{"as_of":"2026-08-20T14:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:56349423fd8533f8d5eec7cc7bf10c7e8a715062d5b6d34799b69db04f7ea598","coverage":[{"denominator":29,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":29,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T10:37:33.207081Z","state":"measured"},{"denominator":29,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":29,"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/2504.18017/citation-record","integrity":"/paper/2504.18017/integrity","json":"/paper/2504.18017/citation-record.json","paper":"/paper/2504.18017"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:37:33.658094Z","title":"Learning and inference in hierarchical models with singularities","venue":null,"work_id":"f1a1f90a-154b-4240-b48e-25ae33fc09fd","year":2003},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.063333Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:e59d8bf6b142e15d75f3d2b3a6a4dde85b231a3b4ff1bf2fd71c50dbac4c2bba","observation_id":"3c6d7d88-dc8d-4d26-947a-252c892f3633","resolution":{"observed_at":"2026-08-16T10:37:33.663521Z","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":"2026-08-16T10:37:33.642109Z","title":"Universal approximation bounds for superpositions of a sigmoidal function","venue":null,"work_id":"ed3a8939-fb29-452f-90c3-96dc0fe86a06","year":1993},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.068842Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:90a5bfb7e0156aee9585a9fdde2579237c3bc27d150939f643601f03b1b7ed5e","observation_id":"c2449daa-e978-45f1-9648-0087135ba91f","resolution":{"observed_at":"2026-08-16T10:37:33.647656Z","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":"2026-08-16T10:37:33.625053Z","title":"Functional vs","venue":null,"work_id":"2af34ee0-86ec-4375-afc7-242e96146e87","year":2020},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.074083Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:522425360b1ce725dbd4c0dd8b930000c5ae1ac5c8bdf80f42e4662d4dcb134c","observation_id":"ba0870b9-5a69-4f2c-94b0-ec3b20c307f7","resolution":{"observed_at":"2026-08-16T10:37:33.630162Z","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":"2026-08-16T10:37:33.607410Z","title":"Approximation by superpositions of a sigmoidal function","venue":null,"work_id":"8a02447a-f902-4ffd-93e1-4fbaf46ddcc6","year":1989},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.079831Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:f6db56ea5307b081cfedb7d619740c56dc63df6a588f1215183289901f1f346b","observation_id":"bfb5078c-a620-4f30-b2d3-f7f035a6e7a8","resolution":{"observed_at":"2026-08-16T10:37:33.614109Z","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":"2026-08-16T10:37:33.592336Z","title":"Shallow vs","venue":null,"work_id":"018c6cae-9f38-42c2-8ce7-73a68ac81dd3","year":2011},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.085048Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:3f5e54c62070582da33459e25fa78b959daa7a44e59aec87bddca8c59f4aa15f","observation_id":"b7bda96e-cacb-405e-808d-456790d88db9","resolution":{"observed_at":"2026-08-16T10:37:33.596980Z","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":"2026-08-16T10:37:33.575760Z","title":"Sharp minima can generalize for deep nets","venue":null,"work_id":"cdb8de4a-0898-4749-910b-7cdc2452a683","year":2017},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.091224Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:6f9d6711fa91eabe66b5b04f07a1c6fdc4d5ac6bf479f8888ab188d495afe0f9","observation_id":"73af1aec-f8f0-49f7-b0a7-44de803c692f","resolution":{"observed_at":"2026-08-16T10:37:33.581110Z","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":"2026-08-16T10:37:33.561306Z","title":"The power of depth for feedforward neural networks","venue":null,"work_id":"d0c508de-88a2-43a5-b21e-877289a26779","year":2016},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.096989Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:633fb4f9927d656d60bc27c8b7b20e98a2377024cfabbfa01b0b12da8681f440","observation_id":"6e743f5b-f009-4b0f-95c8-8ff726eff58b","resolution":{"observed_at":"2026-08-16T10:37:33.566025Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:37:33.101647Z","title":"Real analysis: modern techniques and their applications , volume 