{"as_of":"2026-08-21T01:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f8a1dc06ab3a87a301c43a8ec77ebb566eee20371c98c497460de43d23db17b2","coverage":[{"denominator":68,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":68,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T04:21:45.415002Z","state":"measured"},{"denominator":68,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":68,"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/2506.11357/citation-record","integrity":"/paper/2506.11357/integrity","json":"/paper/2506.11357/citation-record.json","paper":"/paper/2506.11357"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:21:46.171869Z","title":"B., and Misiakiewicz, T","venue":null,"work_id":"be982eab-cca1-4edf-b0b4-a1b966a7ece3","year":2023},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:43.879204Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:5fc17e55ea5a63123c5d6d2a9a58fec7dcab103ec49e3972c96ec6a2cf80a67a","observation_id":"02ce4aaa-b8f1-4dfc-8dbd-9dff8c3bd321","resolution":{"observed_at":"2026-08-07T04:21:46.175042Z","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":"2026-08-07T04:21:46.162799Z","title":"A convergence theory for deep learning via over- parameterization","venue":null,"work_id":"f25b1bbf-f997-41df-8273-8a3064b5a107","year":2019},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:43.964924Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:addfffdb1f182f7a01ff05cf2595c9219f630c165d5803b331908c6de06ee410","observation_id":"ded2f41e-fdbd-4085-b794-61e889a2d219","resolution":{"observed_at":"2026-08-07T04:21:46.165974Z","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":"2026-08-07T04:21:46.153531Z","title":"Thinking outside the ball: Optimal learning with gradient descent for generalized linear stochastic convex optimization","venue":null,"work_id":"c4e7ef5e-18cf-4f18-bc8a-39e7c4c792f3","year":2022},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:44.137285Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:44d08eea4812a98c685c3614107a2602d734918551e109c1c085c462371d697a","observation_id":"f02dc50e-a31c-48d7-a672-93d238bdf094","resolution":{"observed_at":"2026-08-07T04:21:46.156624Z","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":"1802.05296","last_updated":"2018-11-26T19:31:00Z","snapshot_observed_at":"2026-08-16T03:39:23.727567Z","submitted_at":"2018-02-14T19:38:07Z","title":"Stronger generalization bounds for deep nets via a compression approach","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.05296","snapshot_observed_at":"2026-08-07T04:21:44.242404Z","title":"Stronger generalization bounds for deep nets via a compression approach","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:44.242404Z"},"links":{"cited_paper":"/paper/1802.05296","citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:f7115fdf35bfea5c0dff7aa23abe86bb53a20dd916352006ecfcc1fc22dfca03","observation_id":"81bd6e7f-dc58-4ff0-8a1f-5e36dbc2c662","resolution":{"observed_at":"2026-08-07T04:21:44.242404Z","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":"2026-08-07T04:21:46.143718Z","title":"Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks","venue":null,"work_id":"2a156b69-a137-4618-932f-7cd985756479","year":2019},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:44.404648Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:fbfadb3cf21f395dbf91b579d8e40d5d4520358ab9dc6e52c96bce224525e3cd","observation_id":"991d6977-a409-43a3-9450-8ce23dad204e","resolution":{"observed_at":"2026-08-07T04:21:46.147023Z","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":"2026-08-07T04:21:46.134800Z","title":"S., Hu, W., Li, Z., Salakhutdinov, R","venue":null,"work_id":"5084cdc8-b0b5-4bbb-b441-718bb6257337","year":2019},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:44.513169Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:e93ea95a79f15bfbf3d33303c42a8a3b777dbcc2fd4ae2a6e5f4ca489d8241e9","observation_id":"5332a7b0-7059-4f42-a240-d6bd743d3bf2","resolution":{"observed_at":"2026-08-07T04:21:46.137830Z","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":"2026-08-07T04:21:46.125636Z","title":"B., Gheissari, R., and Jagannath, A","venue":null,"work_id":"b1bb2494-8db5-4cf2-a9f3-c155204de09d","year":2021},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:44.590081Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:52670085cc5913ab877c3f8f0d7e1a03bad3f4b52554f8f24fefb3d618d019a0","observation_id":"4ab4d3c0-006f-4ffa-b5b1-377b854c601f","resolution":{"observed_at":"2026-08-07T04:21:46.128950Z","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":"2007.11045","last_updated":"2020-07-21T19:08:21Z","snapshot_observed_at":"2026-07-06T09:40:42.537101Z","submitted_at":"2020-07-21T19:08:21Z","title":"On