{"as_of":"2026-08-12T13:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5ad89e30f3ea1114dd9474c279ab956cab7ba4b1fafc933ad810199eeb3ed5a9","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T20:33:40.049829Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+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/2412.05667/citation-record","integrity":"/paper/2412.05667/integrity","json":"/paper/2412.05667/citation-record.json","paper":"/paper/2412.05667"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:33:42.090079Z","title":"Gradient Followi ng Without Back-Propagation in Layered Networks","venue":null,"work_id":"4e98a5fe-8892-4b28-a145-42263d6e8068","year":1987},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.090374Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:48ad9695aa67c8df4ccb939fc312ae0bb4d0410e016d63a04267a2ead8bc940b","observation_id":"da7c5173-de7a-4b12-914d-1e649b2b63c9","resolution":{"observed_at":"2026-08-11T20:33:42.109046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08587","last_updated":"2022-02-17T11:07:55Z","snapshot_observed_at":"2026-08-10T02:29:01.141729Z","submitted_at":"2022-02-17T11:07:55Z","title":"Gradients without Backpropagation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08587","snapshot_observed_at":"2026-08-11T20:33:39.180370Z","title":"Gradients without Backprop agation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.180370Z"},"links":{"cited_paper":"/paper/2202.08587","citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:f946bfd5f727f16f591c89c51bc3c8693c90c883ece5adfd4d138639a374bc2e","observation_id":"222146c7-4163-45cb-a9b5-93dbf14d86e8","resolution":{"observed_at":"2026-08-11T20:33:39.180370Z","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":"2026-08-11T20:33:42.065864Z","title":null,"venue":null,"work_id":"2e14aac8-b5b8-438f-9ff2-f5794a82b304","year":1995},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.190816Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:ca1d0976d4938226b49007b826ac2c1a517041e4d55dd9b83e29e67d1f859df7","observation_id":"d2187e80-650a-4571-9e17-fe713e509a85","resolution":{"observed_at":"2026-08-11T20:33:42.072725Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T20:33:42.045034Z","title":null,"venue":null,"work_id":"3277413e-be19-47d2-9601-56f3517ed202","year":2006},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.198455Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:a5a73e8a99bd3db7870ec4288b3c07f9860e304df754a26e0d8faa90a77328b9","observation_id":"e4c03353-6542-46c0-8180-7fd8708c4df0","resolution":{"observed_at":"2026-08-11T20:33:42.050835Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.08453","last_updated":"2022-07-13T17:58:15Z","snapshot_observed_at":"2026-08-11T12:16:06.612131Z","submitted_at":"2021-06-15T21:56:38Z","title":"How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective","version":2},"cited_work":{"arxiv_id":"2106.08453","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.08453","snapshot_observed_at":"2026-08-11T20:33:41.594031Z","title":"How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective","venue":"cs.LG","work_id":"6791db92-9b83-49d3-b874-78321a5f67ab","year":2021},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.204681Z"},"links":{"cited_paper":"/paper/2106.08453","citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:86774dca31f035d4218491f68f84e3a1cf1f79e82949b7703186a672a4d31754","observation_id":"f682db04-1af0-4234-8f5f-8c7304f2fa0d","resolution":{"observed_at":"2026-08-11T20:33:41.601298Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"1996.55618","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:33:41.547316Z","title":"Supervised Learning in Ne ural Networks without Feed- back Networks","venue":null,"work_id":"9907753e-b2e4-454f-a7da-035c1903a1d8","year":1996},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.217612Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:14c5eb1b3b6a27bb1f68bc57aea5024237298237e422e640bc2144674f0ae7c2","observation_id":"0aceead8-f51b-4927-9017-fa1013c3a73c","resolution":{"observed_at":"2026-08-11T20:33:41.560386Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18201/ijisae.2019355381","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:33:40.278317Z","title":"Classification of Rice V ari eties Using Artificial Intelligence