{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:63LD6GE74F2D2AP3XMQVZW4DQW","short_pith_number":"pith:63LD6GE7","schema_version":"1.0","canonical_sha256":"f6d63f189fe1743d01fbbb215cdb83858c1c038d9b9697bdcda4eae7f76700da","source":{"kind":"arxiv","id":"1508.04395","version":2},"attestation_state":"computed","paper":{"title":"End-to-End Attention-based Large Vocabulary Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Dmitriy Serdyuk, Dzmitry Bahdanau, Jan Chorowski, Philemon Brakel, Yoshua Bengio","submitted_at":"2015-08-18T17:40:00Z","abstract_excerpt":"Many of the current state-of-the-art Large Vocabulary Continuous Speech Recognition Systems (LVCSR) are hybrids of neural networks and Hidden Markov Models (HMMs). Most of these systems contain separate components that deal with the acoustic modelling, language modelling and sequence decoding. We investigate a more direct approach in which the HMM is replaced with a Recurrent Neural Network (RNN) that performs sequence prediction directly at the character level. Alignment between the input features and the desired character sequence is learned automatically by an attention mechanism built into"},"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":"1508.04395","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-18T17:40:00Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"daed687cf0173b585824b3d0f6fdbc2d22461335755b04d9dcad374965ff7a62","abstract_canon_sha256":"e0747ce165bf2c942069bae85e071b47e59fd7e4ca95b55f42e45b87ea810f2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:05.919927Z","signature_b64":"OJxIYCH6TK1RyglnijNUxOKEMB84RAG+Jx6I5H0vFNsy+hVhugsH4DRZT5ojhUSm6pYsWzyYw6Ot5AlHz2HyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6d63f189fe1743d01fbbb215cdb83858c1c038d9b9697bdcda4eae7f76700da","last_reissued_at":"2026-05-18T01:19:05.919398Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:05.919398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Attention-based Large Vocabulary Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Dmitriy Serdyuk, Dzmitry Bahdanau, Jan Chorowski, Philemon Brakel, Yoshua Bengio","submitted_at":"2015-08-18T17:40:00Z","abstract_excerpt":"Many of the current state-of-the-art Large Vocabulary Continuous Speech Recognition Systems (LVCSR) are hybrids of neural networks and Hidden Markov Models (HMMs). Most of these systems contain separate components that deal with the acoustic modelling, language modelling and sequence decoding. We investigate a more direct approach in which the HMM is replaced with a Recurrent Neural Network (RNN) that performs sequence prediction directly at the character level. Alignment between the input features and the desired character sequence is learned automatically by an attention mechanism built into"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.04395","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":""},"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":"1508.04395","created_at":"2026-05-18T01:19:05.919463+00:00"},{"alias_kind":"arxiv_version","alias_value":"1508.04395v2","created_at":"2026-05-18T01:19:05.919463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.04395","created_at":"2026-05-18T01:19:05.919463+00:00"},{"alias_kind":"pith_short_12","alias_value":"63LD6GE74F2D","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_16","alias_value":"63LD6GE74F2D2AP3","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_8","alias_value":"63LD6GE7","created_at":"2026-05-18T12:29:07.941421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1712.00409","citing_title":"Deep Learning Scaling is Predictable, Empirically","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/63LD6GE74F2D2AP3XMQVZW4DQW","json":"https://pith.science/pith/63LD6GE74F2D2AP3XMQVZW4DQW.json","graph_json":"https://pith.science/api/pith-number/63LD6GE74F2D2AP3XMQVZW4DQW/graph.json","events_json":"https://pith.science/api/pith-number/63LD6GE74F2D2AP3XMQVZW4DQW/events.json","paper":"https://pith.science/paper/63LD6GE7"},"agent_actions":{"view_html":"https://pith.science/pith/63LD6GE74F2D2AP3XMQVZW4DQW","download_json":"https://pith.science/pith/63LD6GE74F2D2AP3XMQVZW4DQW.json","view_paper":"https://pith.science/paper/63LD6GE7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1508.04395&json=true","fetch_graph":"https://pith.science/api/pith-number/63LD6GE74F2D2AP3XMQVZW4DQW/graph.json","fetch_events":"https://pith.science/api/pith-number/63LD6GE74F2D2AP3XMQVZW4DQW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/63LD6GE74F2D2AP3XMQVZW4DQW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/63LD6GE74F2D2AP3XMQVZW4DQW/action/storage_attestation","attest_author":"https://pith.science/pith/63LD6GE74F2D2AP3XMQVZW4DQW/action/author_attestation","sign_citation":"https://pith.science/pith/63LD6GE74F2D2AP3XMQVZW4DQW/action/citation_signature","submit_replication":"https://pith.science/pith/63LD6GE74F2D2AP3XMQVZW4DQW/action/replication_record"}},"created_at":"2026-05-18T01:19:05.919463+00:00","updated_at":"2026-05-18T01:19:05.919463+00:00"}