the Rademacher Complexity of Linear Hypothesis Sets","version":1},"cited_work":{"arxiv_id":"2007.11045","doi":null,"metadata_source":"pith","pith_arxiv_id":"2007.11045","snapshot_observed_at":"2026-08-07T04:21:45.614872Z","title":"On the Rademacher Complexity of Linear Hypothesis Sets","venue":"cs.LG","work_id":"aab9ca76-63dd-4cd6-9acc-872fef8c6d86","year":2020},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:44.688117Z"},"links":{"cited_paper":"/paper/2007.11045","citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:b2dee0187a96184d149821af19f9ec22fefbd6aa0b6883981ebd4b03d9a8b2ab","observation_id":"574c44fe-a603-4e54-88a9-6cd282d6e5fc","resolution":{"observed_at":"2026-08-07T04:21:45.620543Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:21:46.115630Z","title":"A., Suzuki, T., Wang, Z., Wu, D., and Yang, G","venue":null,"work_id":"eb2f1088-a459-482a-8ee9-6d1619e9b6c9","year":2022},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:44.814379Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:59918dd353c5d32764ca74ce383dd8100a3f3cf1d785d66c2f992f9b149e65d6","observation_id":"7c7343ac-f355-49ca-9c50-eefc259c02ad","resolution":{"observed_at":"2026-08-07T04:21:46.118724Z","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":"2026-08-07T04:21:46.106498Z","title":null,"venue":null,"work_id":"9088709f-f7af-413c-81a4-5d7aaa5cef72","year":2002},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:44.888964Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:8d63667bc88c2fc5fb7756d46f0279d0cc33f1791e84a31c33ffb9db2855f0f0","observation_id":"7c2a998e-3516-4526-8be6-75a73f3ddbaf","resolution":{"observed_at":"2026-08-07T04:21:46.109809Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:21:46.097162Z","title":"L., Foster, D","venue":null,"work_id":"cc81f5a8-757b-4532-882d-b5c7c0de25b6","year":2017},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:44.984096Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:ac2e1fb6fa880eceb3da8769b985c9adc5afc79dfeadc5147ff5fd8c502a5224","observation_id":"5c395177-4394-4dac-be5c-a2c0ce15a572","resolution":{"observed_at":"2026-08-07T04:21:46.100472Z","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":"2026-08-07T04:21:46.088135Z","title":"L., Harvey, N., Liaw, C., and Mehrabian, A","venue":null,"work_id":"787710b8-5448-4308-901d-6f795ab18316","year":2019},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.049318Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:3f58f3542cedd427b0f55a1b2bc053434dcddbab563ca8f10a7d64562823497d","observation_id":"bb7e8f11-e503-4e7b-a702-2ae7d688c7bf","resolution":{"observed_at":"2026-08-07T04:21:46.091222Z","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":"2026-08-07T04:21:46.079128Z","title":"Stability of stochastic gradient descent on nonsmooth convex losses","venue":null,"work_id":"e10b733a-8568-44c2-8baa-6f13f0291e8c","year":2020},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.141995Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:96e9e421685ec1f09f2822edc17bea29ee9559e17f3c3c2c2fa240a280e5a23f","observation_id":"2eafb663-1176-4ef8-b270-19d479d0aa4f","resolution":{"observed_at":"2026-08-07T04:21:46.082334Z","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":"2026-08-07T04:21:46.069600Z","title":"Reconciling modern machine-learning practice and the classical bias–variance trade-off","venue":null,"work_id":"a78bbaca-c74b-425f-b77b-d3f73bbfc621","year":2019},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.197522Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:43da4f6467d0ad877ed0440d7341bc92a38b751c000b03f13ea6242af5be193d","observation_id":"b7464057-c6c4-4ddd-adf4-82c46f4238ab","resolution":{"observed_at":"2026-08-07T04:21:46.072750Z","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":"2026-08-07T04:21:46.060786Z","title":null,"venue":null,"work_id":"17abbe0d-54df-4589-9fcd-83a8ec759255","year":2022},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.251201Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:5c5686a90e21ce34ceafd01f302a24000fa7a760ff88ba2bf10aa73293783024","observation_id":"06f433dc-7f57-443c-ad29-76610796fcd5","resolution":{"observed_at":"2026-08-07T04:21:46.063593Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:21:46.051041Z","title":"and Elisseeff, A","venue":null,"work_id":"968a53da-f54d-4765-960c-74e5a2397c9d","year":2002},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.254459Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:e5b43656ec194648acd8430a0c668f2fe1ff0888ad71f59fd0cb33b7ee45c950","observation_id":"6eecc35d-9bb9-44e0-a10c-8327998917bb","resolution":{"observed_at":"2026-08-07T04:21:46.054992Z","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":"2026-08-07T04:21:46.039351Z","title":"and