Methods","venue":null,"work_id":"228b809a-7967-4296-9c9e-1d0d03bf0f6f","year":2019},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.223150Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:5aa7f3c1ee7de132032e95a5834f09f2e04ff7c30133fef49ee55340adb5dca4","observation_id":"c98f646b-9ea6-44c2-96bc-cb1da28d330d","resolution":{"observed_at":"2026-08-11T20:33:40.284485Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T20:33:42.011414Z","title":"Adaptive Subg radient Methods for Online Learning and Stochastic Optimization","venue":null,"work_id":"f03e21a6-e758-478c-aba2-56987929695c","year":2011},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.227116Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:f112f90a6187f368930cfa960e73c1ec250b4087f7fcbb56bc893104e8da22b8","observation_id":"c1224e8a-ab4b-485a-8d5f-9910dca1ab4f","resolution":{"observed_at":"2026-08-11T20:33:42.023263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T20:33:41.985117Z","title":null,"venue":null,"work_id":"4426b899-bfac-47e2-b475-b1369cdcc6ea","year":2001},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.231390Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:afeb95853a29d16d783ef53bf9ba316dba1d33b7c8e8f5a74a12c391022dda52","observation_id":"a4f6f2c1-68db-482b-b269-be4eb3439fc8","resolution":{"observed_at":"2026-08-11T20:33:41.995133Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T20:33:41.956041Z","title":"Neuroevolution in Deep Neural Networks: Current Trends and Future Challenges","venue":null,"work_id":"06238c86-4fcc-4302-ad4c-afdecd07fe1d","year":2021},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.235631Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:38fdea291475cf6d5262a49682e03f9183b4549da4bcb920978b7627e9803960","observation_id":"1c311bd5-b9c4-4e8a-b6a7-2f3513d34310","resolution":{"observed_at":"2026-08-11T20:33:41.962488Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:33:39.247781Z","title":"Exponential natural evolut ion strategies","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.247781Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:c8676652a008e6a3c5a6fa8a945f6e05ef55654357ad6e5ea1e77f4b30434880","observation_id":"5d785d45-6737-4dfc-aaa0-ee389d604dd6","resolution":{"observed_at":"2026-08-11T20:33:39.247781Z","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":"2026-08-11T20:33:41.936471Z","title":"An introduction to neural networks","venue":null,"work_id":"2ed786b6-ad23-4d5a-b014-c065b9e45544","year":1997},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.255197Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:51bcdec5033df54928f819d6dc703a2bc5d5b93453d0b1df9b6d62de38f25f24","observation_id":"c78f8306-d6bd-44d1-842a-c6890371ce86","resolution":{"observed_at":"2026-08-11T20:33:41.940926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.08034","last_updated":"2018-05-31T13:07:07Z","snapshot_observed_at":"2026-07-06T06:40:17.257577Z","submitted_at":"2018-05-21T13:08:31Z","title":"Never look back - A modified EnKF method and its application to the training of neural networks without back propagation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.08034","snapshot_observed_at":"2026-08-11T20:33:39.260281Z","title":"Never loo k back - A modified EnKF method and its application to the training of neural networks witho ut back propagation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.260281Z"},"links":{"cited_paper":"/paper/1805.08034","citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:9bd09655559efb9cb7934bb1332703ef55cd247bcd3ed8eb5010482c06275cd8","observation_id":"17638eb6-a167-4233-8af7-ccb51b46b1d8","resolution":{"observed_at":"2026-08-11T20:33:39.260281Z","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":"2026-08-11T20:33:41.920625Z","title":"Non-Linear Back-propagation: Doing Back-Propagation without Deriva- tives of the Activation Function","venue":null,"work_id":"0de17c26-29f2-4a27-9696-dcf3d26e2688","year":1997},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.318335Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:e0ebdfc8834e5e98f325bb21b6764e4590565607690c617efa8834bbd615b0fd","observation_id":"3bb82b38-9135-4660-b24f-91ba44400666","resolution":{"observed_at":"2026-08-11T20:33:41.926845Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.13345","last_updated":"2022-12-27T02:54:46Z","snapshot_observed_at":"2026-08-09T23:58:03.209262Z","submitted_at":"2022-12-27T02:54:46Z","title":"The