{"as_of":"2026-08-21T03:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:04ac63eb6acca7a656fe69028244d56ff38d47f2de2dd3d423de2acf6ea06711","coverage":[{"denominator":58,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":58,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T15:18:32.821683Z","state":"measured"},{"denominator":58,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":58,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+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/1908.08012/citation-record","integrity":"/paper/1908.08012/integrity","json":"/paper/1908.08012/citation-record.json","paper":"/paper/1908.08012"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T15:18:35.594774Z","title":null,"venue":null,"work_id":"2f05523f-a235-499c-980b-54001e3e1763","year":null},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:31.621688Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:3598cf4c7dad540e67498b647c9267ebaf40423912ad7f15376363f2d5dc9efd","observation_id":"95b75faf-3bf6-4867-9bae-b5ad52dc8c48","resolution":{"observed_at":"2026-08-14T15:18:35.614425Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:35.463972Z","title":"1(a), the network architecture of ANNs imitates the structure of biological neural network which includes a great number of neuron s and connections layer by layer [1]","venue":null,"work_id":"14d48a5e-5640-442b-a611-cbb2da160599","year":null},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:31.721882Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:6cb59b833af1829be5d9db9ce3f272b5a78a8484b184bac4f8faf7339ec701f2","observation_id":"c3bea58a-a3b2-48e1-867c-431d37768cf4","resolution":{"observed_at":"2026-08-14T15:18:35.517584Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:35.417712Z","title":"The iris plants dataset is a simple dataset which includes 150 instances (4 attributes for each instance)","venue":null,"work_id":"b3d60df6-32a3-453b-ac6e-c2b6fc6b30ab","year":2000},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:31.790738Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:c7dd5eca34dd052635b777a28755b38ff21af8c90399a0813c169f93515e901b","observation_id":"bd2cef27-e434-4cba-94c2-8fac35ebc68f","resolution":{"observed_at":"2026-08-14T15:18:35.423771Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:35.134899Z","title":"Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups,","venue":null,"work_id":"c14ac87e-3d0c-4fec-9f7b-052f9bfa51ca","year":2012},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:31.893790Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:fa7daeca57f726df60a3d2eec77e9b8bdcdc2404aacb5b8da864b01615bef11d","observation_id":"58c4aa93-e642-4da9-abf8-3e32e03349ef","resolution":{"observed_at":"2026-08-14T15:18:35.172438Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:35.040435Z","title":"A review of unsupervised feature learning and deep learning for time-series modeling,","venue":null,"work_id":"0627895a-ecfc-4c71-84bb-e5a88de041b0","year":2014},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:31.958885Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:f6ab5fbed3cefe37de6101c42552e80cc3b4efabe04a41f8e1a8d1278237cdc7","observation_id":"9c69d559-b81e-4e55-ac93-77f061e80635","resolution":{"observed_at":"2026-08-14T15:18:35.045800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:35.228629Z","title":"Deep learning,","venue":null,"work_id":"a8bad652-cca4-40d6-b309-c863c4b7d8bd","year":2015},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:31.799826Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:8419a6adc2e52661cf232e5875e84425490f595f523a5b55cc5ce37b5e8a29d6","observation_id":"a6da2eb3-3948-4030-8e8c-fed1adf95f79","resolution":{"observed_at":"2026-08-14T15:18:35.238781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:35.202108Z","title":"Deep learning in neural networks: An overview,","venue":null,"work_id":"272be09b-d17b-43b2-ae1f-579be4bf5a02","year":2015},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:31.804636Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:56e198cdb91d9c54a28b3b491254dd5bef0f29068100be8df19e3edba5f16c4b","observation_id":"cd0f4ab5-29b5-4d49-add1-d3c0c09a71e8","resolution":{"observed_at":"2026-08-14T15:18:35.209652Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:35.184498Z","title":"Recent