Gu, Q","venue":null,"work_id":"cb7411a4-70b2-4214-addc-4800abfd7841","year":2019},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.257632Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:ba764bee4cabc684d30504e80854194887f68e8a3078b9042b78b4f8586cb488","observation_id":"3840f153-3be7-4049-8bb9-0383cbaea734","resolution":{"observed_at":"2026-08-07T04:21:46.042490Z","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":"2026-08-07T04:21:46.029836Z","title":"and Papailiopoulos, D","venue":null,"work_id":"7468dae0-d306-4424-b382-01d30ffcea01","year":2018},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.260907Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:e94b5b0dd4a913b0b2d307c0224bfa9a1994d546fda480f5b909825f7d47540c","observation_id":"4f548245-21bc-4e69-861f-fbab42e73ea4","resolution":{"observed_at":"2026-08-07T04:21:46.033212Z","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":"2102.11535","last_updated":"2021-03-16T00:59:19Z","snapshot_observed_at":"2026-08-16T18:43:41.683427Z","submitted_at":"2021-02-23T07:50:44Z","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.11535","snapshot_observed_at":"2026-08-07T04:21:45.264027Z","title":"Neural architecture search on imagenet in four gpu hours: A theoretically inspired perspective","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.264027Z"},"links":{"cited_paper":"/paper/2102.11535","citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:360a69db461b5e4047c082076a49facc6205b8e95fce8eeec30da6ea13591e72","observation_id":"d559aeb8-7f9b-4771-bb3a-f379e06152c3","resolution":{"observed_at":"2026-08-07T04:21:45.264027Z","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":"2026-08-07T04:21:46.017298Z","title":"M., and Weng, T.-W","venue":null,"work_id":"4e0ed449-cf58-4c98-8970-3e43c59b4d06","year":2023},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.267776Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:e8dd59617b6c15f22575e05ac2de957d5cf1ec212772f0633f6c948c13319355","observation_id":"7e5cc747-6504-4e19-91d8-47b056a3cd77","resolution":{"observed_at":"2026-08-07T04:21:46.021259Z","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":"2026-08-07T04:21:46.007308Z","title":"and Bach, F","venue":null,"work_id":"81256802-8488-4531-bc44-2645be4044f6","year":2020},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.270712Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:6ddf8718c50439f7075f9306f2745e3389476c29833aff06862ee2aeebbbdd8a","observation_id":"525896d1-206c-42ff-89eb-80857962bb07","resolution":{"observed_at":"2026-08-07T04:21:46.010412Z","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":"2026-08-07T04:21:45.997029Z","title":"Neural networks can learn representations with gradient descent","venue":null,"work_id":"0a8e8dcb-761a-4b63-9470-2178b48ebb54","year":2022},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.273562Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:16c41f028937bcd48be6ae8772c17ee33ce99fcda9a3ffc639ca5944cfba25f1","observation_id":"6c8d27d5-c9f1-45e1-aa12-882f49bce2de","resolution":{"observed_at":"2026-08-07T04:21:46.000572Z","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":"2026-08-07T04:21:45.986771Z","title":null,"venue":null,"work_id":"6da6e958-4142-43f5-8490-caf2d02c4b32","year":2023},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.276128Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:dddf9ea5d7ba9f6b0f411916893a947ebb9cfbfca6c986e35650ba4641c224fe","observation_id":"cb4a41a3-6b6d-4be1-8393-0e7a20ec9e17","resolution":{"observed_at":"2026-08-07T04:21:45.989802Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:21:45.976933Z","title":"Gradient descent finds global minima of deep neural networks","venue":null,"work_id":"a937c134-6455-42d4-8d5e-d9ab67ce5967","year":2019},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.279261Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:156be5b7fb759a7464ce207227282afda917b7695d67f29364e38c0f80916a23","observation_id":"0878e67a-2973-4e5d-aec9-94af102b9e8b","resolution":{"observed_at":"2026-08-07T04:21:45.980245Z","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":"1810.02054","last_updated":"2019-02-05T01:59:59Z","snapshot_observed_at":"2026-08-20T07:39:09.579125Z","submitted_at":"2018-10-04T04:47:47Z","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.02054","snapshot_observed_at":"2026-08-07T04:21:45.282264Z","title":"S., Zhai, X., Poczos, B., and