{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3CBDQHI2VYVJOXXAOOKBPTX4AA","short_pith_number":"pith:3CBDQHI2","schema_version":"1.0","canonical_sha256":"d882381d1aae2a975ee0739417cefc002de7d95132890d255460869329568321","source":{"kind":"arxiv","id":"1910.12367","version":2},"attestation_state":"computed","paper":{"title":"Training ASR models by Generation of Contextual Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Mohamed, Dmytro Okhonko, Frank Zhang, Fuchun Peng, Geoffrey Zweig, Jun Liu, Kritika Singh, Ross Girshick, Sergey Edunov, Yatharth Saraf, Yongqiang Wang","submitted_at":"2019-10-27T22:13:09Z","abstract_excerpt":"Supervised ASR models have reached unprecedented levels of accuracy, thanks in part to ever-increasing amounts of labelled training data. However, in many applications and locales, only moderate amounts of data are available, which has led to a surge in semi- and weakly-supervised learning research. In this paper, we conduct a large-scale study evaluating the effectiveness of weakly-supervised learning for speech recognition by using loosely related contextual information as a surrogate for ground-truth labels. For weakly supervised training, we use 50k hours of public English social media vid"},"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":"1910.12367","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-27T22:13:09Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"f9de570589e03c59d92c15d969edb53d84d0a4c82476f7ba2478f72a04617076","abstract_canon_sha256":"ce54dcb66b6dd7381990c9cfad888afb80ffebac35a728b403197bfb00369bf0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:59.965533Z","signature_b64":"nCeOOxLuAcOglvtnUBjwgZrMHAaXps90IKI6Zesy4PeLsJpcW37p3yQOgQf7RHNm7VAiXySt0XWz2cesqwT9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d882381d1aae2a975ee0739417cefc002de7d95132890d255460869329568321","last_reissued_at":"2026-07-05T00:40:59.965043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:59.965043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training ASR models by Generation of Contextual Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Mohamed, Dmytro Okhonko, Frank Zhang, Fuchun Peng, Geoffrey Zweig, Jun Liu, Kritika Singh, Ross Girshick, Sergey Edunov, Yatharth Saraf, Yongqiang Wang","submitted_at":"2019-10-27T22:13:09Z","abstract_excerpt":"Supervised ASR models have reached unprecedented levels of accuracy, thanks in part to ever-increasing amounts of labelled training data. However, in many applications and locales, only moderate amounts of data are available, which has led to a surge in semi- and weakly-supervised learning research. In this paper, we conduct a large-scale study evaluating the effectiveness of weakly-supervised learning for speech recognition by using loosely related contextual information as a surrogate for ground-truth labels. For weakly supervised training, we use 50k hours of public English social media vid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.12367","kind":"arxiv","version":2},"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/1910.12367/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":"1910.12367","created_at":"2026-07-05T00:40:59.965100+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.12367v2","created_at":"2026-07-05T00:40:59.965100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.12367","created_at":"2026-07-05T00:40:59.965100+00:00"},{"alias_kind":"pith_short_12","alias_value":"3CBDQHI2VYVJ","created_at":"2026-07-05T00:40:59.965100+00:00"},{"alias_kind":"pith_short_16","alias_value":"3CBDQHI2VYVJOXXA","created_at":"2026-07-05T00:40:59.965100+00:00"},{"alias_kind":"pith_short_8","alias_value":"3CBDQHI2","created_at":"2026-07-05T00:40:59.965100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3CBDQHI2VYVJOXXAOOKBPTX4AA","json":"https://pith.science/pith/3CBDQHI2VYVJOXXAOOKBPTX4AA.json","graph_json":"https://pith.science/api/pith-number/3CBDQHI2VYVJOXXAOOKBPTX4AA/graph.json","events_json":"https://pith.science/api/pith-number/3CBDQHI2VYVJOXXAOOKBPTX4AA/events.json","paper":"https://pith.science/paper/3CBDQHI2"},"agent_actions":{"view_html":"https://pith.science/pith/3CBDQHI2VYVJOXXAOOKBPTX4AA","download_json":"https://pith.science/pith/3CBDQHI2VYVJOXXAOOKBPTX4AA.json","view_paper":"https://pith.science/paper/3CBDQHI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.12367&json=true","fetch_graph":"https://pith.science/api/pith-number/3CBDQHI2VYVJOXXAOOKBPTX4AA/graph.json","fetch_events":"https://pith.science/api/pith-number/3CBDQHI2VYVJOXXAOOKBPTX4AA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3CBDQHI2VYVJOXXAOOKBPTX4AA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3CBDQHI2VYVJOXXAOOKBPTX4AA/action/storage_attestation","attest_author":"https://pith.science/pith/3CBDQHI2VYVJOXXAOOKBPTX4AA/action/author_attestation","sign_citation":"https://pith.science/pith/3CBDQHI2VYVJOXXAOOKBPTX4AA/action/citation_signature","submit_replication":"https://pith.science/pith/3CBDQHI2VYVJOXXAOOKBPTX4AA/action/replication_record"}},"created_at":"2026-07-05T00:40:59.965100+00:00","updated_at":"2026-07-05T00:40:59.965100+00:00"}