trends in deep learning based natural language processing,","venue":null,"work_id":"e9ba0099-53ce-45f7-a5c8-0f94f6f3dcbc","year":2018},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:31.809330Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:1a81587b0d94910aa0a172d5c011411a425b0e9eee886f9406afe5dc0396fba2","observation_id":"6c2aa1a5-ecff-47a3-a4ea-e884d6f78eb7","resolution":{"observed_at":"2026-08-14T15:18:35.189012Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.999369Z","title":"Imagenet classification with deep convolutional neural networks,","venue":null,"work_id":"537cced4-ebba-4d51-ad14-f58aae1883d7","year":2012},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.083419Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:062f9473924bd95b13bfd588c6f0022ee51ed043f08caa5886fc77daaadfcbe8","observation_id":"39ca90b8-1586-4907-85ea-5d39db6145d5","resolution":{"observed_at":"2026-08-14T15:18:35.007045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-17T19:17:06.411141Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-14T15:18:32.089480Z","title":"Very deep convolutional networks for large-scale image recognition,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.089480Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:d43954bc4f659346f8bab999acd49c22da5185e3c072fab4ed4a4733f97c04bb","observation_id":"f9db6a92-5b2b-4205-8b9c-4e2867e530be","resolution":{"observed_at":"2026-08-14T15:18:32.089480Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1604.07316","last_updated":"2016-04-25T16:03:56Z","snapshot_observed_at":"2026-07-06T04:53:59.754200Z","submitted_at":"2016-04-25T16:03:56Z","title":"End to End Learning for Self-Driving Cars","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1604.07316","snapshot_observed_at":"2026-08-14T15:18:32.029751Z","title":"End to end learning for self-driving cars,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.029751Z"},"links":{"cited_paper":"/paper/1604.07316","citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:c9be089f14eaac37842d309219fde1690101bf02f0756a09596cce196de0e713","observation_id":"85526f3c-7b13-40e0-b3fe-00fb4f7b9c9b","resolution":{"observed_at":"2026-08-14T15:18:32.029751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1312.5602","last_updated":"2013-12-19T16:00:08Z","snapshot_observed_at":"2026-08-17T17:19:33.060917Z","submitted_at":"2013-12-19T16:00:08Z","title":"Playing Atari with Deep Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.5602","snapshot_observed_at":"2026-08-14T15:18:32.071890Z","title":"Playing atari with deep reinforcement learning,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.071890Z"},"links":{"cited_paper":"/paper/1312.5602","citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:1acc842a4e2075873ffa590893abf9b8bba04fd74a657d80ce88062ec9d51e01","observation_id":"a0631bb5-4ea1-465c-bb48-3def7c936a09","resolution":{"observed_at":"2026-08-14T15:18:32.071890Z","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":"2026-08-14T15:18:35.022061Z","title":"Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates,","venue":null,"work_id":"e199abcb-20cc-47e7-aa60-08d17b80e817","year":2017},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.079066Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:909a53ac967e0096975017d0200fe940145a659ad7d704e36a36aa4d4d1eedc8","observation_id":"7a6baef6-fcb5-46bb-b7e6-e766376bf99a","resolution":{"observed_at":"2026-08-14T15:18:35.027718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.765767Z","title":"Theano: Deep learning on gpus with python,","venue":null,"work_id":"dba85fb7-f79a-4ca4-a413-d123bd1edb46","year":2011},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.169559Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:56d2b58083703e631601aa69c14da3970c39da185bd5aabe128ff5bc6a2b8462","observation_id":"265ee624-5aaf-4050-80bb-065aeac8fa20","resolution":{"observed_at":"2026-08-14T15:18:34.772114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.742138Z","title":"Optimizing