{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:57KWUUINNQJ3TZ65G4GUVAD6UH","short_pith_number":"pith:57KWUUIN","canonical_record":{"source":{"id":"1911.10235","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-22T20:11:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fe30e2e617361652e8ce2fd3927eccc48664473b57f4a110843c6899c4f2d8c8","abstract_canon_sha256":"066b9fa269e643db7308077d638c3225d596484b9139edd215022003513b452f"},"schema_version":"1.0"},"canonical_sha256":"efd56a510d6c13b9e7dd370d4a807ea1e887d5bc7c8a658842632fbecc8ccce5","source":{"kind":"arxiv","id":"1911.10235","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.10235","created_at":"2026-07-05T00:23:08Z"},{"alias_kind":"arxiv_version","alias_value":"1911.10235v1","created_at":"2026-07-05T00:23:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.10235","created_at":"2026-07-05T00:23:08Z"},{"alias_kind":"pith_short_12","alias_value":"57KWUUINNQJ3","created_at":"2026-07-05T00:23:08Z"},{"alias_kind":"pith_short_16","alias_value":"57KWUUINNQJ3TZ65","created_at":"2026-07-05T00:23:08Z"},{"alias_kind":"pith_short_8","alias_value":"57KWUUIN","created_at":"2026-07-05T00:23:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:57KWUUINNQJ3TZ65G4GUVAD6UH","target":"record","payload":{"canonical_record":{"source":{"id":"1911.10235","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-22T20:11:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fe30e2e617361652e8ce2fd3927eccc48664473b57f4a110843c6899c4f2d8c8","abstract_canon_sha256":"066b9fa269e643db7308077d638c3225d596484b9139edd215022003513b452f"},"schema_version":"1.0"},"canonical_sha256":"efd56a510d6c13b9e7dd370d4a807ea1e887d5bc7c8a658842632fbecc8ccce5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:08.811088Z","signature_b64":"34sjxMT76iD6TqFtpGnvE/Lmlpp9A/AbVhF+TEmvYmd2g/jmUnrhQEapjEPhdjQSP92HRbKALsD/Lm5y2PcKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efd56a510d6c13b9e7dd370d4a807ea1e887d5bc7c8a658842632fbecc8ccce5","last_reissued_at":"2026-07-05T00:23:08.810689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:08.810689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.10235","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":"2026-07-05T00:23:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CI59IBK36hWkWRSsRFSJXJFH41dChHeTGKblFl2xA+XnQMBmALGye39MdmDUa7cqlddnm9IamKwaDgfBrRXNCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:34:09.458816Z"},"content_sha256":"9cf0c3485d43402b08e1cb023eb711e26e17505664a632038595967ee0da5f28","schema_version":"1.0","event_id":"sha256:9cf0c3485d43402b08e1cb023eb711e26e17505664a632038595967ee0da5f28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:57KWUUINNQJ3TZ65G4GUVAD6UH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving N-gram Language Models with Pre-trained Deep Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"ChengXiang Zhai, Fuchun Peng, Hongzhao Huang, Yiren Wang, Yongqiang Wang, Yutong Pang, Zhe Liu","submitted_at":"2019-11-22T20:11:40Z","abstract_excerpt":"Although n-gram language models (LMs) have been outperformed by the state-of-the-art neural LMs, they are still widely used in speech recognition due to its high efficiency in inference. In this paper, we demonstrate that n-gram LM can be improved by neural LMs through a text generation based data augmentation method. In contrast to previous approaches, we employ a large-scale general domain pre-training followed by in-domain fine-tuning strategy to construct deep Transformer based neural LMs. Large amount of in-domain text data is generated with the well trained deep Transformer to construct "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.10235","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/1911.10235/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":"2026-07-05T00:23:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1jVaFaKnwfoQn26bszUXeuavjf3jYHTHqtKq0KDVQZQ/b58cAheqEWWZnQJEywUloo3sK2da9DRPyGRP4/zXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:34:09.459330Z"},"content_sha256":"92b084d319be4b4df3ef3a87cabc8cf755434157479fcb1228576c1507fa9c75","schema_version":"1.0","event_id":"sha256:92b084d319be4b4df3ef3a87cabc8cf755434157479fcb1228576c1507fa9c75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/57KWUUINNQJ3TZ65G4GUVAD6UH/bundle.json","state_url":"https://pith.science