{"as_of":"2026-08-19T19:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5bba8aa95c2d23a57aa4b4ca6452a632b897505968c8b3eb44c28604c82586eb","coverage":[{"denominator":40,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":40,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T11:10:39.510929Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/1908.09772/citation-record","integrity":"/paper/1908.09772/integrity","json":"/paper/1908.09772/citation-record.json","paper":"/paper/1908.09772"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1706.01350","last_updated":"2018-06-28T17:50:54Z","snapshot_observed_at":"2026-08-15T14:09:03.376490Z","submitted_at":"2017-06-05T14:31:03Z","title":"Emergence of Invariance and Disentanglement in Deep Representations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.01350","snapshot_observed_at":"2026-08-14T11:10:39.344749Z","title":"Emergence of invariance and dis- entanglement in deep representations.arXiv preprint arXiv:1706.01350, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.344749Z"},"links":{"cited_paper":"/paper/1706.01350","citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:693f2fa16b496d90574a875e3afe3fd41423d98f4404d087e52e2f86edd5ac99","observation_id":"859053b7-847c-4593-ad51-df25b15a80c5","resolution":{"observed_at":"2026-08-14T11:10:39.344749Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.02930","last_updated":"2017-10-16T01:29:59Z","snapshot_observed_at":"2026-08-15T05:56:41.643687Z","submitted_at":"2017-03-08T17:35:17Z","title":"Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks","version":3},"cited_work":{"arxiv_id":"1703.02930","doi":null,"metadata_source":"pith","pith_arxiv_id":"1703.02930","snapshot_observed_at":"2026-08-14T11:10:39.626038Z","title":"Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks","venue":"cs.LG","work_id":"85681556-3643-40a5-a3e4-353c0f2092f8","year":2017},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.349904Z"},"links":{"cited_paper":"/paper/1703.02930","citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:a594e98a70a1c6beae46324ac55025181c6011ccad78ab98a1d35221dfc3b35e","observation_id":"35f98708-2cc7-4f4c-9acc-3359eb81710b","resolution":{"observed_at":"2026-08-14T11:10:39.632488Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.354466Z","title":"Representation learning: A review and new perspectives.IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(8):1798–1828, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.354466Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:5363fb94c65a16b8113038b745213f1cf0930202e462f370013217c24fb18cb1","observation_id":"c1984f1b-7a2c-40b7-9a18-adb27b453643","resolution":{"observed_at":"2026-08-14T11:10:39.354466Z","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":"2026-08-14T11:10:40.063235Z","title":"Variational inference: A review for statisticians.Journal of Machine Learning Research, 112:859–877, 2017","venue":null,"work_id":"81a7e840-6196-49c5-be33-f7f38c759436","year":2017},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.359013Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:4bee90a46a9cae6173414266001a8f91c09c9446f2fa5620c7a183fff7c870d7","observation_id":"8c9f55e2-f5c0-4d6e-adb3-9bd70a132c64","resolution":{"observed_at":"2026-08-14T11:10:40.067853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:40.048718Z","title":"Stability and generalization.Journal of Machine Learning Research, pages 499–526, 2002","venue":null,"work_id":"e77e1ae3-db18-400a-b4f4-e9c5b27b8256","year":2002},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.363027Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:9a226e33af228e3ad00c455f6d8ddbaf9e20be85099182bc43d21821858deb03","observation_id":"eac33054-4519-440e-a1c0-218c3aa84ba1","resolution":{"observed_at":"2026-08-14T11:10:40.053577Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:40.033564Z","title":"Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters","venue":null,"work_id":"e0526ccb-38fb-4ada-9451-c4f7a4299212","year":1990},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.366975Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:07b0af60c07a940e13943edf85ac8ed9e0c900dd67118a2960e403544e9801fb","observation_id":"68a94992-c3b5-4592-bd37-383d54001284","resolution":{"observed_at":"2026-08-14T11:10:40.038398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:40.019252Z","title":"Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks","venue":null,"work_id":"61365c98-1327-4fc6-9c45-1ea74f5828bd","year":2018},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.371530Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:d3e0ab4aac259f4d8dd4b2c3fab754588e3697846329c5d5bab3e9adcc9402fe","observation_id":"c6d71125-3f2b-4756-b1df-7e2f3519e381","resolution":{"observed_at":"2026-08-14T11:10:40.024099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:40.004259Z","title":"Wiley- Interscience, Hoboken, New