40","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.101647Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:8d9dcf69b020ded3c31d5defc3f8c7073c584e7e2d428ec0e45f128d75dc9937","observation_id":"d22b88f5-2519-4480-ad86-6b5cb3253864","resolution":{"observed_at":"2026-08-16T10:37:33.101647Z","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":"2026-08-16T10:37:33.537647Z","title":"Structural degeneracy in neural networks","venue":null,"work_id":"bb748733-7a88-4c48-9075-09dd7566029f","year":2022},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.106791Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:dbece71b10766fc22e0e9db4b3fd691a3c66956f32f9ac8f24093cb10a2444e2","observation_id":"125d4187-9f49-4312-a894-bd7717bcd5ed","resolution":{"observed_at":"2026-08-16T10:37:33.542475Z","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":"2026-08-16T10:37:33.522543Z","title":"A regularity condition of the information matrix of a multilayer perceptron network","venue":null,"work_id":"7ebbcb7e-a0f9-4bfb-a972-63e37e5c9634","year":1996},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.112055Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:08c31a8cd2804b93a4e3f6b0341b56394aa999e655935c2e3b149616b10e75be","observation_id":"0a1e1ce9-c88c-40ab-93ce-97e04f85f87c","resolution":{"observed_at":"2026-08-16T10:37:33.527099Z","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":"2026-08-16T10:37:33.508195Z","title":"An investigation into neural net optimization via hessian eigenvalue density","venue":null,"work_id":"a088f6b8-c7c0-4abe-9015-b36b84259b21","year":2019},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.116375Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:23b08aaef2384b4e7cfdd0c46e6aa4c4c9ee24c56a93e01ac636895263d296a1","observation_id":"d39e0807-1668-4ee2-b72f-5e1914986c9d","resolution":{"observed_at":"2026-08-16T10:37:33.512880Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:37:33.120842Z","title":"Universal function approximation by deep neural nets with bounded width and relu activations","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.120842Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:80ee9eb09205a4b8c0bd753e6f6f6243ac57f9980fbf34d50f56fc2e5d13d5e1","observation_id":"9a78e9a6-eab8-4bda-ab20-41165eda8765","resolution":{"observed_at":"2026-08-16T10:37:33.120842Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.11278","last_updated":"2018-03-10T21:47:40Z","snapshot_observed_at":"2026-08-14T20:18:39.640575Z","submitted_at":"2017-10-31T00:26:56Z","title":"Approximating Continuous Functions by ReLU Nets of Minimal Width","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.11278","snapshot_observed_at":"2026-08-16T10:37:33.125694Z","title":"Approximating continuous functions by relu nets of minimal width","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.125694Z"},"links":{"cited_paper":"/paper/1710.11278","citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:7277517c87e8d14e412a3f9f44162fc3252b3694ed82711f7f3e6ad4a07675df","observation_id":"11633dc4-1629-437c-ae3a-f30a160b4f41","resolution":{"observed_at":"2026-08-16T10:37:33.125694Z","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":"2026-08-16T10:37:33.484003Z","title":"Multilayer feedforward networks are universal approximators","venue":null,"work_id":"adbe7750-e980-4d83-b40d-487a5f93a39a","year":1989},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.130951Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:c67973a80a4acf5fd9e6b0da237934eb52e130a209fc077bdac56f9f3da2a6b9","observation_id":"0adf168f-f78e-42bd-91be-e2eb291ec2c7","resolution":{"observed_at":"2026-08-16T10:37:33.488798Z","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":"2026-08-16T10:37:33.468239Z","title":"The normalization method for alleviating pathological sharpness in wide neural networks","venue":null,"work_id":"05e86deb-ec06-4966-a04f-0d719bc4c2de","year":2019},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.135758Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:b7e59fd0b2721ed7a7f231bbe0735ed7b27ddcf3da415d52ae595f4babbd5cb0","observation_id":"cb5676c2-35d6-4e8e-bd67-0bbe7adc8ee2","resolution":{"observed_at":"2026-08-16T10:37:33.474298Z","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":"1910.05992","last_updated":"2020-09-27T08:31:59Z","snapshot_observed_at":"2026-08-14T01:18:43.345273Z","submitted_at":"2019-10-14T08:54:56Z","title":"Pathological spectra of the Fisher information metric and its variants in deep neural networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.05992","snapshot_observed_at":"2026-08-16T10:37:33.140322Z","title":"Pathological spectra of the fisher information metric and its variants in deep neural networks","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.140322Z"},"links":{"cited_paper":"/paper/1910.05992","citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:9c32290ddbf319bfbec6a464ee99dba8859ba9cad451642791f5a6c7faf9f99e","observation_id":"e3240f3c-dfb9-4e3c-a1b0-1f24ddd61ec7","resolution":{"observed_at":"2026-08-16T10:37:33.140322Z","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":"2026-08-16T10:37:33.452385Z","title":"Universal statistics of fisher information in deep neural networks: Mean field approach","venue":null,"work_id":"5f8e7093-7920-4280-ad0b-f012a2ba768a","year":2019},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.145257Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:3cab1f6050796a600e2545883ddf1c0bd6ce4f33d1e86a0f88bd9927e99f668c","observation_id":"d9cfce06-33ab-41b9-b4a4-ca793eea0ede","resolution":{"observed_at":"2026-08-16T10:37:33.457497Z","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":"2026-08-16T10:37:33.437737Z","title":"On the ability of neural nets to express distributions","venue":null,"work_id":"dfe50272-68a4-4bc3-a48f-02476aca03f9","year":2017},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.150514Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:4cb43af1e18e0dac0f0ddb6336b6532fc1e0bad00777dcee9fced75a44022701","observation_id":"f3ab8ffe-338b-4a85-b12e-96d315db48e4","resolution":{"observed_at":"2026-08-16T10:37:33.442506Z","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":"2026-08-16T10:37:33.422975Z","title":"The connection between approximation, depth separation and learnability in neural networks","venue":null,"work_id":"31f0412a-d297-40d8-856b-22fcd5c51e3f","year":2021},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.155600Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:0c78e2b9804b386c69254ef3cdb3f9ec556d523139671a4da2af75ba02127fd7","observation_id":"c03e68f8-2c40-4de5-8946-2fad952c4cc3","resolution":{"observed_at":"2026-08-16T10:37:33.427668Z","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":"1901.08244","last_updated":"2019-01-24T06:02:40Z","snapshot_observed_at":"2026-08-17T15:26:01.792169Z","submitted_at":"2019-01-24T06:02:40Z","title":"Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.08244","snapshot_observed_at":"2026-08-16T10:37:33.160086Z","title":"Measurements of three-level hierarchical structure in the outliers in the spectrum of deepnet hessians","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.160086Z"},"links":{"cited_paper":"/paper/1901.08244","citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:1ed13adc8399beb11507b065c6e3418f9dd18e2a19e0c32c7b70ef3525a859e7","observation_id":"8f396b7c-b810-4260-8b4f-f615cd74b940","resolution":{"observed_at":"2026-08-16T10:37:33.160086Z","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":"2026-08-16T10:37:33.408509Z","title":"Topological properties of the set of functions generated by neural networks of fixed size","venue":null,"work_id":"8805eb16-e689-44ac-969f-1fc927569fce","year":2021},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.165070Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:154d53f49ef284ab919d56b30911eb0ee18a292275b8974af01b11b583a5e642","observation_id":"5ff78364-e0b0-4a24-9db8-3f79bd408e0b","resolution":{"observed_at":"2026-08-16T10:37:33.413228Z","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":"2026-08-16T10:37:33.392169Z","title":"The spectrum of the fisher information matrix of a single-hidden-layer neural network","venue":null,"work_id":"d9f62027-a746-4555-9326-ce46ed9bfedf","year":2018},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.169790Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:e6cd3ac3f6341870cd72f9d6a2c5df379f627d2c8cecbd5def71cbfa05f3ba5c","observation_id":"1e5354ae-0c9f-4080-b33c-4eb4d722d72c","resolution":{"observed_at":"2026-08-16T10:37:33.398039Z","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":"1706.04454","last_updated":"2018-05-07T15:43:39Z","snapshot_observed_at":"2026-08-17T17:22:50.487571Z","submitted_at":"2017-06-14T12:50:00Z","title":"Empirical Analysis of the Hessian of Over-Parametrized Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.04454","snapshot_observed_at":"2026-08-16T10:37:33.174264Z","title":"Empirical