Singh, A","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.282264Z"},"links":{"cited_paper":"/paper/1810.02054","citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:9300e6bc5c1767f4814f7f6dd7d99bf2b77c608fb16effba875067f2f4d7c415","observation_id":"5c0baaaa-d934-454b-afda-47335a3d7c9c","resolution":{"observed_at":"2026-08-07T04:21:45.282264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.11008","last_updated":"2017-10-19T03:39:56Z","snapshot_observed_at":"2026-08-14T21:08:53.042410Z","submitted_at":"2017-03-31T17:56:41Z","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.11008","snapshot_observed_at":"2026-08-07T04:21:45.285475Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.285475Z"},"links":{"cited_paper":"/paper/1703.11008","citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:cf443d83f3afa2687e22cb038bd09c0a0bbfa7a21c3c4c9b88e785c633111ee8","observation_id":"1d8225cc-e45f-40a7-bc83-4e21920b1a29","resolution":{"observed_at":"2026-08-07T04:21:45.285475Z","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":"2026-08-07T04:21:45.965751Z","title":"S., and Bartlett, P","venue":null,"work_id":"667f354c-302c-488e-beb1-2bcbd095ed8f","year":2023},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.289049Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:21c9d2d1f70537d40f0999988a0e98e57f9127e99d5446bdd74da6fcdf3e0c13","observation_id":"e90e7e63-c689-46cf-b4d3-12a2b65f3c9e","resolution":{"observed_at":"2026-08-07T04:21:45.970074Z","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":"2026-08-07T04:21:45.955749Z","title":"D., Soudry, D., and Srebro, N","venue":null,"work_id":"f7bc47cd-d4bc-43ed-a541-ddf259311b8d","year":2018},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.291808Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:3f3610aeb5bdf467602e98430b169afcabc49a14f364167f5d286a9e722aa9d6","observation_id":"1a3ccdea-a044-4915-bb3c-fb85ae93d353","resolution":{"observed_at":"2026-08-07T04:21:45.958733Z","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":"2026-08-07T04:21:45.946441Z","title":"Train faster, generalize better: Stability of stochastic gradient descent","venue":null,"work_id":"f8f1f61a-0f5b-4ed4-85f0-0988735e3fca","year":2016},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.294595Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:33410e02568b121d7c524273dabc338eef61260967e1aa06572ae431d8f51961","observation_id":"50f250c9-ec5d-4053-b70c-a91e591e582d","resolution":{"observed_at":"2026-08-07T04:21:45.949560Z","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":"2404.03176","last_updated":"2025-05-07T20:19:27Z","snapshot_observed_at":"2026-08-19T11:04:00.617406Z","submitted_at":"2024-04-04T03:20:35Z","title":"Information-Theoretic Generalization Bounds for Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.03176","snapshot_observed_at":"2026-08-07T04:21:45.297531Z","title":"and Goldfeld, Z","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.297531Z"},"links":{"cited_paper":"/paper/2404.03176","citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:b92ed8ba18ff0279051e629e2ffb79ebe04a450d0fc0847728fe5ff6e85bdaf7","observation_id":"62a59e50-a156-45bd-98d2-bd5be611d41f","resolution":{"observed_at":"2026-08-07T04:21:45.297531Z","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":"2026-08-07T04:21:45.300887Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.300887Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:9d5f955b65ac3dae1f9365c91da48d5eb8040ef6915b47d895347fc657617461","observation_id":"3a3e1627-892e-4e17-9899-531aee3e24c2","resolution":{"observed_at":"2026-08-07T04:21:45.300887Z","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":"2026-08-07T04:21:45.303815Z","title":"Neural tangent kernel: Convergence and generalization in neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.303815Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:c424feb8a4e9bfd98efb2cdc1f56fdd5b028443abd89379dd3a57a389571d8c1","observation_id":"b6f1b237-024d-418c-8bea-4bf2da4810b3","resolution":{"observed_at":"2026-08-07T04:21:45.303815Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.04836","last_updated":"2017-02-09T20:38:16Z","snapshot_observed_at":"2026-08-15T20:45:29.277746Z","submitted_at":"2016-09-15T20:03:06Z","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.04836","snapshot_observed_at":"2026-08-07T04:21:45.306622Z","title":"S., Mudigere, D., Nocedal, J., Smelyanskiy, M., and Tang, P","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.306622Z"},"links":{"cited_paper":"/paper/1609.04836","citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:295acb4a9322b6103f1ba4de6a3ab6617baa17613d3150045cd2531f4ec8cf27","observation_id":"12800878-9aca-48e2-9619-11f475016cdb","resolution":{"observed_at":"2026-08-07T04:21:45.306622Z","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":"2026-08-07T04:21:45.924352Z","title":"Suprema of chaos processes and the restricted isometry