{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MIWSMLBMTLSHBM3YQCUDBKUX72","short_pith_number":"pith:MIWSMLBM","schema_version":"1.0","canonical_sha256":"622d262c2c9ae470b37880a830aa97fe87851f220a015bbec062b3ec37e2356f","source":{"kind":"arxiv","id":"2405.14021","version":2},"attestation_state":"computed","paper":{"title":"A Study of Posterior Stability for Time-Series Latent Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mihaela van der Schaar, Yangming Li, Yixin Cheng","submitted_at":"2024-05-22T21:54:12Z","abstract_excerpt":"Latent diffusion has demonstrated promising results in image generation and permits efficient sampling. However, this framework might suffer from the problem of posterior collapse when applied to time series. In this paper, we first show that posterior collapse will reduce latent diffusion to a variational autoencoder (VAE), making it less expressive. This highlights the importance of addressing this issue. We then introduce a principled method: dependency measure, that quantifies the sensitivity of a recurrent decoder to input variables. Using this tool, we confirm that posterior collapse sig"},"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":"2405.14021","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T21:54:12Z","cross_cats_sorted":[],"title_canon_sha256":"f64fb4922b7ed75cb387b7e46ab4739a0e1e2c9bcc68287934df3501d826e269","abstract_canon_sha256":"8072f487598da2386ca92252e513a0af5d8265d42373591934d9db9ab80601de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:54.301581Z","signature_b64":"cmjaA9wiUa3Bn1M4cO+aFxvWwNaRzvkzmga2CXajZRWR1Fcexo8R92cTdfsO3tI34YkZYnlm2QNVwAD6ZlkcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"622d262c2c9ae470b37880a830aa97fe87851f220a015bbec062b3ec37e2356f","last_reissued_at":"2026-07-05T09:14:54.301118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:54.301118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Study of Posterior Stability for Time-Series Latent Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mihaela van der Schaar, Yangming Li, Yixin Cheng","submitted_at":"2024-05-22T21:54:12Z","abstract_excerpt":"Latent diffusion has demonstrated promising results in image generation and permits efficient sampling. However, this framework might suffer from the problem of posterior collapse when applied to time series. In this paper, we first show that posterior collapse will reduce latent diffusion to a variational autoencoder (VAE), making it less expressive. This highlights the importance of addressing this issue. We then introduce a principled method: dependency measure, that quantifies the sensitivity of a recurrent decoder to input variables. Using this tool, we confirm that posterior collapse sig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14021","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.14021/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":"2405.14021","created_at":"2026-07-05T09:14:54.301181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14021v2","created_at":"2026-07-05T09:14:54.301181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14021","created_at":"2026-07-05T09:14:54.301181+00:00"},{"alias_kind":"pith_short_12","alias_value":"MIWSMLBMTLSH","created_at":"2026-07-05T09:14:54.301181+00:00"},{"alias_kind":"pith_short_16","alias_value":"MIWSMLBMTLSHBM3Y","created_at":"2026-07-05T09:14:54.301181+00:00"},{"alias_kind":"pith_short_8","alias_value":"MIWSMLBM","created_at":"2026-07-05T09:14:54.301181+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20771","citing_title":"Stochastic and Non-local Closure Modeling for Nonlinear Dynamical Systems via Latent Score-based Generative Models","ref_index":98,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MIWSMLBMTLSHBM3YQCUDBKUX72","json":"https://pith.science/pith/MIWSMLBMTLSHBM3YQCUDBKUX72.json","graph_json":"https://pith.science/api/pith-number/MIWSMLBMTLSHBM3YQCUDBKUX72/graph.json","events_json":"https://pith.science/api/pith-number/MIWSMLBMTLSHBM3YQCUDBKUX72/events.json","paper":"https://pith.science/paper/MIWSMLBM"},"agent_actions":{"view_html":"https://pith.science/pith/MIWSMLBMTLSHBM3YQCUDBKUX72","download_json":"https://pith.science/pith/MIWSMLBMTLSHBM3YQCUDBKUX72.json","view_paper":"https://pith.science/paper/MIWSMLBM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14021&json=true","fetch_graph":"https://pith.science/api/pith-number/MIWSMLBMTLSHBM3YQCUDBKUX72/graph.json","fetch_events":"https://pith.science/api/pith-number/MIWSMLBMTLSHBM3YQCUDBKUX72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MIWSMLBMTLSHBM3YQCUDBKUX72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MIWSMLBMTLSHBM3YQCUDBKUX72/action/storage_attestation","attest_author":"https://pith.science/pith/MIWSMLBMTLSHBM3YQCUDBKUX72/action/author_attestation","sign_citation":"https://pith.science/pith/MIWSMLBMTLSHBM3YQCUDBKUX72/action/citation_signature","submit_replication":"https://pith.science/pith/MIWSMLBMTLSHBM3YQCUDBKUX72/action/replication_record"}},"created_at":"2026-07-05T09:14:54.301181+00:00","updated_at":"2026-07-05T09:14:54.301181+00:00"}