{"as_of":"2026-08-08T13:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fa41ec9a8dee68dfe8685ab153474b79969f5e1b31fe3434ca54a3a209d90a93","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T10:05:57.917104Z","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":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-13T04:24:43.867063Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-20T06:53:22.890144Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"cited_work":{"arxiv_id":"2510.12249","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2510.12249","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Optimal regularization for performative learning","venue":null,"work_id":"75b50eef-03df-4920-ab6e-5624a1953743","year":2025},"citing_paper":{"arxiv_id":"2605.20105","last_updated":"2026-05-19T16:56:56Z","snapshot_observed_at":"2026-07-06T23:30:44.092395Z","submitted_at":"2026-05-19T16:56:56Z","title":"Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-20T06:53:16.925588Z"},"links":{"cited_paper":"/paper/2510.12249","citing_paper":"/paper/2605.20105"},"observation_digest":"sha256:9f622d165e81c3343227d9969699361f0e00e971119f6b371b40422ee029aed1","observation_id":"805f5a3f-2faa-4bb1-b792-2cd200b6b4b4","resolution":{"observed_at":"2026-06-02T02:03:33.830699Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2510.12249","snapshot_observed_at":"2026-07-13T04:24:43.867063Z","title":"arXiv preprint arXiv:2510.12249 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.09250","last_updated":"2026-07-10T10:01:11Z","snapshot_observed_at":"2026-08-08T02:18:28.425569Z","submitted_at":"2026-07-10T10:01:11Z","title":"Influence Diagnostics in High-dimensional M-estimation: Precise Asymptotics","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-07-13T04:24:43.867063Z"},"links":{"cited_paper":"/paper/2510.12249","citing_paper":"/paper/2607.09250"},"observation_digest":"sha256:71a72d5a6b8d44ec02b4dfa0a6f97fcd246bc10b2b2673180c141abfda247b75","observation_id":"55faa137-f003-4da0-9c2b-1d7e1d7365b0","resolution":{"observed_at":"2026-07-13T04:24:43.867063Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2510.12249/citation-record","integrity":"/paper/2510.12249/integrity","json":"/paper/2510.12249/citation-record.json","paper":"/paper/2510.12249"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:05:53.001947Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:53.001947Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:f7eabfa4367af293f0a3440e2279700fdcf5dcf84de9ca0a3a552f08c0a3ffae","observation_id":"47deaa1c-a798-49f5-b49d-9bb0e7670a47","resolution":{"observed_at":"2026-08-04T10:05:53.001947Z","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":"2026-08-04T10:05:53.083221Z","title":"Bartlett, Philip M","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:53.083221Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:346245a82d8a8f603a834932580bab7f398238c58b1246f6e8c3a263908691c5","observation_id":"eea53553-ddc5-47c0-9799-278b4a6fae90","resolution":{"observed_at":"2026-08-04T10:05:53.083221Z","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":"2026-08-04T10:05:53.172956Z","title":"Gaming helps! learning from strategic interactions in natural dynamics","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:53.172956Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:3b1369446a671756e885a64740d8e175e9a3b7a4054914341918411d1d34c66c","observation_id":"3f63efd2-9098-46e6-84e1-6a096025e4ee","resolution":{"observed_at":"2026-08-04T10:05:53.172956Z","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":"2026-08-04T10:05:53.330152Z","title":"Reconciling modern machine-learning practice and the classical bias–variance trade-off","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:53.330152Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:e03ccd7d02649ede2fa091f1871aed4377af1f31c0b9ee43fac3231d45dc32a2","observation_id":"65a61138-67bc-46f2-9854-1e55e2ee0bfc","resolution":{"observed_at":"2026-08-04T10:05:53.330152Z","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":"2026-08-04T10:05:53.418553Z","title":"The role of learning algorithms in collective action","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:53.418553Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:c3fbec23c800c1e0c8c7ef3d741513511956b72b5e9355d310e56ab84f4ecbab","observation_id":"8d2c4066-b428-46f6-b7ce-6b6714cbbb3a","resolution":{"observed_at":"2026-08-04T10:05:53.418553Z","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":"2026-08-04T10:05:53.503892Z","title":"Spurious