{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:UUPZ7EDXTCEXH2CPGL2DP3QBM3","short_pith_number":"pith:UUPZ7EDX","schema_version":"1.0","canonical_sha256":"a51f9f9077988973e84f32f437ee0166d6a335ae83dbdc57b545ef7f7d983d75","source":{"kind":"arxiv","id":"1409.3215","version":3},"attestation_state":"computed","paper":{"title":"Sequence to Sequence Learning with Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ilya Sutskever, Oriol Vinyals, Quoc V. Le","submitted_at":"2014-09-10T19:55:35Z","abstract_excerpt":"Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well whenever large labeled training sets are available, they cannot be used to map sequences to sequences. In this paper, we present a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure. Our method uses a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector. Our main result is t"},"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":"1409.3215","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-09-10T19:55:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4e6d158fd734995ccca6139643f598c5728fd3fba94c36e11a108b82245dd2b8","abstract_canon_sha256":"e3d4adbd9b7281ade4c8550f1e5f9c5a5191a843b4d4a1cdcd3b553f85e0ceff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:31:20.620993Z","signature_b64":"D2gh95rk/wzLH4VrZKBD379LOMxh/Een4JMNdn1pC+G0+QvVB3GBMjcp65aeQQH2z4JstdHjMTthicVK/XMYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a51f9f9077988973e84f32f437ee0166d6a335ae83dbdc57b545ef7f7d983d75","last_reissued_at":"2026-05-18T02:31:20.620331Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:31:20.620331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequence to Sequence Learning with Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ilya Sutskever, Oriol Vinyals, Quoc V. Le","submitted_at":"2014-09-10T19:55:35Z","abstract_excerpt":"Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well whenever large labeled training sets are available, they cannot be used to map sequences to sequences. In this paper, we present a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure. Our method uses a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector. Our main result is t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.3215","kind":"arxiv","version":3},"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":"1409.3215","created_at":"2026-05-18T02:31:20.620436+00:00"},{"alias_kind":"arxiv_version","alias_value":"1409.3215v3","created_at":"2026-05-18T02:31:20.620436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.3215","created_at":"2026-05-18T02:31:20.620436+00:00"},{"alias_kind":"pith_short_12","alias_value":"UUPZ7EDXTCEX","created_at":"2026-05-18T12:28:52.271510+00:00"},{"alias_kind":"pith_short_16","alias_value":"UUPZ7EDXTCEXH2CP","created_at":"2026-05-18T12:28:52.271510+00:00"},{"alias_kind":"pith_short_8","alias_value":"UUPZ7EDX","created_at":"2026-05-18T12:28:52.271510+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":14,"sample":[{"citing_arxiv_id":"1907.01300","citing_title":"Learning to Reformulate the Queries on the WEB","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06876","citing_title":"Separable Convolutional LSTMs for Faster Video Segmentation","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2304.03427","citing_title":"Cleansing Jewel: A Neural Spelling Correction Model Built On Google OCR-ed Tibetan Manuscripts","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2412.19363","citing_title":"Large Language Models for Market Research: A Data-augmentation Approach","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2502.07189","citing_title":"Exploring Vision Neural Network Pruning via Screening Methodology","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2503.22693","citing_title":"Bridging Language Models and Financial Analysis","ref_index":96,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20613","citing_title":"HRM-Text: Efficient Pretraining Beyond Scaling","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19717","citing_title":"Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2507.08458","citing_title":"A document is worth a structured record: Principled inductive bias design for document recognition","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2507.13305","citing_title":"Boosting Team Modeling through Tempo-Relational Representation Learning","ref_index":134,"is_internal_anchor":true},{"citing_arxiv_id":"2102.01293","citing_title":"Scaling Laws for Transfer","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2512.09427","citing_title":"ODMA: On-Demand Memory Allocation Strategy for LLM Serving on LPDDR-Class Accelerators","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2603.05117","citing_title":"SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14689","citing_title":"Are Candidate Models Really Needed for Active Learning?","ref_index":106,"is_internal_anchor":true},{"citing_arxiv_id":"1807.03819","citing_title":"Universal Transformers","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"1410.5401","citing_title":"Neural Turing Machines","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2104.13478","citing_title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"1603.08983","citing_title":"Adaptive Computation Time for Recurrent Neural Networks","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"1611.09268","citing_title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2112.00861","citing_title":"A General Language Assistant as a Laboratory for Alignment","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12220","citing_title":"Learning Project-wise Subsequent Code Edits via Interleaving Neural-based Induction and Tool-based Deduction","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08661","citing_title":"Geometry-Induced Long-Range Correlations in Recurrent Neural Network Quantum States","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2403.08295","citing_title":"Gemma: Open Models Based on Gemini Research and Technology","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05221","citing_title":"Language Models (Mostly) Know What They Know","ref_index":106,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UUPZ7EDXTCEXH2CPGL2DP3QBM3","json":"https://pith.science/pith/UUPZ7EDXTCEXH2CPGL2DP3QBM3.json","graph_json":"https://pith.science/api/pith-number/UUPZ7EDXTCEXH2CPGL2DP3QBM3/graph.json","events_json":"https://pith.science/api/pith-number/UUPZ7EDXTCEXH2CPGL2DP3QBM3/events.json","paper":"https://pith.science/paper/UUPZ7EDX"},"agent_actions":{"view_html":"https://pith.science/pith/UUPZ7EDXTCEXH2CPGL2DP3QBM3","download_json":"https://pith.science/pith/UUPZ7EDXTCEXH2CPGL2DP3QBM3.json","view_paper":"https://pith.science/paper/UUPZ7EDX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1409.3215&json=true","fetch_graph":"https://pith.science/api/pith-number/UUPZ7EDXTCEXH2CPGL2DP3QBM3/graph.json","fetch_events":"https://pith.science/api/pith-number/UUPZ7EDXTCEXH2CPGL2DP3QBM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UUPZ7EDXTCEXH2CPGL2DP3QBM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UUPZ7EDXTCEXH2CPGL2DP3QBM3/action/storage_attestation","attest_author":"https://pith.science/pith/UUPZ7EDXTCEXH2CPGL2DP3QBM3/action/author_attestation","sign_citation":"https://pith.science/pith/UUPZ7EDXTCEXH2CPGL2DP3QBM3/action/citation_signature","submit_replication":"https://pith.science/pith/UUPZ7EDXTCEXH2CPGL2DP3QBM3/action/replication_record"}},"created_at":"2026-05-18T02:31:20.620436+00:00","updated_at":"2026-05-18T02:31:20.620436+00:00"}