{"as_of":"2026-08-10T23:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:10f6f2d0c542922c71e9e41f28c65a83ab680c3f76d7ea61dfa3f8024ea49b21","coverage":[{"denominator":27,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":27,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-09T04:31:29.598247Z","state":"measured"},{"denominator":27,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":27,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2607.07637/citation-record","integrity":"/paper/2607.07637/integrity","json":"/paper/2607.07637/citation-record.json","paper":"/paper/2607.07637"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T04:35:57.912151Z","title":"Learning multiple layers of representation.Trends in cognitive sciences, 11(10):428–434, 2007","venue":null,"work_id":"86589066-93bd-43b0-9c8a-ae120d84fde1","year":2007},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:425c883e1042e3577c8a560d665e3d7989b4fdfc5a38ad7420f7d5f9aa423434","observation_id":"83994ffe-4a39-49c9-a4ff-3698aedda407","resolution":{"observed_at":"2026-07-09T04:35:57.913800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-10T11:37:03.897080Z","title":"Visualizing and understanding convolutional networks","venue":null,"work_id":"7264cd0e-b1d5-4a72-a520-9e67a3ca2f41","year":2014},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:78889799263339a03199f10b1c295a761ef5314ff74b1c1a4574c62459336bd1","observation_id":"13c43772-aab0-479d-b988-3039fcb7d16f","resolution":{"observed_at":"2026-07-09T04:35:57.907427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-10T22:24:05.831832Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":"1409.1556","doi":"10.48550/arxiv.1409.1556","metadata_source":"pith","pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","venue":"cs.CV","work_id":"1c4b4409-c14b-488b-a086-c57a5aab8a29","year":2014},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:0886ba1e668e40c8b3e4dc24c912dde65390407623fdde688f1170358562a50d","observation_id":"b18a8450-8f19-4488-b470-fab3236779d5","resolution":{"observed_at":"2026-07-09T04:35:57.551800Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-07-12T23:51:07.915518+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T23:51:07.915518+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T04:35:57.900763Z","title":"Going deeper with convolutions","venue":null,"work_id":"0c6e6cdd-3fa8-44c1-93eb-026e20015cb6","year":2015},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:7e472a09a997ac622a69f5bd661fe9bbc463317d436aaae2df3a3cf98b04bbf9","observation_id":"5b5062b5-ac0d-42f4-9a7f-91f5e969d67f","resolution":{"observed_at":"2026-07-09T04:35:57.901907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T04:35:57.902474Z","title":"A genetic programming approach to designing convolutional neural network architectures","venue":null,"work_id":"8bbfcbed-4ec9-4a12-8039-bf9aae6469d6","year":2017},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:ded0f24f1a139fe454ea0df965872e4a63bb3a54a43331ac04461aefa7572da0","observation_id":"7dbc9ced-08d0-4b58-8c48-c27f50ec19d4","resolution":{"observed_at":"2026-07-09T04:35:57.903658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T04:35:57.908018Z","title":"A survey on evolutionary neural architecture search.IEEE transactions on neural networks and learning systems, 2021","venue":null,"work_id":"6504138e-3208-47f3-9774-f30400ba1f4c","year":2021},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:43f1da91f2cbb874bbed4fc7a5d6922358f3fedd263c2b11c182ad08eb1fdc32","observation_id":"5bde79de-1bb3-410a-ace1-c2bb40bcb271","resolution":{"observed_at":"2026-07-09T04:35:57.909289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.01578","last_updated":"2017-02-15T05:28:05Z","snapshot_observed_at":"2026-07-06T05:17:29.499249Z","submitted_at":"2016-11-05T00:41:37Z","title":"Neural Architecture Search with Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"1611.01578","doi":"10.1016/j.knosys.2015.01.010","metadata_source":"pith","pith_arxiv_id":"1611.01578","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Neural Architecture Search with Reinforcement