Jersy, 2006","venue":null,"work_id":"05940db6-c0da-4cde-95f0-03b3e0be83d0","year":2006},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.375369Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:b5219435e0e849eaa5961a53160e62e23b37b53ae4448d4d2d6a04fd7cec77a1","observation_id":"05999d27-3d9c-422b-8495-c8b54854c819","resolution":{"observed_at":"2026-08-14T11:10:40.009866Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.990001Z","title":"Geman and D","venue":null,"work_id":"b2aa87ce-0cb1-4280-9ce6-692e135a6329","year":1984},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.379168Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:90093634b9be6fee6e24486933c71a3df8c73a20e15ca5347fad2de03dbaa0f3","observation_id":"6bb7733a-e31c-4470-8748-30fd0040118c","resolution":{"observed_at":"2026-08-14T11:10:39.994480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.975755Z","title":"A probabilistic approach to the understanding and training of neural network classifiers","venue":null,"work_id":"39d78970-1184-429a-8b6c-8033bd801626","year":1990},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.383208Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:a459312413c0420a438cf1b7b365a2b2b0cc6246543afa738aff8db453e1e974","observation_id":"707b26a3-41d1-4901-9bee-47a2206e2457","resolution":{"observed_at":"2026-08-14T11:10:39.980349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.387962Z","title":"MIT Press, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.387962Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:efd7a9e3a4bfb943d257a9afd1d39feb96ab156de02f5771a9306173aadae18a","observation_id":"27eb6335-7ba0-4cc3-8a8a-279392820025","resolution":{"observed_at":"2026-08-14T11:10:39.387962Z","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":"2026-08-14T11:10:39.953138Z","title":"Lawrence","venue":null,"work_id":"fafe9983-3598-4050-8f12-5360908c2496","year":2012},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.392217Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:bc779bc46721491b8aae68731a8afbf33cc27ac676ab2359bec75f1b8a97b8e2","observation_id":"8fd9e69c-9398-414f-9e68-22002dbbe6ae","resolution":{"observed_at":"2026-08-14T11:10:39.957638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.939823Z","title":null,"venue":null,"work_id":"75ea70ba-f105-44b6-a153-09220b4feafc","year":2002},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.396260Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:34171dca9fca92f8034cdd9554f8e434238686ab861199b7ded8ddba426fc45d","observation_id":"bec56d51-7206-4c5d-bcc4-a35c029dfbe4","resolution":{"observed_at":"2026-08-14T11:10:39.944063Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.926764Z","title":"Hoffman, David M","venue":null,"work_id":"5e5da077-9bfc-4522-9434-b1fd38b59622","year":2013},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.400137Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:cf15dfbabc972f2cb30b725ad5fa6ea2010dac04713b39d1b1038707a39c7157","observation_id":"84f3d0de-1f61-4957-83c6-4fc39e824744","resolution":{"observed_at":"2026-08-14T11:10:39.930862Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.913342Z","title":null,"venue":null,"work_id":"5bce43b9-cfe8-454e-85fc-a2bdff619eb5","year":1999},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.404511Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:d7e7f035e70fa5c6208cacb73692b946dbff92deffdc87f94196097e25b113e0","observation_id":"edcc564e-b78f-4051-a95b-9d3c42af2300","resolution":{"observed_at":"2026-08-14T11:10:39.917391Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.901296Z","title":null,"venue":null,"work_id":"8ac8686f-9ce9-4f24-9c75-d7ca22216a75","year":2018},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.408598Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:eea6f950265fd7e3bbd07be498722cae284b86c3ad6f2b010acefa860df06e12","observation_id":"41afecdc-93e3-4c63-8d12-816c0904cdec","resolution":{"observed_at":"2026-08-14T11:10:39.905343Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.887771Z","title":"MIT Press, 