{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GPAC4DKYV4BJNSYXDKMRSIBASV","short_pith_number":"pith:GPAC4DKY","canonical_record":{"source":{"id":"2102.07181","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-14T15:49:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a3ef8750f15fcb8a33cd998d25e25fc40349e09c26c3e08c74f66c96fb07c018","abstract_canon_sha256":"1277a01986eeeeab7cc632a5890c256ffeeed03d530ee71ac1dcd6c217ef1d15"},"schema_version":"1.0"},"canonical_sha256":"33c02e0d58af0296cb171a991920209566e08063ba779a6b5a45d3e82089ca14","source":{"kind":"arxiv","id":"2102.07181","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.07181","created_at":"2026-07-05T02:50:09Z"},{"alias_kind":"arxiv_version","alias_value":"2102.07181v2","created_at":"2026-07-05T02:50:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07181","created_at":"2026-07-05T02:50:09Z"},{"alias_kind":"pith_short_12","alias_value":"GPAC4DKYV4BJ","created_at":"2026-07-05T02:50:09Z"},{"alias_kind":"pith_short_16","alias_value":"GPAC4DKYV4BJNSYX","created_at":"2026-07-05T02:50:09Z"},{"alias_kind":"pith_short_8","alias_value":"GPAC4DKY","created_at":"2026-07-05T02:50:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GPAC4DKYV4BJNSYXDKMRSIBASV","target":"record","payload":{"canonical_record":{"source":{"id":"2102.07181","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-14T15:49:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a3ef8750f15fcb8a33cd998d25e25fc40349e09c26c3e08c74f66c96fb07c018","abstract_canon_sha256":"1277a01986eeeeab7cc632a5890c256ffeeed03d530ee71ac1dcd6c217ef1d15"},"schema_version":"1.0"},"canonical_sha256":"33c02e0d58af0296cb171a991920209566e08063ba779a6b5a45d3e82089ca14","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:09.137018Z","signature_b64":"g0RTn6wU4tnkeX4Q3hHMtuDa4r9LaIgP7ZP/ASLX8+Tg/WTQDSqgbq5dHZYgNKXdhd6vvXOufar8AKrxZBiCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33c02e0d58af0296cb171a991920209566e08063ba779a6b5a45d3e82089ca14","last_reissued_at":"2026-07-05T02:50:09.136680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:09.136680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.07181","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":"2026-07-05T02:50:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SfYzbVSUTdOOQXCqp3LcgX1ARtE9zzSQRu0Moj/ODwgzgWIXtfHfkC1KHS9/xdzNy3UN0TTwvBfkelmT8TglAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T00:23:42.204417Z"},"content_sha256":"e3f33a62b315f0da1b1bda3bff76fdb71b13d9012f5e1f9df1f9244f29cb0f71","schema_version":"1.0","event_id":"sha256:e3f33a62b315f0da1b1bda3bff76fdb71b13d9012f5e1f9df1f9244f29cb0f71"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GPAC4DKYV4BJNSYXDKMRSIBASV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distribution Free Uncertainty for the Minimum Norm Solution of Over-parameterized Linear Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Koby Bibas, Meir Feder","submitted_at":"2021-02-14T15:49:04Z","abstract_excerpt":"A fundamental principle of learning theory is that there is a trade-off between the complexity of a prediction rule and its ability to generalize. Modern machine learning models do not obey this paradigm: They produce an accurate prediction even with a perfect fit to the training set. We investigate over-parameterized linear regression models focusing on the minimum norm solution: This is the solution with the minimal norm that attains a perfect fit to the training set. We utilize the recently proposed predictive normalized maximum likelihood (pNML) learner which is the min-max regret solution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07181","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/2102.07181/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":"2026-07-05T02:50:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oleSgPjIKphFD3YCQU0eTuK2LXa7/ApqZfjFljH9sBBBAshKIrzrbxy9AyiAEwQVaR/twBfAF+qm64CNskwnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T00:23:42.204953Z"},"content_sha256":"2a370018a30f53ba0a4dba97faa00a8f5905450bfe966fe4ab1f2da40954f440","schema_version":"1.0","event_id":"sha256:2a370018a30f53ba0a4dba97faa00a8f5905450bfe966fe4ab1f2da40954f440"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GPAC4DKYV4BJNSYXDKMRSIBASV/bundle.json","state_url":"https://pith