Learning","venue":"cs.LG","work_id":"376934b8-2ad9-4443-87fe-ff630c1b89d9","year":2016},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"cited_paper":"/paper/1611.01578","citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:d5f476b5e88a732f33d611c31de7bdbadf302f66b2e41e3f3f5632bd8ea3e847","observation_id":"c8986f66-862a-48bc-87ef-fd723d9ccdfa","resolution":{"observed_at":"2026-07-09T04:35:57.547037Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T04:35:57.899018Z","title":"Random search and reproducibility for neural architecture search","venue":null,"work_id":"d270bec4-131b-4783-ad5a-11ffd810aec1","year":2020},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:4a70d1b969ac9a2db52e876a35281bb1305dbc63f0449b7a0c9da9b7c6a8c0cf","observation_id":"fb0a50bd-2ea6-4edc-af2a-432afe8bb1c9","resolution":{"observed_at":"2026-07-09T04:35:57.900166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T04:35:57.909998Z","title":"Node splitting: A constructive algorithm for feed-forward neural networks","venue":null,"work_id":"3a4590c9-5992-4f93-9eac-5d78d92c8e61","year":1991},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:f7352d43f041271c2f7898c3bd6cc3bd7331e964ee0e3ea269ad342d1da8a156","observation_id":"a0d19498-bf0e-46d9-aeb6-ba2ae34e1db5","resolution":{"observed_at":"2026-07-09T04:35:57.911502Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.05125","last_updated":"2022-06-07T15:29:01Z","snapshot_observed_at":"2026-08-07T08:07:45.534113Z","submitted_at":"2022-01-13T18:30:18Z","title":"GradMax: Growing Neural Networks using Gradient Information","version":3},"cited_work":{"arxiv_id":"2201.05125","doi":null,"metadata_source":"pith","pith_arxiv_id":"2201.05125","snapshot_observed_at":"2026-07-09T04:35:57.532084Z","title":"Gradmax: Growing neural networks using gradient information.arXiv preprint arXiv:2201.05125","venue":"cs.LG","work_id":"1e07daca-8608-49c6-ba9c-f86df1bbeb40","year":2022},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"cited_paper":"/paper/2201.05125","citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:14c43cae4ab1480e18d4699cf90f5c157915f4e0061d0841056501d4d1fefe66","observation_id":"b250d378-4c49-4d5f-abcf-2d975b75b51a","resolution":{"observed_at":"2026-07-09T04:35:57.533655Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T04:35:57.904224Z","title":"Firefly neural architecture descent: a general approach for growing neural networks.Advances in neural information processing systems, 33:22373–22383, 2020","venue":null,"work_id":"addb67a7-8828-43cf-90d2-2a964c4766b5","year":2020},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:ab5e024a31810db2d5ec39c398aeb5df63f06301b0869fdd6e9d7e35f2510db4","observation_id":"7bbab5d3-31ce-46f3-9bab-0cf5b1edf6a2","resolution":{"observed_at":"2026-07-09T04:35:57.905675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2502.06885","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T04:35:57.535033Z","title":"Topological derivative approach for deep neural network architecture adaptation.arXiv preprint arXiv:2502.06885, 2025","venue":null,"work_id":"3862d445-fed3-413e-8472-93ae3540f534","year":2025},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:cc3a84f757c613545645c6baa9b004d290384c87561f429ab16624fcc6e9a0a1","observation_id":"0218d676-1c9d-4da0-96bc-38f93d175d7a","resolution":{"observed_at":"2026-07-09T04:35:57.536776Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T04:35:57.914559Z","title":"An adaptive and stability-promoting layerwise training approach for sparse deep neural network architecture.Computer Methods in Applied Mechanics and Engineering, 441:117938, 2025","venue":null,"work_id":"1a03a839-36d1-47f2-a670-cfe130195023","year":2025},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:765ca050c334a285abac7fad3d85fe8401fea481f1346eced3ca3e2277a9fbd8","observation_id":"da4f95c5-9932-439e-aae5-f1b2fe3c1fd3","resolution":{"observed_at":"2026-07-09T04:35:57.916530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T04:35:57.932871Z","title":"Splitting steepest descent for growing neural architectures.Advances in neural information processing systems, 32, 2019","venue":null,"work_id":"df579397-65f1-4ad9-bb09-d60bc7898d4b","year":2019},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:c05a2c1f0736a32c230ede04eef9692aba7dfa7bf1d8357bc115da876ed163ed","observation_id":"12ce60f7-cf66-4900-9335-09e10f6a8ffc","resolution":{"observed_at":"2026-07-09T04:35:57.934159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T04:35:57.934763Z","title":"Greedy