2006","venue":null,"work_id":"3e9a7342-bc4c-4a91-a56b-41a635886b2b","year":2006},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.412909Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:aa96450b1b125893b807f322bedfefe66dc7ee26ca502cd75f8cc76690c7d210","observation_id":"8b0f309f-a079-4649-b2de-dd0d15c09401","resolution":{"observed_at":"2026-08-14T11:10:39.892366Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.874958Z","title":"A bayesian hierarchical model for learning natural scene categories","venue":null,"work_id":"29229e05-2d84-4a09-92dd-1ec3996749cc","year":2005},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.417171Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:def34c5dd77040c8f2ae4e979531422e9b6d7d7266a0fd09ce1aa2a1843acd5f","observation_id":"ddd6d887-9abe-4db2-879b-13db87610388","resolution":{"observed_at":"2026-08-14T11:10:39.879089Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.862433Z","title":null,"venue":null,"work_id":"c6982c49-5089-470b-b62b-67bc4bebbf65","year":2001},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.421337Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:1a0c7d66c8514777c8c4972251e56c6e0a51d7c00c97196a9f2b8ebb0984beda","observation_id":"8e90bd15-75a8-432c-8a19-87ddd3ea3b71","resolution":{"observed_at":"2026-08-14T11:10:39.866383Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1410.3831","last_updated":"2014-10-14T20:00:09Z","snapshot_observed_at":"2026-08-14T23:15:43.495106Z","submitted_at":"2014-10-14T20:00:09Z","title":"An exact mapping between the Variational Renormalization Group and Deep Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1410.3831","snapshot_observed_at":"2026-08-14T11:10:39.426031Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.426031Z"},"links":{"cited_paper":"/paper/1410.3831","citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:5ab9ebb6b8aba8ba4dbab7663e76ccd40b59cd351a77a1002fc6d292c4c9e9fa","observation_id":"21511726-3b28-4e2a-b4e2-61b5b926bc26","resolution":{"observed_at":"2026-08-14T11:10:39.426031Z","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":"2026-08-14T11:10:39.848844Z","title":null,"venue":null,"work_id":"2aa80288-5b58-4d63-9e32-c8a148a4b8df","year":2007},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.430582Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:2e123d3fa401ee96217e1090f338f20430dee927d6208e984cff576ae0be926c","observation_id":"d0729cae-cbb5-4fd7-bd28-7fdc803bd22e","resolution":{"observed_at":"2026-08-14T11:10:39.854057Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02406","last_updated":"2015-03-09T09:39:41Z","snapshot_observed_at":"2026-08-19T16:30:07.889432Z","submitted_at":"2015-03-09T09:39:41Z","title":"Deep Learning and the Information Bottleneck Principle","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02406","snapshot_observed_at":"2026-08-14T11:10:39.434688Z","title":"Deeplearningandtheinformationbottleneck principle","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.434688Z"},"links":{"cited_paper":"/paper/1503.02406","citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:b09f4df65fb5e5b757e356a3c16a270f5129a336394f1e0189a5a03bcd038829","observation_id":"1d090719-6a6c-47e1-ae52-0311cac12e88","resolution":{"observed_at":"2026-08-14T11:10:39.434688Z","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":"2026-08-14T11:10:39.835741Z","title":"Exploring generalization in deep learning","venue":null,"work_id":"aa5b901a-5021-4ca6-afaf-c4dd7ab07db2","year":2017},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.439167Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:72e1d1f658f592c4fee1e4f69e61f8f1f49f48b7249713f3445fa0f24c3b0e2e","observation_id":"2aa777d5-5511-4f26-9977-b5af132ad8df","resolution":{"observed_at":"2026-08-14T11:10:39.840102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.823002Z","title":"In search of the real inductive bias: On the role of implicit regularization in deep learning","venue":null,"work_id":"4f6684cc-5c9a-416a-ad2f-32af883b4a18","year":2015},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.443213Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:165d91f62b3cf1ed67a2356161f58b6eaa682b48054fa1f7e139dc1fbe7834f4","observation_id":"7b4d8889-10fd-4c5e-be0b-9c6ff4c7bf5e","resolution":{"observed_at":"2026-08-14T11:10:39.827426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.810076Z","title":"Ng and Michael