fpga-based accelerator design for deep convolutional neural networks,","venue":null,"work_id":"713694ae-b3bf-482d-bcbc-706f50cd9108","year":2015},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.197915Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:83d348a79c307c73ba2b28b0d7d54a3291ff72017e24549aa494d8f7639379e8","observation_id":"608d2811-96cd-461e-b66d-c2f74f73c1a9","resolution":{"observed_at":"2026-08-14T15:18:34.750199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.889568Z","title":"Going deeper with convolutions,","venue":null,"work_id":"4f7d9bfc-0a30-4d44-b092-a0afc9e57b40","year":2015},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.095070Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:7ba794844503aba428a7be0a2bfdc29bf09383b9942696110fac832875866388","observation_id":"06d070c9-6272-4c8f-8843-a7f1f713cb0f","resolution":{"observed_at":"2026-08-14T15:18:34.928486Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.804529Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":"e75cdfd4-e758-4119-85b9-cf24ce6ba440","year":2016},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.099523Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:d8d8d2315705d619acfd5a8d34c9272749ddb7422d45c5853fda51445b5f2a43","observation_id":"9ba0ecc2-f50a-4ab3-bd66-f54f55d16464","resolution":{"observed_at":"2026-08-14T15:18:34.809447Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.786161Z","title":"Long short-term memory,","venue":null,"work_id":"5bf76130-3fdd-424b-9a41-8dfad033fdd3","year":1997},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.103513Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:8511cbccc3bb5806d5392163dd165a95c3ce5268c1746b9698a44ec680b8ea24","observation_id":"d7e91874-dfc5-4585-8599-2bb4dd0c91be","resolution":{"observed_at":"2026-08-14T15:18:34.791191Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.486335Z","title":"The spinnaker project,","venue":null,"work_id":"49a72c72-6e47-4cac-b368-d5e192828fac","year":2014},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.221865Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:a376afc73e9e8751c58d4712e29f4ca5cbf4159c846fa53fea9b4a27f5950b55","observation_id":"b57bc999-9c0f-4c69-bed1-a412d02b27ad","resolution":{"observed_at":"2026-08-14T15:18:34.492410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.467081Z","title":"A CMOS Spiking Neuron for Brain-Inspired Neural Networks With Resistive Synapses andIn SituLearning,","venue":null,"work_id":"a48c8d02-e052-4e57-a0a8-11468c45ae75","year":2015},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.227154Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:05649609016e091e3890aa94bbcfd00ba2a91a2244db0807f5ef95170b75be23","observation_id":"b52633d4-e573-4d7f-bc96-83376b6930ef","resolution":{"observed_at":"2026-08-14T15:18:34.474232Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.661496Z","title":"Diannao: A small-footprint high- throughput accelerator for ubiquitous machine-learning,","venue":null,"work_id":"2e2dae54-8f8c-4c0c-aa6b-f19a4ec65cd8","year":2014},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.205371Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:6549a6e280a4cf0f40ccfd9d83619f87a867db89fd527852e2b793ddc2822156","observation_id":"d3e716c1-4837-465f-9872-56ac165de11e","resolution":{"observed_at":"2026-08-14T15:18:34.683602Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.547785Z","title":"Truenorth: Design and tool flow of a 65 mw 1 million neuron programmable neurosynaptic chip,","venue":null,"work_id":"abe22981-cf6a-4148-937c-9749d864d7a4","year":2015},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.210822Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:6b89c96730ff2bd316dc98bed17b912091cc7b315e689507191325c8bddc5462","observation_id":"6cb3c81b-c44f-4d8d-ae44-e3bbf8729067","resolution":{"observed_at":"2026-08-14T15:18:34.598376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.510056Z","title":"Loihi: A neuromorphic