{"as_of":"2026-08-18T06:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fb911ae8ef891e57d587f3c080a1e02a78208d143966c003b9facc9c04bcc61d","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:21:01.484787Z","state":"measured"},{"denominator":34,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":34,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2505.07792/citation-record","integrity":"/paper/2505.07792/integrity","json":"/paper/2505.07792/citation-record.json","paper":"/paper/2505.07792"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1207.0580","last_updated":"2012-07-03T06:35:15Z","snapshot_observed_at":"2026-08-15T00:54:35.320150Z","submitted_at":"2012-07-03T06:35:15Z","title":"Improving neural networks by preventing co-adaptation of feature detectors","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1207.0580","snapshot_observed_at":"2026-08-15T22:21:01.347377Z","title":"Improving neural networks by preventing co-adaptation of feature detectors.arXiv preprint arXiv:1207.0580, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.347377Z"},"links":{"cited_paper":"/paper/1207.0580","citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:0c5e6db78a0041401e0f2d3b2d73f8410486add5c6d51c2bc32b8f8e0d16f1e3","observation_id":"106212c4-26b1-4830-bbcf-045be2b279ab","resolution":{"observed_at":"2026-08-15T22:21:01.347377Z","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":"2026-08-15T22:21:01.353881Z","title":"Dropout: a simple way to prevent neural networks from overfitting.The journal of machine learning research, 15(1):1929–1958, 2014","venue":null,"work_id":null,"year":1929},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.353881Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:28517b6d6faea041e57b2347be7432f29ae6c1eca938f0d377fd9501071e5369","observation_id":"c59f8d9b-b030-45d0-973c-c4c4e229fe04","resolution":{"observed_at":"2026-08-15T22:21:01.353881Z","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":"2026-08-15T22:21:01.829964Z","title":"A review on dropout regularization approaches for deep neural networks within the scholarly domain.Electronics, 12(14):3106, 2023","venue":null,"work_id":"3999fd58-4ad8-42ec-a34d-f9aa0e84e437","year":2023},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.358690Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:44842480495ce68203b27db26911066a9c78a31eb17e4bd5f77549647beb2bb8","observation_id":"b01b8c10-4e19-4930-8b87-e1dfc1359290","resolution":{"observed_at":"2026-08-15T22:21:01.833586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.363562Z","title":"Regularization of neural networks using dropconnect","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.363562Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:efea8b64859298a0cd406d7f119dfe02eb5674a70cf03ef060af183724d863a8","observation_id":"1e6e8163-c7ce-45ff-9622-8ebd13beff5f","resolution":{"observed_at":"2026-08-15T22:21:01.363562Z","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":"2026-08-15T22:21:01.813876Z","title":"Curriculum dropout","venue":null,"work_id":"a9d27f2a-c36b-4c60-a428-fa4c480a463b","year":2017},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.368523Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:895b33d37775d58119e6e978901678b6d2da835f34bd90aeb7f8db92398837cc","observation_id":"42bb8c5e-6414-4ca4-8bef-66c0e32d4f23","resolution":{"observed_at":"2026-08-15T22:21:01.817141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.372880Z","title":"Dropout reduces under- fitting","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.372880Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:1b10d87051f5d3a4331f6c1882df330d1d20489652545e9884115377fdefab86","observation_id":"64b4c0c3-3e84-4045-960a-79409551ebe9","resolution":{"observed_at":"2026-08-15T22:21:01.372880Z","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":"2026-08-15T22:21:01.796789Z","title":"Dropout training, data-dependent reg- ularization, and generalization bounds","venue":null,"work_id":"7160ca1d-608b-4e69-8914-43044a14d8e4","year":2018},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.377183Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:d185e4af1cf7b9c8d6819347ab90436a15645123415fb697e48a5ee9bd0f8d90","observation_id":"2aff4ad4-dbc6-4518-b35c-a0d73005859c","resolution":{"observed_at":"2026-08-15T22:21:01.800973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.785968Z","title":"Dropout: Explicit forms and capacity control","venue":null,"work_id":"b5cdd547-a8b5-4c14-97f9-229673bded4e","year":2021},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.380831Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:296a907f83b19389c1fc35922e43a8ecb5a7eb4df996710b8db862ac15d5fb45","observation_id":"5d66d7cf-1451-4d34-8753-ed4c143d5b09","resolution":{"observed_at":"2026-08-15T22:21:01.790153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.775820Z","title":"Regularization