property","venue":null,"work_id":"de1350ac-879d-4ebd-9c42-6bc4684691db","year":1904},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.309679Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:978cf29452344c6a43ff68f95ed170161576f8b16048d17ec26442c6efd17955","observation_id":"8861512f-610c-4904-ab71-90a64fa4fdc8","resolution":{"observed_at":"2026-08-07T04:21:45.927902Z","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":"2026-08-07T04:21:45.313256Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.313256Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:e64f3e35eecabac2ab3450f7e9bbb8bbe87418c55de0525bf7452e029ee8ecb7","observation_id":"f660e488-846e-4ab0-a966-b305da03f01c","resolution":{"observed_at":"2026-08-07T04:21:45.313256Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.00621","last_updated":"2020-02-29T03:36:22Z","snapshot_observed_at":"2026-08-14T17:22:04.224739Z","submitted_at":"2019-02-02T02:15:25Z","title":"On Generalization Error Bounds of Noisy Gradient Methods for Non-Convex Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.00621","snapshot_observed_at":"2026-08-07T04:21:45.316106Z","title":"On generalization error bounds of noisy gradient methods for non-convex learning","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.316106Z"},"links":{"cited_paper":"/paper/1902.00621","citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:3d5aba8a156b89aa96fbba60002f591fcc9bd89bcf06309a720c53e554cb5f83","observation_id":"704d6717-9c78-4c4f-944a-55c06a16d419","resolution":{"observed_at":"2026-08-07T04:21:45.316106Z","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":"2026-08-07T04:21:45.906226Z","title":"ridgeless","venue":null,"work_id":"7968f3ba-f569-4a6a-b9fa-a78624ffe251","year":2020},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.319146Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:db51f31eb5638e135e5cd4707e1db20cea5a67e3ec083e162cb7317bdb838593","observation_id":"e5e66956-6d47-441a-b48b-5b57553e4d97","resolution":{"observed_at":"2026-08-07T04:21:45.910781Z","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":"2026-08-07T04:21:45.894734Z","title":"On the multiple descent of minimum-norm interpolants and restricted lower isometry of kernels","venue":null,"work_id":"9b2ba8a4-4721-4de2-99db-33ddb562f5ac","year":2020},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.322131Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:f1944222751466cdbb1849947ff00f0bb3e505426cbcf2e75a15db553e5ac651","observation_id":"1cde994e-4508-4676-91bc-1de2b28001c9","resolution":{"observed_at":"2026-08-07T04:21:45.898555Z","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":"cs/0411099","last_updated":"2004-11-30T08:36:59Z","snapshot_observed_at":"2026-07-07T03:06:10.700436Z","submitted_at":"2004-11-30T08:36:59Z","title":"A Note on the PAC Bayesian Theorem","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"cs/0411099","snapshot_observed_at":"2026-08-07T04:21:45.325079Z","title":"A note on the pac bayesian theorem","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.325079Z"},"links":{"cited_paper":"/paper/cs/0411099","citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:8abf088871ec848dfab69a083d1ef8d1867160a95f9cdbbf999af45d86298357","observation_id":"a6cfe7cc-0d0a-438b-aa63-57a087384d02","resolution":{"observed_at":"2026-08-07T04:21:45.325079Z","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":"2026-08-07T04:21:45.883875Z","title":null,"venue":null,"work_id":"c172709f-4f56-498b-96c4-665f2f1b1a52","year":2021},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.328177Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:e54b4209bc2c74f3bda330ecfe3f29ebcf2d99035a5eeb6bdc76007e082938c8","observation_id":"1e259a30-2a89-4792-9982-07d2a1cac811","resolution":{"observed_at":"2026-08-07T04:21:45.887522Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:21:45.330934Z","title":"Foundations of machine learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.330934Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:53fd61ef070a07c89b5184e5916dcf3a51d9e5aea1b9c2a9bae4668d9ffdaed7","observation_id":"c74958f1-dc50-4ebf-989f-d6d99064332d","resolution":{"observed_at":"2026-08-07T04:21:45.330934Z","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":"2026-08-07T04:21:45.865917Z","title":null,"venue":null,"work_id":"5d616f9c-7a1f-4e6e-bf4c-73c48b53a417","year":2022},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.333900Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:5ffd55844b314c989ff0b16e6628658acbf2c598f5dc6c3692e3be7cce356a88","observation_id":"d842418c-dca8-449e-9110-cb62d2a0eda3","resolution":{"observed_at":"2026-08-07T04:21:45.869693Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:21:45.337003Z","title":"and