{"as_of":"2026-08-10T14:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:47fa9451183e2fd79f03c1e904be6d6ab22a4497dcf884d6ee218fca0fb715c4","coverage":[{"denominator":15,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":15,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-11T11:50:26.030339Z","state":"measured"},{"denominator":15,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":15,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.07778/citation-record","integrity":"/paper/2607.07778/integrity","json":"/paper/2607.07778/citation-record.json","paper":"/paper/2607.07778"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T18:37:31.867368Z","title":"Bubeck, Y","venue":null,"work_id":"1f5d08f7-8f3c-478d-bdd5-6e3b098e530c","year":null},"citing_paper":{"arxiv_id":"2607.07778","last_updated":"2026-07-08T17:44:15Z","snapshot_observed_at":"2026-08-06T08:48:39.937315Z","submitted_at":"2026-07-08T17:44:15Z","title":"A law of robustness for two-layer neural networks with arbitrary weights","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-10T18:18:29.599481Z"},"links":{"citing_paper":"/paper/2607.07778"},"observation_digest":"sha256:2baa5ee3a9db3973a4698d54a07fbf39a15ab88ad6bbf58777ae798079a91a49","observation_id":"6014b1f0-319e-424c-8059-1a5a25f22710","resolution":{"observed_at":"2026-07-10T18:37:31.868417Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.12806","last_updated":"2022-12-23T19:17:30Z","snapshot_observed_at":"2026-08-06T03:10:38.937459Z","submitted_at":"2021-05-26T19:49:47Z","title":"A Universal Law of Robustness via Isoperimetry","version":4},"cited_work":{"arxiv_id":"2105.12806","doi":"10.48550/arxiv.2105.12806","metadata_source":"pith","pith_arxiv_id":"2105.12806","snapshot_observed_at":"2026-07-10T18:27:31.258790Z","title":"arXiv preprint arXiv:2105.12806 , year=","venue":"cs.LG","work_id":"d7a03bed-db43-4eec-9348-ad450fab0018","year":2021},"citing_paper":{"arxiv_id":"2607.07778","last_updated":"2026-07-08T17:44:15Z","snapshot_observed_at":"2026-08-06T08:48:39.937315Z","submitted_at":"2026-07-08T17:44:15Z","title":"A law of robustness for two-layer neural networks with arbitrary weights","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-11T11:50:26.030339Z"},"links":{"cited_paper":"/paper/2105.12806","citing_paper":"/paper/2607.07778"},"observation_digest":"sha256:344fe733fc2ad3e2c0c6a269db0b93a9dcb2fdcc8e7f568fa56176a428b2bea1","observation_id":"ed96db01-b98d-45cd-bc86-a52eba8531c1","resolution":{"observed_at":"2026-07-10T18:27:31.260340Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T18:37:31.865572Z","title":null,"venue":null,"work_id":"04568577-1775-47c7-b02b-7494de2d1ae0","year":null},"citing_paper":{"arxiv_id":"2607.07778","last_updated":"2026-07-08T17:44:15Z","snapshot_observed_at":"2026-08-06T08:48:39.937315Z","submitted_at":"2026-07-08T17:44:15Z","title":"A law of robustness for two-layer neural networks with arbitrary weights","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-10T18:18:29.599481Z"},"links":{"citing_paper":"/paper/2607.07778"},"observation_digest":"sha256:19265c7206c871b59cddec1dc25292f3da4964dd47ea448fc55d7f2412d9dfc6","observation_id":"603213d0-4fe4-42a5-933b-85f1209f0e7f","resolution":{"observed_at":"2026-07-10T18:37:31.866835Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T18:37:31.859228Z","title":"Dubhashi and D","venue":null,"work_id":"2afe2b61-191f-4185-93a5-01f0ac102394","year":1998},"citing_paper":{"arxiv_id":"2607.07778","last_updated":"2026-07-08T17:44:15Z","snapshot_observed_at":"2026-08-06T08:48:39.937315Z","submitted_at":"2026-07-08T17:44:15Z","title":"A law of robustness for two-layer neural networks with