{"as_of":"2026-08-22T03:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:58980b905c2a889632f9c008e79924179110f6467b8ba38fac4691516b62c512","coverage":[{"denominator":50,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":50,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T17:24:36.013732Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-29T08:53:49.780277Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-06-29T09:03:16.195560Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"cited_work":{"arxiv_id":"2508.16643","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.16643","snapshot_observed_at":"2026-06-29T09:03:16.195560Z","title":null,"venue":null,"work_id":"95628f29-421c-4411-8f67-44a785c67d76","year":2025},"citing_paper":{"arxiv_id":"2605.29713","last_updated":"2026-05-28T10:12:00Z","snapshot_observed_at":"2026-08-21T22:04:21.890501Z","submitted_at":"2026-05-28T10:12:00Z","title":"The Little Book of Generative AI Foundations: An Intuitive Mathematical Primer","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-29T08:53:49.780277Z"},"links":{"cited_paper":"/paper/2508.16643","citing_paper":"/paper/2605.29713"},"observation_digest":"sha256:ba4a1a05e918b832bc410ca9f1ce0bfc61a644f36b2842ff64caeaae2815f9b7","observation_id":"f86015fd-f539-4edb-a169-102b1283749b","resolution":{"observed_at":"2026-06-29T09:03:16.197073Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2508.16643/citation-record","integrity":"/paper/2508.16643/integrity","json":"/paper/2508.16643/citation-record.json","paper":"/paper/2508.16643"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.729007Z","title":"Deep learning day: Generative modeling","venue":null,"work_id":"75910243-47db-4528-8675-4b5c9a6a2b63","year":2025},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.791800Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:b42e43efbf310a1eb7d1b8269b78f4958a9baec1890a207bd7f2c156c599b915","observation_id":"982c7017-72a2-47ca-b461-2014795c8899","resolution":{"observed_at":"2026-08-15T17:24:36.734386Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:35.797040Z","title":"The promise and peril of generative ai","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.797040Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:f2807b62f8f8bb39ea63666cf3d5ff637b5441fe25642fd1e3c0b9b39e60e258","observation_id":"43befff6-5bb8-4698-9d8c-fc17c910c8a8","resolution":{"observed_at":"2026-08-15T17:24:35.797040Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:35.801025Z","title":"Art and the science of generative ai","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.801025Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:3b025a4d77b630d1b311c5d22def9880d715cd5cc4193d86ccde9f73e8f8bfe5","observation_id":"1a013c4a-7168-4680-849b-50e4a644dead","resolution":{"observed_at":"2026-08-15T17:24:35.801025Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.687437Z","title":"Learning deep generative models","venue":null,"work_id":"c88b361d-7ace-47c2-b8d4-304bcedfbe43","year":2015},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.805525Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:9799a102de3a6acbd5893e392828a79197ba99233d0478e5e006369bb56c813f","observation_id":"7cef4bc8-58b3-4786-85c1-f9b74f991db4","resolution":{"observed_at":"2026-08-15T17:24:36.693416Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.04226","last_updated":"2023-03-07T20:36:13Z","snapshot_observed_at":"2026-08-20T06:34:12.060046Z","submitted_at":"2023-03-07T20:36:13Z","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.04226","snapshot_observed_at":"2026-08-15T17:24:35.810701Z","title":"A comprehensive survey of ai-generated content (aigc): A history of generative ai from gan to chatgpt","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.810701Z"},"links":{"cited_paper":"/paper/2303.04226","citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:443f343461c9e6c0fda3254f62b3d6b4c335efc4915a9d41aa84fef95d308df8","observation_id":"3397e076-44ed-4b17-8ea4-950da318a90a","resolution":{"observed_at":"2026-08-15T17:24:35.810701Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:35.815406Z","title":null,"venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.815406Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:bea8e9ab512dc4d3ef6313f8c6effd2b1497608fecad1947ee2f4889d53193d6","observation_id":"464bb508-4427-4687-bb60-09bba8e615f1","resolution":{"observed_at":"2026-08-15T17:24:35.815406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:35.820238Z","title":"Latent