{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:YXDVAKSAIEKSYBSSGTMMZBUSBX","short_pith_number":"pith:YXDVAKSA","schema_version":"1.0","canonical_sha256":"c5c7502a4041152c065234d8cc86920dfd470a8628dbaf59914faa2d7775296b","source":{"kind":"arxiv","id":"1211.3711","version":1},"attestation_state":"computed","paper":{"title":"Sequence Transduction with Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Alex Graves","submitted_at":"2012-11-14T19:25:21Z","abstract_excerpt":"Many machine learning tasks can be expressed as the transformation---or \\emph{transduction}---of input sequences into output sequences: speech recognition, machine translation, protein secondary structure prediction and text-to-speech to name but a few. One of the key challenges in sequence transduction is learning to represent both the input and output sequences in a way that is invariant to sequential distortions such as shrinking, stretching and translating. Recurrent neural networks (RNNs) are a powerful sequence learning architecture that has proven capable of learning such representation"},"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":"1211.3711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2012-11-14T19:25:21Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"234f0cd3a2f11973dbc9b7d76bc5a974247128fa9268fb15bd9c804060efc346","abstract_canon_sha256":"0c74fac3a554e3582ad792cb4e6022abf2104c22fd14d720ccab8c640e0d5f37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:40:39.016979Z","signature_b64":"pi7lGJbJBKweC6cYmxde+WvFqrHsC54zu8nMTUlcI5PHXrKDOmtpvSM5STYKsF3P6Srcef2Hsi8S1CN9u1m3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5c7502a4041152c065234d8cc86920dfd470a8628dbaf59914faa2d7775296b","last_reissued_at":"2026-05-18T03:40:39.016286Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:40:39.016286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequence Transduction with Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Alex Graves","submitted_at":"2012-11-14T19:25:21Z","abstract_excerpt":"Many machine learning tasks can be expressed as the transformation---or \\emph{transduction}---of input sequences into output sequences: speech recognition, machine translation, protein secondary structure prediction and text-to-speech to name but a few. One of the key challenges in sequence transduction is learning to represent both the input and output sequences in a way that is invariant to sequential distortions such as shrinking, stretching and translating. Recurrent neural networks (RNNs) are a powerful sequence learning architecture that has proven capable of learning such representation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1211.3711","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":"1211.3711","created_at":"2026-05-18T03:40:39.016430+00:00"},{"alias_kind":"arxiv_version","alias_value":"1211.3711v1","created_at":"2026-05-18T03:40:39.016430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1211.3711","created_at":"2026-05-18T03:40:39.016430+00:00"},{"alias_kind":"pith_short_12","alias_value":"YXDVAKSAIEKS","created_at":"2026-05-18T12:27:30.460161+00:00"},{"alias_kind":"pith_short_16","alias_value":"YXDVAKSAIEKSYBSS","created_at":"2026-05-18T12:27:30.460161+00:00"},{"alias_kind":"pith_short_8","alias_value":"YXDVAKSA","created_at":"2026-05-18T12:27:30.460161+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":10,"sample":[{"citing_arxiv_id":"1906.09292","citing_title":"Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23463","citing_title":"StepAudio 2.5 Technical Report","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"1907.04916","citing_title":"Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2410.04155","citing_title":"Toxic Subword Pruning for Dialogue Response Generation on Large Language Models","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18222","citing_title":"Contextual Biasing for Streaming ASR via CTC-based Word Spotting","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19283","citing_title":"EviTrack: Selection over Sampling for Delayed Disambiguation","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18222","citing_title":"Contextual Biasing for Streaming ASR via CTC-based Word Spotting","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16555","citing_title":"MedASR: An Open-Source Model for High-Accuracy Medical Dictation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2411.10440","citing_title":"LLaVA-CoT: Let Vision Language Models Reason Step-by-Step","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2602.11298","citing_title":"Voxtral Realtime","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06582","citing_title":"PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18105","citing_title":"NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":156,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09916","citing_title":"Regularized Entropy Information Adaptation with Temporal-Awareness Networks for Simultaneous Speech Translation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19797","citing_title":"Enhancing ASR Performance in the Medical Domain for Dravidian Languages","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08003","citing_title":"Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09121","citing_title":"Interactive ASR: Towards Human-Like Interaction and Semantic Coherence Evaluation for Agentic Speech Recognition","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YXDVAKSAIEKSYBSSGTMMZBUSBX","json":"https://pith.science/pith/YXDVAKSAIEKSYBSSGTMMZBUSBX.json","graph_json":"https://pith.science/api/pith-number/YXDVAKSAIEKSYBSSGTMMZBUSBX/graph.json","events_json":"https://pith.science/api/pith-number/YXDVAKSAIEKSYBSSGTMMZBUSBX/events.json","paper":"https://pith.science/paper/YXDVAKSA"},"agent_actions":{"view_html":"https://pith.science/pith/YXDVAKSAIEKSYBSSGTMMZBUSBX","download_json":"https://pith.science/pith/YXDVAKSAIEKSYBSSGTMMZBUSBX.json","view_paper":"https://pith.science/paper/YXDVAKSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1211.3711&json=true","fetch_graph":"https://pith.science/api/pith-number/YXDVAKSAIEKSYBSSGTMMZBUSBX/graph.json","fetch_events":"https://pith.science/api/pith-number/YXDVAKSAIEKSYBSSGTMMZBUSBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YXDVAKSAIEKSYBSSGTMMZBUSBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YXDVAKSAIEKSYBSSGTMMZBUSBX/action/storage_attestation","attest_author":"https://pith.science/pith/YXDVAKSAIEKSYBSSGTMMZBUSBX/action/author_attestation","sign_citation":"https://pith.science/pith/YXDVAKSAIEKSYBSSGTMMZBUSBX/action/citation_signature","submit_replication":"https://pith.science/pith/YXDVAKSAIEKSYBSSGTMMZBUSBX/action/replication_record"}},"created_at":"2026-05-18T03:40:39.016430+00:00","updated_at":"2026-05-18T03:40:39.016430+00:00"}