{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:SRBM34ZOYJT4GZRWECBV4XQ2HX","short_pith_number":"pith:SRBM34ZO","schema_version":"1.0","canonical_sha256":"9442cdf32ec267c3663620835e5e1a3de0d310ab4484d4cb46040257a5a31985","source":{"kind":"arxiv","id":"1511.06349","version":4},"attestation_state":"computed","paper":{"title":"Generating Sentences from a Continuous Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Andrew M. Dai, Luke Vilnis, Oriol Vinyals, Rafal Jozefowicz, Samuel R. Bowman, Samy Bengio","submitted_at":"2015-11-19T20:38:45Z","abstract_excerpt":"The standard recurrent neural network language model (RNNLM) generates sentences one word at a time and does not work from an explicit global sentence representation. In this work, we introduce and study an RNN-based variational autoencoder generative model that incorporates distributed latent representations of entire sentences. This factorization allows it to explicitly model holistic properties of sentences such as style, topic, and high-level syntactic features. Samples from the prior over these sentence representations remarkably produce diverse and well-formed sentences through simple de"},"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":"1511.06349","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T20:38:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f0a2171b24df44c80fb8ba6096ea032d730dba4350bfffd07508434f7d8ed232","abstract_canon_sha256":"f8b865639ad3f5e0fcbfb44bb25a5dbcdc7771dd9f5b7a06d5858ba4e55572a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:52.519783Z","signature_b64":"MzakpKMJgDdxPGQ0SeAZco5YtJClaJjx5TcTXTRGyVGfYbxvQZeE4WYC53uNfGmMZafpJchYAW1cVQPWmexQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9442cdf32ec267c3663620835e5e1a3de0d310ab4484d4cb46040257a5a31985","last_reissued_at":"2026-05-18T00:49:52.519362Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:52.519362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Sentences from a Continuous Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Andrew M. Dai, Luke Vilnis, Oriol Vinyals, Rafal Jozefowicz, Samuel R. Bowman, Samy Bengio","submitted_at":"2015-11-19T20:38:45Z","abstract_excerpt":"The standard recurrent neural network language model (RNNLM) generates sentences one word at a time and does not work from an explicit global sentence representation. In this work, we introduce and study an RNN-based variational autoencoder generative model that incorporates distributed latent representations of entire sentences. This factorization allows it to explicitly model holistic properties of sentences such as style, topic, and high-level syntactic features. Samples from the prior over these sentence representations remarkably produce diverse and well-formed sentences through simple de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06349","kind":"arxiv","version":4},"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":"1511.06349","created_at":"2026-05-18T00:49:52.519422+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.06349v4","created_at":"2026-05-18T00:49:52.519422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06349","created_at":"2026-05-18T00:49:52.519422+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRBM34ZOYJT4","created_at":"2026-05-18T12:29:42.218222+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRBM34ZOYJT4GZRW","created_at":"2026-05-18T12:29:42.218222+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRBM34ZO","created_at":"2026-05-18T12:29:42.218222+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"1906.08972","citing_title":"A Deep Generative Model for Code-Switched Text","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"1907.01607","citing_title":"MIDI-Sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN networks for Symbolic Single-track Music Generation","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"1907.03189","citing_title":"I Am Not What I Write: Privacy Preserving Text Representation Learning","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18262","citing_title":"On Improving Multimodal Pedestrian Trajectory Prediction with CVAE: A Study on Benchmark and Robot Data","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2505.17384","citing_title":"Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"1909.01066","citing_title":"Language Models as Knowledge Bases?","ref_index":126,"is_internal_anchor":true},{"citing_arxiv_id":"2602.15451","citing_title":"Molecular Design beyond Training Data with Novel Extended Objective Functionals of Generative AI Models Driven by Quantum Annealing Computer","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"1910.10683","citing_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"1605.08803","citing_title":"Density estimation using Real NVP","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":186,"is_internal_anchor":false},{"citing_arxiv_id":"1910.03771","citing_title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","ref_index":104,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SRBM34ZOYJT4GZRWECBV4XQ2HX","json":"https://pith.science/pith/SRBM34ZOYJT4GZRWECBV4XQ2HX.json","graph_json":"https://pith.science/api/pith-number/SRBM34ZOYJT4GZRWECBV4XQ2HX/graph.json","events_json":"https://pith.science/api/pith-number/SRBM34ZOYJT4GZRWECBV4XQ2HX/events.json","paper":"https://pith.science/paper/SRBM34ZO"},"agent_actions":{"view_html":"https://pith.science/pith/SRBM34ZOYJT4GZRWECBV4XQ2HX","download_json":"https://pith.science/pith/SRBM34ZOYJT4GZRWECBV4XQ2HX.json","view_paper":"https://pith.science/paper/SRBM34ZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.06349&json=true","fetch_graph":"https://pith.science/api/pith-number/SRBM34ZOYJT4GZRWECBV4XQ2HX/graph.json","fetch_events":"https://pith.science/api/pith-number/SRBM34ZOYJT4GZRWECBV4XQ2HX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRBM34ZOYJT4GZRWECBV4XQ2HX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRBM34ZOYJT4GZRWECBV4XQ2HX/action/storage_attestation","attest_author":"https://pith.science/pith/SRBM34ZOYJT4GZRWECBV4XQ2HX/action/author_attestation","sign_citation":"https://pith.science/pith/SRBM34ZOYJT4GZRWECBV4XQ2HX/action/citation_signature","submit_replication":"https://pith.science/pith/SRBM34ZOYJT4GZRWECBV4XQ2HX/action/replication_record"}},"created_at":"2026-05-18T00:49:52.519422+00:00","updated_at":"2026-05-18T00:49:52.519422+00:00"}