Forward-Forward Algorithm: Some Preliminary Investigations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.13345","snapshot_observed_at":"2026-08-11T20:33:39.464147Z","title":"The Forward-Forward Algorithm: Som e Preliminary Investigations","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.464147Z"},"links":{"cited_paper":"/paper/2212.13345","citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:f746a0929f0515717be90ee9e0439707d2cebcbd481bab2ca21cacef889baaa3","observation_id":"50a63220-7de9-49f3-a263-9d9f7ab74418","resolution":{"observed_at":"2026-08-11T20:33:39.464147Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.05343","last_updated":"2017-07-03T10:52:04Z","snapshot_observed_at":"2026-07-06T05:07:27.342709Z","submitted_at":"2016-08-18T17:29:09Z","title":"Decoupled Neural Interfaces using Synthetic Gradients","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.05343","snapshot_observed_at":"2026-08-11T20:33:39.509557Z","title":"Decoupled Neural Interfaces usin g Synthetic Gradients","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.509557Z"},"links":{"cited_paper":"/paper/1608.05343","citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:62832313bdbc858ab7d2a5bd201ca4ef13d62905ec85f8a7762d1d87134e399e","observation_id":"bda824a2-b18a-4858-b421-9820583b30fa","resolution":{"observed_at":"2026-08-11T20:33:39.509557Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.08960","last_updated":"2023-10-13T15:52:36Z","snapshot_observed_at":"2026-08-07T05:11:46.656843Z","submitted_at":"2023-05-15T19:02:46Z","title":"One Forward is Enough for Neural Network Training via Likelihood Ratio Method","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.08960","snapshot_observed_at":"2026-08-11T20:33:39.515054Z","title":"One forward is enough for neural ne twork training via likelihood ratio method","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.515054Z"},"links":{"cited_paper":"/paper/2305.08960","citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:fe60eb30b1c7163a4d83c4b2f31c18fa0c1d1452054e3c811ba9dc134ba66477","observation_id":"9756aa5b-eeb5-436b-b879-594407a60536","resolution":{"observed_at":"2026-08-11T20:33:39.515054Z","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":"2026-08-11T20:33:41.905995Z","title":"Particle swarm optimization","venue":null,"work_id":"86e1cd33-994f-4e13-8395-4cb2d506cef5","year":1995},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.520103Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:d107f4ae1b3630f21998b622858a02612709aac1f8fb4f5684ea7e833e8b910b","observation_id":"b115bdc9-12e2-4bac-9551-3d057b31822b","resolution":{"observed_at":"2026-08-11T20:33:41.910347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T20:33:41.880611Z","title":"Eberhart, and Shi Y","venue":null,"work_id":"646cbf41-c1e7-4353-871c-0fb992e87ac3","year":2001},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.529053Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:2f4bd57a518d1a4a4b96e77bb980a773755bd84381d4e5dd9fb3d9cb7004b37b","observation_id":"75c6dace-da87-4f61-add3-571ee1d2db13","resolution":{"observed_at":"2026-08-11T20:33:41.889801Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T20:33:41.853173Z","title":"Adam: a Method for S tochastic Optimization","venue":null,"work_id":"5dbe65e3-f4a4-43a0-b144-760452c56683","year":2015},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.544688Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:0c6eae7bd3ce5f246d7f3c40b38fbef325a4a87663290893910bd09d167a5a3b","observation_id":"78cc137b-ea91-48b8-bedd-10b65daa4214","resolution":{"observed_at":"2026-08-11T20:33:41.860753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:33:39.558601Z","title":"Multiclass Classifica tion of Dry Beans Using Computer Vision and Machine Learning Techniques","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.558601Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:a8e109c173dae8a7b7257a55bf1316d573779120311c852a292176958eb590a8","observation_id":"fedd1859-1872-4aae-ab29-ca280e4e8caa","resolution":{"observed_at":"2026-08-11T20:33:39.558601Z","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":"1994.37448","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:33:41.004492Z","title":"Back-Propagation Without Weight