dirichlet allocation","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.820238Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:956dc4ab9d607625c23313f64feb56db4eaf8a7782981e0c4b08fe77a2c42c93","observation_id":"33ca752d-974e-476d-9fbc-4bfbb4dcc396","resolution":{"observed_at":"2026-08-15T17:24:35.820238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:35.824439Z","title":"Autoencoders and their applications in machine learning: a survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.824439Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:3d515d15a18019674f6c7519f35d72fb8a9a82dc118d23ec2d7b70a96059c96b","observation_id":"a6738c74-d8c0-4e43-8d7e-0dfdb3cd56ca","resolution":{"observed_at":"2026-08-15T17:24:35.824439Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:35.829954Z","title":"Auto-encoding variational bayes, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.829954Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:cdd6316907d9ccb319a23730b283a3556530dfc939a03cb5e319e7a227b51fcf","observation_id":"a5183234-c653-46c3-a45c-a652b378ab66","resolution":{"observed_at":"2026-08-15T17:24:35.829954Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.616969Z","title":"Normalizing flows: An introduction and review of current methods","venue":null,"work_id":"41070cf7-52cf-43f4-88ab-ad774e4fb951","year":2020},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.833903Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:86ed83f000938936b220eb598005ace8ef481b21b2c55df980a8523e335314e6","observation_id":"270bd25c-73a6-4cc0-a0bd-8238be315397","resolution":{"observed_at":"2026-08-15T17:24:36.622278Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.02747","last_updated":"2023-02-08T15:46:05Z","snapshot_observed_at":"2026-08-16T02:30:42.660030Z","submitted_at":"2022-10-06T08:32:20Z","title":"Flow Matching for Generative Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.02747","snapshot_observed_at":"2026-08-15T17:24:35.838878Z","title":"Flow matching for generative modeling","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.838878Z"},"links":{"cited_paper":"/paper/2210.02747","citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:17c134577f8284fc2af38291bff6c679f0100b8a5c7f86ac1287f25d3e5e97f0","observation_id":"1696c5f6-888a-4619-9b22-1e2eb984ae80","resolution":{"observed_at":"2026-08-15T17:24:35.838878Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.599496Z","title":"Deep unsupervised learning using nonequilibrium thermodynamics","venue":null,"work_id":"ff59e62f-816e-450d-8e6e-e896a0b808f4","year":2015},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.844344Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:1cd42fc6657bb375ac2a3656be1746738d0ca49d07f05148a1cb73807dd68bb3","observation_id":"aabcb463-8f43-4e2d-99d1-2522cbf09c12","resolution":{"observed_at":"2026-08-15T17:24:36.604838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:35.848523Z","title":"Generative adversarial nets","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.848523Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:9ff4d3899042b1f8bc8e00ed82cc3183094488611836bc857c0f877182ceab14","observation_id":"d8175491-51f3-4894-920e-41d8ca0d0fd1","resolution":{"observed_at":"2026-08-15T17:24:35.848523Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.570149Z","title":"A review on kalman filter models","venue":null,"work_id":"37b7e8f7-2d7a-4947-95b1-15dce2769e1a","year":2023},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.852485Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:ffaef557a9472c8060a96320e15238b1eed5ee82ed980656ef9f9e91b38504fe","observation_id":"b57a2151-3877-458b-96fd-f4d3ec642cc0","resolution":{"observed_at":"2026-08-15T17:24:36.574972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.552725Z","title":"Item Response Theory: Principles and Applications","venue":null,"work_id":"8b4941f3-9544-443f-a1a1-240cb571486e","year":2013},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.856968Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:beeaf0edfdc7f4ca2d08e84eb0c18bb57a894c921af53fa3ceeb863806158cdc","observation_id":"824f2da1-5d44-4892-8ba8-8395185c1d4c","resolution":{"observed_at":"2026-08-15T17:24:36.557966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.534118Z","title":"Hidden