I","venue":null,"work_id":"93fc6b8c-2c65-42a1-adc4-cae44a1017e4","year":2002},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.447313Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:2c865b33214fdd60acfe09c2d324874eb5a84afff6eb73a1f6fee72e42da420f","observation_id":"6a22792c-37c1-408e-a5ba-9eda90f7164b","resolution":{"observed_at":"2026-08-14T11:10:39.814273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"0911.4863","last_updated":"2011-05-13T01:52:49Z","snapshot_observed_at":"2026-08-15T05:33:03.647176Z","submitted_at":"2009-11-25T14:26:54Z","title":"Statistical exponential families: A digest with flash cards","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"0911.4863","snapshot_observed_at":"2026-08-14T11:10:39.451344Z","title":"Statistical exponential families: A digest with flash cards.arxiv preprint arXiv:0911.4863, 2011","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.451344Z"},"links":{"cited_paper":"/paper/0911.4863","citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:69b0d50a6c92f196a2d6b599d722ec211b06cc29ccfbd92d65afac8de9a97586","observation_id":"468dbdfa-5b55-4cf2-b676-77a4b96d5c50","resolution":{"observed_at":"2026-08-14T11:10:39.451344Z","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":"2026-08-14T11:10:39.797102Z","title":"Aprobabilisticframework for deep learning","venue":null,"work_id":"0f41dff8-c14d-4e1d-b39b-af53c1c5b832","year":2016},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.455585Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:b2e5f2d621b44b158222edbd312605b5835e94059878b96ee37e87e2247e38dc","observation_id":"c4cbb117-bf74-4442-97b5-22e6b41b08ea","resolution":{"observed_at":"2026-08-14T11:10:39.801357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1801.04016","last_updated":"2018-01-11T23:37:48Z","snapshot_observed_at":"2026-08-15T19:05:02.238052Z","submitted_at":"2018-01-11T23:37:48Z","title":"Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.04016","snapshot_observed_at":"2026-08-14T11:10:39.460022Z","title":"Theoretical impediments to machine learning with seven sparks from the causal revolution.arXiv preprint arXiv:1801.04016, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.460022Z"},"links":{"cited_paper":"/paper/1801.04016","citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:ee844fa76c9eccf8865224a7c4326369b04049dfb0e00e2e347cf5ee33857abc","observation_id":"d913b689-fa70-4c16-8169-70d0816d588c","resolution":{"observed_at":"2026-08-14T11:10:39.460022Z","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":"2026-08-14T11:10:39.784041Z","title":"Richard and R.P","venue":null,"work_id":"be642c35-9be6-4562-8fd4-b87be5658a56","year":1991},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.464434Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:d22a23af632c1b5cabffba9902d92076d916a1c1d4c7382f1a86697bacc2fb81","observation_id":"232f9aae-af9b-4fed-898d-e9a65ebb2756","resolution":{"observed_at":"2026-08-14T11:10:39.788416Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.770637Z","title":"Rumelhart, Geoffrey E","venue":null,"work_id":"0dda423d-531f-4c25-a457-6a6cc75a0171","year":1986},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.468536Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:69d212957419a430bd73e18e8f42c8ac4c2500bba9a97b50285d170930325254","observation_id":"1cfa1785-8f6b-494e-bc5a-96ad2450f46c","resolution":{"observed_at":"2026-08-14T11:10:39.775011Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.755583Z","title":"Deep boltzmann machines","venue":null,"work_id":"234ba6a6-799d-413c-990d-6e7c66628e6c","year":2009},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.472984Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:674a31c08f551d55e954b23c0a515613f5f33c8add3a915b4e16d557503e7f3b","observation_id":"efcfc163-628b-4b05-b2fd-f5905126f79c","resolution":{"observed_at":"2026-08-14T11:10:39.760385Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.741379Z","title":"On the information bottleneck theory of deep learning","venue":null,"work_id":"1c091c09-817d-479b-b858-569728f15a59","year":2018},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.478078Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:0d846872f90621cc40a71f142e579ad3604e3e72b2379e84295a1d8390a3a285","observation_id":"98462bf6-7f62-4325-a2e7-fa807dd99899","resolution":{"observed_at":"2026-08-14T11:10:39.746590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.00810","last_updated":"2017-04-29T17:32:47Z","snapshot_observed_at":"2026-08-14T21:13:52.487817Z","submitted_at":"2017-03-02T14:53:14Z","title":"Opening the Black Box of Deep Neural Networks via Information","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.00810","snapshot_observed_at":"2026-08-14T11:10:39.482581Z","title":"Opening the black box of