{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:5NI6XX4NOFDILMMDJ2WNKKRYUI","short_pith_number":"pith:5NI6XX4N","canonical_record":{"source":{"id":"2103.07040","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-12T02:01:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c3ae4177d2af06d3989a256b6f1367dd907c4fda4586452d78d53a633bbf5b75","abstract_canon_sha256":"cb88708d2f326a6f3c7868e01a329022939afb8176cf3f69a2e23cc255ed2133"},"schema_version":"1.0"},"canonical_sha256":"eb51ebdf8d714685b1834eacd52a38a21003df6d1771b1ab04195c223f4afd85","source":{"kind":"arxiv","id":"2103.07040","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.07040","created_at":"2026-07-05T02:22:27Z"},{"alias_kind":"arxiv_version","alias_value":"2103.07040v1","created_at":"2026-07-05T02:22:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.07040","created_at":"2026-07-05T02:22:27Z"},{"alias_kind":"pith_short_12","alias_value":"5NI6XX4NOFDI","created_at":"2026-07-05T02:22:27Z"},{"alias_kind":"pith_short_16","alias_value":"5NI6XX4NOFDILMMD","created_at":"2026-07-05T02:22:27Z"},{"alias_kind":"pith_short_8","alias_value":"5NI6XX4N","created_at":"2026-07-05T02:22:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:5NI6XX4NOFDILMMDJ2WNKKRYUI","target":"record","payload":{"canonical_record":{"source":{"id":"2103.07040","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-12T02:01:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c3ae4177d2af06d3989a256b6f1367dd907c4fda4586452d78d53a633bbf5b75","abstract_canon_sha256":"cb88708d2f326a6f3c7868e01a329022939afb8176cf3f69a2e23cc255ed2133"},"schema_version":"1.0"},"canonical_sha256":"eb51ebdf8d714685b1834eacd52a38a21003df6d1771b1ab04195c223f4afd85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:27.968016Z","signature_b64":"whaFuHtsJbSSxa6a9MDdwV4FjS72wvs2AddVi+dkOgLufpEQYhSOMqSjAthGQJNzGFFq65DanGM/hWoaHoCoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb51ebdf8d714685b1834eacd52a38a21003df6d1771b1ab04195c223f4afd85","last_reissued_at":"2026-07-05T02:22:27.967554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:27.967554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.07040","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":"2026-07-05T02:22:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D5XR8XgJnvXwLThXKmGtW0J8QtTZBqt7ANggFYMV1SzZ433JbqVEcCMW7E9zTnyeF1XbGk7t9dy+WMf2YCmRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T21:06:11.121142Z"},"content_sha256":"c548973dc466cdb2fb707b014c4af2df1049d628c1332a600efb8d1ba4e51983","schema_version":"1.0","event_id":"sha256:c548973dc466cdb2fb707b014c4af2df1049d628c1332a600efb8d1ba4e51983"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:5NI6XX4NOFDILMMDJ2WNKKRYUI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bilingual Dictionary-based Language Model Pretraining for Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haoying Dai, Jiayong Lin, Shuaicheng Zhang, Yusen Lin","submitted_at":"2021-03-12T02:01:22Z","abstract_excerpt":"Recent studies have demonstrated a perceivable improvement on the performance of neural machine translation by applying cross-lingual language model pretraining (Lample and Conneau, 2019), especially the Translation Language Modeling (TLM). To alleviate the need for expensive parallel corpora by TLM, in this work, we incorporate the translation information from dictionaries into the pretraining process and propose a novel Bilingual Dictionary-based Language Model (BDLM). We evaluate our BDLM in Chinese, English, and Romanian. For Chinese-English, we obtained a 55.0 BLEU on WMT-News19 (Tiedeman"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.07040","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.07040/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":"2026-07-05T02:22:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xUIB5oF4YFF3Vw+xHKlRMLWpRzy9lupb9kh6J4DhLKZt59wrY2RUm/PI9XO+/8UfdhxUWCHejJccZha51DsGDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T21:06:11.121776Z"},"content_sha256":"a7d5787aed925564649eda282a1903c7a4ac6293d36061b807602f9268ca75bf","schema_version":"1.0","event_id":"sha256:a7d5787aed925564649eda282a1903c7a4ac6293d36061b807602f9268ca75bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5NI6XX4NOFDILMMDJ2WNKKRYUI/bundle.json","state_url":"https://