layer-wise training of deep networks.Advances in neural information processing systems, 19, 2006","venue":null,"work_id":"8c9b4d2a-1b25-4a38-af71-eac86e0512ab","year":2006},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:5345fb0de515811ae61fdd25a0d36631527fd2d75967e096b2667ca87d35e68b","observation_id":"a35cb5ed-9ec9-44ac-a752-bd006fdb2fc1","resolution":{"observed_at":"2026-07-09T04:35:57.936007Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.02480","last_updated":"2017-06-08T08:53:00Z","snapshot_observed_at":"2026-08-10T12:41:11.056366Z","submitted_at":"2017-06-08T08:53:00Z","title":"Forward Thinking: Building and Training Neural Networks One Layer at a Time","version":1},"cited_work":{"arxiv_id":"1706.02480","doi":null,"metadata_source":"pith","pith_arxiv_id":"1706.02480","snapshot_observed_at":"2026-07-09T04:35:57.540753Z","title":"Forward Thinking: Building and Training Neural Networks One Layer at a Time","venue":"stat.ML","work_id":"da90728b-a47e-4df4-8cf8-bda0acb5b609","year":2017},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"cited_paper":"/paper/1706.02480","citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:df96288c0fddec252e1a8a4ffddb40a4f79da1dde307112a14b14a29f630ebeb","observation_id":"5bbf92ad-fc06-4e66-97ec-28002d5867df","resolution":{"observed_at":"2026-07-09T04:35:57.542179Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1511.05641","last_updated":"2016-04-23T23:14:39Z","snapshot_observed_at":"2026-07-06T04:36:52.555912Z","submitted_at":"2015-11-18T02:09:20Z","title":"Net2Net: Accelerating Learning via Knowledge Transfer","version":4},"cited_work":{"arxiv_id":"1511.05641","doi":null,"metadata_source":"pith","pith_arxiv_id":"1511.05641","snapshot_observed_at":"2026-07-09T04:35:57.543400Z","title":"Net2Net: Accelerating Learning via Knowledge Transfer","venue":"cs.LG","work_id":"2834821a-1c72-4b92-b3a6-2570e45901f8","year":2015},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"cited_paper":"/paper/1511.05641","citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:d0f7448f5e16fe2d1b93d2198646e11523fe3cb25c9587b836fa0945b524c5a3","observation_id":"4ac569aa-1ed1-414f-8abf-94f37ff639ae","resolution":{"observed_at":"2026-07-09T04:35:57.544585Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.15995","last_updated":"2025-06-16T21:12:13Z","snapshot_observed_at":"2026-07-06T16:53:13.810552Z","submitted_at":"2023-11-27T16:44:13Z","title":"SensLI: Sensitivity-Based Layer Insertion for Neural Networks","version":2},"cited_work":{"arxiv_id":"2311.15995","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.15995","snapshot_observed_at":"2026-07-09T04:35:57.548200Z","title":"SensLI: Sensitivity-Based Layer Insertion for Neural Networks","venue":"cs.LG","work_id":"02790f58-d77b-46a2-8b76-57aac83ee981","year":2023},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"cited_paper":"/paper/2311.15995","citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:a60a66494b06c02b2230612fe79405dba8b9a351f4e7e7250fd12230618f9218","observation_id":"30d19827-c5e8-4260-b662-df15d341ddca","resolution":{"observed_at":"2026-07-09T04:35:57.549417Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-10T11:37:04.068830Z","title":"An optimal control approach to deep learning and applications to discrete-weight neural networks","venue":null,"work_id":"5b3047bd-48a2-4535-b1f2-9d4703cf7f3c","year":2018},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:9ebd51675c3b1c8654c6e588d125bfe0fe257c4421024ddb27ee18e8910ef050","observation_id":"7ec281e1-5045-4cc6-be36-c22aa831cd97","resolution":{"observed_at":"2026-07-09T04:35:57.924941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T04:35:57.925491Z","title":"Neural ordinary differential equations.Advances in neural information processing systems, 31","venue":null,"work_id":"32de569a-cbec-44d8-a3c1-0ec3a37b8cc3","year":2018},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:3730ff61e2c3add2ca6faa4413896934b3897291fc8c341a8f00ba1fd3982f89","observation_id":"b1b2ad61-5273-4f62-a44c-3ae96dcbba88","resolution":{"observed_at":"2026-07-09T04:35:57.926778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T04:35:57.927421Z","title":"An