manycore processor with on-chip learning,","venue":null,"work_id":"2c68c315-eec7-49ce-aacb-27947c99aed7","year":2018},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.216212Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:7da38fc333de1993a3bc70d5faf8db8b952c56dfabda36767e545f92feb89a01","observation_id":"d22df329-7559-47dc-8e93-9ec6121bb8c6","resolution":{"observed_at":"2026-08-14T15:18:34.517653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.315201Z","title":"Recent progress in semiconductor excitable lasers for photonic spike processing,","venue":null,"work_id":"b4eedbde-770c-4796-8639-4879190059e0","year":2016},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.248298Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:454ebfb9e5a72e056571748fc60935b1dd1d87d16286f63abf8a4aee33f6a7fc","observation_id":"ba66d5d7-0807-439b-bb0d-7038e24964d4","resolution":{"observed_at":"2026-08-14T15:18:34.321879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:35.434965Z","title":"As alternative approaches to gradient - based methods, evolutionary algorithms are representative gradient free methods to optimize the weights of ANNs [41, 42]","venue":null,"work_id":"8c1741c3-50d2-4c58-a374-11c2dbe8dc75","year":null},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:31.784729Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:277203cddc8300239552542f4f8ba00ef351667498144b84ad530a6429c30eef","observation_id":"132979cf-6321-47f8-85b1-f842e3d7a411","resolution":{"observed_at":"2026-08-14T15:18:35.441607Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.397852Z","title":"Optical computing,","venue":null,"work_id":"0b4e52e4-0d0c-4306-9002-eb419bf4c1d9","year":2017},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.232628Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:b7ca353c6c01ce3b58ca20b44d50b4e21c64742494432c16a72bd8359021ce3e","observation_id":"3849ce6c-bd17-44f6-bcea-48f8a7b5d120","resolution":{"observed_at":"2026-08-14T15:18:34.425254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.349530Z","title":"A leaky integrate-and-fire laser neuron for ultrafast cognitive computing,","venue":null,"work_id":"e224ac3f-62bd-4d2f-9ec9-e002be5f8298","year":2013},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.237751Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:282cd748cc3bec9567c5d90a67de98fd6f38010c08a32e8ea0dc66555469f2b5","observation_id":"48a425fd-a8c9-428b-b4c3-fb2471ef2cb7","resolution":{"observed_at":"2026-08-14T15:18:34.355415Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.333254Z","title":"Multi-channel control for microring weight banks,","venue":null,"work_id":"7b614181-f867-4e2f-a9dc-bc486e10274a","year":2016},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.243563Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:8440f33a6872a48fa8ed5d9a21417da33d8164dbb3d26d48b52048e82e82cc4b","observation_id":"09cae002-46b8-4f94-ad63-bf6da028ced4","resolution":{"observed_at":"2026-08-14T15:18:34.338527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.201479Z","title":"Variance preserving initialization for training deep neuromorphic photonic networks with sinusoidal activations,","venue":null,"work_id":"d1e6b74d-31ae-4e77-9712-1f7e3a5d0202","year":2019},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.511458Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:ac43b761304258c4c5c61ba37e852f164cc9f1ce660dd9888aa8cbddb4666cd7","observation_id":"150ef774-2d0c-468b-8682-9474d51befdf","resolution":{"observed_at":"2026-08-14T15:18:34.207208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.288626Z","title":"Deep learning with coherent nanophotonic circuits,","venue":null,"work_id":"a9aeb048-f19b-4431-91e8-28e0be848ed9","year":2017},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.258560Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:f4389b52771e6bcb3d8e65864da56881cc04f03008ea234dcc1cd2ffc7099c99","observation_id":"d9c9df27-6cb5-4758-a7b2-93b6ee037145","resolution":{"observed_at":"2026-08-14T15:18:34.301027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1808.03303","last_updated":"2018-08-16T22:16:27Z","snapshot_observed_at":"2026-08-17T06:40:30.584064Z","submitted_at":"2018-08-09T18:52:50Z","title":"On-Chip Optical Convolutional Neural Networks","version":2},"cited_work":{"arxiv_id":"1808.