{"as_of":"2026-08-04T22:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:876f750a6f50f029f5e7c9803ebd0d720951f4929eb62b523231efccd3f677ef","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-16T15:05:53.247993Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+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":"2026-08-01T15:35:24.756492Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.06597","snapshot_observed_at":"2026-08-01T15:35:24.756492Z","title":"Understandingandinversedesign of implicit bias in stochastic learning: a geometric per- spective","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18422","last_updated":"2026-07-20T18:12:00Z","snapshot_observed_at":"2026-08-01T15:35:24.196798Z","submitted_at":"2026-07-20T18:12:00Z","title":"PAC--Bayes Bounds on Quotient Parameter Spaces: Geometry-induced Implicit-Bias Priors","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T15:35:24.756492Z"},"links":{"cited_paper":"/paper/2601.06597","citing_paper":"/paper/2607.18422"},"observation_digest":"sha256:b12da6eef49fc465ab68979fb61a1c8343dd58ca66842b0dd736d902849de378","observation_id":"5e63aa1f-f676-45b0-8a7e-0acb0f9824dc","resolution":{"observed_at":"2026-08-01T15:35:24.756492Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2601.06597/citation-record","integrity":"/paper/2601.06597/integrity","json":"/paper/2601.06597/citation-record.json","paper":"/paper/2601.06597"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Reconciling modern machine- learning practice and the classical bias–variance trade-off.Proceedings of the National Academy of Sciences, 116(32):15849–15854, July 2019","venue":null,"work_id":"3e9f5eb4-17d5-4bf7-8092-774a928442ef","year":2019},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:cc2e0d1a8db9561709d70ab5e85e2ab9e685f036984e83a81ddf1be763a554f4","observation_id":"4558508c-0486-4dc1-a2ea-4e6d18706f9f","resolution":{"observed_at":"2026-05-16T15:08:02.598095Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"In search of the real inductive bias: On the role of implicit regularization in deep learning","venue":null,"work_id":"0f4a961f-3f3c-4386-a667-980dd5b82346","year":2015},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:891b9850b727487d651c670b421dccd6c1ab0360aeeda9592906411420eb9cb5","observation_id":"b8b698cf-7b91-4d42-b048-f0d18f5dbb77","resolution":{"observed_at":"2026-05-16T15:08:02.595068Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"The implicit bias of gradient descent on separable data.Journal of Machine Learning Research, 19(70):1–57","venue":null,"work_id":"cf458039-be34-48ee-a020-773c26d3da3e","year":2018},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:0660889eea73b2684aef9053894bde0fa963fbfe21be956b39a56f0bdf2f9452","observation_id":"2b470e5e-b260-4e06-824e-cc18085c0dd7","resolution":{"observed_at":"2026-05-16T15:08:02.606186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"On the implicit bias in deep-learning algorithms.Communications of the ACM, 66(6):86–93","venue":null,"work_id":"697e30c1-fff5-4bb3-ab35-33844bc5b9d5","year":2023},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:a51173634cfcb27fdc198b8e2b34edd58e2348a20daa94d979324f16dcc70187","observation_id":"f5971906-6674-4a14-9826-8a1e1568cf61","resolution":{"observed_at":"2026-05-16T15:08:02.592246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"The implicit bias of gradient descent on nonseparable data","venue":null,"work_id":"98b8a513-cf64-4e76-8d4a-61d2ecf7f53c","year":2019},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:aae298adee483606b50352ee19a4e2b7861d96c70cbd480ff332ad96e6a1e930","observation_id":"31f0d703-195b-4729-93f4-de7683be4a8b","resolution":{"observed_at":"2026-05-16T15:08:02.603301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Gradient descent maximizes the margin of homogeneous neural networks","venue":null,"work_id":"d1acd9fa-32b4-4a77-8a96-697e0e528df2","year":2020},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:ffc284bad6a95baaca17b87e62d6ea5790c6075509eb2f9e0f8f189e8281f0f4","observation_id":"8f5d545c-3913-45da-92d2-13309c4fb49a","resolution":{"observed_at":"2026-05-16T15:08:02.625224Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Schapire, and