{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OXKN63NXRCZ3WISBYU2VVZZ2YF","short_pith_number":"pith:OXKN63NX","canonical_record":{"source":{"id":"2502.01347","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-03T13:38:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f106083835dccb9ec6c2d89451f2f3dab4d3e63a85addf1616b6de7f652202ea","abstract_canon_sha256":"aa50042e2450eca43db6d254e748c07031ff794613e9039d55fc8582bd001443"},"schema_version":"1.0"},"canonical_sha256":"75d4df6db788b3bb2241c5355ae73ac140c581eec0b34204079bc94f75232d81","source":{"kind":"arxiv","id":"2502.01347","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01347","created_at":"2026-07-05T11:10:51Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01347v2","created_at":"2026-07-05T11:10:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01347","created_at":"2026-07-05T11:10:51Z"},{"alias_kind":"pith_short_12","alias_value":"OXKN63NXRCZ3","created_at":"2026-07-05T11:10:51Z"},{"alias_kind":"pith_short_16","alias_value":"OXKN63NXRCZ3WISB","created_at":"2026-07-05T11:10:51Z"},{"alias_kind":"pith_short_8","alias_value":"OXKN63NX","created_at":"2026-07-05T11:10:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OXKN63NXRCZ3WISBYU2VVZZ2YF","target":"record","payload":{"canonical_record":{"source":{"id":"2502.01347","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-03T13:38:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f106083835dccb9ec6c2d89451f2f3dab4d3e63a85addf1616b6de7f652202ea","abstract_canon_sha256":"aa50042e2450eca43db6d254e748c07031ff794613e9039d55fc8582bd001443"},"schema_version":"1.0"},"canonical_sha256":"75d4df6db788b3bb2241c5355ae73ac140c581eec0b34204079bc94f75232d81","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:51.161234Z","signature_b64":"F6NC26iYvGerFemZstNixC9vBvwjcvvSe7rQeMRgGhEavEirq6IK/Nx4Fg45olHy2JvZ1GHwU8MtG+vCKMvTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75d4df6db788b3bb2241c5355ae73ac140c581eec0b34204079bc94f75232d81","last_reissued_at":"2026-07-05T11:10:51.160718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:51.160718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.01347","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fbcHnQkqb92AXLwpZwV821xPbHk08+trQNoqK8JU1fxAEON3QEchxYBGOH8TPGk0ze35xPxu3btj69RFQGbDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:32:41.659230Z"},"content_sha256":"b619e2d152170b3f27c83669fdfc72da9e66965dadbe05d90f91435361ded994","schema_version":"1.0","event_id":"sha256:b619e2d152170b3f27c83669fdfc72da9e66965dadbe05d90f91435361ded994"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OXKN63NXRCZ3WISBYU2VVZZ2YF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Marco Mondelli, Simone Bombari","submitted_at":"2025-02-03T13:38:42Z","abstract_excerpt":"Learning models have been shown to rely on spurious correlations between non-predictive features and the associated labels in the training data, with negative implications on robustness, bias and fairness. In this work, we provide a statistical characterization of this phenomenon for high-dimensional regression, when the data contains a predictive core feature $x$ and a spurious feature $y$. Specifically, we quantify the amount of spurious correlations $C$ learned via linear regression, in terms of the data covariance and the strength $\\lambda$ of the ridge regularization. As a consequence, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01347","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.01347/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+cwIs4FwzUfLsQD3NN0qVqCmxAb750NP0TDRAMFGLugfZNkrxY4pA+SHJvNzz+PyD257PgQziIaN/hMe+6jzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:32:41.659777Z"},"content_sha256":"ba92f5eadb7f508249318c907a890acefae61bd9dd9f19dcbb2add40f74044ab","schema_version":"1.0","event_id":"sha256:ba92f5eadb7f508249318c907a890acefae61bd9dd9f19dcbb2add40f74044ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OXKN63NXRCZ3WISBYU2VVZZ2YF/bundle.json","state_url":"https://pith.science/pith/OXKN63NXRCZ3WISBYU2VVZZ2YF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OXKN63NXRCZ3WISBYU2VVZZ2YF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T09:32:41Z","links":{"resolver":"https://pith.science/pith/OXKN63NXRCZ3WISBYU2VVZZ2YF","bundle":"https://pith.science/pith/OXKN63NXRCZ3WISBYU2VVZZ2YF/bundle.json","state":"https://pith.science/pith/OXKN63NXRCZ3WISBYU2VVZZ2YF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OXKN63NXRCZ3WISBYU2VVZZ2YF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OXKN63NXRCZ3WISBYU2VVZZ2YF","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":"aa50042e2450eca43db6d254e748c07031ff794613e9039d55fc8582bd001443","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-03T13:38:42Z","title_canon_sha256":"f106083835dccb9ec6c2d89451f2f3dab4d3e63a85addf1616b6de7f652202ea"},"schema_version":"1.0","source":{"id":"2502.01347","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01347","created_at":"2026-07-05T11:10:51Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01347v2","created_at":"2026-07-05T11:10:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01347","created_at":"2026-07-05T11:10:51Z"},{"alias_kind":"pith_short_12","alias_value":"OXKN63NXRCZ3","created_at":"2026-07-05T11:10:51Z"},{"alias_kind":"pith_short_16","alias_value":"OXKN63NXRCZ3WISB","created_at":"2026-07-05T11:10:51Z"},{"alias_kind":"pith_short_8","alias_value":"OXKN63NX","created_at":"2026-07-05T11:10:51Z"}],"graph_snapshots":[{"event_id":"sha256:ba92f5eadb7f508249318c907a890acefae61bd9dd9f19dcbb2add40f74044ab","target":"graph","created_at":"2026-07-05T11:10:51Z","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/2502.01347/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning models have been shown to rely on spurious correlations between non-predictive features and the associated labels in the training data, with negative implications on robustness, bias and fairness. In this work, we provide a statistical characterization of this phenomenon for high-dimensional regression, when the data contains a predictive core feature $x$ and a spurious feature $y$. Specifically, we quantify the amount of spurious correlations $C$ learned via linear regression, in terms of the data covariance and the strength $\\lambda$ of the ridge regularization. As a consequence, we","authors_text":"Marco Mondelli, Simone Bombari","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-03T13:38:42Z","title":"Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01347","kind":"arxiv","version":2},"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:b619e2d152170b3f27c83669fdfc72da9e66965dadbe05d90f91435361ded994","target":"record","created_at":"2026-07-05T11:10:51Z","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":"aa50042e2450eca43db6d254e748c07031ff794613e9039d55fc8582bd001443","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-03T13:38:42Z","title_canon_sha256":"f106083835dccb9ec6c2d89451f2f3dab4d3e63a85addf1616b6de7f652202ea"},"schema_version":"1.0","source":{"id":"2502.01347","kind":"arxiv","version":2}},"canonical_sha256":"75d4df6db788b3bb2241c5355ae73ac140c581eec0b34204079bc94f75232d81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75d4df6db788b3bb2241c5355ae73ac140c581eec0b34204079bc94f75232d81","first_computed_at":"2026-07-05T11:10:51.160718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:51.160718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F6NC26iYvGerFemZstNixC9vBvwjcvvSe7rQeMRgGhEavEirq6IK/Nx4Fg45olHy2JvZ1GHwU8MtG+vCKMvTAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:51.161234Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01347","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b619e2d152170b3f27c83669fdfc72da9e66965dadbe05d90f91435361ded994","sha256:ba92f5eadb7f508249318c907a890acefae61bd9dd9f19dcbb2add40f74044ab"],"state_sha256":"e48a5254f82d8330ce1f470ea29d43aa5f7dae14d74a6b730a3e1c8fc2b6603a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ND6bW3C4Akgj+1eLS1pKTDjnVeUY3q3mhiYsGz13KPni3ca+zrBB1L2/4TAO7UuUqRoEnamFrKiZ0aSwjT1FDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:32:41.664252Z","bundle_sha256":"f29052dc9bfd5fb66e3fbc62da900d3b9570c977fe755b240a23423cc0c22ca1"}}