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"1808.03303","snapshot_observed_at":"2026-08-14T15:18:33.047560Z","title":"On-Chip Optical Convolutional Neural Networks","venue":"cs.ET","work_id":"f4dcf3bf-3aa4-4a12-b6d4-7e6089044259","year":2018},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.335228Z"},"links":{"cited_paper":"/paper/1808.03303","citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:bc4ab7bee5c08e47c22805a4eb0b92802d2823cc3022ff1c598a4d80a525b83f","observation_id":"1f9a2dab-8ec0-4efb-8112-2255bfe8d1ff","resolution":{"observed_at":"2026-08-14T15:18:33.052088Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.243417Z","title":"Reinforcement learning in a large-scale photonic recurrent neural network,","venue":null,"work_id":"b757482c-6f8d-4f95-aacb-b951aa1565e5","year":2018},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.454372Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:97235d262ed9f74f3ee36060eb07b3a3d903c21a843225e260eda027ea6c513c","observation_id":"dfe9c7d8-ffd8-44ff-af0a-f2de43544134","resolution":{"observed_at":"2026-08-14T15:18:34.252188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.217114Z","title":"All-optical machine learning using diffractive deep neural networks,","venue":null,"work_id":"e9891130-b58e-4a00-89ad-f4b49a849398","year":2018},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.506213Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:1b68337f6b4bc95d12125b98d10d9a181e3fbfcc6c231ce116e538921918ec0c","observation_id":"7f1d62a7-6a3b-4afd-aab7-6974f40dbbe4","resolution":{"observed_at":"2026-08-14T15:18:34.223695Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.046326Z","title":"Inverse design in nanophotonics,","venue":null,"work_id":"42f11921-b2ab-41bd-9ef6-efca6a43827b","year":2018},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.536642Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:d5494e2e84031469553a52c6a889407eb1be0f1d3db9f94541c82024bf805c23","observation_id":"e82ada52-b085-4949-af81-72310d6a6c98","resolution":{"observed_at":"2026-08-14T15:18:34.050647Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.155097Z","title":"An all-optical neuron with sigmoid activation function,","venue":null,"work_id":"4d081399-4041-41e1-8025-63b52e766179","year":2019},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.515529Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:475c8fdc1da4b3c4e78afbac464cbc03b3ac20ead654db6ef6c07a8b11a421eb","observation_id":"58da6789-6d6b-4fcc-9713-18f0639cc32d","resolution":{"observed_at":"2026-08-14T15:18:34.187985Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.04579","last_updated":"2019-07-23T02:17:08Z","snapshot_observed_at":"2026-08-14T17:03:48.595656Z","submitted_at":"2019-03-12T04:02:25Z","title":"Reprogrammable Electro-Optic Nonlinear Activation Functions for Optical Neural Networks","version":2},"cited_work":{"arxiv_id":"1903.04579","doi":null,"metadata_source":"pith","pith_arxiv_id":"1903.04579","snapshot_observed_at":"2026-08-14T15:18:32.918364Z","title":"Reprogrammable Electro-Optic Nonlinear Activation Functions for Optical Neural Networks","venue":"eess.SP","work_id":"356305aa-270e-4bd3-90e4-e625bc86d85a","year":2019},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.519491Z"},"links":{"cited_paper":"/paper/1903.04579","citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:17089160109c057c50191103c70d424771b3359b8c38b15c70a121f0a1ba4ebf","observation_id":"94066fb3-c7d3-49ec-9d47-c4074f944fb3","resolution":{"observed_at":"2026-08-14T15:18:32.977096Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.07318","last_updated":"2019-02-18T11:22:04Z","snapshot_observed_at":"2026-08-19T05:42:44.206950Z","submitted_at":"2019-02-18T11:22:04Z","title":"Self-learning photonic signal processor with an optical neural network