Matus Telgarsky","venue":null,"work_id":"82e0ac5b-2a03-42d7-b122-a40064721de0","year":2020},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:dceaa1c7fad03d4c4f2af450eb007d6d32f905b200437ce075689e9765edaa71","observation_id":"316545b6-779a-42f0-a689-95de3460aea2","resolution":{"observed_at":"2026-05-16T15:08:02.622400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Implicit bias of gradient descent for logistic regression at the edge of stability","venue":null,"work_id":"8d274277-a55f-404b-8fd3-48992a61a685","year":2023},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:f92de7117559368140a04ba3699ef843dbca2305d5d4df5c66a43b000f594c5b","observation_id":"4fbcfe1c-9afe-447a-ba3c-65ef67c2b1a7","resolution":{"observed_at":"2026-05-16T15:08:02.620101Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"The implicit bias of gradient descent on separable multiclass data","venue":null,"work_id":"34b1c052-0938-402b-8466-111e67bb6c84","year":2024},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:80b179874445f57addb1b700d416a5419f8626e237350fb7baca78784f6b330a","observation_id":"78b0d7df-1f9d-43cd-8a67-4709a350cebb","resolution":{"observed_at":"2026-05-16T15:08:02.617272Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"A unifying view on implicit bias in training linear neural networks","venue":null,"work_id":"b34ae13b-7fad-4f7a-b79e-4a5c9e407b25","year":2021},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:cf7428ecaebb0a9189d7d5e4d9f2e303d4705428146781b36739faa71645ad08","observation_id":"3bb0058a-a060-49b0-9cad-838360c67c7c","resolution":{"observed_at":"2026-05-16T15:08:02.614504Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Characterizing implicit bias in terms of optimization geometry","venue":null,"work_id":"649902dc-c04d-48fd-b21e-9503d8242d42","year":2018},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:d0fc5cb60c5d26b5f76094168a4852a42a62f82784d9da197cf1f2eb63bb9a20","observation_id":"99386dc1-7100-4111-bda2-a581f85a61db","resolution":{"observed_at":"2026-05-16T15:08:02.600709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Implicit regularization in deep matrix factorization","venue":null,"work_id":"c8c5571c-64aa-46cf-a920-df1a0860bf0c","year":2019},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:89e49a0632dbe91c9e59f890c9ac19ead32d40632135f05ea58155b43825e256","observation_id":"02c21d1f-2db7-4805-bfe6-ff13c63a4618","resolution":{"observed_at":"2026-05-16T15:08:02.611803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Implicit regularization of discrete gradient dynamics in linear neural networks","venue":null,"work_id":"dc774994-4f95-4603-bebc-1b4c8afe8c10","year":2019},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:37e5d11075c2f6ae7f209822b38138621c4c213745268b59ab39aff373e432ef","observation_id":"085625dc-2737-419c-8ec4-eb894e915c85","resolution":{"observed_at":"2026-05-16T15:08:02.608879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Gradient descent for deep matrix factorization: Dynamics and implicit bias towards low rank.Applied and Computational Harmonic Analysis, 68:101595","venue":null,"work_id":"fde915e7-261a-4503-a884-07f205ec185a","year":2024},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:34b13b784d6e870b9031ce6988a01d271cabfc815112f5671ea1308c36402f6e","observation_id":"ff9218a9-43f9-47de-a398-ad86cde80575","resolution":{"observed_at":"2026-05-16T15:08:02.589672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Dynamics in deep classifiers trained with the square loss: Normalization, low rank, neural collapse, and generalization bounds.Research, 6:0024","venue":null,"work_id":"a9c26d5b-f426-488e-a417-5cff192c65a4","year":2023},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:46f0d331133f9071fa24a1ec521d08de27a1963ec08a75fdc8385fe209d3a63a","observation_id":"b3019ee4-68be-451f-8836-4efb1adb18ed","resolution":{"observed_at":"2026-05-16T15:08:02.587140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Implicit regularization in deep learning may not be explainable by