correlations in high dimensional regression: The roles of regularization, simplicity bias and over-parameterization","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:53.503892Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:3b01d627795d466e0c752e32ce361b49a377e9354ead2606e6386a1296947a7d","observation_id":"a9ffd724-299a-43b1-ac82-f91dc75a3a0b","resolution":{"observed_at":"2026-08-04T10:05:53.503892Z","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":"2026-08-04T10:05:53.623083Z","title":"Provable benefits of overparameterization in model compression: From double descent to pruning neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:53.623083Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:158674c4a2ee0673cc4ea4de00e7c1d2857dfdbdcc6216413cb1a72c8a4daa5c","observation_id":"e51dd82f-7d0b-4539-bc71-8ed6c5f97113","resolution":{"observed_at":"2026-08-04T10:05:53.623083Z","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":"2026-08-04T10:05:53.701217Z","title":"Dimension free ridge regression","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:53.701217Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:e20370c101d7eb63f46442fd5445466a20607d35e907df52c135e8a8c01360fc","observation_id":"01548eb3-6404-48a1-aaa2-0df8d6fc0727","resolution":{"observed_at":"2026-08-04T10:05:53.701217Z","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":"2026-08-04T10:05:53.769343Z","title":"Optimal classification under performative distribution shift","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:53.769343Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:225a79d6b11232fff19bb0fe7b317835b11403a2426a58daacb1be0920c9c9e2","observation_id":"511eab27-ee1c-452a-bd8c-6708556fc988","resolution":{"observed_at":"2026-08-04T10:05:53.769343Z","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":"2026-08-04T10:05:53.872790Z","title":"A model of double descent for high-dimensional binary linear classification","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:53.872790Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:3a60e76ce2c7b2a6c7f3f7ff55b72e57430657d92494491e660d829347b6736b","observation_id":"7b507753-a49c-42a2-9e2d-8b2487a2601c","resolution":{"observed_at":"2026-08-04T10:05:53.872790Z","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":"2026-08-04T10:05:54.016601Z","title":"Stochastic optimization with decision-dependent distributions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:54.016601Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:305d5af5b7d95cba8c290f46521abd5b14beebfe1174f0211842a2cde46ff58e","observation_id":"3c995df0-c719-4cbb-9ed6-759e372e769f","resolution":{"observed_at":"2026-08-04T10:05:54.016601Z","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":"2026-08-04T10:05:54.113808Z","title":"Friedler, Scott Neville, Carlos Scheidegger, and Suresh Venkatasubramanian","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:54.113808Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:730262cdbbd639215775303f57f67e35aba18f65107e618ff4f3e0c469cdfb62","observation_id":"06f2370a-e52e-4dd8-b243-d50cf27728df","resolution":{"observed_at":"2026-08-04T10:05:54.113808Z","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":"2026-08-04T10:05:54.203938Z","title":"Analysis of classifiers’ robustness to adversarial perturbations","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:54.203938Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:ad10f128ae045f4555d24d9f52a545994de744801355fe65182fc74ba95259e3","observation_id":"af351922-42b1-4814-a5ca-6c3cd8a40f51","resolution":{"observed_at":"2026-08-04T10:05:54.203938Z","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":"2026-08-04T10:05:54.317031Z","title":"The distribution of ridgeless least squares interpolators","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:54.317031Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:81def6057a89c27ad5aa5a064ec8b6ecef2090f40e7f1b2aa70df502472fb01c","observation_id":"b4f6cfe7-b65a-4533-baf4-b45128762285","resolution":{"observed_at":"2026-08-04T10:05:54.317031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.16608","last_updated":"2025-05-20T09:38:03Z","snapshot_observed_at":"2026-08-06T14:31:52.153623Z","submitted_at":"2023-10-25T13:02:45Z","title":"Performative Prediction: Past and Future","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.16608","snapshot_observed_at":"2026-08-04T10:05:54.414356Z","title":"Performative prediction: Past and