Trans- port","venue":null,"work_id":"280b186d-4e0b-450b-a90f-6f58e57a9191","year":1994},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.562991Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:e811668aafe02896632d957b9dae3516a90455efc3c71c6a8b0df95f3e89abfe","observation_id":"5289b644-d241-4770-ac89-8437d79787cc","resolution":{"observed_at":"2026-08-11T20:33:41.016845Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T20:33:41.832129Z","title":"Ensemble Kalman inversion: a derivative-free technique for machine learning tasks","venue":null,"work_id":"560d64e3-8cdc-4dd1-86b5-8e8556f7f1e6","year":2019},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.567742Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:c2b50ef78a2459e7a0509da4ddc6abe15a0dc557876266a80e24b4cfc4c274c3","observation_id":"2cbdb36a-5f0e-485a-a1b3-6bcd867e42af","resolution":{"observed_at":"2026-08-11T20:33:41.838304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/s12046-016-0466-y","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:33:40.233795Z","title":"Binary classifica tion posed as a quadratically con- strained quadratic programming and solved using particle s warm optimization","venue":null,"work_id":"56c749ff-3978-42e7-b080-d14e927c97c2","year":2016},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.572573Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:7ffd9685b426ef721806ca5938b65ec3599aae8ea13a28e0bfd711d40d83eec3","observation_id":"2aff6c4b-5096-4153-8853-b335964f354d","resolution":{"observed_at":"2026-08-11T20:33:40.243879Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1407.6315","last_updated":"2014-07-23T18:04:23Z","snapshot_observed_at":"2026-07-06T03:49:52.519484Z","submitted_at":"2014-07-23T18:04:23Z","title":"Quadratically constrained quadratic programming for classification using particle swarms and applications","version":1},"cited_work":{"arxiv_id":"1407.6315","doi":null,"metadata_source":"pith","pith_arxiv_id":"1407.6315","snapshot_observed_at":"2026-08-11T20:33:40.903743Z","title":"Quadratically constrained quadratic programming for classification using particle swarms and applications","venue":"cs.AI","work_id":"beb29306-3984-4eb3-a132-60e4c5974014","year":2014},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.576789Z"},"links":{"cited_paper":"/paper/1407.6315","citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:61eba8ef7c61b2f63277485730c93e3247d85b35986ebc0786173103395a03ac","observation_id":"fb96c42d-4547-4f30-aabb-d623324e99b6","resolution":{"observed_at":"2026-08-11T20:33:40.910485Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:33:39.659019Z","title":"Backpropagation and the br ain","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.659019Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:b7f0af117845c0f11f84c73f794631aaaec5e42cf2a30dde8da7d7ef826e0e87","observation_id":"209e67c3-cefc-4ee2-bff3-b19abd922336","resolution":{"observed_at":"2026-08-11T20:33:39.659019Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1411.0247","last_updated":"2014-11-02T12:31:15Z","snapshot_observed_at":"2026-08-01T12:10:47.587112Z","submitted_at":"2014-11-02T12:31:15Z","title":"Random feedback weights support learning in deep neural networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1411.0247","snapshot_observed_at":"2026-08-11T20:33:39.742757Z","title":"Random feedback weights su pport learning in deep neural net- works","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.742757Z"},"links":{"cited_paper":"/paper/1411.0247","citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:b41caa4cda6a72a43cc273eb5b5b0bd0e7d60b1c2584c4a7ff44ff521896e1ca","observation_id":"114531af-dd01-4862-a1f5-98a51c0c1015","resolution":{"observed_at":"2026-08-11T20:33:39.742757Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:33:39.796834Z","title":"Random synaptic feedback w eights support error back- propagation for deep learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.796834Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:6931154511c4416d6ec2c5c4732d4f39c70b7fed7de47f6923778ec289125103","observation_id":"776eba8b-fdb7-4809-95cd-c3ea36c15a57","resolution":{"observed_at":"2026-08-11T20:33:39.796834Z","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":"2026-08-11T20:33:41.805206Z","title":"Th e HSIC Bottleneck: Deep Learning without