{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:JE5GDYQUW2M4DYNXKOXPTQZUFJ","short_pith_number":"pith:JE5GDYQU","canonical_record":{"source":{"id":"2203.05417","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"stat.ML","submitted_at":"2022-03-10T15:13:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a9631aeee4da98e506c716716c018dab2c7a3f547a870897b2d04b1772d8864d","abstract_canon_sha256":"bff2117b72c291f987a3437d4af89f432473cae5186fa272466291fb700af093"},"schema_version":"1.0"},"canonical_sha256":"493a61e214b699c1e1b753aef9c3342a57213c6d52a5eb1249d757ae8db8a675","source":{"kind":"arxiv","id":"2203.05417","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.05417","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"arxiv_version","alias_value":"2203.05417v1","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.05417","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"pith_short_12","alias_value":"JE5GDYQUW2M4","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"pith_short_16","alias_value":"JE5GDYQUW2M4DYNX","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"pith_short_8","alias_value":"JE5GDYQU","created_at":"2026-07-05T04:03:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:JE5GDYQUW2M4DYNXKOXPTQZUFJ","target":"record","payload":{"canonical_record":{"source":{"id":"2203.05417","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"stat.ML","submitted_at":"2022-03-10T15:13:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a9631aeee4da98e506c716716c018dab2c7a3f547a870897b2d04b1772d8864d","abstract_canon_sha256":"bff2117b72c291f987a3437d4af89f432473cae5186fa272466291fb700af093"},"schema_version":"1.0"},"canonical_sha256":"493a61e214b699c1e1b753aef9c3342a57213c6d52a5eb1249d757ae8db8a675","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:03:41.241234Z","signature_b64":"SVaEu6pQJqqfm/0pk47+6XaGsh2B0hSRoiaBYZ17yIWwQVPhjcIDrEQKIQ8jxzYm3vBRvd29ZAXNtvtg/CMqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"493a61e214b699c1e1b753aef9c3342a57213c6d52a5eb1249d757ae8db8a675","last_reissued_at":"2026-07-05T04:03:41.240827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:03:41.240827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.05417","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":"2026-07-05T04:03:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AQguuPX0ePp9Zrfn0SCmPFRfQf0MazCIZ/1HUHkyoTIxIYRU6vo+nr73Dkhl+HseBI+yd93znRRSds4JAcf+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:18:51.503050Z"},"content_sha256":"857d47c8b48fae69ee5ac05daa34c865d6174792c634b73854705eac02af2447","schema_version":"1.0","event_id":"sha256:857d47c8b48fae69ee5ac05daa34c865d6174792c634b73854705eac02af2447"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:JE5GDYQUW2M4DYNXKOXPTQZUFJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Regression Ensembles","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Antoine Didisheim, Bryan Kelly, Semyon Malamud","submitted_at":"2022-03-10T15:13:46Z","abstract_excerpt":"We introduce a methodology for designing and training deep neural networks (DNN) that we call \"Deep Regression Ensembles\" (DRE). It bridges the gap between DNN and two-layer neural networks trained with random feature regression. Each layer of DRE has two components, randomly drawn input weights and output weights trained myopically (as if the final output layer) using linear ridge regression. Within a layer, each neuron uses a different subset of inputs and a different ridge penalty, constituting an ensemble of random feature ridge regressions. Our experiments show that a single DRE architect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.05417","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/2203.05417/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":"2026-07-05T04:03:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nChTSZjds19Hhuqxd3aUcTufPP7FQefuoaXhwoMClKQtPo/3m78xLfT1E2LYB/GZjEVgYRtDRCwMfmSG4NxsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:18:51.503725Z"},"content_sha256":"191e9bf229b2acb25ce5b385029e3b8ac5e522b2d07e128998561d6ecf7de493","schema_version":"1.0","event_id":"sha256:191e9bf229b2acb25ce5b385029e3b8ac5e522b2d07e128998561d6ecf7de493"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JE5GDYQUW2M4DYNXKOXPTQZUFJ/bundle.json","state_url":"https://pith.science