optimal control approach to a posteriori error estimation in finite element methods.Acta numerica, 10:1–102, 2001","venue":null,"work_id":"676a76ba-8a10-4b54-9289-b4eb5a58d9e7","year":2001},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:ac30d09bac0c224ed982f757a26fa365caa64580963d5558e3992c40019421e5","observation_id":"0de11ab2-854c-40b4-a876-42568d300e17","resolution":{"observed_at":"2026-07-09T04:35:57.928688Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T04:35:57.929251Z","title":"The dual weighted residuals approach to optimal control of ordinary differential equations.BIT Numerical Mathematics, 50(3):587–607, 2010","venue":null,"work_id":"b99b3cc8-d575-4a0e-a103-f82ebf7bba33","year":2010},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:b2d7394bfdfd98d1f7246c8072e2a53a3d55c3a1025e3d0058ed8ad277f7428b","observation_id":"45e78aa5-11d2-4b1b-9f7f-42bdaa26b4f4","resolution":{"observed_at":"2026-07-09T04:35:57.930511Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-11T03:47:55.367441Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"9a00f23b-71b4-4f99-a115-0d30a296f178","year":2016},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:ed0416f0614d3e29d44de8f0d0e4ffde6dab687ccc51428c7108b891010f1c92","observation_id":"e7aa217f-60f3-4368-92ad-adb9779c0ddb","resolution":{"observed_at":"2026-07-09T04:35:57.932264Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1904.05657","last_updated":"2019-09-30T21:33:06Z","snapshot_observed_at":"2026-07-06T07:45:26.065542Z","submitted_at":"2019-04-11T12:15:00Z","title":"Deep learning as optimal control problems: models and numerical methods","version":3},"cited_work":{"arxiv_id":"1904.05657","doi":null,"metadata_source":"pith","pith_arxiv_id":"1904.05657","snapshot_observed_at":"2026-07-09T04:35:57.538061Z","title":"Benning, E","venue":"math.OC","work_id":"01c5b89c-bda1-46b2-8b6a-1abd81bf1b95","year":2019},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"cited_paper":"/paper/1904.05657","citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:8000f65745dae0bd2b38ea929012d4987b3cedcf19b8f81e280f7f858833674a","observation_id":"93874226-f9ad-4f59-ade8-1631c8926cfa","resolution":{"observed_at":"2026-07-09T04:35:57.539461Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T04:35:57.919645Z","title":"Explicit-in-time goal-oriented adaptivity.Computer Methods in Applied Mechanics and Engineering, 347:176–200, 2019","venue":null,"work_id":"9fac0176-b63f-4460-92e4-b630745498c1","year":2019},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:d6b3d0b9f99e766aba219b57902064f8b9db6df48f4a6abd814d1de607620c3e","observation_id":"668c4df0-cf81-4177-af9b-28917f3fd4a9","resolution":{"observed_at":"2026-07-09T04:35:57.921065Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T04:35:57.921650Z","title":"Numerical solution of the navier-stokes equations.Mathematics of computation, 22(104):745–762, 1968","venue":null,"work_id":"37b813d4-51b1-4b57-85c0-06761804bb63","year":1968},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:7e3440760bbb44211552d0a8b0f3df91613c5a270e6f758f4580b2538d0c2fc2","observation_id":"5805988e-5a9b-42fe-b490-f7cbb87ab8be","resolution":{"observed_at":"2026-07-09T04:35:57.923071Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-07-09T04:35:57.917330Z","title":"Springer, 2006","venue":null,"work_id":"e4dfd848-0bca-4a2e-98b2-edaddb4e9eea","year":2006},"citing_paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-09T04:31:29.598247Z"},"links":{"citing_paper":"/paper/2607.07637"},"observation_digest":"sha256:d3e7ef53acbc62a264d4ca65bb6a5e36c711bbd43573011e9bcc2e89e5c1d343","observation_id":"fb2d4c9b-546f-4668-b593-0d862ffd4c68","resolution":{"observed_at":"2026-07-09T04:35:57.918928Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2607.07637","last_updated":"2026-07-08T16:55:16Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T19:22:45.344291Z","submitted_at":"2026-07-08T16:55:16Z","title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation"},"reference_resolution":{"displayed":27,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":0,"verified_exact":7,"verified_fuzzy":19},"total_outbound_references":27},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2607.07637."}