{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4FWD5H4PNSLS3YER2X5CXETFXT","short_pith_number":"pith:4FWD5H4P","canonical_record":{"source":{"id":"2206.08757","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-17T13:16:46Z","cross_cats_sorted":[],"title_canon_sha256":"8922278075fcb6d6cd94a0f0b0f5a05eeb92bed99d1742f3e6a3efc12d317913","abstract_canon_sha256":"8ae01bee644653ab768c21e1791c37ac347a7764cf088319d4de3f49606df70d"},"schema_version":"1.0"},"canonical_sha256":"e16c3e9f8f6c972de091d5fa2b9265bced4dd4ce372cc9e1c012a9e7ff8572a3","source":{"kind":"arxiv","id":"2206.08757","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.08757","created_at":"2026-07-05T04:32:43Z"},{"alias_kind":"arxiv_version","alias_value":"2206.08757v1","created_at":"2026-07-05T04:32:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08757","created_at":"2026-07-05T04:32:43Z"},{"alias_kind":"pith_short_12","alias_value":"4FWD5H4PNSLS","created_at":"2026-07-05T04:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"4FWD5H4PNSLS3YER","created_at":"2026-07-05T04:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"4FWD5H4P","created_at":"2026-07-05T04:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4FWD5H4PNSLS3YER2X5CXETFXT","target":"record","payload":{"canonical_record":{"source":{"id":"2206.08757","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-17T13:16:46Z","cross_cats_sorted":[],"title_canon_sha256":"8922278075fcb6d6cd94a0f0b0f5a05eeb92bed99d1742f3e6a3efc12d317913","abstract_canon_sha256":"8ae01bee644653ab768c21e1791c37ac347a7764cf088319d4de3f49606df70d"},"schema_version":"1.0"},"canonical_sha256":"e16c3e9f8f6c972de091d5fa2b9265bced4dd4ce372cc9e1c012a9e7ff8572a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:43.030861Z","signature_b64":"dBR3Wvg0ETnMDB94Ua9gzWMXt9e3WmYlgaVHc6S2GMYSJdr/agUG5YSALyJEeaA+V3InVaWPbP9CrIANFKCxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e16c3e9f8f6c972de091d5fa2b9265bced4dd4ce372cc9e1c012a9e7ff8572a3","last_reissued_at":"2026-07-05T04:32:43.030435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:43.030435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.08757","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:32:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bdBLnMyFk/bNaHuv+JYpjf78nYN/nbwCHFDLK+QEYEND/qpWkFjNkGgFoAEpaXxZoMBhUwCw97WgYUKBD9L4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T03:17:33.708072Z"},"content_sha256":"616fdd7b0513fd38c42d10226849d46fba5fbe71c9a5addd0771a63571bb08af","schema_version":"1.0","event_id":"sha256:616fdd7b0513fd38c42d10226849d46fba5fbe71c9a5addd0771a63571bb08af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4FWD5H4PNSLS3YER2X5CXETFXT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Ridge Regression for Distribution-Free Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Koby Bibas, Meir Feder","submitted_at":"2022-06-17T13:16:46Z","abstract_excerpt":"In supervised batch learning, the predictive normalized maximum likelihood (pNML) has been proposed as the min-max regret solution for the distribution-free setting, where no distributional assumptions are made on the data. However, the pNML is not defined for a large capacity hypothesis class as over-parameterized linear regression. For a large class, a common approach is to use regularization or a model prior. In the context of online prediction where the min-max solution is the Normalized Maximum Likelihood (NML), it has been suggested to use NML with ``luckiness'': A prior-like function is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08757","kind":"arxiv","version":1},"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/2206.08757/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":"2026-07-05T04:32:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sqGQmCCT/NAJdGAogeZ40G9nbNZoA2oF2qqbDSCOPgv1AImq1N71W+atlORIlbKOpgf6IqcJg5nxbAydEAkWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T03:17:33.708459Z"},"content_sha256":"b6e2cddb468e72a43db6a648dc724a465471055a9f4bf4b73a1b6ce0322ed857","schema_version":"1.0","event_id":"sha256:b6e2cddb468e72a43db6a648dc724a465471055a9f4bf4b73a1b6ce0322ed857"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4FWD5H4PNSLS3YER2X5CXETFXT/bundle.json","state_url":"https://pith.science