{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GHBZNKNZKVMY5ULX577X5CZ7U5","short_pith_number":"pith:GHBZNKNZ","schema_version":"1.0","canonical_sha256":"31c396a9b955598ed177efff7e8b3fa741d14facea8e55248363f899a6199adc","source":{"kind":"arxiv","id":"2301.00537","version":1},"attestation_state":"computed","paper":{"title":"Posterior Collapse and Latent Variable Non-identifiability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"David M. Blei, John P. Cunningham, Yixin Wang","submitted_at":"2023-01-02T06:16:56Z","abstract_excerpt":"Variational autoencoders model high-dimensional data by positing low-dimensional latent variables that are mapped through a flexible distribution parametrized by a neural network. Unfortunately, variational autoencoders often suffer from posterior collapse: the posterior of the latent variables is equal to its prior, rendering the variational autoencoder useless as a means to produce meaningful representations. Existing approaches to posterior collapse often attribute it to the use of neural networks or optimization issues due to variational approximation. In this paper, we consider posterior "},"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":"2301.00537","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-01-02T06:16:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c6e89f804f98a6e8325e946605f1bfd5e48d2f7a223d75f7ab06189d30fc57c9","abstract_canon_sha256":"5cf8c5793b7e7a1b2bbdabbb1c5d100f1f35a89ea825f8a24f7755d7c894378f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:29:47.453102Z","signature_b64":"k/s60V4i0dBggFTspDhRGH19aE1C2gDsa4o4f3QBI7s/OnbLe0vM6f3QB2rwohrvYqj+LVsy7XfAlFYgbKNoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31c396a9b955598ed177efff7e8b3fa741d14facea8e55248363f899a6199adc","last_reissued_at":"2026-07-05T05:29:47.452617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:29:47.452617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Posterior Collapse and Latent Variable Non-identifiability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"David M. Blei, John P. Cunningham, Yixin Wang","submitted_at":"2023-01-02T06:16:56Z","abstract_excerpt":"Variational autoencoders model high-dimensional data by positing low-dimensional latent variables that are mapped through a flexible distribution parametrized by a neural network. Unfortunately, variational autoencoders often suffer from posterior collapse: the posterior of the latent variables is equal to its prior, rendering the variational autoencoder useless as a means to produce meaningful representations. Existing approaches to posterior collapse often attribute it to the use of neural networks or optimization issues due to variational approximation. In this paper, we consider posterior "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.00537","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2301.00537/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2301.00537","created_at":"2026-07-05T05:29:47.452674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.00537v1","created_at":"2026-07-05T05:29:47.452674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.00537","created_at":"2026-07-05T05:29:47.452674+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHBZNKNZKVMY","created_at":"2026-07-05T05:29:47.452674+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHBZNKNZKVMY5ULX","created_at":"2026-07-05T05:29:47.452674+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHBZNKNZ","created_at":"2026-07-05T05:29:47.452674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07137","citing_title":"Exploring coupled tropical Pacific variability within a Multi-branch $\\beta$-Variational Autoencoder","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GHBZNKNZKVMY5ULX577X5CZ7U5","json":"https://pith.science/pith/GHBZNKNZKVMY5ULX577X5CZ7U5.json","graph_json":"https://pith.science/api/pith-number/GHBZNKNZKVMY5ULX577X5CZ7U5/graph.json","events_json":"https://pith.science/api/pith-number/GHBZNKNZKVMY5ULX577X5CZ7U5/events.json","paper":"https://pith.science/paper/GHBZNKNZ"},"agent_actions":{"view_html":"https://pith.science/pith/GHBZNKNZKVMY5ULX577X5CZ7U5","download_json":"https://pith.science/pith/GHBZNKNZKVMY5ULX577X5CZ7U5.json","view_paper":"https://pith.science/paper/GHBZNKNZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.00537&json=true","fetch_graph":"https://pith.science/api/pith-number/GHBZNKNZKVMY5ULX577X5CZ7U5/graph.json","fetch_events":"https://pith.science/api/pith-number/GHBZNKNZKVMY5ULX577X5CZ7U5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHBZNKNZKVMY5ULX577X5CZ7U5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHBZNKNZKVMY5ULX577X5CZ7U5/action/storage_attestation","attest_author":"https://pith.science/pith/GHBZNKNZKVMY5ULX577X5CZ7U5/action/author_attestation","sign_citation":"https://pith.science/pith/GHBZNKNZKVMY5ULX577X5CZ7U5/action/citation_signature","submit_replication":"https://pith.science/pith/GHBZNKNZKVMY5ULX577X5CZ7U5/action/replication_record"}},"created_at":"2026-07-05T05:29:47.452674+00:00","updated_at":"2026-07-05T05:29:47.452674+00:00"}