future","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:54.414356Z"},"links":{"cited_paper":"/paper/2310.16608","citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:a3e82c1932e4b2815e65703daafa67058813840c9ead6ec25a767d626173ae80","observation_id":"198f8899-0255-4e42-9c90-22a33a1eb498","resolution":{"observed_at":"2026-08-04T10:05:54.414356Z","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":"2026-08-04T10:05:54.512761Z","title":"Surprises in high-dimensional ridgeless least squares interpolation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:54.512761Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:c38b1d13f288cf41697f242f0d2c2182645b23dea746ec4be821ba3e2fc5d2dd","observation_id":"8c394049-096f-43da-9207-416c2f14e808","resolution":{"observed_at":"2026-08-04T10:05:54.512761Z","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":"2026-08-04T10:05:54.698874Z","title":"High-dimensional analysis of knowledge distillation: Weak-to-strong generalization and scaling laws","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:54.698874Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:e09d55f71f129e7182ce71429a3e635891c5e64acb2f65b7eda11846bf79c270","observation_id":"eedd76d7-4664-4eef-aecc-985e491298ba","resolution":{"observed_at":"2026-08-04T10:05:54.698874Z","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":"2026-08-04T10:05:54.868178Z","title":"How to learn when data gradually reacts to your model","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:54.868178Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:e8248293700400b155b20e0c1d2dffb4a23f866d4c1b993f475effdbf14d8596","observation_id":"33821fef-63b7-48a8-ba9f-96694790c338","resolution":{"observed_at":"2026-08-04T10:05:54.868178Z","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":"2026-08-04T10:05:54.966015Z","title":"Scaling laws for learning with real and surrogate data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:54.966015Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:b413f938ae3dec6e3849706b28eff75d2aa8272725ec8d5fa95d49dc0dd3bf98","observation_id":"c415439f-0986-479c-90a7-67ec4144256d","resolution":{"observed_at":"2026-08-04T10:05:54.966015Z","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":"2026-08-04T10:05:55.113286Z","title":"Towards a statistical theory of data selection under weak supervision","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:55.113286Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:f487fb176c8f68952f0845ae1cde06196b9c26de9f309afa35b917e57430fe65","observation_id":"2bead2c7-0a04-4003-90b6-8f9006b01ffa","resolution":{"observed_at":"2026-08-04T10:05:55.113286Z","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":"2026-08-04T10:05:55.239364Z","title":"Multi-agent performative prediction with greedy deployment and consensus seeking agents","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:55.239364Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:d74d33576b22c3ef39a132652aef65de0d50f31799a11f6955b7dd2efaeb4e3e","observation_id":"ac2d0dba-0332-44c9-83eb-199f8ecae169","resolution":{"observed_at":"2026-08-04T10:05:55.239364Z","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":"2026-08-04T10:05:55.371552Z","title":"Minimum-norm interpolation under covariate shift","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:55.371552Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:adb79dae4b172aa1733d8cf514d09a994c8208a8b826036bb6fc3dbe1e883e3c","observation_id":"b33d2a84-5383-4333-8659-dbd60c362a4e","resolution":{"observed_at":"2026-08-04T10:05:55.371552Z","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":"2026-08-04T10:05:55.433605Z","title":"Perdomo, and Tijana Zrnic","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:55.433605Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:c37a441f9ddc8c11cee3a7f7c53f0a7a2373f355c91e3b6aa64dd678fef58388","observation_id":"9d5345ed-ca82-431b-b022-9c3b45e40ec4","resolution":{"observed_at":"2026-08-04T10:05:55.433605Z","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":"2026-08-04T10:05:55.609281Z","title":"The generalization error of max-margin linear classifiers: Benign overfitting and high dimensional asymptotics in the overparametrized regime","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:55.609281Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:9a02289207e0d2b582da3d0bcc8d17f08c09bf3140edd28b623c20a3c26bd8dd","observation_id":"ecccf025-b60d-4087-8770-8db521106034","resolution":{"observed_at":"2026-08-04T10:05:55.609281Z","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":"2026-08-04T10:05:55.831997Z","title":"Wirtschaftsprognose: Eine Untersuchung ihrer Voraussetzungen und Möglichkeiten","venue":null,"work_id":null,"year":1928},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:55.831997Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:5691160f02a4210f1c7e7990562a1c173d078ca31c71256d7dd1cec47bd6eb71","observation_id":"9b7d888e-e64f-4934-a386-f7afcf7a5988","resolution":{"observed_at":"2026-08-04T10:05:55.831997Z","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":"2026-08-04T10:05:56.002505Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:56.002505Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:c0a195315df9c56b5afbc6e5c6f5c6de8146bce99978cdc3abb96f345c226176","observation_id":"8c4f878b-fba5-44a8-a461-e18f8bed885d","resolution":{"observed_at":"2026-08-04T10:05:56.002505Z","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":"2026-08-04T10:05:56.111804Z","title":"Feedback loops with language models drive in-context reward hacking","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:56.111804Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:f2aa7a5ead59e175541198d5c3171a19490d426ac1c6544aed7d95edbcbd257c","observation_id":"b6b5998a-fdf1-4732-8cc4-69b24e15041d","resolution":{"observed_at":"2026-08-04T10:05:56.111804Z","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":"2026-08-04T10:05:56.289720Z","title":"Optimal ridge regularization for out-of-distribution prediction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:56.289720Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:ed859fc76fab59d888a3a16a7194b1b48059163c2fca715d75d7467994a56f93","observation_id":"66d632c7-fedd-4443-99ec-82acfc83d25f","resolution":{"observed_at":"2026-08-04T10:05:56.289720Z","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":"2026-08-04T10:05:56.371878Z","title":"Performative prediction","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:56.371878Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:1675fe56c8e88b59521e38328a7816bd0ae183a754fa8c6140bbe7b9c227a74d","observation_id":"70422f56-9684-4299-9c46-b1cf1c3210f6","resolution":{"observed_at":"2026-08-04T10:05:56.371878Z","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":"2026-08-04T10:05:56.471043Z","title":"Ribeiro, Dave Zachariah, Francis Bach, and Thomas B","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:56.471043Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:660c39774805eb86a540577fc580ccaf54617c73e4cc2976c6a000efd3e0c6e3","observation_id":"15ed5279-9cd5-4de7-97f3-b4a418056c8d","resolution":{"observed_at":"2026-08-04T10:05:56.471043Z","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":"2026-08-04T10:05:56.608805Z","title":"Asymptotics of ridge (less) regression under general source condition","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:56.608805Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:6ac412cd7d21515ddd1635c9e9796a06da9d327de54db73a9a47bea36ff6e11b","observation_id":"e7a76ed3-683e-46bc-83bf-3dfbd326b76d","resolution":{"observed_at":"2026-08-04T10:05:56.608805Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.13944","last_updated":"2026-06-27T02:08:29Z","snapshot_observed_at":"2026-08-06T20:36:35.792109Z","submitted_at":"2024-06-20T02:23:28Z","title":"Generalization error of min-norm interpolators in transfer learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.13944","snapshot_observed_at":"2026-08-04T10:05:56.777827Z","title":"Generalization error of min-norm interpolators in transfer learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:56.777827Z"},"links":{"cited_paper":"/paper/2406.13944","citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:ac6283c984b206765c15b7393a83918d90ea0ed16d94f1864869db65b875e202","observation_id":"4bf10035-161d-451f-8dd3-5a40a29ee1b0","resolution":{"observed_at":"2026-08-04T10:05:56.777827Z","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":"2026-08-04T10:05:56.833692Z","title":"Data feedback loops: Model-driven amplification of dataset biases","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:56.833692Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:0466099715d049aafc79aead0406cf27c3f328e883ef0d3f56b7a5c8ed2a0b9b","observation_id":"29e405f4-3468-4e80-bf3e-360d8a2b4764","resolution":{"observed_at":"2026-08-04T10:05:56.833692Z","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":"2026-08-04T10:05:56.948509Z","title":"Benign overfitting in ridge