/pith/57KWUUINNQJ3TZ65G4GUVAD6UH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/57KWUUINNQJ3TZ65G4GUVAD6UH/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":"2026-08-06T16:34:09Z","links":{"resolver":"https://pith.science/pith/57KWUUINNQJ3TZ65G4GUVAD6UH","bundle":"https://pith.science/pith/57KWUUINNQJ3TZ65G4GUVAD6UH/bundle.json","state":"https://pith.science/pith/57KWUUINNQJ3TZ65G4GUVAD6UH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/57KWUUINNQJ3TZ65G4GUVAD6UH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:57KWUUINNQJ3TZ65G4GUVAD6UH","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":"066b9fa269e643db7308077d638c3225d596484b9139edd215022003513b452f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-22T20:11:40Z","title_canon_sha256":"fe30e2e617361652e8ce2fd3927eccc48664473b57f4a110843c6899c4f2d8c8"},"schema_version":"1.0","source":{"id":"1911.10235","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.10235","created_at":"2026-07-05T00:23:08Z"},{"alias_kind":"arxiv_version","alias_value":"1911.10235v1","created_at":"2026-07-05T00:23:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.10235","created_at":"2026-07-05T00:23:08Z"},{"alias_kind":"pith_short_12","alias_value":"57KWUUINNQJ3","created_at":"2026-07-05T00:23:08Z"},{"alias_kind":"pith_short_16","alias_value":"57KWUUINNQJ3TZ65","created_at":"2026-07-05T00:23:08Z"},{"alias_kind":"pith_short_8","alias_value":"57KWUUIN","created_at":"2026-07-05T00:23:08Z"}],"graph_snapshots":[{"event_id":"sha256:92b084d319be4b4df3ef3a87cabc8cf755434157479fcb1228576c1507fa9c75","target":"graph","created_at":"2026-07-05T00:23:08Z","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/1911.10235/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although n-gram language models (LMs) have been outperformed by the state-of-the-art neural LMs, they are still widely used in speech recognition due to its high efficiency in inference. In this paper, we demonstrate that n-gram LM can be improved by neural LMs through a text generation based data augmentation method. In contrast to previous approaches, we employ a large-scale general domain pre-training followed by in-domain fine-tuning strategy to construct deep Transformer based neural LMs. Large amount of in-domain text data is generated with the well trained deep Transformer to construct ","authors_text":"ChengXiang Zhai, Fuchun Peng, Hongzhao Huang, Yiren Wang, Yongqiang Wang, Yutong Pang, Zhe Liu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-22T20:11:40Z","title":"Improving N-gram Language Models with Pre-trained Deep Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.10235","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":"sha256:9cf0c3485d43402b08e1cb023eb711e26e17505664a632038595967ee0da5f28","target":"record","created_at":"2026-07-05T00:23:08Z","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":"066b9fa269e643db7308077d638c3225d596484b9139edd215022003513b452f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-22T20:11:40Z","title_canon_sha256":"fe30e2e617361652e8ce2fd3927eccc48664473b57f4a110843c6899c4f2d8c8"},"schema_version":"1.0","source":{"id":"1911.10235","kind":"arxiv","version":1}},"canonical_sha256":"efd56a510d6c13b9e7dd370d4a807ea1e887d5bc7c8a658842632fbecc8ccce5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efd56a510d6c13b9e7dd370d4a807ea1e887d5bc7c8a658842632fbecc8ccce5","first_computed_at":"2026-07-05T00:23:08.810689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:23:08.810689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"34sjxMT76iD6TqFtpGnvE/Lmlpp9A/AbVhF+TEmvYmd2g/jmUnrhQEapjEPhdjQSP92HRbKALsD/Lm5y2PcKCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:23:08.811088Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.10235","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cf0c3485d43402b08e1cb023eb711e26e17505664a632038595967ee0da5f28","sha256:92b084d319be4b4df3ef3a87cabc8cf755434157479fcb1228576c1507fa9c75"],"state_sha256":"c73d0934619ed6881c3a303c79730586397ec528f7efdb070d3afffe9196f63b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H+YUg6KtcVkeklXEGNh/HN67kxxR8wRQNAV1LLjIE6EjoAKqodhenD5wbkOV2wl5W5ye9kwXfkxrGUNuKzfCAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:34:09.466343Z","bundle_sha256":"5310330e7465215c2929f2e7e2e841b913ab8369370671fe1a1e148ef946f17f"}}