{"as_of":"2026-08-10T14:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:730123aa2563db3d40b661dfa59911596edc54edaad3a8658b0d830d5c98bf29","coverage":[{"denominator":12,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T20:47:40.701033Z","state":"measured"},{"denominator":13,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":13,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-30T07:12:21.293282Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":1,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.19281","last_updated":"2025-01-31T16:43:57Z","snapshot_observed_at":"2026-08-10T06:32:18.706641Z","submitted_at":"2025-01-31T16:43:57Z","title":"Statistical Physics of Deep Neural Networks: Generalization Capability, Beyond the Infinite Width, and Feature Learning","version":1},"cited_work":{"arxiv_id":"2501.19281","doi":"10.48550/arxiv.2501.19281","metadata_source":"arxiv_reference","pith_arxiv_id":"2501.19281","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Ariosto,Statistical Physics of Deep Neural Networks: Generalization Capability, Beyond the Infinite Width, and Feature Learning, 2025, 10.48550/arXiv.2501.19281","venue":"ArXiv.org","work_id":"b8fe28ab-5661-4a5e-bbc9-71ac6fbc69f2","year":2025},"citing_paper":{"arxiv_id":"2606.30064","last_updated":"2026-06-29T09:57:39Z","snapshot_observed_at":"2026-07-07T00:03:56.075924Z","submitted_at":"2026-06-29T09:57:39Z","title":"Data-Driven Energy-Based Learning via Gibbs Measures on Hierarchical Structures","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-30T07:12:21.293282Z"},"links":{"cited_paper":"/paper/2501.19281","citing_paper":"/paper/2606.30064"},"observation_digest":"sha256:f9bc75a4de89b7caa6d295c2263b35f66075096664b04ee49c153b8e7fa5ab40","observation_id":"9985edb4-6803-427d-9628-072ca1ce058f","resolution":{"observed_at":"2026-06-30T07:14:20.437985Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.19281/citation-record","integrity":"/paper/2501.19281/integrity","json":"/paper/2501.19281/citation-record.json","paper":"/paper/2501.19281"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1511.07289","last_updated":"2016-02-22T07:02:58Z","snapshot_observed_at":"2026-07-06T04:37:28.029641Z","submitted_at":"2015-11-23T15:58:05Z","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.07289","snapshot_observed_at":"2026-08-09T20:47:40.675318Z","title":"1088 / 1751 - 8121 / aba028","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.19281","last_updated":"2025-01-31T16:43:57Z","snapshot_observed_at":"2026-08-10T06:32:18.706641Z","submitted_at":"2025-01-31T16:43:57Z","title":"Statistical Physics of Deep Neural Networks: Generalization Capability, Beyond the Infinite Width, and Feature Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T20:47:40.675318Z"},"links":{"cited_paper":"/paper/1511.07289","citing_paper":"/paper/2501.19281"},"observation_digest":"sha256:8a54853a30da6ab687e297186c46eb3a7bbb3c4805c49eff6c25e0c22878ff7b","observation_id":"cd002fed-ef04-43b1-8940-c9946c662d6c","resolution":{"observed_at":"2026-08-09T20:47:40.675318Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1301.3605","last_updated":"2013-03-08T19:42:37Z","snapshot_observed_at":"2026-07-06T03:04:08.204892Z","submitted_at":"2013-01-16T07:23:19Z","title":"Feature Learning in Deep Neural Networks - Studies on Speech Recognition Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1301.3605","snapshot_observed_at":"2026-08-09T20:47:40.701033Z","title":"[YSL+13] Dong Yu, Michael L Seltzer, Jinyu Li, Jui-Ting Huang, and Frank Seide","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.19281","last_updated":"2025-01-31T16:43:57Z","snapshot_observed_at":"2026-08-10T06:32:18.706641Z","submitted_at":"2025-01-31T16:43:57Z","title":"Statistical