norms","venue":null,"work_id":"83692395-5ea9-4580-a7f1-341a8084b1fd","year":2020},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:6893bab2c357bcd9419b226c63ab257152f277d177bda88a60347ed707a6ed0a","observation_id":"f5fc438e-39f0-476b-a5ba-70f8bead96f1","resolution":{"observed_at":"2026-05-16T15:08:02.584460Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"What happens after SGD reaches zero loss? – a mathematical framework","venue":null,"work_id":"5d4c2e05-841e-4932-8b93-55f16121c93e","year":2022},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:f9e794e74d851c3b1ad4b29c5c8761377a5f9e464e97b954dfd36220a45dff97","observation_id":"c343e0f9-10e3-4d04-b4b5-d40e3b7120a9","resolution":{"observed_at":"2026-05-16T15:08:02.581811Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Implicit bias of deep linear networks in the large learning rate phase","venue":null,"work_id":"0a82e9f5-8a53-49ee-aab9-1cf016ab8afa","year":2020},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:ff465430b3d8c5421a884af6f669be886fe402ca486ebb67542d419dea2ca868","observation_id":"db58c945-b475-4e8e-9f58-d622c1d7ed19","resolution":{"observed_at":"2026-05-16T15:08:02.579688Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"d82dc083-7edc-40bf-8ea9-082b9d539528","year":1993},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:19bef5e8d016a4cecd548e717791c4e86be45899cdb120736a65ff6471400b30","observation_id":"f789ccd1-faf8-445d-895f-197ac5fc4eb5","resolution":{"observed_at":"2026-05-16T15:08:02.577093Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"PhD thesis, Toyota Technological Institute at Chicago","venue":null,"work_id":"ae783734-1c2c-4313-8612-7e8058a1c841","year":2017},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:3224c436b7ab3ea02d9a3d323b5555d1d3ad1e7cd67db0012769dcae3860ec0c","observation_id":"53b36b0a-25d2-4fc1-8995-91116b1869bd","resolution":{"observed_at":"2026-05-16T15:08:02.574658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Implicit bias of gradient descent for wide two-layer neural networks trained with the logistic loss","venue":null,"work_id":"0d19965d-45d2-49a9-b8e9-c44c50e253d8","year":2020},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:ff497e3c1d2e8dec89f841fae543e649364d15eec3889268a9d3039fa16f54ac","observation_id":"2d65080c-af37-4488-87c0-846d7e7d17d6","resolution":{"observed_at":"2026-05-16T15:08:02.572348Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Stochastic gradient descent as approximate Bayesian inference.Journal of Machine Learning Research, 18(134):1–35","venue":null,"work_id":"14091824-dfef-4861-b6f3-3b00e3de6a0f","year":2017},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:45c0832c555acce219bb753a5a1bc1ea54357847bb6d9f4e6d5f7f1f67165bae","observation_id":"e4261c9f-64c7-4070-a111-c3e45a154e54","resolution":{"observed_at":"2026-05-16T15:08:02.569541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Stochastic modified equations and adaptive stochastic gradient algorithms","venue":null,"work_id":"aef35817-1348-4337-aecc-b780779fa065","year":2017},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:fb2b105be1c8b1f44e94acff4b704151f2d6a3ebb7d00a7cc5836ef0da439a77","observation_id":"2214ca9e-5a86-4a33-9946-b44d62eab83e","resolution":{"observed_at":"2026-05-16T15:08:02.567042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Stochastic modified equations and dynamics of stochastic gradient algorithms I: Mathematical foundations.Journal of Machine Learning Research, 20(40):1–47","venue":null,"work_id":"29d3e65d-fc70-452c-94f6-7a09fb81d271","year":2019},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:1b034a7f7ad6a144d86f2125a70bb833ef15a1d843c68799bfbc0701b17d3dd7","observation_id":"f6ce314b-b44a-4ae9-8f73-915192804c3a","resolution":{"observed_at":"2026-05-16T15:08:02.564206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Theory of deep learning IIb: Optimization properties of SGD","venue":null,"work_id":"1aff0dc3-99dd-4a47-812c-b53cd74eb224","year":2018},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:270da675bcedccd3ff818cbf46f9794900632ffe3c919a6f173781ead0039f3e","observation_id":"77c06635-d19e-4bbc-9ece-5121913c3542","resolution":{"observed_at":"2026-05-16T15:08:02.561294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"A