of neural networks using dropconnect","venue":null,"work_id":"f2dbc4a1-dda8-417b-b1f4-0f7737827db0","year":2013},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.384659Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:2b45be67dbe764009c8b8d256cbafae63d70c2cb8d6911b0f4cbb72b1499b66b","observation_id":"22866263-64cd-4f04-acc4-edca4de11b8d","resolution":{"observed_at":"2026-08-15T22:21:01.779299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.765277Z","title":"Adaptive dropout with rademacher complexity regularization","venue":null,"work_id":"1c348eed-f65b-49ab-9b9d-2ae224f5557f","year":2018},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.388902Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:b11b54f0a686378d8c278bd94d2199650281b3099e28bc9106b5749b3db7f698","observation_id":"6a80f81b-2e7c-430b-9f2a-f55433defab4","resolution":{"observed_at":"2026-08-15T22:21:01.769175Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.754608Z","title":"Understanding dropout","venue":null,"work_id":"46e361dc-828b-4fe1-8167-cb7d2232ea21","year":2013},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.392878Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:7f0844a8447a70058fdaec7e13c205d75bd29780c87474444e7fd49d52615d26","observation_id":"d0202e86-1485-49ba-90dd-bdc0416b5a56","resolution":{"observed_at":"2026-08-15T22:21:01.758550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.742605Z","title":"Dropout training as adaptive regularization","venue":null,"work_id":"546f0a6d-82fc-4c37-94a2-f619df969239","year":2013},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.396739Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:43094874f8f01a545557b9bd9f473102f338c70d7662057bebbb4b001ecb5b51","observation_id":"bd33f073-7ae3-4dcd-b6b9-8db90b679d77","resolution":{"observed_at":"2026-08-15T22:21:01.747309Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.730528Z","title":"On the implicit bias of dropout","venue":null,"work_id":"6541d137-c257-4bd3-8ce8-2e265cbcc154","year":2018},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.400814Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:51cfb58d629790a759d4cbc417dd609dbb30cdc7e4d48c0b8c2a626ad817098d","observation_id":"ad0d7aaf-d6be-47b9-b851-bf9da4fdb13c","resolution":{"observed_at":"2026-08-15T22:21:01.734513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.404792Z","title":"Implicit regularization of dropout.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(6):4206–4217, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.404792Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:9c0c80953b127e8b95218ea9d747080bb7b8c0a4e024bb9e72ac62ab9e28d5fe","observation_id":"a0f78eb0-423c-4877-9553-9c980a81372f","resolution":{"observed_at":"2026-08-15T22:21:01.404792Z","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":"2026-08-15T22:21:01.712632Z","title":"Deep information propagation","venue":null,"work_id":"c22df6b1-8921-41c4-b088-ce6680daab00","year":2017},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.408866Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:9b9bd405129c9a36ce5edec402dc97f28a80a68fb188a730a8e249946bda6392","observation_id":"9d0d58a3-3fac-4ec8-b356-1be987563684","resolution":{"observed_at":"2026-08-15T22:21:01.716670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.412724Z","title":"Learning by on-line gradient descent.Journal of Physics A: Mathematical and general, 28(3):643, 1995","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.412724Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:ff5a9753894ec0c843b1ead5f7612051e8acb3371814fde920173c7a80faa326","observation_id":"d6939e00-b55f-4234-acfe-0309e868afda","resolution":{"observed_at":"2026-08-15T22:21:01.412724Z","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":"2026-08-15T22:21:01.416337Z","title":"Exact solution for on-line learning in multilayer neural networks","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.416337Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:c2e1d0dc9549850d8c5b652290328bc7112f9a032082246edb9fdd1c48bc31d3","observation_id":"467dd5f4-0f9d-4d84-9d77-740d980bf204","resolution":{"observed_at":"2026-08-15T22:21:01.416337Z","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":"2026-08-15T22:21:01.686702Z","title":"On-line learning in soft committee machines.Physical Review E, 52(4):4225, 1995","venue":null,"work_id":"626d487f-905a-4b75-b803-a059b2a9b6a8","year":1995},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.420219Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:846cc2164c46bcb278a5789974f531c811b2244aba9b8dc70f4b905b9398778a","observation_id":"83c1f68d-d355-4a68-8c9d-e14fcca5824d","resolution":{"observed_at":"2026-08-15T22:21:01.692201Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.424138Z","title":"Dy- namics