Markov models and applications","venue":null,"work_id":"e597b5b1-f6f7-4da1-bd96-fe520549a240","year":2022},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.860771Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:cfdd77827289d9d3993061f08649e004486d5a0595ebdc9ad900b229d2bbcf3e","observation_id":"022dfdb9-277d-4db7-a48a-572578a9036a","resolution":{"observed_at":"2026-08-15T17:24:36.541248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.515057Z","title":"Latent class analysis: a guide to best practice","venue":null,"work_id":"ec5b2f93-4285-42e3-b786-4ab14e4534cf","year":2020},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.864532Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:265bc54058cf8b98d692cea4b50b9275f1835914be3db7f4542edada8ac2900e","observation_id":"b2368cf2-f5fe-4368-8985-616170ade9a8","resolution":{"observed_at":"2026-08-15T17:24:36.521486Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.493650Z","title":"Cs229 lecture notes","venue":null,"work_id":"54364da7-ee7f-48fd-a6f7-872f8332423a","year":2022},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.869307Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:02a605a930e056800085c97657b759d1df6e557f303438068e0d4ecd0897419e","observation_id":"2b0b342b-1092-49b2-a408-36cd5b8cece3","resolution":{"observed_at":"2026-08-15T17:24:36.500847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.478774Z","title":"Deep Learning, volume 1","venue":null,"work_id":"049bbe33-6df4-4368-98e1-8c7eb5d4c9e5","year":2016},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.873798Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:2cd11dea0d63b88573f0cfe778b606e5aaa134289aefa7974c0e9987d46e8ab4","observation_id":"82bb92eb-3736-4233-b75b-d93e59242814","resolution":{"observed_at":"2026-08-15T17:24:36.483765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.464370Z","title":"Item Response Theory: Parameter Estimation Techniques","venue":null,"work_id":"a1bb9acd-8f7d-4254-8056-41342422edac","year":2004},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.878331Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:53f33ea97ed9f5a7b19afc9f00d9162b57907db38004eefbf91cc7a39f542ff7","observation_id":"6d872de4-374c-492f-8e39-5b3a37ca69c5","resolution":{"observed_at":"2026-08-15T17:24:36.469838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.447497Z","title":"Probabilistic principal component analysis","venue":null,"work_id":"0479078f-4e8f-491f-bda8-5324a2de0594","year":1999},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.883596Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:10c6ad70d20735a9f5675cf9eac71ab0578e6288019e66ae5c18f1794912c192","observation_id":"1a40908e-a628-4df1-8781-f3daf14acd13","resolution":{"observed_at":"2026-08-15T17:24:36.452623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:35.888382Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.888382Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:c0aa28a287cfced3c1319a8ebc91135c17be4edd6513c0b8c378bc7bb2d6f93a","observation_id":"274a2cd7-787c-4148-8130-779b5ce5f027","resolution":{"observed_at":"2026-08-15T17:24:35.888382Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.424571Z","title":null,"venue":null,"work_id":"ceaf9840-64a0-4a4f-83ef-ef1ba2f1c111","year":1999},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.892164Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:c4354ef2687b37cce228a579fde99bbbce000112a15b08de0cedbab1bf12996f","observation_id":"910e250e-af4d-498a-9e2f-c5aced4dec4e","resolution":{"observed_at":"2026-08-15T17:24:36.428544Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.409855Z","title":"Principal component analysis","venue":null,"work_id":"6317878c-5a14-47b7-8174-df443b315acf","year":2010},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.896028Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:1a9fecfda307782cc596008527b34c8425aa045b3f5c344db53a2150213b5454","observation_id":"4ff01911-0135-4747-bcef-6338740743f6","resolution":{"observed_at":"2026-08-15T17:24:36.414670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:35.899961Z","title":"Maximum likelihood