Bayesian perspective on generalization and stochastic gradient descent","venue":null,"work_id":"5df14998-2921-4424-bd80-3237b7e78481","year":2018},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:2de76d56bca3a2b2367c537be5dd3a47335af80a605cdf871da121213669b236","observation_id":"c6864c4b-193b-437f-9112-f7d770fa5653","resolution":{"observed_at":"2026-05-16T15:08:02.558740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"A diffusion theory for deep learning dynamics: Stochastic gradient descent exponentially favors flat minima","venue":null,"work_id":"b8e1dfe8-5dbf-4994-ae79-c3222ea556ef","year":2021},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:6d0cabc1bca1da5a01d3f324474501e700ce9db13cbc0df50f3281345c9f03bd","observation_id":"14410bd6-8a0d-4faa-beb4-4e204cc1f7bf","resolution":{"observed_at":"2026-05-16T15:08:02.555932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Topological invariance and breakdown in learning","venue":null,"work_id":"b09adfb7-849d-44c5-9ff5-e228f7345cb2","year":2025},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:3f3feea55d816f48db0e4be4dd14cdfcbad18650674ac0a496153c2c77aaf266","observation_id":"3eb89ed5-d1d5-4dd3-a05f-af4e269ae4ff","resolution":{"observed_at":"2026-05-16T15:08:02.550138Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Neural thermodynamics: Entropic forces in deep and universal representation learning","venue":null,"work_id":"01dcdcce-cbe2-4502-b5ec-96f198728178","year":2025},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:1d0fd9b58f98fd742d5dc85664c76142d7f53c7fc699a5bc09a98df947729605","observation_id":"77982a00-1354-4ce0-8aed-31e4e8302094","resolution":{"observed_at":"2026-05-16T15:08:02.552804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Parameter symmetry and noise equilibrium of stochastic gradient descent","venue":null,"work_id":"342bb509-2747-4cf9-83e1-84e1e75a92d6","year":2024},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:62064d7c0c5141e26c771c6d0287627d17335a99c2c818e2ea5d671fd6a90f00","observation_id":"4654c433-abe0-45e4-b1cf-30347639d5cf","resolution":{"observed_at":"2026-05-16T15:08:02.547522Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Symmetry induces structure and constraint of learning","venue":null,"work_id":"b53251a1-87ac-416c-bad2-63267f422fb9","year":2024},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:c289a0020142bada6340645417b179926f3fd823e8ce5c63c1a381328b9e1391","observation_id":"31fef6e4-7465-498f-bb06-710e9364dcad","resolution":{"observed_at":"2026-05-16T15:08:02.509146Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Parameter symmetry potentially unifies deep learning theory","venue":null,"work_id":"de68cc69-5796-41b5-9ccb-97e9eacb504b","year":2025},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:94db499f1744a94300096d8c6c8b6f70f4ee211eb6c4f886200b3ea9014f011b","observation_id":"2eeb9125-dc46-4885-924f-2a9d21d40ebf","resolution":{"observed_at":"2026-05-16T15:08:02.544562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Cambridge University Press, Cambridge, UK","venue":null,"work_id":"222935bd-9bd4-417a-b8cc-810c57b95909","year":2009},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:a4ccf35a3c02a274c9be9ae574933da1f134a2822d586b1b50ffa9f2d4a35b13","observation_id":"580e12b0-955a-4608-a809-084ba7cf9fc1","resolution":{"observed_at":"2026-05-16T15:08:02.541777Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"3f9cfe2a-376d-4588-99e0-52e062ad49c5","year":1989},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:069eed8f870ce882ba575f06384e05a49a096d0d917278b53fb45461ed412987","observation_id":"6987b6c4-bf7b-42e5-81f9-b6c7d9cfc096","resolution":{"observed_at":"2026-05-16T15:08:02.538988Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Intrinsic statistics on Riemannian manifolds: Basic tools for geometric mea- surements.Journal of Mathematical Imaging and Vision, 25(1):127–154","venue":null,"work_id":"75520993-6bfc-424f-a434-86a901f18529","year":2006},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:710cc3291d70c9d99852c460637127f0720cd646b8e465bdca823c57748d2c25","observation_id":"4da4b0d8-74db-4d59-9c4c-88725ecb8986","resolution":{"observed_at":"2026-05-16T15:08:02.536861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Intrinsic