{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LQ2OVIXFSHCEOHDBZVBGYBCZAL","short_pith_number":"pith:LQ2OVIXF","schema_version":"1.0","canonical_sha256":"5c34eaa2e591c4471c61cd426c045902df193d918b4ec0279dc784587eb3386a","source":{"kind":"arxiv","id":"1808.10805","version":2},"attestation_state":"computed","paper":{"title":"Spherical Latent Spaces for Stable Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Greg Durrett, Jiacheng Xu","submitted_at":"2018-08-31T15:21:05Z","abstract_excerpt":"A hallmark of variational autoencoders (VAEs) for text processing is their combination of powerful encoder-decoder models, such as LSTMs, with simple latent distributions, typically multivariate Gaussians. These models pose a difficult optimization problem: there is an especially bad local optimum where the variational posterior always equals the prior and the model does not use the latent variable at all, a kind of \"collapse\" which is encouraged by the KL divergence term of the objective. In this work, we experiment with another choice of latent distribution, namely the von Mises-Fisher (vMF)"},"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":"1808.10805","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-31T15:21:05Z","cross_cats_sorted":[],"title_canon_sha256":"71070c9d3d46770c77aff8ed4269e9537bb2c9631cea46cbe7de31634ab0287b","abstract_canon_sha256":"67957ef8f558144fbc9024c3f0f2126aa86f247353a3e3667bf5b825e5315602"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:31.695365Z","signature_b64":"aRq3sJPIXOpvA9slavqH/3ODDhHk4FpSXGtIRj5dhMwt+Zq8w5ljCSQcyYlZj+Lt1DgPG2ji/NuK54bro+hgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c34eaa2e591c4471c61cd426c045902df193d918b4ec0279dc784587eb3386a","last_reissued_at":"2026-05-18T00:03:31.694713Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:31.694713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spherical Latent Spaces for Stable Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Greg Durrett, Jiacheng Xu","submitted_at":"2018-08-31T15:21:05Z","abstract_excerpt":"A hallmark of variational autoencoders (VAEs) for text processing is their combination of powerful encoder-decoder models, such as LSTMs, with simple latent distributions, typically multivariate Gaussians. These models pose a difficult optimization problem: there is an especially bad local optimum where the variational posterior always equals the prior and the model does not use the latent variable at all, a kind of \"collapse\" which is encouraged by the KL divergence term of the objective. In this work, we experiment with another choice of latent distribution, namely the von Mises-Fisher (vMF)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10805","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":"1808.10805","created_at":"2026-05-18T00:03:31.694813+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.10805v2","created_at":"2026-05-18T00:03:31.694813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10805","created_at":"2026-05-18T00:03:31.694813+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQ2OVIXFSHCE","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQ2OVIXFSHCEOHDB","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQ2OVIXF","created_at":"2026-05-18T12:32:37.024351+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/LQ2OVIXFSHCEOHDBZVBGYBCZAL","json":"https://pith.science/pith/LQ2OVIXFSHCEOHDBZVBGYBCZAL.json","graph_json":"https://pith.science/api/pith-number/LQ2OVIXFSHCEOHDBZVBGYBCZAL/graph.json","events_json":"https://pith.science/api/pith-number/LQ2OVIXFSHCEOHDBZVBGYBCZAL/events.json","paper":"https://pith.science/paper/LQ2OVIXF"},"agent_actions":{"view_html":"https://pith.science/pith/LQ2OVIXFSHCEOHDBZVBGYBCZAL","download_json":"https://pith.science/pith/LQ2OVIXFSHCEOHDBZVBGYBCZAL.json","view_paper":"https://pith.science/paper/LQ2OVIXF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.10805&json=true","fetch_graph":"https://pith.science/api/pith-number/LQ2OVIXFSHCEOHDBZVBGYBCZAL/graph.json","fetch_events":"https://pith.science/api/pith-number/LQ2OVIXFSHCEOHDBZVBGYBCZAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQ2OVIXFSHCEOHDBZVBGYBCZAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQ2OVIXFSHCEOHDBZVBGYBCZAL/action/storage_attestation","attest_author":"https://pith.science/pith/LQ2OVIXFSHCEOHDBZVBGYBCZAL/action/author_attestation","sign_citation":"https://pith.science/pith/LQ2OVIXFSHCEOHDBZVBGYBCZAL/action/citation_signature","submit_replication":"https://pith.science/pith/LQ2OVIXFSHCEOHDBZVBGYBCZAL/action/replication_record"}},"created_at":"2026-05-18T00:03:31.694813+00:00","updated_at":"2026-05-18T00:03:31.694813+00:00"}