{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:G3KR4UHKUGOCB5M7EOAGMAXXFN","short_pith_number":"pith:G3KR4UHK","schema_version":"1.0","canonical_sha256":"36d51e50eaa19c20f59f23806602f72b6ec663e50690698ed72131e27efd8af7","source":{"kind":"arxiv","id":"1904.10584","version":1},"attestation_state":"computed","paper":{"title":"Realizing Petabyte Scale Acoustic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Nikko Strom, Nitin Sivakrishnan, Pranav Ladkat, Sree Hari Krishnan Parthasarathi","submitted_at":"2019-04-24T00:39:25Z","abstract_excerpt":"Large scale machine learning (ML) systems such as the Alexa automatic speech recognition (ASR) system continue to improve with increasing amounts of manually transcribed training data. Instead of scaling manual transcription to impractical levels, we utilize semi-supervised learning (SSL) to learn acoustic models (AM) from the vast firehose of untranscribed audio data. Learning an AM from 1 Million hours of audio presents unique ML and system design challenges. We present the design and evaluation of a highly scalable and resource efficient SSL system for AM. Employing the student/teacher lear"},"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":"1904.10584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-04-24T00:39:25Z","cross_cats_sorted":["cs.LG","eess.AS","stat.ML"],"title_canon_sha256":"2a1639355edf1ef3952913721a1935c2c6d6f0118e9d46f863c3b4b1a1453840","abstract_canon_sha256":"fbd10394683df08ab28113745f86d8ec898bb48cdcc9076ffdbc43b24099a3f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:53.334864Z","signature_b64":"S1LMmtFmhjPzCV9b4Qt/AgQMvJdXxjIN8PlSwtkS06MfIsR+gC9g6iIoPuFLNC+m90gcRaQpMXhOXwg3iEa3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36d51e50eaa19c20f59f23806602f72b6ec663e50690698ed72131e27efd8af7","last_reissued_at":"2026-05-17T23:47:53.334221Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:53.334221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Realizing Petabyte Scale Acoustic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Nikko Strom, Nitin Sivakrishnan, Pranav Ladkat, Sree Hari Krishnan Parthasarathi","submitted_at":"2019-04-24T00:39:25Z","abstract_excerpt":"Large scale machine learning (ML) systems such as the Alexa automatic speech recognition (ASR) system continue to improve with increasing amounts of manually transcribed training data. Instead of scaling manual transcription to impractical levels, we utilize semi-supervised learning (SSL) to learn acoustic models (AM) from the vast firehose of untranscribed audio data. Learning an AM from 1 Million hours of audio presents unique ML and system design challenges. We present the design and evaluation of a highly scalable and resource efficient SSL system for AM. Employing the student/teacher lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.10584","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1904.10584","created_at":"2026-05-17T23:47:53.334312+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.10584v1","created_at":"2026-05-17T23:47:53.334312+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.10584","created_at":"2026-05-17T23:47:53.334312+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3KR4UHKUGOC","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3KR4UHKUGOCB5M7","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3KR4UHK","created_at":"2026-05-18T12:33:18.533446+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/G3KR4UHKUGOCB5M7EOAGMAXXFN","json":"https://pith.science/pith/G3KR4UHKUGOCB5M7EOAGMAXXFN.json","graph_json":"https://pith.science/api/pith-number/G3KR4UHKUGOCB5M7EOAGMAXXFN/graph.json","events_json":"https://pith.science/api/pith-number/G3KR4UHKUGOCB5M7EOAGMAXXFN/events.json","paper":"https://pith.science/paper/G3KR4UHK"},"agent_actions":{"view_html":"https://pith.science/pith/G3KR4UHKUGOCB5M7EOAGMAXXFN","download_json":"https://pith.science/pith/G3KR4UHKUGOCB5M7EOAGMAXXFN.json","view_paper":"https://pith.science/paper/G3KR4UHK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.10584&json=true","fetch_graph":"https://pith.science/api/pith-number/G3KR4UHKUGOCB5M7EOAGMAXXFN/graph.json","fetch_events":"https://pith.science/api/pith-number/G3KR4UHKUGOCB5M7EOAGMAXXFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3KR4UHKUGOCB5M7EOAGMAXXFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3KR4UHKUGOCB5M7EOAGMAXXFN/action/storage_attestation","attest_author":"https://pith.science/pith/G3KR4UHKUGOCB5M7EOAGMAXXFN/action/author_attestation","sign_citation":"https://pith.science/pith/G3KR4UHKUGOCB5M7EOAGMAXXFN/action/citation_signature","submit_replication":"https://pith.science/pith/G3KR4UHKUGOCB5M7EOAGMAXXFN/action/replication_record"}},"created_at":"2026-05-17T23:47:53.334312+00:00","updated_at":"2026-05-17T23:47:53.334312+00:00"}