{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WCE57WVM5AVYGHMZB7XRIID5Q3","short_pith_number":"pith:WCE57WVM","canonical_record":{"source":{"id":"1907.01677","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-02T23:28:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b6f04fac20f1f7442cd9f7f2c8c2f5d0a43f105cd0e59c606cf937c556e2172b","abstract_canon_sha256":"7793d9a6bc896f0a29b056d333512391c119f4f3a323be21749e8eca724f80c8"},"schema_version":"1.0"},"canonical_sha256":"b089dfdaace82b831d990fef14207d86fc595222a4ab3df4692a2cfc3ef4ad63","source":{"kind":"arxiv","id":"1907.01677","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.01677","created_at":"2026-05-17T23:41:35Z"},{"alias_kind":"arxiv_version","alias_value":"1907.01677v1","created_at":"2026-05-17T23:41:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01677","created_at":"2026-05-17T23:41:35Z"},{"alias_kind":"pith_short_12","alias_value":"WCE57WVM5AVY","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WCE57WVM5AVYGHMZ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WCE57WVM","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WCE57WVM5AVYGHMZB7XRIID5Q3","target":"record","payload":{"canonical_record":{"source":{"id":"1907.01677","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-02T23:28:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b6f04fac20f1f7442cd9f7f2c8c2f5d0a43f105cd0e59c606cf937c556e2172b","abstract_canon_sha256":"7793d9a6bc896f0a29b056d333512391c119f4f3a323be21749e8eca724f80c8"},"schema_version":"1.0"},"canonical_sha256":"b089dfdaace82b831d990fef14207d86fc595222a4ab3df4692a2cfc3ef4ad63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:35.521649Z","signature_b64":"QJJIYg6c3nAG0Yxt6tOD2lyskwkchkUH1mJ4NbW1tE0SuubOfeu2daaOGuZLMICtRSP3UIhs9+As4bJ8Naz4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b089dfdaace82b831d990fef14207d86fc595222a4ab3df4692a2cfc3ef4ad63","last_reissued_at":"2026-05-17T23:41:35.521051Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:35.521051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.01677","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":"2026-05-17T23:41:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UulOjYBsxXgMiH+1XHSDJZXwPm996KO4gSy70YtCJFu/pY8sCInyub3sCOzRnLsv8mgcvJdU1WViKBi6OBiIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:56:03.008868Z"},"content_sha256":"bb109fcd84053bdecea643c6e33958048b29dbf612709a2d4bf4e079d8ec8168","schema_version":"1.0","event_id":"sha256:bb109fcd84053bdecea643c6e33958048b29dbf612709a2d4bf4e079d8ec8168"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WCE57WVM5AVYGHMZB7XRIID5Q3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable Multi Corpora Neural Language Models for ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anirudh Raju, Ariya Rastrow, Denis Filimonov, Gautam Tiwari, Guitang Lan","submitted_at":"2019-07-02T23:28:52Z","abstract_excerpt":"Neural language models (NLM) have been shown to outperform conventional n-gram language models by a substantial margin in Automatic Speech Recognition (ASR) and other tasks. There are, however, a number of challenges that need to be addressed for an NLM to be used in a practical large-scale ASR system. In this paper, we present solutions to some of the challenges, including training NLM from heterogenous corpora, limiting latency impact and handling personalized bias in the second-pass rescorer. Overall, we show that we can achieve a 6.2% relative WER reduction using neural LM in a second-pass"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01677","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":"2026-05-17T23:41:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eusnQM9KsCjSYhXGwDL35KBXhz0EqGv1+ZjQgwZNs47yuVEVq5Prlqntxqt0I6qGb/IBpX81DAVglsIOSkLUBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:56:03.009574Z"},"content_sha256":"35cb41817dfc919f0c1eb37f89e8d0f9ed189b93679a73ca7358456ab87f522f","schema_version":"1.0","event_id":"sha256:35cb41817dfc919f0c1eb37f89e8d0f9ed189b93679a73ca7358456ab87f522f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WCE57WVM5AVYGHMZB7XRIID5Q3/bundle.json","state_url":"https://pith.science