arbitrary weights","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-10T18:18:29.599481Z"},"links":{"citing_paper":"/paper/2607.07778"},"observation_digest":"sha256:0f8c3023ee92f767d9c73fca9598d16f7d75564f7ae88c3ec2d59e55c0efecc2","observation_id":"019f4460-f670-4f36-a2f7-79327fa52591","resolution":{"observed_at":"2026-07-10T18:37:31.860806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"aos/1176346","doi":"10.1214/aos/1176346079","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas Hofmann, Bernhard Sch¨ olkopf, and Alexander J Smola","venue":"The Annals of Statistics","work_id":"cb5f05de-6a1f-42d6-9bb1-7ed4f79fec44","year":1983},"citing_paper":{"arxiv_id":"2607.07778","last_updated":"2026-07-08T17:44:15Z","snapshot_observed_at":"2026-08-06T08:48:39.937315Z","submitted_at":"2026-07-08T17:44:15Z","title":"A law of robustness for two-layer neural networks with arbitrary weights","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-10T18:18:29.599481Z"},"links":{"citing_paper":"/paper/2607.07778"},"observation_digest":"sha256:b42bd6b30dea6a95ece4f42c297168c6430cf5c18aea9e7c878f6eaf7a1ade4e","observation_id":"bfc5986a-186f-4987-bb64-b49c6febc109","resolution":{"observed_at":"2026-07-10T18:27:31.272404Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-07-11T17:50:25.528181+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T17:50:25.528181+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T18:37:31.856488Z","title":"Pinkus.Ridge Functions","venue":null,"work_id":"601e543c-60f5-4290-924b-dc52ea3604b4","year":null},"citing_paper":{"arxiv_id":"2607.07778","last_updated":"2026-07-08T17:44:15Z","snapshot_observed_at":"2026-08-06T08:48:39.937315Z","submitted_at":"2026-07-08T17:44:15Z","title":"A law of robustness for two-layer neural networks with arbitrary weights","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-10T18:18:29.599481Z"},"links":{"citing_paper":"/paper/2607.07778"},"observation_digest":"sha256:2e649ba0ee79e0ad09f68441795368ed7d9ea11565b94d18407ebd1a066031da","observation_id":"95a135e9-076f-41b6-b3d8-6d4bc0db382f","resolution":{"observed_at":"2026-07-10T18:37:31.858281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1017/cbo9781316408124","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Cambridge University Press, Cambr idge, UK (2015)","venue":"Cambridge University Press eBooks","work_id":"b16ee37e-b81e-4ddf-add8-0bd839cb66d2","year":2015},"citing_paper":{"arxiv_id":"2607.07778","last_updated":"2026-07-08T17:44:15Z","snapshot_observed_at":"2026-08-06T08:48:39.937315Z","submitted_at":"2026-07-08T17:44:15Z","title":"A law of robustness for two-layer neural networks with arbitrary weights","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-10T18:18:29.599481Z"},"links":{"citing_paper":"/paper/2607.07778"},"observation_digest":"sha256:62b3d7e4a075cc4c4892c108a47cb170eb5abb5ce6d70668ddaf50a9f0d6c640","observation_id":"0aa60333-5fcd-425d-9057-f84a62516bff","resolution":{"observed_at":"2026-07-10T18:27:31.269655Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1017/9781108231596","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Comput.54, 2 (2025), 193–232","venue":null,"work_id":"324f3b32-472c-40d1-b839-4c22ba21e656","year":2018},"citing_paper":{"arxiv_id":"2607.07778","last_updated":"2026-07-08T17:44:15Z","snapshot_observed_at":"2026-08-06T08:48:39.937315Z","submitted_at":"2026-07-08T17:44:15Z","title":"A law of robustness for two-layer neural networks with arbitrary