analysis of the hessian of over-parametrized neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.174264Z"},"links":{"cited_paper":"/paper/1706.04454","citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:c3d62cf6ac63583ac6659934b5bae1cb66f44c2e9df54258a02c7121a4ef927e","observation_id":"0d70e040-19f8-42d4-b8ca-efa0a40a63e4","resolution":{"observed_at":"2026-08-16T10:37:33.174264Z","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":"2026-08-16T10:37:33.179297Z","title":"Understanding machine learning: From theory to algorithms","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.179297Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:b596fe0b9748fecb0c7429fe82890f322e1c1c37b386b551a9343069204ce1b5","observation_id":"79eba81f-c08a-4708-ab20-f19d0be90cce","resolution":{"observed_at":"2026-08-16T10:37:33.179297Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1509.08101","last_updated":"2015-09-29T13:44:37Z","snapshot_observed_at":"2026-08-14T22:30:40.043393Z","submitted_at":"2015-09-27T15:26:58Z","title":"Representation Benefits of Deep Feedforward Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1509.08101","snapshot_observed_at":"2026-08-16T10:37:33.184516Z","title":"Representation benefits of deep feedforward networks","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.184516Z"},"links":{"cited_paper":"/paper/1509.08101","citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:9aed705a4801724ed954f95e90a4c5211d083aa045a0873fadecdc1caad26919","observation_id":"2967f474-e37f-4a87-9638-cf1e0d55d5b6","resolution":{"observed_at":"2026-08-16T10:37:33.184516Z","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":"2026-08-16T10:37:33.367442Z","title":"Algebraic geometry and statistical learning theory , volume 25","venue":null,"work_id":"16dd627c-0e56-452c-9760-79b64315e65c","year":2009},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.189916Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:90dfcd5f582e81c884bcd596dc8917e73d98e8ad05a0c4b81198289577b0a295","observation_id":"6f83104d-afb7-4097-ab33-8db553433405","resolution":{"observed_at":"2026-08-16T10:37:33.372300Z","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":"2026-08-16T10:37:33.352609Z","title":"Mathematical theory of Bayesian statistics","venue":null,"work_id":"ad83037e-9032-44bd-96d8-1b74a2faa533","year":2018},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.195088Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:9e3149206d0ddedd12bacba0df2a585787ac52b320dbdea41b853bd40034cf11","observation_id":"821d83b5-fcc8-47d8-a086-bbb6a07f1c03","resolution":{"observed_at":"2026-08-16T10:37:33.357248Z","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":"2026-08-16T10:37:33.336909Z","title":"Deep learning is singular, and that’s good","venue":null,"work_id":"5431b27b-67a5-4fb1-af0b-d2d44ee98d7e","year":2022},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.201105Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:a74394d5467616d416131aaf41a70060ba3357b5445a82a8bf944afdda5e0d9c","observation_id":"b29dc414-f9fc-4aa4-b9bd-83fa1e4cedae","resolution":{"observed_at":"2026-08-16T10:37:33.341932Z","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":"2026-08-16T10:37:33.318140Z","title":"The lack of a priori distinctions between learning algorithms","venue":null,"work_id":"8f4f2ecb-bec4-428d-bd45-69ca3b9e2886","year":1996},"citing_paper":{"arxiv_id":"2504.18017","last_updated":"2025-05-27T02:31:37Z","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-16T10:37:33.207081Z"},"links":{"citing_paper":"/paper/2504.18017"},"observation_digest":"sha256:f5a66c5b8964744abfd456ce4f01c523bd12fcdf30cc22caccf43d14b2f0408f","observation_id":"948ccda7-8b39-4891-9a89-354e4b8a15f6","resolution":{"observed_at":"2026-08-16T10:37:33.326044Z","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":"2504.18017","last_updated":"2025-05-27T02:31:37Z","latest_version":2,"primary_category":"math.ST","snapshot_observed_at":"2026-08-20T09:15:24.265232Z","submitted_at":"2025-04-25T01:59:02Z","title":"Non-identifiability distinguishes Neural Networks among Parametric Models"},"reference_resolution":{"displayed":29,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":21},"total_outbound_references":29},"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 20 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2504.18017."}