from incomplete data via the em algorithm","venue":null,"work_id":null,"year":1977},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.899961Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:d443507a4505aa39de3749c2ce5ac2114261c63b51b9287cf29bc74dfcd94899","observation_id":"3f520336-171d-4be3-8f8f-04eadec440ec","resolution":{"observed_at":"2026-08-15T17:24:35.899961Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.384962Z","title":"Latent class analysis, volume 64","venue":null,"work_id":"d40904f1-6455-48e5-b21a-f6ba2afe9976","year":1987},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.904433Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:285926e9800b263ba5995d68cea17d2546873b306e7519048de99b2d387fcd8a","observation_id":"da2a01d7-5394-4eac-a742-4c4c96ea0308","resolution":{"observed_at":"2026-08-15T17:24:36.389635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.369494Z","title":"Latent class and latent transition analysis: With applications in the social, behavioral, and health sciences","venue":null,"work_id":"ac740db5-e7ae-418c-8676-c32dc9ead773","year":2009},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.908867Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:55338872f0006528130b5548d5432b380de892cb9d6a1a0fc64fd9b78f9fde64","observation_id":"ecac11e0-e757-4378-8785-24e9dd1c4f30","resolution":{"observed_at":"2026-08-15T17:24:36.374551Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.355034Z","title":"Blei, Alp Kucukelbir, and Jon D","venue":null,"work_id":"cc1a47bb-4b1f-45b5-b5b7-c5c75420812c","year":2017},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.913162Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:3bcf7fb444bc63f83d8c936bd696fe78443b93ae17ac515defb236a7608157bb","observation_id":"4ad8930d-af1b-44ed-86bf-cfb24317a6c3","resolution":{"observed_at":"2026-08-15T17:24:36.359526Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.341156Z","title":"Topic modeling using latent dirichlet allocation: A survey","venue":null,"work_id":"77b469bf-e12d-4f5f-a125-24c74bd87e39","year":2021},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.917065Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:d67c03ee1fb55c8bdda12f556a49ecf5c2c4e8d14577083e357404b261c51e2d","observation_id":"2da95552-f9af-4fa3-bf3d-05892fbf3674","resolution":{"observed_at":"2026-08-15T17:24:36.345480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.327663Z","title":"A systematic review of hidden markov models and their applications","venue":null,"work_id":"013121bf-7390-4a90-9e2d-719a6666a95a","year":2021},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.921025Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:caced13b88303df950ac9b32598aac56eb7bf24bfa69a4a3276988c93d491cf7","observation_id":"6d92b8c1-1a2e-4230-b5a8-2ab4065ab373","resolution":{"observed_at":"2026-08-15T17:24:36.332150Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:35.925420Z","title":"Markov decision processes: discrete stochastic dynamic programming","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.925420Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:6f0da284d50f86b7946a467af34a3293bcca8c327caa046bfe83d99babe41b9a","observation_id":"8c65338b-f09f-4763-9a39-ea3092c52276","resolution":{"observed_at":"2026-08-15T17:24:35.925420Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.305834Z","title":"Industrial applications of the kalman filter: A review","venue":null,"work_id":"d81809fb-6702-4ee7-8351-dd5e6e4bf749","year":2013},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.929595Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:8c80e85c3fea1b07659fe46de92e898f3ad12f0df5968e43d7b4d96b5b852586","observation_id":"62310831-79f9-4c4a-b8ba-b2570f5e945e","resolution":{"observed_at":"2026-08-15T17:24:36.310524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.290345Z","title":"A survey on variational autoencoders in recommender systems","venue":null,"work_id":"8ace4da0-0e7c-496e-8c74-47eb64e8eda0","year":2024},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.933889Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:623ad0fbed95f1ab452711ae764c88ed54965538d862201b87c6bd4f558ec323","observation_id":"7d97fc24-6a15-4a0b-9d8d-f13f8e494ee5","resolution":{"observed_at":"2026-08-15T17:24:36.296422Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:35.937905Z","title":"Normalizing