/pith/4FWD5H4PNSLS3YER2X5CXETFXT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4FWD5H4PNSLS3YER2X5CXETFXT/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":"2026-08-24T03:17:33Z","links":{"resolver":"https://pith.science/pith/4FWD5H4PNSLS3YER2X5CXETFXT","bundle":"https://pith.science/pith/4FWD5H4PNSLS3YER2X5CXETFXT/bundle.json","state":"https://pith.science/pith/4FWD5H4PNSLS3YER2X5CXETFXT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4FWD5H4PNSLS3YER2X5CXETFXT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4FWD5H4PNSLS3YER2X5CXETFXT","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":"8ae01bee644653ab768c21e1791c37ac347a7764cf088319d4de3f49606df70d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-17T13:16:46Z","title_canon_sha256":"8922278075fcb6d6cd94a0f0b0f5a05eeb92bed99d1742f3e6a3efc12d317913"},"schema_version":"1.0","source":{"id":"2206.08757","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.08757","created_at":"2026-07-05T04:32:43Z"},{"alias_kind":"arxiv_version","alias_value":"2206.08757v1","created_at":"2026-07-05T04:32:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08757","created_at":"2026-07-05T04:32:43Z"},{"alias_kind":"pith_short_12","alias_value":"4FWD5H4PNSLS","created_at":"2026-07-05T04:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"4FWD5H4PNSLS3YER","created_at":"2026-07-05T04:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"4FWD5H4P","created_at":"2026-07-05T04:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:b6e2cddb468e72a43db6a648dc724a465471055a9f4bf4b73a1b6ce0322ed857","target":"graph","created_at":"2026-07-05T04:32:43Z","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/2206.08757/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In supervised batch learning, the predictive normalized maximum likelihood (pNML) has been proposed as the min-max regret solution for the distribution-free setting, where no distributional assumptions are made on the data. However, the pNML is not defined for a large capacity hypothesis class as over-parameterized linear regression. For a large class, a common approach is to use regularization or a model prior. In the context of online prediction where the min-max solution is the Normalized Maximum Likelihood (NML), it has been suggested to use NML with ``luckiness'': A prior-like function is","authors_text":"Koby Bibas, Meir Feder","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-17T13:16:46Z","title":"Beyond Ridge Regression for Distribution-Free Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08757","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":"sha256:616fdd7b0513fd38c42d10226849d46fba5fbe71c9a5addd0771a63571bb08af","target":"record","created_at":"2026-07-05T04:32:43Z","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":"8ae01bee644653ab768c21e1791c37ac347a7764cf088319d4de3f49606df70d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-17T13:16:46Z","title_canon_sha256":"8922278075fcb6d6cd94a0f0b0f5a05eeb92bed99d1742f3e6a3efc12d317913"},"schema_version":"1.0","source":{"id":"2206.08757","kind":"arxiv","version":1}},"canonical_sha256":"e16c3e9f8f6c972de091d5fa2b9265bced4dd4ce372cc9e1c012a9e7ff8572a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e16c3e9f8f6c972de091d5fa2b9265bced4dd4ce372cc9e1c012a9e7ff8572a3","first_computed_at":"2026-07-05T04:32:43.030435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:43.030435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dBR3Wvg0ETnMDB94Ua9gzWMXt9e3WmYlgaVHc6S2GMYSJdr/agUG5YSALyJEeaA+V3InVaWPbP9CrIANFKCxCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:43.030861Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.08757","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:616fdd7b0513fd38c42d10226849d46fba5fbe71c9a5addd0771a63571bb08af","sha256:b6e2cddb468e72a43db6a648dc724a465471055a9f4bf4b73a1b6ce0322ed857"],"state_sha256":"a05147503f117e1e216b630324351ac1b62de3ca6dac65d6e303103d9d1f762e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w9MMvpYcQP8LPHc7xVkWd/vUe9rn7py8ccwUI+HsQ9fCyAwUqHi3xzdKiS0zwdVr85aDSvyDMVWafpkZfZ+OBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T03:17:33.712052Z","bundle_sha256":"2464678c2d588254b69fd612c72363690972c99b05ddfd63dd440b02b2644a3f"}}