Physics of Deep Neural Networks: Generalization Capability, Beyond the Infinite Width, and Feature Learning","version":1},"reference_index":296,"source":"pdf_text","source_observed_at":"2026-08-09T20:47:40.701033Z"},"links":{"cited_paper":"/paper/1301.3605","citing_paper":"/paper/2501.19281"},"observation_digest":"sha256:85a07d4b4db1b144727d7ab82d439d3b7026efc083c4a2c7e2afd78dd06d7eac","observation_id":"aff180b7-9778-4c6f-8d34-cc4fcea01b31","resolution":{"observed_at":"2026-08-09T20:47:40.701033Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1511.06434","last_updated":"2016-01-07T23:09:39Z","snapshot_observed_at":"2026-08-04T04:34:27.861448Z","submitted_at":"2015-11-19T22:50:32Z","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.06434","snapshot_observed_at":"2026-08-09T20:47:40.693178Z","title":"[RHW86b] David E Rumelhart, Geoffrey E Hinton, and Ronald J Williams","venue":null,"work_id":null,"year":1986},"citing_paper":{"arxiv_id":"2501.19281","last_updated":"2025-01-31T16:43:57Z","snapshot_observed_at":"2026-08-10T06:32:18.706641Z","submitted_at":"2025-01-31T16:43:57Z","title":"Statistical Physics of Deep Neural Networks: Generalization Capability, Beyond the Infinite Width, and Feature Learning","version":1},"reference_index":362,"source":"pdf_text","source_observed_at":"2026-08-09T20:47:40.693178Z"},"links":{"cited_paper":"/paper/1511.06434","citing_paper":"/paper/2501.19281"},"observation_digest":"sha256:245bf8cbb147881927b2be72e731e054e19e37e25f2d6c227ee76b76779eb630","observation_id":"2a7b4802-887e-468f-94a9-3ab6b72fc139","resolution":{"observed_at":"2026-08-09T20:47:40.693178Z","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":"2026-08-09T20:47:40.653239Z","title":"[AGS87] Daniel J Amit, Hanoch Gutfreund, and Haim Sompolinsky","venue":null,"work_id":null,"year":1987},"citing_paper":{"arxiv_id":"2501.19281","last_updated":"2025-01-31T16:43:57Z","snapshot_observed_at":"2026-08-10T06:32:18.706641Z","submitted_at":"2025-01-31T16:43:57Z","title":"Statistical Physics of Deep Neural Networks: Generalization Capability, Beyond the Infinite Width, and Feature Learning","version":1},"reference_index":1530,"source":"pdf_text","source_observed_at":"2026-08-09T20:47:40.653239Z"},"links":{"citing_paper":"/paper/2501.19281"},"observation_digest":"sha256:e99a91edcf29ea37674af9153aee5c00c1d991408d9a6916c4fe28031225be5b","observation_id":"4abda10f-d860-4fa4-9284-8598d75eb289","resolution":{"observed_at":"2026-08-09T20:47:40.653239Z","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":"2026-08-09T20:47:40.662035Z","title":"url: https ://www.sciencedirect.com/science/article/pii/0047259X83900192","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.19281","last_updated":"2025-01-31T16:43:57Z","snapshot_observed_at":"2026-08-10T06:32:18.706641Z","submitted_at":"2025-01-31T16:43:57Z","title":"Statistical Physics of Deep Neural Networks: Generalization Capability, Beyond the Infinite Width, and Feature Learning","version":1},"reference_index":1983,"source":"pdf_text","source_observed_at":"2026-08-09T20:47:40.662035Z"},"links":{"citing_paper":"/paper/2501.19281"},"observation_digest":"sha256:156b0b83799bd790972405f1021d585e68f52b03b6294b80dd243f3a323f35af","observation_id":"cbd9e003-c228-459a-bb3f-8bfca07e0bdb","resolution":{"observed_at":"2026-08-09T20:47:40.662035Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-07-06T04:04:16.777653Z","submitted_at":"2014-12-20T01:17:12Z","title":"Explaining and Harnessing Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6572","snapshot_observed_at":"2026-08-09T20:47:40.679879Z","title":"187 [GSJ+20] Mario Geiger, Stefano Spigler, Arthur Jacot, and Matthieu