/pith/JE5GDYQUW2M4DYNXKOXPTQZUFJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JE5GDYQUW2M4DYNXKOXPTQZUFJ/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":"2026-08-19T09:18:51Z","links":{"resolver":"https://pith.science/pith/JE5GDYQUW2M4DYNXKOXPTQZUFJ","bundle":"https://pith.science/pith/JE5GDYQUW2M4DYNXKOXPTQZUFJ/bundle.json","state":"https://pith.science/pith/JE5GDYQUW2M4DYNXKOXPTQZUFJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JE5GDYQUW2M4DYNXKOXPTQZUFJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JE5GDYQUW2M4DYNXKOXPTQZUFJ","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":"bff2117b72c291f987a3437d4af89f432473cae5186fa272466291fb700af093","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"stat.ML","submitted_at":"2022-03-10T15:13:46Z","title_canon_sha256":"a9631aeee4da98e506c716716c018dab2c7a3f547a870897b2d04b1772d8864d"},"schema_version":"1.0","source":{"id":"2203.05417","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.05417","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"arxiv_version","alias_value":"2203.05417v1","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.05417","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"pith_short_12","alias_value":"JE5GDYQUW2M4","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"pith_short_16","alias_value":"JE5GDYQUW2M4DYNX","created_at":"2026-07-05T04:03:41Z"},{"alias_kind":"pith_short_8","alias_value":"JE5GDYQU","created_at":"2026-07-05T04:03:41Z"}],"graph_snapshots":[{"event_id":"sha256:191e9bf229b2acb25ce5b385029e3b8ac5e522b2d07e128998561d6ecf7de493","target":"graph","created_at":"2026-07-05T04:03:41Z","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/2203.05417/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a methodology for designing and training deep neural networks (DNN) that we call \"Deep Regression Ensembles\" (DRE). It bridges the gap between DNN and two-layer neural networks trained with random feature regression. Each layer of DRE has two components, randomly drawn input weights and output weights trained myopically (as if the final output layer) using linear ridge regression. Within a layer, each neuron uses a different subset of inputs and a different ridge penalty, constituting an ensemble of random feature ridge regressions. Our experiments show that a single DRE architect","authors_text":"Antoine Didisheim, Bryan Kelly, Semyon Malamud","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"stat.ML","submitted_at":"2022-03-10T15:13:46Z","title":"Deep Regression Ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.05417","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":"sha256:857d47c8b48fae69ee5ac05daa34c865d6174792c634b73854705eac02af2447","target":"record","created_at":"2026-07-05T04:03:41Z","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":"bff2117b72c291f987a3437d4af89f432473cae5186fa272466291fb700af093","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"stat.ML","submitted_at":"2022-03-10T15:13:46Z","title_canon_sha256":"a9631aeee4da98e506c716716c018dab2c7a3f547a870897b2d04b1772d8864d"},"schema_version":"1.0","source":{"id":"2203.05417","kind":"arxiv","version":1}},"canonical_sha256":"493a61e214b699c1e1b753aef9c3342a57213c6d52a5eb1249d757ae8db8a675","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"493a61e214b699c1e1b753aef9c3342a57213c6d52a5eb1249d757ae8db8a675","first_computed_at":"2026-07-05T04:03:41.240827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:03:41.240827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SVaEu6pQJqqfm/0pk47+6XaGsh2B0hSRoiaBYZ17yIWwQVPhjcIDrEQKIQ8jxzYm3vBRvd29ZAXNtvtg/CMqCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:03:41.241234Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.05417","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:857d47c8b48fae69ee5ac05daa34c865d6174792c634b73854705eac02af2447","sha256:191e9bf229b2acb25ce5b385029e3b8ac5e522b2d07e128998561d6ecf7de493"],"state_sha256":"89f689c8ba530472151d750214ea787c57e6b85a1bb66433e4c12d355879f1e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ANAOV33uwaU8YzPIY0KzNHhp3wiVYYI7LWWLhM6PqwGBLBRW8cVmY0xHcEejh632NlUDSlKj2LsHX0v7Y2Z1BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T09:18:51.508589Z","bundle_sha256":"4ef1f971a11153020ba7baea39ad8132e9f52134ad43540f3b3656de8ab43670"}}