Urbani, P","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.337003Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:e61897f00c6b88679f15cd52dcb41aa634fae761572cfd147ac478006f5a7e33","observation_id":"86cd2332-8c75-488e-891b-74f59ebef09c","resolution":{"observed_at":"2026-08-07T04:21:45.337003Z","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":"2026-08-07T04:21:45.855543Z","title":"and Zhong, Y","venue":null,"work_id":"3c117323-e318-4d87-88e0-05b9a0dd2af6","year":2022},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.339758Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:18608ac9d7bc5023caeb3e79c35f6701ef373ac14d93bb883760f2b226e31584","observation_id":"3a715bcc-4197-4fea-86e5-41e810e4e1a3","resolution":{"observed_at":"2026-08-07T04:21:45.859167Z","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":"2026-08-07T04:21:45.844277Z","title":"Generalization bounds of sgld for non-convex learning: Two theoretical viewpoints","venue":null,"work_id":"52889eb6-984a-4d31-9d56-2f7770a2049d","year":2018},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.342581Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:14d667b4b571993c6d859c9dadd5e3d4d2c11b910bd83f59e641b688029db6b1","observation_id":"bc76c483-23ea-4f89-9880-de189663b8c8","resolution":{"observed_at":"2026-08-07T04:21:45.848012Z","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":"2026-08-07T04:21:45.834472Z","title":"K., Khisti, A., and Roy, D","venue":null,"work_id":"c490f76d-b0ba-47ab-b062-898ba542a598","year":2019},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.345504Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:f670e04e10e9f5094e1ed7200fa0e51ce9450f9d61417175ed1a4559f74c0d7e","observation_id":"198a3c8c-63cc-4413-a230-82f2a5cd529f","resolution":{"observed_at":"2026-08-07T04:21:45.837947Z","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":"2026-08-07T04:21:45.823984Z","title":"K., Haghifam, M., and Roy, D","venue":null,"work_id":"92bb2132-3c6a-4320-9019-84d6d084d7ba","year":2021},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.348501Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:b62eaba0c89fc228891e478762a0360602026cf9edabad626613a144aef180d3","observation_id":"8a1c74b7-755b-40d3-a0d2-b2cfcca5c1ca","resolution":{"observed_at":"2026-08-07T04:21:45.827342Z","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":"1412.6614","last_updated":"2015-04-16T18:48:31Z","snapshot_observed_at":"2026-08-14T23:06:39.936635Z","submitted_at":"2014-12-20T06:52:25Z","title":"In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6614","snapshot_observed_at":"2026-08-07T04:21:45.351480Z","title":"In search of the real inductive bias: On the role of implicit regularization in deep learning","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.351480Z"},"links":{"cited_paper":"/paper/1412.6614","citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:54f9f395758756b5fb7cd2d4754c24e489ecb367c6e096b6a2b1835bcc7cba1a","observation_id":"1dcda37f-49f9-410c-933c-9ff5e8ed3c35","resolution":{"observed_at":"2026-08-07T04:21:45.351480Z","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":"2026-08-07T04:21:45.813171Z","title":"Norm-based capacity control in neural networks","venue":null,"work_id":"7053dacd-373d-4d3c-98d7-891a1d9438c6","year":2015},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.354964Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:7cdfc60ec280e92fa859e646ec9d0871c45a140acbb647a881fa561a1f732043","observation_id":"214aea65-28e2-4daa-b18a-8b8dc3c266e8","resolution":{"observed_at":"2026-08-07T04:21:45.817133Z","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":"2026-08-07T04:21:45.801954Z","title":"Exploring generalization in deep learning","venue":null,"work_id":"7af3c6e9-2bce-43e9-8390-6481afb55b52","year":2017},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.358053Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:453a4328f63432425da133a4c0af61ca195b8f6f2fef2c6e8911828789b799b4","observation_id":"fb23254b-261e-4f5c-b611-da04445c4d82","resolution":{"observed_at":"2026-08-07T04:21:45.805995Z","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":"1707.09564","last_updated":"2018-02-23T22:30:45Z","snapshot_observed_at":"2026-08-14T20:44:26.541416Z","submitted_at":"2017-07-29T22:36:35Z","title":"A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.09564","snapshot_observed_at":"2026-08-07T04:21:45.361410Z","title":"A pac-bayesian approach to spectrally- normalized margin bounds for neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.361410Z"},"links":{"cited_paper":"/paper/1707.09564","citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:9098aef43f04b00aa953e4a7864985556ee73f308b4bec847090816634c9c5c9","observation_id":"b0279c73-7001-4f95-bf9a-6d8a1b17c955","resolution":{"observed_at":"2026-08-07T04:21:45.361410Z","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":"2026-08-07T04:21:45.792312Z","title":"The