Wyart","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.19281","last_updated":"2025-01-31T16:43:57Z","snapshot_observed_at":"2026-08-10T06:32:18.706641Z","submitted_at":"2025-01-31T16:43:57Z","title":"Statistical Physics of Deep Neural Networks: Generalization Capability, Beyond the Infinite Width, and Feature Learning","version":1},"reference_index":1999,"source":"pdf_text","source_observed_at":"2026-08-09T20:47:40.679879Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2501.19281"},"observation_digest":"sha256:76dc166e657a871486f23386fe7f62c466f03a22cb39193c680b3101b87fe5d4","observation_id":"da09dd8c-4a29-408f-8703-d75fd28ca14e","resolution":{"observed_at":"2026-08-09T20:47:40.679879Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-07-06T03:53:32.549552Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-09T20:47:40.697130Z","title":"[SZ14] Karen Simonyan and Andrew Zisserman","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2501.19281","last_updated":"2025-01-31T16:43:57Z","snapshot_observed_at":"2026-08-10T06:32:18.706641Z","submitted_at":"2025-01-31T16:43:57Z","title":"Statistical Physics of Deep Neural Networks: Generalization Capability, Beyond the Infinite Width, and Feature Learning","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-09T20:47:40.697130Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2501.19281"},"observation_digest":"sha256:06d53b7bf468019e08cdb73c0177f6d3f82dc0e63a7ee8386789819d4d9145d8","observation_id":"07d56dc9-4523-4211-a7c7-128a1a78d209","resolution":{"observed_at":"2026-08-09T20:47:40.697130Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.00165","last_updated":"2018-03-03T00:45:00Z","snapshot_observed_at":"2026-08-04T10:06:19.819372Z","submitted_at":"2017-11-01T02:13:25Z","title":"Deep Neural Networks as Gaussian Processes","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.00165","snapshot_observed_at":"2026-08-09T20:47:40.684251Z","title":"[LBB+98] Yann LeCun, Leon Bottou, Yoshua Bengio, and Patrick Haffner","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2501.19281","last_updated":"2025-01-31T16:43:57Z","snapshot_observed_at":"2026-08-10T06:32:18.706641Z","submitted_at":"2025-01-31T16:43:57Z","title":"Statistical Physics of Deep Neural Networks: Generalization Capability, Beyond the Infinite Width, and Feature Learning","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-09T20:47:40.684251Z"},"links":{"cited_paper":"/paper/1711.00165","citing_paper":"/paper/2501.19281"},"observation_digest":"sha256:01e84b6bdc86e7e9421d92a8fd81f40962b807340fe0cab7dd10a6d625db5ebc","observation_id":"b4b41658-556c-47d9-90ab-8ef9a2cb9b2e","resolution":{"observed_at":"2026-08-09T20:47:40.684251Z","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":"2026-08-09T20:47:40.670322Z","title":"url: https://link.aps.org/ doi/10.1103/PhysRevX.8.031003","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.19281","last_updated":"2025-01-31T16:43:57Z","snapshot_observed_at":"2026-08-10T06:32:18.706641Z","submitted_at":"2025-01-31T16:43:57Z","title":"Statistical Physics of Deep Neural Networks: Generalization Capability, Beyond the Infinite Width, and Feature Learning","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-09T20:47:40.670322Z"},"links":{"citing_paper":"/paper/2501.19281"},"observation_digest":"sha256:02a57ce2ea95632223abf5ea1043f4810dca97878e4bab738b42b43852f9b168","observation_id":"5c235f9e-0e8e-4d4b-a760-69c98252c991","resolution":{"observed_at":"2026-08-09T20:47:40.670322Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.11440","last_updated":"2023-03-08T20:43:36Z","snapshot_observed_at":"2026-07-06T09:30:56.502340Z","submitted_at":"2020-06-19T23:50:51Z","title":"Local Convolutions Cause an Implicit Bias