chip","version":1},"cited_work":{"arxiv_id":"1902.07318","doi":null,"metadata_source":"pith","pith_arxiv_id":"1902.07318","snapshot_observed_at":"2026-08-14T15:18:32.870566Z","title":"Self-learning photonic signal processor with an optical neural network chip","venue":"eess.SP","work_id":"2d871d2d-0596-4bac-b1b2-b906a2d7a82d","year":2019},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.524187Z"},"links":{"cited_paper":"/paper/1902.07318","citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:c3d6447670edb3bf0a09fd31238e8ecf325478256a160d705ffd8a42fb3b9790","observation_id":"db4ce5b6-f273-4450-bdf4-4a152e1383b2","resolution":{"observed_at":"2026-08-14T15:18:32.877029Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.070291Z","title":"Training of photonic neural networks through in situ backpropagation and gradient measurement,","venue":null,"work_id":"8ca2ee7f-fdaa-49f8-acc8-59128fa8a4f6","year":2018},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.528489Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:f31d3de159dd89504692aef64a5b178e7a594df3fe297628241ca6a7f3f82fdf","observation_id":"543c7cd2-6460-416e-a62a-4132b71a2b94","resolution":{"observed_at":"2026-08-14T15:18:34.099992Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:33.774182Z","title":"Binary particle swarm optimized 2× 2 power splitters in a standard foundry silicon photonic platform,","venue":null,"work_id":"13a286b4-6d84-40de-9d22-2b5240e85fde","year":2016},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.668542Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:a78922e0f41a053576672dd6d5ebf78469fb0b6c028d0cec11baf85b69c009ab","observation_id":"f664fba2-5325-493d-8bf3-6ec0fdbbdaee","resolution":{"observed_at":"2026-08-14T15:18:33.849709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:34.028341Z","title":"Silicon photonics circuit design: methods, tools and challenges,","venue":null,"work_id":"512a4c44-0be9-4991-a2c4-6d0dec50bf2e","year":2018},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.542374Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:727cbeef3a9521afbac076928c4fd628ae0e04fc2444971415235d091975aa50","observation_id":"6c0adaa8-07d9-4ed4-a550-fee3d1855686","resolution":{"observed_at":"2026-08-14T15:18:34.033599Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:33.985648Z","title":"Efficient spectrum prediction and inverse design for plasmonic waveguide systems based on artificial neural networks,","venue":null,"work_id":"28abefb0-fc99-47ae-9432-7f3032245429","year":2019},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.579018Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:18a89683ad3cd852af81fa2e9aad6fb1ab507f5985598b0917e3ae10696c2019","observation_id":"54fc0694-b7b2-43f0-9e82-fad8d0ac3e27","resolution":{"observed_at":"2026-08-14T15:18:34.015893Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:33.925638Z","title":"Genetically optimized on-chip wideband ultracompact reflectors and Fabry–Perot cavities,","venue":null,"work_id":"6140c391-1981-41af-8d01-bed2d8e691b0","year":2017},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.632575Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:ea7f7675838b445968c35aced69d7b7fe4c1cd80ead178af44dcacbcbf571211","observation_id":"19b00263-0f0c-4278-90bd-de1fbfe67550","resolution":{"observed_at":"2026-08-14T15:18:33.930986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:33.901553Z","title":"Optimization for Gold Nanostructure-Based Surface Plasmon Biosensors Using a Microgenetic Algorithm,","venue":null,"work_id":"2c5988b7-5b46-4180-92a8-c0a5ffa7dc87","year":2018},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.664315Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:6453aba4303a00c6969c51429b21c5040f684057928771412984b4674a9b5ada","observation_id":"6ae58990-01a9-4d5f-99aa-42f428274b30","resolution":{"observed_at":"2026-08-14T15:18:33.911140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:33.643253Z","title":"Spiking neural networks for handwritten digit recognition—Supervised learning and network