regression","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:56.948509Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:eec9417456fe95000429338f953dfc050d72d3878b4c43ca41d0041cce6e367c","observation_id":"71799254-9671-4e47-895d-3bc9ab99c3ac","resolution":{"observed_at":"2026-08-04T10:05:56.948509Z","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":"2026-08-04T10:05:57.099441Z","title":"The power of rankings: Quantifying the effects of rankings on online consumer search and choice","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:57.099441Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:cf29fbce5bee7c455f6c0477b7b43221435182e044ba7e2ebd53cd37884c6949","observation_id":"68222cd7-1e1b-42ba-b095-e4715115acdd","resolution":{"observed_at":"2026-08-04T10:05:57.099441Z","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":"2026-08-04T10:05:57.246604Z","title":"Network effects in performative prediction games","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:57.246604Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:7ca5d8a3ace43247f85a12516b154ce13e3c6c1192ac0164ca7b5a8cc653a789","observation_id":"40aac4d4-6043-44a8-b2ff-f7bdef0934ae","resolution":{"observed_at":"2026-08-04T10:05:57.246604Z","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":"2026-08-04T10:05:57.368477Z","title":"On the optimal weighted _2 regularization in overparameterized linear regression","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:57.368477Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:59875c27332f426b6470de4a20538dd68d66d9acb47c5bd4f644171b5d5365d8","observation_id":"5da711b6-a2d1-45af-a13f-078ba3441fa2","resolution":{"observed_at":"2026-08-04T10:05:57.368477Z","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":"2026-08-04T10:05:57.452489Z","title":"Precise high-dimensional asymptotics for quantifying heterogeneous transfers","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:57.452489Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:ae72770b6ba14ed3c894a3cbd6188098d01f3064501fc20a64cea5ea463f493f","observation_id":"139604a1-759f-4041-9baf-e892fb8726dd","resolution":{"observed_at":"2026-08-04T10:05:57.452489Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08349","last_updated":"2025-04-30T09:11:15Z","snapshot_observed_at":"2026-07-06T16:31:56.083710Z","submitted_at":"2023-10-12T14:18:13Z","title":"Performativity and Prospective Fairness","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.08349","snapshot_observed_at":"2026-08-04T10:05:57.533859Z","title":"Performativity and Prospective Fairness","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:57.533859Z"},"links":{"cited_paper":"/paper/2310.08349","citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:d626d3beeeffd5341aaeafe60c9bb47f08858eeca495c3b5f5a508ef29ec849c","observation_id":"15cc1956-267a-407b-8e18-3509b0fc6259","resolution":{"observed_at":"2026-08-04T10:05:57.533859Z","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":"2026-08-04T10:05:57.686313Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:57.686313Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:f266ed62d675aa7305100984c09afe84a66d0be3c75c1e69cb98b1dd0e9e313b","observation_id":"092c2938-b9dd-487f-ac68-68664ed68c1d","resolution":{"observed_at":"2026-08-04T10:05:57.686313Z","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":"2026-08-04T10:05:57.815095Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:57.815095Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:c38f19a9c37b53e5c9eed39d78eee5d9dc805349815a9a7b298380a8b4bb8337","observation_id":"0b7f45c3-682d-4e32-8b3b-25bcfcd2636f","resolution":{"observed_at":"2026-08-04T10:05:57.815095Z","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":"2026-08-04T10:05:57.917104Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-04T10:05:57.917104Z"},"links":{"citing_paper":"/paper/2510.12249"},"observation_digest":"sha256:fd8e887c7bee93e719a11b9c79a8c2331334165b479b7ca24f4b7faf3855d62a","observation_id":"0a87b353-7600-49d7-af21-df38967ce1ee","resolution":{"observed_at":"2026-08-04T10:05:57.917104Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2510.12249","last_updated":"2026-05-29T20:27:43Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T10:05:42.280214Z","submitted_at":"2025-10-14T08:00:08Z","title":"Optimal Regularization for Performative Learning"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":42,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":42},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 2 inbound Pith citation observations for arXiv:2510.12249."}