towards High Frequency Adversarial Examples","version":5},"cited_work":{"arxiv_id":"2006.11440","doi":null,"metadata_source":"pith","pith_arxiv_id":"2006.11440","snapshot_observed_at":"2026-08-09T20:47:41.072859Z","title":"Local Convolutions Cause an Implicit Bias towards High Frequency Adversarial Examples","venue":"stat.ML","work_id":"d53cb6e7-9369-4e45-b523-ac1ef35455b6","year":2020},"citing_paper":{"arxiv_id":"2501.19281","last_updated":"2025-01-31T16:43:57Z","snapshot_observed_at":"2026-08-10T06:32:18.706641Z","submitted_at":"2025-01-31T16:43:57Z","title":"Statistical Physics of Deep Neural Networks: Generalization Capability, Beyond the Infinite Width, and Feature Learning","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-09T20:47:40.665571Z"},"links":{"cited_paper":"/paper/2006.11440","citing_paper":"/paper/2501.19281"},"observation_digest":"sha256:d93e0cdc7904afc49ba0e567bcf1cc252fc90ea6f12c2f91b38d8475449e3630","observation_id":"ca815033-a176-4b10-be75-c823562a008e","resolution":{"observed_at":"2026-08-09T20:47:41.078115Z","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":{"arxiv_id":"1706.05394","last_updated":"2017-07-01T14:26:51Z","snapshot_observed_at":"2026-08-07T16:13:32.354938Z","submitted_at":"2017-06-16T18:11:09Z","title":"A Closer Look at Memorization in Deep Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.05394","snapshot_observed_at":"2026-08-09T20:47:40.657531Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.19281","last_updated":"2025-01-31T16:43:57Z","snapshot_observed_at":"2026-08-10T06:32:18.706641Z","submitted_at":"2025-01-31T16:43:57Z","title":"Statistical Physics of Deep Neural Networks: Generalization Capability, Beyond the Infinite Width, and Feature Learning","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-09T20:47:40.657531Z"},"links":{"cited_paper":"/paper/1706.05394","citing_paper":"/paper/2501.19281"},"observation_digest":"sha256:d288e8b456a0db765aa9482dfe0f868a8e8485acc62ad787a989f48927cfef40","observation_id":"07acc972-d739-4ca6-9174-83ae57525ee9","resolution":{"observed_at":"2026-08-09T20:47:40.657531Z","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":"pii/0888613","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T20:47:41.018245Z","title":"url: https://link.aps","venue":null,"work_id":"92351a0e-8c4b-4afd-a90f-504cd8d7bc73","year":2012},"citing_paper":{"arxiv_id":"2501.19281","last_updated":"2025-01-31T16:43:57Z","snapshot_observed_at":"2026-08-10T06:32:18.706641Z","submitted_at":"2025-01-31T16:43:57Z","title":"Statistical Physics of Deep Neural Networks: Generalization Capability, Beyond the Infinite Width, and Feature Learning","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-09T20:47:40.688933Z"},"links":{"citing_paper":"/paper/2501.19281"},"observation_digest":"sha256:1af7d480e0df928eb62dea3ad082d9d00dec73ef51b9f62a812257ad11c20d41","observation_id":"c047a3f9-f7bc-49b0-a0bf-44aada2c7250","resolution":{"observed_at":"2026-08-09T20:47:41.024793Z","resolver_source":"raw_fallback","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"}}],"paper":{"arxiv_id":"2501.19281","last_updated":"2025-01-31T16:43:57Z","latest_version":1,"primary_category":"cond-mat.dis-nn","snapshot_observed_at":"2026-08-10T06:32:18.706641Z","submitted_at":"2025-01-31T16:43:57Z","title":"Statistical Physics of Deep Neural Networks: Generalization Capability, Beyond the Infinite Width, and Feature Learning"},"reference_resolution":{"displayed":12,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":10,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":12},"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 12 of 12 outbound references and 1 inbound Pith citation observation for arXiv:2501.19281."}