role of over- parametrization in generalization of neural networks","venue":null,"work_id":"0d8b6791-db8d-4b28-a561-c64b4a4a97d4","year":2019},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.365006Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:5833f226de2a9a1b6795808514750170421fc2be319bc00e8829063abd9adfbd","observation_id":"7bfec5ce-90fa-4d28-95f2-7542542edb0f","resolution":{"observed_at":"2026-08-07T04:21:45.795772Z","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":"2026-08-07T04:21:45.781931Z","title":null,"venue":null,"work_id":"567ba426-5a02-4de6-a87c-8ce1e3ff539d","year":2021},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.368529Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:b421637b2c0cd535207bec1446633ac1eb84b9486339d40cd3be21ae7f5eefd8","observation_id":"ba5f6b90-d629-439c-b13a-9a7610b7b139","resolution":{"observed_at":"2026-08-07T04:21:45.785399Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.12446","last_updated":"2023-02-09T22:05:06Z","snapshot_observed_at":"2026-08-20T07:36:55.005466Z","submitted_at":"2022-04-26T17:05:57Z","title":"Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GD","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.12446","snapshot_observed_at":"2026-08-07T04:21:45.371585Z","title":"E., Haddadpour, F., Karbasi, A., and Kalogerias, D","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.371585Z"},"links":{"cited_paper":"/paper/2204.12446","citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:fe8e991d9a19eb2cec9d3e533341533aa550e3b8388a284fa28c0aeed6eba258","observation_id":"f3407976-de60-4078-a9f9-d9b08a0d3eef","resolution":{"observed_at":"2026-08-07T04:21:45.371585Z","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":"2026-08-07T04:21:45.771679Z","title":"Generalization guarantees for neural architecture search with train-validation split","venue":null,"work_id":"863c221f-7863-4144-8dc3-92faf1994f55","year":2021},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.374917Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:2a2a82a25b0f46c7c82fca73c1baead3908eb9fcb2dc71f8992d667d805fdd6e","observation_id":"73d19ffc-db37-4ddf-9117-ef1567de21cc","resolution":{"observed_at":"2026-08-07T04:21:45.775299Z","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":"2026-08-07T04:21:45.378107Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.378107Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:1e6c0dadf908966965f8fcab5816cc110a98bd09612cdd80d3d9359d812d3037","observation_id":"122f9b08-5e91-42e5-bc7f-206c9fb5968a","resolution":{"observed_at":"2026-08-07T04:21:45.378107Z","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":"2026-08-07T04:21:45.754944Z","title":"Generalization error bounds for noisy, iterative algorithms","venue":null,"work_id":"147ea950-3d49-4073-8f8e-8b4dbd6ed336","year":2018},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.381111Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:53be123ab8c99fa2e00abfdc500e2f88182b4dd19705ffafb23a989ff59a898e","observation_id":"3cdca47c-dbe0-4e9f-b9eb-5b755d2382cc","resolution":{"observed_at":"2026-08-07T04:21:45.758393Z","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":"2026-08-07T04:21:45.743951Z","title":"and Zou, J","venue":null,"work_id":"d09e84f7-724e-4f93-af21-ee9cbf3bb08c","year":2016},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.383919Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:b0d7939375041794409dd3451746af25281377971801877ca5a46307dfcd773f","observation_id":"8ef0bf33-015f-4a95-9f6f-bf8965b49558","resolution":{"observed_at":"2026-08-07T04:21:45.747157Z","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":"2026-08-07T04:21:45.733697Z","title":"How do infinite width bounded norm networks look in function space? In Conference on Learning Theory, pp","venue":null,"work_id":"eddfcdd7-e838-4ef7-90ac-029b4d52d0ea","year":2019},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.387065Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:f7790460a2594628bf2adc6298a41693ba66fdbc188c5ec1d238a27d2b612c47","observation_id":"45d8ade6-d35c-4da9-befe-1d5d132a45ef","resolution":{"observed_at":"2026-08-07T04:21:45.737072Z","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":"2026-08-07T04:21:45.723262Z","title":"S., Gunasekar, S., and Srebro, N","venue":null,"work_id":"ec587569-ac72-4cc2-a458-7c3177c34431","year":2018},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.390183Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:8b49a96ef9c01b4abbbef6b5cea0a879211a55ec155263b7b3815ccf1ca68437","observation_id":"0db4d8ca-7764-42b0-8ab1-0d3cf7f1a157","resolution":{"observed_at":"2026-08-07T04:21:45.726544Z","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":"2026-08-07T04:21:45.713080Z","title":"and