{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YJEHQWKL7FOEZHF5GAWJLW7YEQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f0359cad84b36210dd8d0607214b748125bdf85104eb58c44edbfad9aae8e3c9","cross_cats_sorted":["cond-mat.dis-nn","cs.LG","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-21T14:53:12Z","title_canon_sha256":"76900b3b1de4fbfa6f28169f1af8c13cbbac48772b27d27d3b40058e96a7db93"},"schema_version":"1.0","source":{"id":"2410.16073","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16073","created_at":"2026-07-05T09:23:28Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16073v1","created_at":"2026-07-05T09:23:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16073","created_at":"2026-07-05T09:23:28Z"},{"alias_kind":"pith_short_12","alias_value":"YJEHQWKL7FOE","created_at":"2026-07-05T09:23:28Z"},{"alias_kind":"pith_short_16","alias_value":"YJEHQWKL7FOEZHF5","created_at":"2026-07-05T09:23:28Z"},{"alias_kind":"pith_short_8","alias_value":"YJEHQWKL","created_at":"2026-07-05T09:23:28Z"}],"graph_snapshots":[{"event_id":"sha256:8acd0a847979834183bc9afedd38b4123e811fee8e4f1c59f577e2f2af223d42","target":"graph","created_at":"2026-07-05T09:23:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.16073/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Regularization, whether explicit in terms of a penalty in the loss or implicit in the choice of algorithm, is a cornerstone of modern machine learning. Indeed, controlling the complexity of the model class is particularly important when data is scarce, noisy or contaminated, as it translates a statistical belief on the underlying structure of the data. This work investigates the question of how to choose the regularization norm $\\lVert \\cdot \\rVert$ in the context of high-dimensional adversarial training for binary classification. To this end, we first derive an exact asymptotic description of","authors_text":"Bruno Loureiro, Julia Kempe, Matteo Vilucchio, Nikolaos Tsilivis","cross_cats":["cond-mat.dis-nn","cs.LG","math.ST","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-21T14:53:12Z","title":"On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Bounds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16073","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:60d5d49fac4097da9800aa0d11a4ed87de3bc8a1f2e103d40f8b47d2416ea444","target":"record","created_at":"2026-07-05T09:23:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f0359cad84b36210dd8d0607214b748125bdf85104eb58c44edbfad9aae8e3c9","cross_cats_sorted":["cond-mat.dis-nn","cs.LG","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-21T14:53:12Z","title_canon_sha256":"76900b3b1de4fbfa6f28169f1af8c13cbbac48772b27d27d3b40058e96a7db93"},"schema_version":"1.0","source":{"id":"2410.16073","kind":"arxiv","version":1}},"canonical_sha256":"c24878594bf95c4c9cbd302c95dbf82404aebdc3c8e50ed3f6fc2e316dd662ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c24878594bf95c4c9cbd302c95dbf82404aebdc3c8e50ed3f6fc2e316dd662ac","first_computed_at":"2026-07-05T09:23:28.939143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:28.939143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w1aReQ0e1P2zTOo9HTSB/re2Gj0nuPLP/M2KMpguuVeizqxreezSn/w01BW5YP74yKMc6XqwYsBMuTBFHoJCCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:28.939676Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16073","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60d5d49fac4097da9800aa0d11a4ed87de3bc8a1f2e103d40f8b47d2416ea444","sha256:8acd0a847979834183bc9afedd38b4123e811fee8e4f1c59f577e2f2af223d42"],"state_sha256":"ad916319b392f28f96496a936f7296876d7ea24168952900736f736d368d5ecb"}