weights","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-10T18:18:29.599481Z"},"links":{"citing_paper":"/paper/2607.07778"},"observation_digest":"sha256:5d02586b9c57dc2664b6e8290029d78d6bd1a0b1426e6e56b3d9f398a65ac209","observation_id":"fbf57cae-e01a-4b46-81b1-b08d6fe29498","resolution":{"observed_at":"2026-07-10T18:27:31.264164Z","resolver_source":"doi","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-07-18T16:21:17.228774+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-18T16:21:17.228774+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1109/18.256506","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"IEEE Transactions on Information Theory","work_id":"aebeebd8-9491-4d0e-b06f-aabfc5549abe","year":1993},"citing_paper":{"arxiv_id":"2607.07778","last_updated":"2026-07-08T17:44:15Z","snapshot_observed_at":"2026-08-06T08:48:39.937315Z","submitted_at":"2026-07-08T17:44:15Z","title":"A law of robustness for two-layer neural networks with arbitrary weights","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-10T18:18:29.599481Z"},"links":{"citing_paper":"/paper/2607.07778"},"observation_digest":"sha256:7baebc04fbda2f07c8e70b77842792a6d4d04889720bfc8021ad7d8b0330f264","observation_id":"8b34a680-0d56-4bf8-b6d6-90f70c63393d","resolution":{"observed_at":"2026-07-10T18:27:31.262124Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.01491","last_updated":"2018-02-28T02:23:47Z","snapshot_observed_at":"2026-08-10T00:02:44.491653Z","submitted_at":"2016-11-04T18:54:50Z","title":"Understanding Deep Neural Networks with Rectified Linear Units","version":6},"cited_work":{"arxiv_id":"1611.01491","doi":"10.48550/arxiv.1611.01491","metadata_source":"pith","pith_arxiv_id":"1611.01491","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Understanding Deep Neural Networks with Rectified Linear Units","venue":"cs.LG","work_id":"146fb03a-08b5-4078-ac21-4aa3619ceb20","year":2016},"citing_paper":{"arxiv_id":"2607.07778","last_updated":"2026-07-08T17:44:15Z","snapshot_observed_at":"2026-08-06T08:48:39.937315Z","submitted_at":"2026-07-08T17:44:15Z","title":"A law of robustness for two-layer neural networks with arbitrary weights","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-10T18:18:29.599481Z"},"links":{"cited_paper":"/paper/1611.01491","citing_paper":"/paper/2607.07778"},"observation_digest":"sha256:28a8b0437590c568b07a5b30a2f4275cb32e568866fb4a35d35f3134d748c8b6","observation_id":"8cdd12f7-4c08-42ee-9f95-e297fd3c2e75","resolution":{"observed_at":"2026-07-10T18:27:31.884412Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-05-26T00:23:52.340191+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-26T00:23:52.340191+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/978-3-642-25983-8","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Atkinson and W","venue":"Lecture notes in mathematics","work_id":"e51eb86a-664b-41c8-bac9-db3e305628f6","year":2044},"citing_paper":{"arxiv_id":"2607.07778","last_updated":"2026-07-08T17:44:15Z","snapshot_observed_at":"2026-08-06T08:48:39.937315Z","submitted_at":"2026-07-08T17:44:15Z","title":"A law of robustness for two-layer neural networks with arbitrary weights","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-10T18:18:29.599481Z"},"links":{"citing_paper":"/paper/2607.07778"},"observation_digest":"sha256:42643dd35c1c8597726bc1a5f1025eb9a5cb88918c669c4014864d55dbdd8e28","observation_id":"b490027e-55a1-472e-946b-f91bee075eca","resolution":{"observed_at":"2026-07-10T18:27:31.267712Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/978-3-642-20212-4","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Ledoux and M","venue":null,"work_id":"91b34f4e-3903-4889-a590-33a537a9a49c","year":1991},"citing_paper":{"arxiv_id":"2607.07778","last_updated":"2026-07-08T17:44:15Z","snapshot_observed_at":"2026-08-06T08:48:39.937315Z","submitted_at":"2026-07-08T17:44:15Z","title":"A