Back-Propagation","venue":null,"work_id":"3b5d91af-fd39-4499-98ce-f1942434d278","year":2020},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.822097Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:3c052c828f82c316295d5d6d63b0510925d8f74b8566b647a35bfef1efa73d9d","observation_id":"d8eb611d-4dc1-4709-a0b8-499d947ba60a","resolution":{"observed_at":"2026-08-11T20:33:41.813249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:33:39.827540Z","title":"Simple Evolutio nary Optimization Can Rival Stochastic Gradient Descent in Neural Networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.827540Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:fbcc9e44332c1a9d966fab8fe0c86b023aa711ca336629485221d77f41ae351a","observation_id":"c83366f4-efd4-4eb5-90e2-73d4974a2d13","resolution":{"observed_at":"2026-08-11T20:33:39.827540Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:33:39.833186Z","title":"Random Gradient-Free Min imization of Convex Func- tions","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.833186Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:32c4f8101dfbec0904c1e1804da902dab8dd965e5993dc9d3f55f9592d5786b4","observation_id":"2b98556f-0a1e-4cd5-8f2f-7173417effce","resolution":{"observed_at":"2026-08-11T20:33:39.833186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:33:39.840454Z","title":"Derivativ e-free optimization: a review of algo- rithms and comparison of software implementations","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.840454Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:15a9d766b181491d315c8183346d0c1cf6fb5a0a2f1880b1d005095df99839ce","observation_id":"476ba9d3-5399-4c2b-a18d-29d2bccf766c","resolution":{"observed_at":"2026-08-11T20:33:39.840454Z","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":"2026-08-11T20:33:41.778655Z","title":"Learning representations by back-propagating errors","venue":null,"work_id":"afe06c88-a6e9-4c2a-b5f4-ac412fb0e134","year":1986},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.848829Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:b0ba8e11d562d1e3027c39a95a23588743e38ac60b115c1584c520a1c34712d4","observation_id":"e3576291-6d95-4cd7-9bce-c0b9984a9f2c","resolution":{"observed_at":"2026-08-11T20:33:41.788018Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T20:33:41.749783Z","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","venue":null,"work_id":"2222c17f-45fb-441c-9cd6-5f3a6aff4123","year":null},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.857970Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:d017330645d072d45406ddeb262a94e1b9529b5641f8d320085c4bbe6f34c3d7","observation_id":"ef2f9b65-d83d-46dd-baa4-43addfb8e24a","resolution":{"observed_at":"2026-08-11T20:33:41.762619Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2412.02482","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:33:40.671234Z","title":"Schneider et al","venue":null,"work_id":"ee31b404-3e73-406b-8ad9-8893fbb00a22","year":2024},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.876570Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:fb5ad0d97474a9fbf4dc3ef77fd173b62b460f6d2a029b7f4fc1a9f01d0b575c","observation_id":"b5ceca77-7cfc-42c9-8e52-9d228fce6f42","resolution":{"observed_at":"2026-08-11T20:33:40.695299Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.06567","last_updated":"2018-04-20T18:38:34Z","snapshot_observed_at":"2026-08-03T09:28:27.095641Z","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":"2026-08-11T20:33:39.882224Z","title":"Deep Neuroevolution: Gene tic Algorithms Are a Competitive Al- ternative for Training Deep Neural Networks for Reinforcem ent Learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.882224Z"},"links":{"cited_paper":"/paper/1712.06567","citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:4d8d6586add212e6cba85b9558f407cced9f2653de3d2ef80f9ac6cbfac59676","observation_id":"c3954c73-87b3-4f36-b013-a286c05ba88c","resolution":{"observed_at":"2026-08-11T20:33:39.882224Z","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":"9901.15699","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:33:40.528624Z","title":"Efficient natural evolution strategies","venue":null,"work_id":"4c517cbd-2b4b-4824-86ae-51a687495e5c","year":2009},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.887975Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:1108599a7c33ece1aced224f669b41656c61d357b303eec6abb24b13f7ff7e17","observation_id":"fc3aa779-b408-4566-86ee-4e5b40092306","resolution":{"observed_at":"2026-08-11T20:33:40.565551Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.05951","last_updated":"2019-07-12T20:49:19Z","snapshot_observed_at":"2026-08-03T14:39:57.240672Z","submitted_at":"2019-07-12T20:49:19Z","title":"An