optimization,","venue":null,"work_id":"7b52cbdb-b552-4b21-a155-42a80cd298ae","year":2018},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.695430Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:6fe9ca18382957a97f749cb5e7d931b24402f81ef8859d84ec4066aff2de06fd","observation_id":"e7e29ae8-ff7b-4d28-a341-7de885050321","resolution":{"observed_at":"2026-08-14T15:18:33.648766Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:33.692760Z","title":"Designing neural networks through neuroevolution,","venue":null,"work_id":"7760ba93-0c66-43ef-9253-8cb7fa8ab2d2","year":2019},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.673461Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:4c5fc1c294d78fd66e70d47aaa228e529005ed5ac4c58d98cc757c6a41e15e03","observation_id":"29df41c5-cd23-4663-b941-231e318f9817","resolution":{"observed_at":"2026-08-14T15:18:33.696741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.06567","last_updated":"2018-04-20T18:38:34Z","snapshot_observed_at":"2026-08-14T20:02:29.132687Z","submitted_at":"2017-12-18T18:22:05Z","title":"Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.06567","snapshot_observed_at":"2026-08-14T15:18:32.680745Z","title":"Deep neuroevolution: Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.680745Z"},"links":{"cited_paper":"/paper/1712.06567","citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:01df838dd0cb0c98adb1cfc110f3afdfaa42c2328804e907aa5407fd8bee1d91","observation_id":"d90b5b6c-1a1e-4417-bb4a-57be99934546","resolution":{"observed_at":"2026-08-14T15:18:32.680745Z","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":"2026-08-14T15:18:33.675387Z","title":"Rainbow: Combining improvements in deep reinforcement learning,","venue":null,"work_id":"7ed18f38-2251-4461-8ddc-538a2a2d64e2","year":2018},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.685661Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:dc3ec5993daa0839f0ca280b03f1ee3b2227abeec92d3c3b2555235083f98931","observation_id":"e010bd0a-397e-4143-882d-f8dab4fe4135","resolution":{"observed_at":"2026-08-14T15:18:33.681142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:33.657786Z","title":"Deep learning in spiking neural networks,","venue":null,"work_id":"b4a74391-9f7e-4ef9-9ec0-c1b374f415a9","year":2018},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.691093Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:9653280fa68030210205c44e8d31761311baf7c271425539e1e8f35f61bdb237","observation_id":"e682819d-10cf-4b0b-a415-71b1659bff0e","resolution":{"observed_at":"2026-08-14T15:18:33.663690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:33.480357Z","title":"Optimal design for universal multiport interferometers,","venue":null,"work_id":"c64f8fa9-3f8f-45bd-aa24-09d817895262","year":2016},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.718509Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:cdc8dfe8caf7d0cc45e5b695315b1f2ced7009d4607390ee6193d2257ebc06ce","observation_id":"01bd2eae-8870-4841-afc5-4edc804ced8b","resolution":{"observed_at":"2026-08-14T15:18:33.486003Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:33.547841Z","title":"Deep learning with spiking neurons: opportunities and challenges,","venue":null,"work_id":"778307d3-6681-4214-954a-7156173e5d0b","year":2018},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.700270Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:b39bdf08ef3630020af03d3710984286156acf1298c4266c52a7fbc90bf0b4cd","observation_id":"aec82912-6503-4f68-ba56-a57377c72616","resolution":{"observed_at":"2026-08-14T15:18:33.620164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:33.525562Z","title":"Nonlinear optics with 2D layered materials,","venue":null,"work_id":"fb82088f-4946-4ce0-bcc5-85bd3c7dd8ec","year":2018},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.705010Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:4ec12cc81fb1ac964203308825c6d385f2097a973b1e53e67241caee483ed680","observation_id":"d71763a7-644f-4d2f-be09-91496a4b48c8","resolution":{"observed_at":"2026-08-14T15:18:33.530422Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:33.511830Z","title":null,"venue":null,"work_id":"bff690d5-0e61-4f88-a91b-d2e74f7cf8a8","year":null},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.709844Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:dffbac6bb3e20ca3f605fd5369074f5cfc4798f703cd49f393a645cc9e0413e1","observation_id":"a6ea8bfb-bdf0-4a9b-b3ef-f7ad6f60fa56","resolution":{"observed_at":"2026-08-14T15:18:33.515798Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:33.495609Z","title":"Experimental