flows for probabilistic modeling and inference","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.937905Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:016eeb868e78733fc1bdcf62d014c80fecb4db6bbb00ea23885f7f321d524913","observation_id":"58ab084c-508c-42cc-b4f0-8d71de24a272","resolution":{"observed_at":"2026-08-15T17:24:35.937905Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:35.942468Z","title":"Variational inference with normalizing flows, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.942468Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:878d119b8069f8e072ef2848b631a65a10bbd34f337b50e4534eb150e2eaf93a","observation_id":"ec0aaf23-d35f-41a5-ab46-8046efed53af","resolution":{"observed_at":"2026-08-15T17:24:35.942468Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:35.948713Z","title":"Density estimation using real nvp, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.948713Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:ad45eb39a1ffe0677645a3c914e08a73890d73f2a11d62b8156cdf5a5882a882","observation_id":"dda9710f-b59e-45de-8dce-7a38772845ec","resolution":{"observed_at":"2026-08-15T17:24:35.948713Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:35.953323Z","title":"Denoising diffusion probabilistic models, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.953323Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:da29deae3f0806aa0b2915aca788556291623befdd02ca2e8e08ef930a8ea8e4","observation_id":"9754cfde-1f44-48ba-a8a1-d35d97ecf411","resolution":{"observed_at":"2026-08-15T17:24:35.953323Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.13807","last_updated":"2022-05-02T19:35:26Z","snapshot_observed_at":"2026-08-16T17:04:41.030388Z","submitted_at":"2022-04-25T18:54:39Z","title":"A very preliminary analysis of DALL-E 2","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.13807","snapshot_observed_at":"2026-08-15T17:24:35.957807Z","title":"A very preliminary analysis of dall-e 2","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.957807Z"},"links":{"cited_paper":"/paper/2204.13807","citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:c0276d52e33302f3e5176006a2acff2435a7c74a6f39a768c71476088a829244","observation_id":"fb124bb9-472d-4138-b909-090aba1174de","resolution":{"observed_at":"2026-08-15T17:24:35.957807Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.230638Z","title":"Stable diffusion 3.5","venue":null,"work_id":"69708402-0162-4142-952f-17c8e3fde63d","year":2024},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.964030Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:b417c07404ef1bf71fc2d2544e4a6417756e157ea23d63ad385e1aecf84ab58d","observation_id":"bc19f2d1-03f0-4b59-85d2-38b00b4ae816","resolution":{"observed_at":"2026-08-15T17:24:36.236220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:35.970303Z","title":"Diffusion models: A comprehensive survey of methods and applications","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.970303Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:6d185fbaed2b2df126cf7179288afd593c45b8e880f869d5a21167f42a2651a1","observation_id":"79603ee9-3f6d-4136-bb13-1e7926e7b668","resolution":{"observed_at":"2026-08-15T17:24:35.970303Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.208993Z","title":"Conditional image generation with pixelcnn decoders, 2016","venue":null,"work_id":"54a09383-1f1a-402a-b9ff-cdd6ff395efc","year":2016},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.975226Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:fb67f59f186c617fbe4553bb9be17e7d024f63fa35a5dc1f9a1e55c3de352fae","observation_id":"2b7f7874-0e68-4bc3-b562-e348152e160e","resolution":{"observed_at":"2026-08-15T17:24:36.213571Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.193559Z","title":"Wavenet: A generative model for raw audio, 2016","venue":null,"work_id":"729c470b-8228-4fdb-ba7a-87671243e550","year":2016},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.979616Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:ade8179bcdf754735596acf8c56a6f887848039ccde3f8e48476f12b3c9d25fa","observation_id":"52c968f3-eb4b-4ec5-9d37-69182f470124","resolution":{"observed_at":"2026-08-15T17:24:36.198790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.178964Z","title":null,"venue":null,"work_id":"723ce777-6791-46f7-b39c-177c2a2b031a","year":2024},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.983995Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:24d1f7402e2c6483451879112dc9ddb52e143c7e7b63d7bb927b081e1c029736","observation_id":"81acfc9f-085f-4abc-89fa-745919310b3b","resolution":{"observed_at":"2026-08-15T17:24:36.184045Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.166338Z","title":"Hybrid