pith.science/pith/5NI6XX4NOFDILMMDJ2WNKKRYUI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5NI6XX4NOFDILMMDJ2WNKKRYUI/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":"2026-08-19T21:06:11Z","links":{"resolver":"https://pith.science/pith/5NI6XX4NOFDILMMDJ2WNKKRYUI","bundle":"https://pith.science/pith/5NI6XX4NOFDILMMDJ2WNKKRYUI/bundle.json","state":"https://pith.science/pith/5NI6XX4NOFDILMMDJ2WNKKRYUI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5NI6XX4NOFDILMMDJ2WNKKRYUI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5NI6XX4NOFDILMMDJ2WNKKRYUI","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":"cb88708d2f326a6f3c7868e01a329022939afb8176cf3f69a2e23cc255ed2133","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-12T02:01:22Z","title_canon_sha256":"c3ae4177d2af06d3989a256b6f1367dd907c4fda4586452d78d53a633bbf5b75"},"schema_version":"1.0","source":{"id":"2103.07040","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.07040","created_at":"2026-07-05T02:22:27Z"},{"alias_kind":"arxiv_version","alias_value":"2103.07040v1","created_at":"2026-07-05T02:22:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.07040","created_at":"2026-07-05T02:22:27Z"},{"alias_kind":"pith_short_12","alias_value":"5NI6XX4NOFDI","created_at":"2026-07-05T02:22:27Z"},{"alias_kind":"pith_short_16","alias_value":"5NI6XX4NOFDILMMD","created_at":"2026-07-05T02:22:27Z"},{"alias_kind":"pith_short_8","alias_value":"5NI6XX4N","created_at":"2026-07-05T02:22:27Z"}],"graph_snapshots":[{"event_id":"sha256:a7d5787aed925564649eda282a1903c7a4ac6293d36061b807602f9268ca75bf","target":"graph","created_at":"2026-07-05T02:22:27Z","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/2103.07040/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have demonstrated a perceivable improvement on the performance of neural machine translation by applying cross-lingual language model pretraining (Lample and Conneau, 2019), especially the Translation Language Modeling (TLM). To alleviate the need for expensive parallel corpora by TLM, in this work, we incorporate the translation information from dictionaries into the pretraining process and propose a novel Bilingual Dictionary-based Language Model (BDLM). We evaluate our BDLM in Chinese, English, and Romanian. For Chinese-English, we obtained a 55.0 BLEU on WMT-News19 (Tiedeman","authors_text":"Haoying Dai, Jiayong Lin, Shuaicheng Zhang, Yusen Lin","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-12T02:01:22Z","title":"Bilingual Dictionary-based Language Model Pretraining for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.07040","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:c548973dc466cdb2fb707b014c4af2df1049d628c1332a600efb8d1ba4e51983","target":"record","created_at":"2026-07-05T02:22:27Z","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":"cb88708d2f326a6f3c7868e01a329022939afb8176cf3f69a2e23cc255ed2133","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-12T02:01:22Z","title_canon_sha256":"c3ae4177d2af06d3989a256b6f1367dd907c4fda4586452d78d53a633bbf5b75"},"schema_version":"1.0","source":{"id":"2103.07040","kind":"arxiv","version":1}},"canonical_sha256":"eb51ebdf8d714685b1834eacd52a38a21003df6d1771b1ab04195c223f4afd85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb51ebdf8d714685b1834eacd52a38a21003df6d1771b1ab04195c223f4afd85","first_computed_at":"2026-07-05T02:22:27.967554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:22:27.967554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"whaFuHtsJbSSxa6a9MDdwV4FjS72wvs2AddVi+dkOgLufpEQYhSOMqSjAthGQJNzGFFq65DanGM/hWoaHoCoAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:22:27.968016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.07040","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c548973dc466cdb2fb707b014c4af2df1049d628c1332a600efb8d1ba4e51983","sha256:a7d5787aed925564649eda282a1903c7a4ac6293d36061b807602f9268ca75bf"],"state_sha256":"d5845a388e648e8e166fc7ce141277da3d1c213d2c692fcf9010bdadfa6f56fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"efGF+uJpX5LnxUnrCdXLeULNXpFzx1TAuljIAobg3uOntQS+P50E9myBisfNhzfvuLT5BfaOMVBVr4KYNGwIBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T21:06:11.126776Z","bundle_sha256":"fe9aff1824866b104d21829d4eed207d8b3a7439f9dd63635849f86311dcf309"}}