTZ6OBBZ7KBJEQG2K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2VHNNPUDYBTZ6OBBZ7KBJEQG2K/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":"2026-07-03T18:56:34Z","links":{"resolver":"https://pith.science/pith/2VHNNPUDYBTZ6OBBZ7KBJEQG2K","bundle":"https://pith.science/pith/2VHNNPUDYBTZ6OBBZ7KBJEQG2K/bundle.json","state":"https://pith.science/pith/2VHNNPUDYBTZ6OBBZ7KBJEQG2K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2VHNNPUDYBTZ6OBBZ7KBJEQG2K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2VHNNPUDYBTZ6OBBZ7KBJEQG2K","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":"3feb6eb65992d39a85d8f9ed4bd0f201923acb1ee5d849712b33bc8f751668d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-06T17:29:24Z","title_canon_sha256":"5682bb8d99203bd3e12666714c706418d81273e913dd6ef4eb746105cac2da43"},"schema_version":"1.0","source":{"id":"1901.01577","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.01577","created_at":"2026-05-17T23:56:51Z"},{"alias_kind":"arxiv_version","alias_value":"1901.01577v1","created_at":"2026-05-17T23:56:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.01577","created_at":"2026-05-17T23:56:51Z"},{"alias_kind":"pith_short_12","alias_value":"2VHNNPUDYBTZ","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2VHNNPUDYBTZ6OBB","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2VHNNPUD","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:e48ec11cb98c05a71359983e2cd0efe1199444c4bb29c6fc0818305d69b84a25","target":"graph","created_at":"2026-05-17T23:56:51Z","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 address for the first time unsupervised training for a translation task with hundreds of thousands of vocabulary words. We scale up the expectation-maximization (EM) algorithm to learn a large translation table without any parallel text or seed lexicon. First, we solve the memory bottleneck and enforce the sparsity with a simple thresholding scheme for the lexicon. Second, we initialize the lexicon training with word classes, which efficiently boosts the performance. Our methods produced promising results on two large-scale unsupervised translation tasks.","authors_text":"Hermann Ney, Julian Schamper, Yunsu Kim","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-06T17:29:24Z","title":"Unsupervised Training for Large Vocabulary Translation Using Sparse Lexicon and Word Classes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.01577","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":"sha256:749ed7894950c9ede7a459ca06a55c8b4663e4eb653a456dc9f2f94c8cff638c","target":"record","created_at":"2026-05-17T23:56:51Z","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":"3feb6eb65992d39a85d8f9ed4bd0f201923acb1ee5d849712b33bc8f751668d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-06T17:29:24Z","title_canon_sha256":"5682bb8d99203bd3e12666714c706418d81273e913dd6ef4eb746105cac2da43"},"schema_version":"1.0","source":{"id":"1901.01577","kind":"arxiv","version":1}},"canonical_sha256":"d54ed6be83c0679f3821cfd4149206d2969c8c3abc6c6adbda900ff5d35627fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d54ed6be83c0679f3821cfd4149206d2969c8c3abc6c6adbda900ff5d35627fd","first_computed_at":"2026-05-17T23:56:51.682650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:51.682650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wCIkMVxlQv9NWhY1d9mOCuEASGsL/8ulUKL+n/FucuJkJwNWbuCvyfPVKInsWth9s3Y7k2n/vaxJAR4OypkWDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:51.683037Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.01577","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:749ed7894950c9ede7a459ca06a55c8b4663e4eb653a456dc9f2f94c8cff638c","sha256:e48ec11cb98c05a71359983e2cd0efe1199444c4bb29c6fc0818305d69b84a25"],"state_sha256":"39e09ac30e1f4db5b1af6e0c0fc1fcf46a97292985f15d6a61ee298cdd720d46"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VwIO72KP7bPzwKx9xufk6gJ2/jCl3ANOGli5VeI/l0E6Kw554shZadLUSzhvjXrQHUJAF7t4Fr0FyJI1UP7xCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T18:56:34.257556Z","bundle_sha256":"546b8fae520c5c1a6c4a4e5c86d922c61a6ee0e2fe87bc1ce3660a52a9ec0680"}}