.science/pith/GPAC4DKYV4BJNSYXDKMRSIBASV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GPAC4DKYV4BJNSYXDKMRSIBASV/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":"2026-08-24T00:23:42Z","links":{"resolver":"https://pith.science/pith/GPAC4DKYV4BJNSYXDKMRSIBASV","bundle":"https://pith.science/pith/GPAC4DKYV4BJNSYXDKMRSIBASV/bundle.json","state":"https://pith.science/pith/GPAC4DKYV4BJNSYXDKMRSIBASV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GPAC4DKYV4BJNSYXDKMRSIBASV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GPAC4DKYV4BJNSYXDKMRSIBASV","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":"1277a01986eeeeab7cc632a5890c256ffeeed03d530ee71ac1dcd6c217ef1d15","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-14T15:49:04Z","title_canon_sha256":"a3ef8750f15fcb8a33cd998d25e25fc40349e09c26c3e08c74f66c96fb07c018"},"schema_version":"1.0","source":{"id":"2102.07181","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.07181","created_at":"2026-07-05T02:50:09Z"},{"alias_kind":"arxiv_version","alias_value":"2102.07181v2","created_at":"2026-07-05T02:50:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07181","created_at":"2026-07-05T02:50:09Z"},{"alias_kind":"pith_short_12","alias_value":"GPAC4DKYV4BJ","created_at":"2026-07-05T02:50:09Z"},{"alias_kind":"pith_short_16","alias_value":"GPAC4DKYV4BJNSYX","created_at":"2026-07-05T02:50:09Z"},{"alias_kind":"pith_short_8","alias_value":"GPAC4DKY","created_at":"2026-07-05T02:50:09Z"}],"graph_snapshots":[{"event_id":"sha256:2a370018a30f53ba0a4dba97faa00a8f5905450bfe966fe4ab1f2da40954f440","target":"graph","created_at":"2026-07-05T02:50:09Z","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/2102.07181/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A fundamental principle of learning theory is that there is a trade-off between the complexity of a prediction rule and its ability to generalize. Modern machine learning models do not obey this paradigm: They produce an accurate prediction even with a perfect fit to the training set. We investigate over-parameterized linear regression models focusing on the minimum norm solution: This is the solution with the minimal norm that attains a perfect fit to the training set. We utilize the recently proposed predictive normalized maximum likelihood (pNML) learner which is the min-max regret solution","authors_text":"Koby Bibas, Meir Feder","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-14T15:49:04Z","title":"Distribution Free Uncertainty for the Minimum Norm Solution of Over-parameterized Linear Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07181","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:e3f33a62b315f0da1b1bda3bff76fdb71b13d9012f5e1f9df1f9244f29cb0f71","target":"record","created_at":"2026-07-05T02:50:09Z","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":"1277a01986eeeeab7cc632a5890c256ffeeed03d530ee71ac1dcd6c217ef1d15","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-14T15:49:04Z","title_canon_sha256":"a3ef8750f15fcb8a33cd998d25e25fc40349e09c26c3e08c74f66c96fb07c018"},"schema_version":"1.0","source":{"id":"2102.07181","kind":"arxiv","version":2}},"canonical_sha256":"33c02e0d58af0296cb171a991920209566e08063ba779a6b5a45d3e82089ca14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33c02e0d58af0296cb171a991920209566e08063ba779a6b5a45d3e82089ca14","first_computed_at":"2026-07-05T02:50:09.136680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:50:09.136680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g0RTn6wU4tnkeX4Q3hHMtuDa4r9LaIgP7ZP/ASLX8+Tg/WTQDSqgbq5dHZYgNKXdhd6vvXOufar8AKrxZBiCBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:50:09.137018Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.07181","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3f33a62b315f0da1b1bda3bff76fdb71b13d9012f5e1f9df1f9244f29cb0f71","sha256:2a370018a30f53ba0a4dba97faa00a8f5905450bfe966fe4ab1f2da40954f440"],"state_sha256":"05530a61bb72a48b3b4c7e7e5e4349930688cf7e4fd1ad1eb7b56509e25e08b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Thl58ZbfewWo+PM1SxzMvmOBSRmnnBlXAKs2ZzhWKfpbWoJH4bkH8nHLOZM5xOho7mFn0rrZ+0837hXtLE3EAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T00:23:42.210682Z","bundle_sha256":"f4f1896d6761c3a4d42833023803a923ddfea63802a69e9b20f496e18b3b0c00"}}