shape analysis: Geodesic principal component analysis for Riemannian manifolds modulo Lie group actions.Statistica Sinica, 20(1):1–100","venue":null,"work_id":"405d18bc-9fec-4af7-b80b-5b39db544d3b","year":2010},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:c948cb4c342aa70e9ee5716616531c68cfce106902f7e0ba40494aa51188057b","observation_id":"fcb00998-cd8d-4d4f-8e2d-ce55776d1f4f","resolution":{"observed_at":"2026-05-16T15:08:02.534005Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Classical statistical mechanics of constraints: A theorem and applications to polymers.The Journal of Chemical Physics, 69(4):1527–1537","venue":null,"work_id":"933174d5-7c50-4410-a757-e3716b3955f1","year":1974},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:e804f76ddea2c61b932d226b3499ac7c16604fba8f175e13e883438d32c22b97","observation_id":"575f0f12-72b3-48c6-9280-facee61593db","resolution":{"observed_at":"2026-05-16T15:08:02.531355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Imperial College Press, London","venue":null,"work_id":"85561317-98e9-4b5f-a894-5e3972893f43","year":2010},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:3bd389d969a4561f23c7e6bb69507c852b0f39e402f9c124adb5804c8047043f","observation_id":"82af91f5-e329-4acc-a3d1-ceb71baffd8c","resolution":{"observed_at":"2026-05-16T15:08:02.528529Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Numerical-integration of Cartesian equations of motion of a system with constraints – molecular-dynamics of N-alkanes","venue":null,"work_id":"38cf97ad-d6bd-4c2b-817d-945f95054e8b","year":1977},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:93eeb8af59b0730aba8d5c037951d767d855a2393f4e4860954742313f4472b1","observation_id":"8438e8fd-77ff-4e09-92c7-d79c46d1f4fa","resolution":{"observed_at":"2026-05-16T15:08:02.525460Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Riemann manifold Langevin and Hamiltonian Monte Carlo methods.Journal of the Royal Statistical Society: Series B, 73(2):123–214","venue":null,"work_id":"9a525732-26c5-4872-b74a-baec6e813c6b","year":2011},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:61920dca84684a7b8492b3ab87d695b03421fe2c20c72a61f50b458c05313d1c","observation_id":"a36f3954-7d41-4025-8770-b0b2d398447e","resolution":{"observed_at":"2026-05-16T15:08:02.522695Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Chrysos, YongtaoWu, RazvanPascanu, Philip Torr, andVolkan Cevher","venue":null,"work_id":"f83b6c01-9cda-423e-a478-78824da54649","year":2025},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:9c35abe1781c0f5906d52b8803e567efcc0376efe5ceed5710f2aae36e88a945","observation_id":"ff0827ef-dbf9-4c51-bb05-6711de059906","resolution":{"observed_at":"2026-05-16T15:08:02.517997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"A survey on deep matrix factoriza- tions.Comput","venue":null,"work_id":"727f6579-a8b8-43ee-b7e0-adc2e9b46a96","year":2021},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:541bb0589d2eeee09fad6ed0fb532f0bc7a12ae1c6b8a58f05e3864d7ebd8cca","observation_id":"9f0f507d-92f4-47fe-b7a9-5a445ac978bc","resolution":{"observed_at":"2026-05-16T15:08:02.515166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Springer, Berlin","venue":null,"work_id":"2d71825e-c465-43be-b0d0-2bd942442092","year":1969},"citing_paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-16T15:05:53.247993Z"},"links":{"citing_paper":"/paper/2601.06597"},"observation_digest":"sha256:a314ce6a85a22337d870d84e676e7639ae89bdf868686932b63fc5c92d075207","observation_id":"f310fd19-6810-47db-959f-eda548f39e1b","resolution":{"observed_at":"2026-05-16T15:08:02.512201Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2601.06597","last_updated":"2026-04-04T15:02:39Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-02T18:52:31.114238Z","submitted_at":"2026-01-10T15:33:09Z","title":"Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":2,"verified_exact":0,"verified_fuzzy":41},"total_outbound_references":43},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 1 inbound Pith citation observation for arXiv:2601.06597."}