variational autoencoder for time series forecasting","venue":null,"work_id":"0f5a2028-a4ed-4f88-a34a-e8d2a3597e23","year":2023},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.989295Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:b0951a15fa9a6ab06d6fe4af0f7b57b7da033a38ae62f7166593e8b57c02478e","observation_id":"ef6365d3-eb6c-43b5-bbaf-7dabf772ee10","resolution":{"observed_at":"2026-08-15T17:24:36.170508Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:35.993300Z","title":"A style-based generator architecture for generative adversarial networks, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.993300Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:8cfdd59a81bc473c8193986fdd1f3ef1b0caa49add8af9c75d524ec7d16cfa64","observation_id":"1341706b-1226-49d1-bf1d-17937923b8b4","resolution":{"observed_at":"2026-08-15T17:24:35.993300Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.144590Z","title":"E2gan: Efficient training of efficient gans for image-to-image translation, 2024","venue":null,"work_id":"bacef143-2b75-4c99-9d3c-60e98a16a91d","year":2024},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:35.997245Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:56aae74446ec7291b65d99a4d4782735debeeb95319fd44570ceea06253c0855","observation_id":"fc99b7cf-35aa-48ab-a006-83ffb400319f","resolution":{"observed_at":"2026-08-15T17:24:36.149096Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.130977Z","title":"Generative adversarial networks for image super-resolution: A survey, 2024","venue":null,"work_id":"2e9e89da-2417-4b75-8d06-f92f6a70ced7","year":2024},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:36.001811Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:7127f8953db4912075b92507ded88939617c8e75578662ede7a4492fc68ea918","observation_id":"b77f9458-53c7-47aa-b124-19d8a6582a57","resolution":{"observed_at":"2026-08-15T17:24:36.135625Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.005861Z","title":"Wasserstein gan, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:36.005861Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:6a39e941bb8a3969a231bcdee772e8cc38729f28220f9cfb47d9376458c8115a","observation_id":"a3c97dbb-5b88-43a3-8c1d-43e6352d4bf1","resolution":{"observed_at":"2026-08-15T17:24:36.005861Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.110287Z","title":"Diffusion-gan: Training gans with diffusion, 2023","venue":null,"work_id":"ad577645-2faf-42a1-927a-8204c1a1f9cb","year":2023},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:36.009885Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:b4e40c4eb39018220e84593deea05484c4f7094033ce9c29a63e2b4803eea1db","observation_id":"b489a9b9-0881-4daa-9acf-04062c358925","resolution":{"observed_at":"2026-08-15T17:24:36.114679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:24:36.095489Z","title":"Seriesgan: Time series generation via adversarial and autoregressive learning, 2024","venue":null,"work_id":"42fbb5f1-e884-463b-b60f-c9e07fa29e10","year":2024},"citing_paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T17:24:36.013732Z"},"links":{"citing_paper":"/paper/2508.16643"},"observation_digest":"sha256:eff8a7faf02ad7098880b5e7a6ee1c16fd3f18ade2c3d8b2340de20e5a071c7d","observation_id":"8faa7c6f-713f-4c9b-8c26-485edbe33577","resolution":{"observed_at":"2026-08-15T17:24:36.101366Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.16643","last_updated":"2025-08-18T11:02:32Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-20T06:34:35.915990Z","submitted_at":"2025-08-18T11:02:32Z","title":"From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective"},"reference_resolution":{"displayed":50,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":0,"verified_fuzzy":28},"total_outbound_references":50},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 1 inbound Pith citation observation for arXiv:2508.16643."}