{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7I5VIT5QYUIPVW3EH4DFT5KEJU","short_pith_number":"pith:7I5VIT5Q","schema_version":"1.0","canonical_sha256":"fa3b544fb0c510fadb643f0659f5444d2b433954b461e3fb53fd9b0c7114ce9f","source":{"kind":"arxiv","id":"1712.08207","version":3},"attestation_state":"computed","paper":{"title":"Variational Attention for Sequence-to-Sequence Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hareesh Bahuleyan, Lili Mou, Olga Vechtomova, Pascal Poupart","submitted_at":"2017-12-21T20:47:27Z","abstract_excerpt":"The variational encoder-decoder (VED) encodes source information as a set of random variables using a neural network, which in turn is decoded into target data using another neural network. In natural language processing, sequence-to-sequence (Seq2Seq) models typically serve as encoder-decoder networks. When combined with a traditional (deterministic) attention mechanism, the variational latent space may be bypassed by the attention model, and thus becomes ineffective. In this paper, we propose a variational attention mechanism for VED, where the attention vector is also modeled as Gaussian di"},"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":"1712.08207","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-12-21T20:47:27Z","cross_cats_sorted":[],"title_canon_sha256":"c671f31fd8ff8bb41e2ff9fb96d1635af5cbf33e756e27ff12fa4cf2e6efa85a","abstract_canon_sha256":"eaceb3ab4990497ad5241c9e1086ab4f2e64b8b115ee974fc69ee99bb8ee59ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:38.381715Z","signature_b64":"UlzT16Z6H1yr/ZrH5iyv7QD+ud+N14YE3a6qjPMnt8xcYvb1Gr6dLQLN1o6vFijLLXdJg7peVIn0GtNz96LcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa3b544fb0c510fadb643f0659f5444d2b433954b461e3fb53fd9b0c7114ce9f","last_reissued_at":"2026-05-18T00:12:38.381081Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:38.381081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Attention for Sequence-to-Sequence Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hareesh Bahuleyan, Lili Mou, Olga Vechtomova, Pascal Poupart","submitted_at":"2017-12-21T20:47:27Z","abstract_excerpt":"The variational encoder-decoder (VED) encodes source information as a set of random variables using a neural network, which in turn is decoded into target data using another neural network. In natural language processing, sequence-to-sequence (Seq2Seq) models typically serve as encoder-decoder networks. When combined with a traditional (deterministic) attention mechanism, the variational latent space may be bypassed by the attention model, and thus becomes ineffective. In this paper, we propose a variational attention mechanism for VED, where the attention vector is also modeled as Gaussian di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.08207","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":"1712.08207","created_at":"2026-05-18T00:12:38.381160+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.08207v3","created_at":"2026-05-18T00:12:38.381160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.08207","created_at":"2026-05-18T00:12:38.381160+00:00"},{"alias_kind":"pith_short_12","alias_value":"7I5VIT5QYUIP","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7I5VIT5QYUIPVW3E","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7I5VIT5Q","created_at":"2026-05-18T12:31:05.417338+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/7I5VIT5QYUIPVW3EH4DFT5KEJU","json":"https://pith.science/pith/7I5VIT5QYUIPVW3EH4DFT5KEJU.json","graph_json":"https://pith.science/api/pith-number/7I5VIT5QYUIPVW3EH4DFT5KEJU/graph.json","events_json":"https://pith.science/api/pith-number/7I5VIT5QYUIPVW3EH4DFT5KEJU/events.json","paper":"https://pith.science/paper/7I5VIT5Q"},"agent_actions":{"view_html":"https://pith.science/pith/7I5VIT5QYUIPVW3EH4DFT5KEJU","download_json":"https://pith.science/pith/7I5VIT5QYUIPVW3EH4DFT5KEJU.json","view_paper":"https://pith.science/paper/7I5VIT5Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.08207&json=true","fetch_graph":"https://pith.science/api/pith-number/7I5VIT5QYUIPVW3EH4DFT5KEJU/graph.json","fetch_events":"https://pith.science/api/pith-number/7I5VIT5QYUIPVW3EH4DFT5KEJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7I5VIT5QYUIPVW3EH4DFT5KEJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7I5VIT5QYUIPVW3EH4DFT5KEJU/action/storage_attestation","attest_author":"https://pith.science/pith/7I5VIT5QYUIPVW3EH4DFT5KEJU/action/author_attestation","sign_citation":"https://pith.science/pith/7I5VIT5QYUIPVW3EH4DFT5KEJU/action/citation_signature","submit_replication":"https://pith.science/pith/7I5VIT5QYUIPVW3EH4DFT5KEJU/action/replication_record"}},"created_at":"2026-05-18T00:12:38.381160+00:00","updated_at":"2026-05-18T00:12:38.381160+00:00"}