{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:34KIOYGKTNUTRKDJCHF3XNSCGA","short_pith_number":"pith:34KIOYGK","schema_version":"1.0","canonical_sha256":"df148760ca9b6938a86911cbbbb6423034d2dd348719c6047a6a37369b5f1392","source":{"kind":"arxiv","id":"1702.08139","version":2},"attestation_state":"computed","paper":{"title":"Improved Variational Autoencoders for Text Modeling using Dilated Convolutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.NE","authors_text":"Ruslan Salakhutdinov, Taylor Berg-Kirkpatrick, Zhiting Hu, Zichao Yang","submitted_at":"2017-02-27T04:16:01Z","abstract_excerpt":"Recent work on generative modeling of text has found that variational auto-encoders (VAE) incorporating LSTM decoders perform worse than simpler LSTM language models (Bowman et al., 2015). This negative result is so far poorly understood, but has been attributed to the propensity of LSTM decoders to ignore conditioning information from the encoder. In this paper, we experiment with a new type of decoder for VAE: a dilated CNN. By changing the decoder's dilation architecture, we control the effective context from previously generated words. In experiments, we find that there is a trade off betw"},"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":"1702.08139","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-02-27T04:16:01Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d7504b8c698174e87ca77b957039962d7ea99bfc061aaaba20cf618254c0b0d2","abstract_canon_sha256":"e4beab964db166df51599d9cd6f4ec6f1b5033e909d8c0372be26e129a33062d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:12.349544Z","signature_b64":"qxk/2/+w/0MuKMgjnIkCGcH9Te8ia/br7yhHDxV8FuvGy051LRfHDGo1VhexhFXg+PlOhulxzUrKuaM+aHynDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df148760ca9b6938a86911cbbbb6423034d2dd348719c6047a6a37369b5f1392","last_reissued_at":"2026-05-18T00:42:12.349121Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:12.349121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Variational Autoencoders for Text Modeling using Dilated Convolutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.NE","authors_text":"Ruslan Salakhutdinov, Taylor Berg-Kirkpatrick, Zhiting Hu, Zichao Yang","submitted_at":"2017-02-27T04:16:01Z","abstract_excerpt":"Recent work on generative modeling of text has found that variational auto-encoders (VAE) incorporating LSTM decoders perform worse than simpler LSTM language models (Bowman et al., 2015). This negative result is so far poorly understood, but has been attributed to the propensity of LSTM decoders to ignore conditioning information from the encoder. In this paper, we experiment with a new type of decoder for VAE: a dilated CNN. By changing the decoder's dilation architecture, we control the effective context from previously generated words. In experiments, we find that there is a trade off betw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08139","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":"1702.08139","created_at":"2026-05-18T00:42:12.349181+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.08139v2","created_at":"2026-05-18T00:42:12.349181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08139","created_at":"2026-05-18T00:42:12.349181+00:00"},{"alias_kind":"pith_short_12","alias_value":"34KIOYGKTNUT","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"34KIOYGKTNUTRKDJ","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"34KIOYGK","created_at":"2026-05-18T12:30:58.224056+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/34KIOYGKTNUTRKDJCHF3XNSCGA","json":"https://pith.science/pith/34KIOYGKTNUTRKDJCHF3XNSCGA.json","graph_json":"https://pith.science/api/pith-number/34KIOYGKTNUTRKDJCHF3XNSCGA/graph.json","events_json":"https://pith.science/api/pith-number/34KIOYGKTNUTRKDJCHF3XNSCGA/events.json","paper":"https://pith.science/paper/34KIOYGK"},"agent_actions":{"view_html":"https://pith.science/pith/34KIOYGKTNUTRKDJCHF3XNSCGA","download_json":"https://pith.science/pith/34KIOYGKTNUTRKDJCHF3XNSCGA.json","view_paper":"https://pith.science/paper/34KIOYGK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.08139&json=true","fetch_graph":"https://pith.science/api/pith-number/34KIOYGKTNUTRKDJCHF3XNSCGA/graph.json","fetch_events":"https://pith.science/api/pith-number/34KIOYGKTNUTRKDJCHF3XNSCGA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/34KIOYGKTNUTRKDJCHF3XNSCGA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/34KIOYGKTNUTRKDJCHF3XNSCGA/action/storage_attestation","attest_author":"https://pith.science/pith/34KIOYGKTNUTRKDJCHF3XNSCGA/action/author_attestation","sign_citation":"https://pith.science/pith/34KIOYGKTNUTRKDJCHF3XNSCGA/action/citation_signature","submit_replication":"https://pith.science/pith/34KIOYGKTNUTRKDJCHF3XNSCGA/action/replication_record"}},"created_at":"2026-05-18T00:42:12.349181+00:00","updated_at":"2026-05-18T00:42:12.349181+00:00"}