{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:H3FIRBWXNV3L57VPHOGYQ2CLJA","short_pith_number":"pith:H3FIRBWX","schema_version":"1.0","canonical_sha256":"3eca8886d76d76befeaf3b8d88684b482425fc298d002acf75931435bba8b0c8","source":{"kind":"arxiv","id":"1901.10055","version":2},"attestation_state":"computed","paper":{"title":"Self-Attention Networks for Connectionist Temporal Classification in Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Julian Salazar, Katrin Kirchhoff, Zhiheng Huang","submitted_at":"2019-01-22T21:37:07Z","abstract_excerpt":"The success of self-attention in NLP has led to recent applications in end-to-end encoder-decoder architectures for speech recognition. Separately, connectionist temporal classification (CTC) has matured as an alignment-free, non-autoregressive approach to sequence transduction, either by itself or in various multitask and decoding frameworks. We propose SAN-CTC, a deep, fully self-attentional network for CTC, and show it is tractable and competitive for end-to-end speech recognition. SAN-CTC trains quickly and outperforms existing CTC models and most encoder-decoder models, with character err"},"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":"1901.10055","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-01-22T21:37:07Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"25814be4d94b0bb44df68962ae6637d6cf3ce8d456924b7f45542e9fdc116588","abstract_canon_sha256":"5042319643a9795e5276a628986726a615d2f8c003c6f4712b9a475293388196"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:53.517496Z","signature_b64":"NAsAphmlcm+BouX5ZcR4foOmap39LO0V5NHtNHpAVCebEcvcZToJsnMNn75TcZ/yR7ZBGovz44VJuNgE9Pc8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3eca8886d76d76befeaf3b8d88684b482425fc298d002acf75931435bba8b0c8","last_reissued_at":"2026-05-17T23:41:53.516839Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:53.516839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Attention Networks for Connectionist Temporal Classification in Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Julian Salazar, Katrin Kirchhoff, Zhiheng Huang","submitted_at":"2019-01-22T21:37:07Z","abstract_excerpt":"The success of self-attention in NLP has led to recent applications in end-to-end encoder-decoder architectures for speech recognition. Separately, connectionist temporal classification (CTC) has matured as an alignment-free, non-autoregressive approach to sequence transduction, either by itself or in various multitask and decoding frameworks. We propose SAN-CTC, a deep, fully self-attentional network for CTC, and show it is tractable and competitive for end-to-end speech recognition. SAN-CTC trains quickly and outperforms existing CTC models and most encoder-decoder models, with character err"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10055","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":"1901.10055","created_at":"2026-05-17T23:41:53.516929+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.10055v2","created_at":"2026-05-17T23:41:53.516929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10055","created_at":"2026-05-17T23:41:53.516929+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3FIRBWXNV3L","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3FIRBWXNV3L57VP","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3FIRBWX","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/H3FIRBWXNV3L57VPHOGYQ2CLJA","json":"https://pith.science/pith/H3FIRBWXNV3L57VPHOGYQ2CLJA.json","graph_json":"https://pith.science/api/pith-number/H3FIRBWXNV3L57VPHOGYQ2CLJA/graph.json","events_json":"https://pith.science/api/pith-number/H3FIRBWXNV3L57VPHOGYQ2CLJA/events.json","paper":"https://pith.science/paper/H3FIRBWX"},"agent_actions":{"view_html":"https://pith.science/pith/H3FIRBWXNV3L57VPHOGYQ2CLJA","download_json":"https://pith.science/pith/H3FIRBWXNV3L57VPHOGYQ2CLJA.json","view_paper":"https://pith.science/paper/H3FIRBWX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.10055&json=true","fetch_graph":"https://pith.science/api/pith-number/H3FIRBWXNV3L57VPHOGYQ2CLJA/graph.json","fetch_events":"https://pith.science/api/pith-number/H3FIRBWXNV3L57VPHOGYQ2CLJA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3FIRBWXNV3L57VPHOGYQ2CLJA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3FIRBWXNV3L57VPHOGYQ2CLJA/action/storage_attestation","attest_author":"https://pith.science/pith/H3FIRBWXNV3L57VPHOGYQ2CLJA/action/author_attestation","sign_citation":"https://pith.science/pith/H3FIRBWXNV3L57VPHOGYQ2CLJA/action/citation_signature","submit_replication":"https://pith.science/pith/H3FIRBWXNV3L57VPHOGYQ2CLJA/action/replication_record"}},"created_at":"2026-05-17T23:41:53.516929+00:00","updated_at":"2026-05-17T23:41:53.516929+00:00"}