realization of any discrete unitary operator,","venue":null,"work_id":"a4d2be86-a389-4534-93f0-4e42d39abe32","year":1994},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.714073Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:a95a1ede94264a7f6b0caa26e95d5a9279eba1b681325755f87ccd35240b6893","observation_id":"e7105fc2-4102-4a2f-8efd-408fcced2760","resolution":{"observed_at":"2026-08-14T15:18:33.501124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:33.311567Z","title":"Feature selection based on hybridization of genetic algorithm and particle swarm optimization,","venue":null,"work_id":"933a080c-833d-4f5d-a3ac-a5c505e4c6f1","year":2015},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.722334Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:c0297f4e4e5b2e45e46fe51bc0d1f0d0c5ca535ca96d041cbbf3374f98e65d2c","observation_id":"1af3c7b9-6b17-4413-975a-2bdbb81dc885","resolution":{"observed_at":"2026-08-14T15:18:33.413189Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:33.286982Z","title":"A study of cross-validation and bootstrap for accuracy estimation and model selection,","venue":null,"work_id":"baeac9fa-d0bb-449e-b87d-d88b368ada1b","year":1995},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.726517Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:6adbd2ba0e5d3a30ed2eefa11d148f3c5509f16cb228c894d97f9a664c50d1d6","observation_id":"f6412510-a0e9-4838-86fa-4fcaeefe74f9","resolution":{"observed_at":"2026-08-14T15:18:33.292923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:33.269183Z","title":"Maximum certainty data partitioning,","venue":null,"work_id":"3a3bf925-92b4-4178-a2be-24ed1e059595","year":2000},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.752124Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:f1fa6212a9d3ef3d131ea6145d78307bf295dd8cef673729c449a4d3213a9afb","observation_id":"8ffa95ed-783e-4a33-b21e-d74cfd7f0f0c","resolution":{"observed_at":"2026-08-14T15:18:33.274424Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:33.099929Z","title":"Automatic identification of digital modulation types,","venue":null,"work_id":"03bab64e-6521-470a-a353-40807f4b905e","year":1995},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:32.821683Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:6f09e9df8d284163aa81074447bd3c90bd371a59732e6dbc15088e0fb053e750","observation_id":"55724615-dce7-41c3-8ded-d4506ac55b40","resolution":{"observed_at":"2026-08-14T15:18:33.188249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-14T15:18:35.300005Z","title":"This phenomenon is easy to explain because the large populations enhance the global searching ability of the evolution algorithms [36]","venue":null,"work_id":"f2457222-ff34-479f-8224-01e5a94aa2c3","year":null},"citing_paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution","version":1},"reference_index":200,"source":"pdf_text","source_observed_at":"2026-08-14T15:18:31.795565Z"},"links":{"citing_paper":"/paper/1908.08012"},"observation_digest":"sha256:e857138022d854c64b9a6106cc617817c0f9cc7d05deeffb89a751ac11e14cf3","observation_id":"03b55f23-aba8-4f9d-bf7e-624aabd1ad01","resolution":{"observed_at":"2026-08-14T15:18:35.383292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1908.08012","last_updated":"2019-08-04T14:45:07Z","latest_version":1,"primary_category":"cs.NE","snapshot_observed_at":"2026-08-21T00:11:11.870749Z","submitted_at":"2019-08-04T14:45:07Z","title":"Efficient training and design of photonic neural network through neuroevolution"},"reference_resolution":{"displayed":58,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":3,"verified_fuzzy":49},"total_outbound_references":58},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 0 inbound Pith citation observations for arXiv:1908.08012."}