Evolutionary Algorithm of Linear complexity: Application to Training of Deep Neural Networks","version":1},"cited_work":{"arxiv_id":"1907.05951","doi":null,"metadata_source":"pith","pith_arxiv_id":"1907.05951","snapshot_observed_at":"2026-08-11T20:33:40.413427Z","title":"An Evolutionary Algorithm of Linear complexity: Application to Training of Deep Neural Networks","venue":"cs.NE","work_id":"1b164a16-e87c-470e-871e-5fece811c7cd","year":2019},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.894761Z"},"links":{"cited_paper":"/paper/1907.05951","citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:3ae4faa8120a7ab40684dca46de13427e8bb82927d14fd8a9e91778a3b58a8b4","observation_id":"f8f1717b-042e-4951-9d26-690897bb172d","resolution":{"observed_at":"2026-08-11T20:33:40.422167Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T20:33:41.694596Z","title":"Natural evolution strategies","venue":null,"work_id":"06abb495-2b8a-4d0a-ae1f-1b2df5c85c7c","year":2014},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.908721Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:ff992b56ee3219506cdc4be00d4384df1d94c1d9fbd117903619ff3e0aa5c03c","observation_id":"f4bd5714-51eb-40b2-898f-b7128350718a","resolution":{"observed_at":"2026-08-11T20:33:41.701603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T20:33:41.658386Z","title":"Neural Network Learni ng without Backpropagation","venue":null,"work_id":"fc39c16f-0448-48d0-b5d7-f6489e2d3a26","year":2010},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.991954Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:1b8e225c80e9de2a0c50a9bbf01fa47063cbe96b22c328f32348e09bad461cf7","observation_id":"f149b44b-376f-4902-be00-bde82454ea65","resolution":{"observed_at":"2026-08-11T20:33:41.670328Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2021.30616","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:33:40.374600Z","title":"A Gradient-Guided Evolutionar y Approach to Training Deep Neural Networks","venue":null,"work_id":"ef0439ae-4673-4c9e-bc15-957ae80f040a","year":2022},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:40.049829Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:2d06901c92472176ccc78b75aa7f27bb50b1e12652c17a63a47b7c9c7e5a6b35","observation_id":"b787b3b8-cedf-43fa-bc84-49ef469a401e","resolution":{"observed_at":"2026-08-11T20:33:40.389220Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:33:39.240824Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":493,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.240824Z"},"links":{"citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:59a7bd8d41cf7caec7d334d451e6e8ceeac31df67e31e0930def459b9ff02a14","observation_id":"015d7f49-b18e-4d90-9c68-deea9d04f8d5","resolution":{"observed_at":"2026-08-11T20:33:39.240824Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.03864","last_updated":"2017-09-07T23:28:48Z","snapshot_observed_at":"2026-07-06T05:33:17.404544Z","submitted_at":"2017-03-10T23:02:19Z","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.03864","snapshot_observed_at":"2026-08-11T20:33:39.867240Z","title":"URL : https://arxiv.org/abs/1703.03864","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles","version":3},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-11T20:33:39.867240Z"},"links":{"cited_paper":"/paper/1703.03864","citing_paper":"/paper/2412.05667"},"observation_digest":"sha256:3dcc91d673d1766e1358b024b72b94414ca61e636b2b22440c96da28f125433d","observation_id":"211b787b-83ab-4581-84c4-ec37c4abbf93","resolution":{"observed_at":"2026-08-11T20:33:39.867240Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.05667","last_updated":"2025-04-20T15:41:36Z","latest_version":3,"primary_category":"cs.NE","snapshot_observed_at":"2026-08-11T20:26:56.200277Z","submitted_at":"2024-12-07T14:30:48Z","title":"Training neural networks without backpropagation using particles"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":0,"metadata_mismatch":4,"parse_uncertain":0,"unresolved":19,"verified_exact":6,"verified_fuzzy":14},"total_outbound_references":43},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2412.05667."}