{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3I2YS2QO5EFK6L5UCJ37SG4BAL","short_pith_number":"pith:3I2YS2QO","schema_version":"1.0","canonical_sha256":"da35896a0ee90aaf2fb41277f91b8102f63d778161232d6d5ae4508dcc7e977b","source":{"kind":"arxiv","id":"1910.11450","version":1},"attestation_state":"computed","paper":{"title":"An Empirical Study of Efficient ASR Rescoring with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Fuchun Peng, Hongzhao Huang","submitted_at":"2019-10-24T23:00:12Z","abstract_excerpt":"Neural language models (LMs) have been proved to significantly outperform classical n-gram LMs for language modeling due to their superior abilities to model long-range dependencies in text and handle data sparsity problems. And recently, well configured deep Transformers have exhibited superior performance over shallow stack of recurrent neural network layers for language modeling. However, these state-of-the-art deep Transformer models were mostly engineered to be deep with high model capacity, which makes it computationally inefficient and challenging to be deployed into large-scale real-wo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1910.11450","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-24T23:00:12Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"b86ae672d0da7f3ff40f1d2437c37ee261021f7a4279ec8d2bcf7c4014c4bef9","abstract_canon_sha256":"2537b8a88a01d3a46f74d47f92fb403c25224579899cdccf0d793d2e3a1a687d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:14:46.363310Z","signature_b64":"alrTcL312VT8HIKn2DK5sPWokAF3Tp3jiGCnQkX0z2ECMbsgEC6PLhoxhHwG9E4tnfHsJBWh+zWJYLjwWuOZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da35896a0ee90aaf2fb41277f91b8102f63d778161232d6d5ae4508dcc7e977b","last_reissued_at":"2026-07-05T00:14:46.362847Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:14:46.362847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Study of Efficient ASR Rescoring with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Fuchun Peng, Hongzhao Huang","submitted_at":"2019-10-24T23:00:12Z","abstract_excerpt":"Neural language models (LMs) have been proved to significantly outperform classical n-gram LMs for language modeling due to their superior abilities to model long-range dependencies in text and handle data sparsity problems. And recently, well configured deep Transformers have exhibited superior performance over shallow stack of recurrent neural network layers for language modeling. However, these state-of-the-art deep Transformer models were mostly engineered to be deep with high model capacity, which makes it computationally inefficient and challenging to be deployed into large-scale real-wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.11450","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/1910.11450/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1910.11450","created_at":"2026-07-05T00:14:46.362902+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.11450v1","created_at":"2026-07-05T00:14:46.362902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.11450","created_at":"2026-07-05T00:14:46.362902+00:00"},{"alias_kind":"pith_short_12","alias_value":"3I2YS2QO5EFK","created_at":"2026-07-05T00:14:46.362902+00:00"},{"alias_kind":"pith_short_16","alias_value":"3I2YS2QO5EFK6L5U","created_at":"2026-07-05T00:14:46.362902+00:00"},{"alias_kind":"pith_short_8","alias_value":"3I2YS2QO","created_at":"2026-07-05T00:14:46.362902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.07285","citing_title":"Non-Intrusive Automatic Speech Recognition Refinement: A Survey","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3I2YS2QO5EFK6L5UCJ37SG4BAL","json":"https://pith.science/pith/3I2YS2QO5EFK6L5UCJ37SG4BAL.json","graph_json":"https://pith.science/api/pith-number/3I2YS2QO5EFK6L5UCJ37SG4BAL/graph.json","events_json":"https://pith.science/api/pith-number/3I2YS2QO5EFK6L5UCJ37SG4BAL/events.json","paper":"https://pith.science/paper/3I2YS2QO"},"agent_actions":{"view_html":"https://pith.science/pith/3I2YS2QO5EFK6L5UCJ37SG4BAL","download_json":"https://pith.science/pith/3I2YS2QO5EFK6L5UCJ37SG4BAL.json","view_paper":"https://pith.science/paper/3I2YS2QO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.11450&json=true","fetch_graph":"https://pith.science/api/pith-number/3I2YS2QO5EFK6L5UCJ37SG4BAL/graph.json","fetch_events":"https://pith.science/api/pith-number/3I2YS2QO5EFK6L5UCJ37SG4BAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3I2YS2QO5EFK6L5UCJ37SG4BAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3I2YS2QO5EFK6L5UCJ37SG4BAL/action/storage_attestation","attest_author":"https://pith.science/pith/3I2YS2QO5EFK6L5UCJ37SG4BAL/action/author_attestation","sign_citation":"https://pith.science/pith/3I2YS2QO5EFK6L5UCJ37SG4BAL/action/citation_signature","submit_replication":"https://pith.science/pith/3I2YS2QO5EFK6L5UCJ37SG4BAL/action/replication_record"}},"created_at":"2026-07-05T00:14:46.362902+00:00","updated_at":"2026-07-05T00:14:46.362902+00:00"}