deep neural networks via information.arXiv preprint arXiv:1703.00810, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.482581Z"},"links":{"cited_paper":"/paper/1703.00810","citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:4668193ccf2ffd46bb164fe3f52083b8bc78ccf1623ae4f6a978be925a5edf56","observation_id":"d02adc9f-2995-4e6c-9867-261508277f69","resolution":{"observed_at":"2026-08-14T11:10:39.482581Z","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":"2026-08-14T11:10:39.727478Z","title":null,"venue":null,"work_id":"cbf914a6-47bc-45bc-a6c5-da8d377727b7","year":1997},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.486561Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:a5bea34b7aaf52929a2429c8eed0f3b05e42c0dafb55e7fcd5138854aec20733","observation_id":"3abe59eb-f634-49ba-af34-ad691ccca99e","resolution":{"observed_at":"2026-08-14T11:10:39.732110Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.712307Z","title":"Jaakkola","venue":null,"work_id":"9c41792e-d290-4d11-aae8-fbf3d6273afe","year":2003},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.490330Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:663486a01bb70300040d6a8a3bad9c4f55a5c0aa31bad2d78c2bbf792a0e1e26","observation_id":"11e6bda5-88f1-4ad1-beff-bc7d26747187","resolution":{"observed_at":"2026-08-14T11:10:39.716765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1206.4635","last_updated":"2012-06-18T15:14:57Z","snapshot_observed_at":"2026-08-15T00:56:30.507233Z","submitted_at":"2012-06-18T15:14:57Z","title":"Deep Mixtures of Factor Analysers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1206.4635","snapshot_observed_at":"2026-08-14T11:10:39.494696Z","title":"Deep mixtures of factor analysers.arXiv preprint arXiv:1206.4635, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.494696Z"},"links":{"cited_paper":"/paper/1206.4635","citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:35513b5610590b6038a2ccaaed3bea47e54fce307735afb066b2ee518672d25a","observation_id":"8ea8e7ab-7fef-4fe1-94ab-352644b1ecb3","resolution":{"observed_at":"2026-08-14T11:10:39.494696Z","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":"2026-08-14T11:10:39.698469Z","title":null,"venue":null,"work_id":"f7eb7dee-c5c0-4a61-bc11-2adf60072bba","year":2000},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.498654Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:6bf6e03f1d53ac4c8dd92848380724b1eb2f9a041f755d332c3809fae219b5eb","observation_id":"6bd05c9b-063c-4be2-87f5-f4593e5e0440","resolution":{"observed_at":"2026-08-14T11:10:39.702803Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.684415Z","title":"Understanding deep learning requires rethinking generalization","venue":null,"work_id":"28ac2a00-d522-4f6b-ba7f-8c5a858ee02f","year":2016},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.502498Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:b3646f5453b61487f7e48023101a78306850f25674a086edd1a36e0aae61872c","observation_id":"1237d842-c587-4674-a973-0c8993e2c991","resolution":{"observed_at":"2026-08-14T11:10:39.688888Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.670874Z","title":null,"venue":null,"work_id":"f25d5bcf-c8ea-4b7c-82d2-adab98490a94","year":2000},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.507114Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:b8947e201e888bb89c7dc5ae763c7b61f9d36becdfb09df07f6c314980a7cb54","observation_id":"0c0ce6b6-8b7e-4493-98f6-dbbfc3590b17","resolution":{"observed_at":"2026-08-14T11:10:39.675164Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T11:10:39.657662Z","title":"Conditional random fields as recurrent neural networks","venue":null,"work_id":"509e3c8f-1f84-4d0e-9b0b-d0c9f506546e","year":2015},"citing_paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T11:10:39.510929Z"},"links":{"citing_paper":"/paper/1908.09772"},"observation_digest":"sha256:906666cfc22b13a79de455d3611f79e3504fb4c177aa0c200c4f88619bd654ee","observation_id":"57e49a3b-8b60-4929-b741-7c70c93abd0a","resolution":{"observed_at":"2026-08-14T11:10:39.661847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1908.09772","last_updated":"2019-08-26T16:18:22Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T18:35:31.440580Z","submitted_at":"2019-08-26T16:18:22Z","title":"A Probabilistic Representation of Deep Learning"},"reference_resolution":{"displayed":40,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":17,"verified_exact":0,"verified_fuzzy":22},"total_outbound_references":40},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:1908.09772."}