of stochastic gradient descent for two-layer neural networks in the teacher-student setup","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.424138Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:505614dec98eb56af01121f026b3f697a7bf195395222d8dc9a9d016ea16e7aa","observation_id":"73665470-ea4a-4c4e-b13c-ecf3f3078fb9","resolution":{"observed_at":"2026-08-15T22:21:01.424138Z","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":"2026-08-15T22:21:01.667077Z","title":"Three unfinished works on the optimal storage capacity of networks.Journal of Physics A: Mathematical and General, 22(12):1983, 1989","venue":null,"work_id":"21337241-b855-4017-a81a-70e2687b5433","year":1983},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.428507Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:86ce47cb82ecb853af544b21ee83321c36ee9141ba545dcb28c20d5d3ebaf753","observation_id":"d2a1dc5b-d9f7-4541-90d6-22a9f69c613f","resolution":{"observed_at":"2026-08-15T22:21:01.671879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.655976Z","title":null,"venue":null,"work_id":"5c623e00-5717-46b3-8c80-339b18c37c4f","year":1992},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.433099Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:53d4c2784e8461da1ed0ebbdbe6adb37ede6346958ef8da1f88bb4d17df2bd99","observation_id":"8bf48e3a-4f14-4cd0-9352-03430d5907aa","resolution":{"observed_at":"2026-08-15T22:21:01.659922Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.643781Z","title":"Cambridge University Press, 2001","venue":null,"work_id":"1a83c865-e594-49ff-bf91-4e261b66c5d9","year":2001},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.437034Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:9349054c8197b91292c42a44998effc651978b9465ef2c6ad6b023056bb2a639","observation_id":"b21714da-fa9d-409c-8ddc-20474a030de7","resolution":{"observed_at":"2026-08-15T22:21:01.648161Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.632219Z","title":null,"venue":null,"work_id":"aea1043f-2dff-41f2-845e-dc89ed08864d","year":null},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.440728Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:72217e7af319800e61d0774770eeede6be0affd013db2018930160ead9baef9d","observation_id":"db01c066-e225-430f-ac6a-df3af116e568","resolution":{"observed_at":"2026-08-15T22:21:01.636424Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.620955Z","title":"Modeling the influence of data structure on learning in neural networks: The hidden manifold model.Physical Review X, 10(4):041044, 2020","venue":null,"work_id":"b767cc13-8359-4c0a-873f-c0d6d2d01ee2","year":2020},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.444814Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:4075adf90f0af138614a873afd4b9fddc1c8163a0479039832e85ec2bffd8a0d","observation_id":"2cde4436-ac9d-448d-9598-2c2aec235cf0","resolution":{"observed_at":"2026-08-15T22:21:01.625202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.608884Z","title":"Transient dynamics of on-line learning in two-layered neural networks.Journal of Physics A: Mathematical and General, 29(16):4769, 1996","venue":null,"work_id":"4c085b71-67b1-4327-81e8-61a2101c58c2","year":1996},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.448646Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:a6bb8b22d65a512c73388da18ef4f180d44ad70803fc049f21dac8707c0422c7","observation_id":"6a38dab8-d479-467a-88e0-6d046c1450fc","resolution":{"observed_at":"2026-08-15T22:21:01.613673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.07378","last_updated":"2019-03-18T12:09:36Z","snapshot_observed_at":"2026-08-14T17:00:48.153240Z","submitted_at":"2019-03-18T12:09:36Z","title":"On-line learning dynamics of ReLU neural networks using statistical physics techniques","version":1},"cited_work":{"arxiv_id":"1903.07378","doi":null,"metadata_source":"pith","pith_arxiv_id":"1903.07378","snapshot_observed_at":"2026-08-15T22:21:01.520582Z","title":"On-line learning dynamics of ReLU neural networks using statistical physics techniques","venue":"cs.LG","work_id":"e923bbe1-6dbe-42e4-a8bf-eef300397649","year":2019},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.452340Z"},"links":{"cited_paper":"/paper/1903.07378","citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:8202c27ba45a41f0a9b27bdb3f35e471d5781bd3c9feeff13dd2f144729f1c3a","observation_id":"48b8a65e-b589-4267-b450-c50e4c913566","resolution":{"observed_at":"2026-08-15T22:21:01.526492Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.598386Z","title":"A theory of initialisation’s impact on