Christmann, A","venue":null,"work_id":"c10bee6e-b332-41f6-934c-e289091e6341","year":2008},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.393425Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:dabf47d100053f3e0e5c03a5077c3972df49c0779f35e59f0f751999d4d7c8f5","observation_id":"30afc771-6e87-4fb0-9f74-5b2557b7d5f9","resolution":{"observed_at":"2026-08-07T04:21:45.716420Z","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":"2026-08-07T04:21:45.703313Z","title":"and Chervonenkis, A","venue":null,"work_id":"bafb8546-7e76-4f19-8bbd-a90e870ad988","year":1971},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.396195Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:fd5da099abe62f6d5aeda69020630fc3150dc4fa1d7231804f5a2dc7ed37fffb","observation_id":"ec1c99a2-fd27-4749-a6f5-6840edca0834","resolution":{"observed_at":"2026-08-07T04:21:45.706620Z","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":"2026-08-07T04:21:45.398921Z","title":"High-dimensional probability: An introduction with applications in data science, volume 47","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.398921Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:ff1b0eba28eabc8137048dd926876281cba80cd6ee7e70d264d005a36d19e6d2","observation_id":"70721486-663f-42dd-b3c2-4b93cb9a63d3","resolution":{"observed_at":"2026-08-07T04:21:45.398921Z","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":"2026-08-07T04:21:45.683812Z","title":null,"venue":null,"work_id":"07264151-60c9-4d47-bdb0-326b5a2b5074","year":2023},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.401743Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:3bbe62f5ac2eabcc8139bc8c6729d6593a5b2dd4ae91b4100b864c7da8be5b39","observation_id":"b0f5326a-3526-4ef8-9856-3705868674ca","resolution":{"observed_at":"2026-08-07T04:21:45.687433Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:21:45.672150Z","title":"and Zhu, Y","venue":null,"work_id":"b15e66ed-bf61-48df-a144-acbff9f234b4","year":1947},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.404622Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:cad123b43d3f3ab2c4ba27253916a5e9ec82bf1eaad97fb7f3b945c0ec80f5a7","observation_id":"cbb6de04-dd05-4b20-8a24-ab1b7616ea95","resolution":{"observed_at":"2026-08-07T04:21:45.675261Z","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":"2026-08-07T04:21:45.661932Z","title":"and Raginsky, M","venue":null,"work_id":"e307b0c0-aef7-443b-bf96-b2d29f1988c6","year":2017},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.408258Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:34a6896bb458348ef3c5adb72ef34d39be7bf6f38c3f8746a5bdf0b934142621","observation_id":"31ac1225-c2bc-4f3c-8bd1-066ce7d757c3","resolution":{"observed_at":"2026-08-07T04:21:45.665453Z","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":"2026-08-07T04:21:45.649458Z","title":"nX i=1 KT (zi, zi; S) # + L2T + L2βT 2 r 2n log 2 δ′ ! + δ′nL2T Take δ′ = 1 n, ln E S e Pn i=1 KT (zi,zi;S) ≤ E S","venue":null,"work_id":"bf738a58-c5ea-412d-ab28-3ac9d5d6c22f","year":2021},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.411145Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:0d332a7613ce6d4843ab017577f7095dd06435c28c6f5494bfd50bf7da35bab3","observation_id":"bdf0b6be-c120-443b-81b5-8abc08591ead","resolution":{"observed_at":"2026-08-07T04:21:45.655197Z","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":"2026-08-07T04:21:45.639461Z","title":"Theorem G.2 (Theorem 6.1 in Bietti et al","venue":null,"work_id":"a3e2ac02-80fe-49c5-be88-223e78da2c91","year":null},"citing_paper":{"arxiv_id":"2506.11357","last_updated":"2025-06-12T23:17:09Z","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T04:21:45.415002Z"},"links":{"citing_paper":"/paper/2506.11357"},"observation_digest":"sha256:4d3d4d1c1a04888eac1f1a237606833913ab66e85d9fd8e0825693970929c39c","observation_id":"b2fdb6d2-51cf-45d4-ab5a-80ba48624bb6","resolution":{"observed_at":"2026-08-07T04:21:45.642485Z","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":"2506.11357","last_updated":"2025-06-12T23:17:09Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T23:18:02.630901Z","submitted_at":"2025-06-12T23:17:09Z","title":"Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel"},"reference_resolution":{"displayed":68,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":25,"verified_exact":1,"verified_fuzzy":42},"total_outbound_references":68},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 0 inbound Pith citation observations for arXiv:2506.11357."}