law of robustness for two-layer neural networks with arbitrary weights","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-10T18:18:29.599481Z"},"links":{"citing_paper":"/paper/2607.07778"},"observation_digest":"sha256:dbe1208acfebfde8868b8b8173201cc9018ab5aa3a219b31e87e0179a3370190","observation_id":"8bc78d2f-1936-4fa1-bea5-8bfac97ba590","resolution":{"observed_at":"2026-07-10T18:27:31.265952Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-07-14T22:50:49.385951+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-14T22:50:49.385951+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1017/cbo9781107359949.008","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"McDiarmid,On the method of bounded differences, inSurveys in Combinatorics, 1989(Norwich, 1989), London Math","venue":"Cambridge University Press eBooks","work_id":"cca0b09e-bb6d-4ada-935d-2d81c935f081","year":1989},"citing_paper":{"arxiv_id":"2607.07778","last_updated":"2026-07-08T17:44:15Z","snapshot_observed_at":"2026-08-06T08:48:39.937315Z","submitted_at":"2026-07-08T17:44:15Z","title":"A law of robustness for two-layer neural networks with arbitrary weights","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-10T18:18:29.599481Z"},"links":{"citing_paper":"/paper/2607.07778"},"observation_digest":"sha256:997875ef5a904b823413d9d66165afca94dd8adb9851972310101eb871854a80","observation_id":"5933af56-9911-4938-ba3e-a0ebf6463787","resolution":{"observed_at":"2026-07-10T18:27:31.274679Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T18:37:31.861390Z","title":null,"venue":null,"work_id":"3ac1b222-ac4d-4f60-8735-e842bd094364","year":null},"citing_paper":{"arxiv_id":"2607.07778","last_updated":"2026-07-08T17:44:15Z","snapshot_observed_at":"2026-08-06T08:48:39.937315Z","submitted_at":"2026-07-08T17:44:15Z","title":"A law of robustness for two-layer neural networks with arbitrary weights","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-10T18:18:29.599481Z"},"links":{"citing_paper":"/paper/2607.07778"},"observation_digest":"sha256:33c989df87bd6f8817d2d60f4151ff795989596575900eb6b69597a1d977b9c0","observation_id":"65075eeb-e347-4f84-af61-02150322ef93","resolution":{"observed_at":"2026-07-10T18:37:31.862636Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T18:37:31.868955Z","title":"Einstein Institute of Mathematics, The Hebrew University of Jerusalem, Givat Ram, Jerusalem, Israel Email address:yitzchak.shmalo@gmail.com","venue":null,"work_id":"3888b210-a0d2-47f9-a387-4d8591be39d6","year":null},"citing_paper":{"arxiv_id":"2607.07778","last_updated":"2026-07-08T17:44:15Z","snapshot_observed_at":"2026-08-06T08:48:39.937315Z","submitted_at":"2026-07-08T17:44:15Z","title":"A law of robustness for two-layer neural networks with arbitrary weights","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-10T18:18:29.599481Z"},"links":{"citing_paper":"/paper/2607.07778"},"observation_digest":"sha256:07f2b69ed54d3c71074d29cf82c31221050f171567b9c5543349b922fc1bdc44","observation_id":"e5adfbef-1e69-4f37-b469-ce45e76dfb38","resolution":{"observed_at":"2026-07-10T18:37:31.870175Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2607.07778","last_updated":"2026-07-08T17:44:15Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T08:48:39.937315Z","submitted_at":"2026-07-08T17:44:15Z","title":"A law of robustness for two-layer neural networks with arbitrary weights"},"reference_resolution":{"displayed":15,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":2,"verified_exact":7,"verified_fuzzy":4},"total_outbound_references":15},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2607.07778."}