specialisation","venue":null,"work_id":"320e5ec1-7a89-4ad2-a5be-e4e26febb4f9","year":2025},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.456717Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:3f123c9725f7610d8abbca5f5f64ed1c6203ed686075789752bc6f0406f2cbe2","observation_id":"1dfb085f-ad2c-4e69-96b4-c305999924e4","resolution":{"observed_at":"2026-08-15T22:21:01.601689Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.588076Z","title":"Soft mode in the dynamics of over- realizable online learning for soft committee machines.Phys","venue":null,"work_id":"0be5cf83-223a-4569-8c0b-4b469985a22c","year":2022},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.460704Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:029b72b26eed29f8e2e0887f85e539778cb1bd783263eb80e92285f5a6e7ff2d","observation_id":"bdc22005-46b0-4384-86f3-2095052ba8d3","resolution":{"observed_at":"2026-08-15T22:21:01.591497Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.577659Z","title":"Hidden unit specialization in layered neural networks: Relu vs","venue":null,"work_id":"ce56e9c8-5df8-4eb4-9a33-611161c7fe60","year":2021},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.464728Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:18ca056027558ab83b356e1a27c9e8259abda268ccb4b4d67c98cc5e2975e2f0","observation_id":"154bf73a-9159-401d-9a69-c167d472a78f","resolution":{"observed_at":"2026-08-15T22:21:01.581296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.567540Z","title":"The committee machine: Computational to statistical gaps in learning a two-layers neural network","venue":null,"work_id":"d65c7f27-54bb-4faa-b384-122b3ebf5d12","year":2018},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.468652Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:794d7a4fa347744c011479e6b601a0b6c98d60f805627a5aa8f9a74c6be9ab5c","observation_id":"f88ff09e-4d95-4747-bde0-8979ed2370f2","resolution":{"observed_at":"2026-08-15T22:21:01.571002Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.557406Z","title":"Out-of- equilibrium dynamical mean-field equations for the perceptron model.Journal of Physics A: Mathematical and Theoretical, 51(8):085002, 2018","venue":null,"work_id":"6e3d33f6-2752-482a-8020-4df2758b383e","year":2018},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.473192Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:f791c610d545ea959d41880d140031aae8c2f0d0fba9d031b1ac1e04f46bbe89","observation_id":"54abd2c3-b3e9-4559-81dc-03210d7daba1","resolution":{"observed_at":"2026-08-15T22:21:01.561042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T22:21:01.476902Z","title":"Dynamical mean-field theory for stochastic gradient descent in gaussian mixture classification.Advances in Neural Information Processing Systems, 33:9540–9550, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.476902Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:4d081cceff3fd323329363341963dc38da679edd395277929732901685a9ae3c","observation_id":"60cb4631-b284-4d3f-a9d1-df564303c003","resolution":{"observed_at":"2026-08-15T22:21:01.476902Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.18061","last_updated":"2025-05-29T09:27:57Z","snapshot_observed_at":"2026-08-16T13:15:02.629058Z","submitted_at":"2024-09-26T17:01:41Z","title":"Optimal Protocols for Continual Learning via Statistical Physics and Control Theory","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.18061","snapshot_observed_at":"2026-08-15T22:21:01.480568Z","title":"Optimal protocols for continual learning via statistical physics and control theory.arXiv preprint arXiv:2409.18061, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.480568Z"},"links":{"cited_paper":"/paper/2409.18061","citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:da702fe7c18a28450bdcc37bb950082f86ab86f27b2469ac8e33693092a29c5b","observation_id":"af89e7d4-de5f-4a1f-a423-5c1fba4a0300","resolution":{"observed_at":"2026-08-15T22:21:01.480568Z","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":"2026-08-15T22:21:01.542436Z","title":"in preparation","venue":null,"work_id":"c8847ea0-3409-432c-b045-2c2f42f26251","year":null},"citing_paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T22:21:01.484787Z"},"links":{"citing_paper":"/paper/2505.07792"},"observation_digest":"sha256:30b7e52373fecf7659a64bb922ed4f9ccb19a1e87fcf4b89cf0ad6e6b0ac03ef","observation_id":"612cca34-b61c-4be2-a7ec-22f2b669419b","resolution":{"observed_at":"2026-08-15T22:21:01.545648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.07792","last_updated":"2025-09-08T20:19:29Z","latest_version":2,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-15T22:05:46.641596Z","submitted_at":"2025-05-12T17:45:02Z","title":"Analytic theory of dropout regularization"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":1,"verified_fuzzy":21},"total_outbound_references":34},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:2505.07792."}