/pith/WCE57WVM5AVYGHMZB7XRIID5Q3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WCE57WVM5AVYGHMZB7XRIID5Q3/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":"2026-05-27T22:56:03Z","links":{"resolver":"https://pith.science/pith/WCE57WVM5AVYGHMZB7XRIID5Q3","bundle":"https://pith.science/pith/WCE57WVM5AVYGHMZB7XRIID5Q3/bundle.json","state":"https://pith.science/pith/WCE57WVM5AVYGHMZB7XRIID5Q3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WCE57WVM5AVYGHMZB7XRIID5Q3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WCE57WVM5AVYGHMZB7XRIID5Q3","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":"7793d9a6bc896f0a29b056d333512391c119f4f3a323be21749e8eca724f80c8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-02T23:28:52Z","title_canon_sha256":"b6f04fac20f1f7442cd9f7f2c8c2f5d0a43f105cd0e59c606cf937c556e2172b"},"schema_version":"1.0","source":{"id":"1907.01677","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.01677","created_at":"2026-05-17T23:41:35Z"},{"alias_kind":"arxiv_version","alias_value":"1907.01677v1","created_at":"2026-05-17T23:41:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01677","created_at":"2026-05-17T23:41:35Z"},{"alias_kind":"pith_short_12","alias_value":"WCE57WVM5AVY","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WCE57WVM5AVYGHMZ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WCE57WVM","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:35cb41817dfc919f0c1eb37f89e8d0f9ed189b93679a73ca7358456ab87f522f","target":"graph","created_at":"2026-05-17T23:41:35Z","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":"Neural language models (NLM) have been shown to outperform conventional n-gram language models by a substantial margin in Automatic Speech Recognition (ASR) and other tasks. There are, however, a number of challenges that need to be addressed for an NLM to be used in a practical large-scale ASR system. In this paper, we present solutions to some of the challenges, including training NLM from heterogenous corpora, limiting latency impact and handling personalized bias in the second-pass rescorer. Overall, we show that we can achieve a 6.2% relative WER reduction using neural LM in a second-pass","authors_text":"Anirudh Raju, Ariya Rastrow, Denis Filimonov, Gautam Tiwari, Guitang Lan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-02T23:28:52Z","title":"Scalable Multi Corpora Neural Language Models for ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01677","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:bb109fcd84053bdecea643c6e33958048b29dbf612709a2d4bf4e079d8ec8168","target":"record","created_at":"2026-05-17T23:41:35Z","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":"7793d9a6bc896f0a29b056d333512391c119f4f3a323be21749e8eca724f80c8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-02T23:28:52Z","title_canon_sha256":"b6f04fac20f1f7442cd9f7f2c8c2f5d0a43f105cd0e59c606cf937c556e2172b"},"schema_version":"1.0","source":{"id":"1907.01677","kind":"arxiv","version":1}},"canonical_sha256":"b089dfdaace82b831d990fef14207d86fc595222a4ab3df4692a2cfc3ef4ad63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b089dfdaace82b831d990fef14207d86fc595222a4ab3df4692a2cfc3ef4ad63","first_computed_at":"2026-05-17T23:41:35.521051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:35.521051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QJJIYg6c3nAG0Yxt6tOD2lyskwkchkUH1mJ4NbW1tE0SuubOfeu2daaOGuZLMICtRSP3UIhs9+As4bJ8Naz4AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:35.521649Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.01677","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb109fcd84053bdecea643c6e33958048b29dbf612709a2d4bf4e079d8ec8168","sha256:35cb41817dfc919f0c1eb37f89e8d0f9ed189b93679a73ca7358456ab87f522f"],"state_sha256":"ea32a895aa062666b70332721edd1346c0c0b22f057def7e3efc9762e279dd6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aywtwvImo2HyRik7MO6PfjN5JycCjxodgxpJw1/ExN4GRG6iXOC+jVQ5UPwjPYOkjlxD870yEccxbrUMLtn/Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T22:56:03.012342Z","bundle_sha256":"aea3d3322e5de8858f8ee868bb5ef3fce722319bfd101f4e22033c2141d70082"}}