{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:A3ELVCBMHYW7VJQZMVZUTIB66E","short_pith_number":"pith:A3ELVCBM","canonical_record":{"source":{"id":"1902.01846","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-05T18:31:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8a9fd44a5d1764c55fcef6837432138559369c3d52a70fb343e1bd0ceee04902","abstract_canon_sha256":"a83f435fff18a45e863add21d611a031117a1b50ce08693da9c6f75b1a25d506"},"schema_version":"1.0"},"canonical_sha256":"06c8ba882c3e2dfaa619657349a03ef139502a995ab96e08eba5877bc274fa57","source":{"kind":"arxiv","id":"1902.01846","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.01846","created_at":"2026-05-17T23:54:42Z"},{"alias_kind":"arxiv_version","alias_value":"1902.01846v1","created_at":"2026-05-17T23:54:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01846","created_at":"2026-05-17T23:54:42Z"},{"alias_kind":"pith_short_12","alias_value":"A3ELVCBMHYW7","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"A3ELVCBMHYW7VJQZ","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"A3ELVCBM","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:A3ELVCBMHYW7VJQZMVZUTIB66E","target":"record","payload":{"canonical_record":{"source":{"id":"1902.01846","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-05T18:31:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8a9fd44a5d1764c55fcef6837432138559369c3d52a70fb343e1bd0ceee04902","abstract_canon_sha256":"a83f435fff18a45e863add21d611a031117a1b50ce08693da9c6f75b1a25d506"},"schema_version":"1.0"},"canonical_sha256":"06c8ba882c3e2dfaa619657349a03ef139502a995ab96e08eba5877bc274fa57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:42.195215Z","signature_b64":"xqhPp0VY7sE7xBFmzHHvuTsPnVIPBKl/NkqbQ+s6Hs3XIB62EFAj0oQZYXUkIS/UUC8KpfOdKWxX0XLaGuACDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06c8ba882c3e2dfaa619657349a03ef139502a995ab96e08eba5877bc274fa57","last_reissued_at":"2026-05-17T23:54:42.194637Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:42.194637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.01846","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":"2026-05-17T23:54:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YuDq7eVhCYcJQQ4p8JoIZ9xTNnYwS7UJ6BzHxEOannUJTx0h4ql47r8isN0vRj9WAY52TOjMjdP7Ifhike4UAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T18:08:58.477867Z"},"content_sha256":"909a49f04639ad0b450946bbc991446c3cbfa3ed7b927739392c3e2992ad8ab7","schema_version":"1.0","event_id":"sha256:909a49f04639ad0b450946bbc991446c3cbfa3ed7b927739392c3e2992ad8ab7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:A3ELVCBMHYW7VJQZMVZUTIB66E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distribution-Dependent Analysis of Gibbs-ERM Principle","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Csaba Szepesv\\'ari, Ilja Kuzborskij, Nicol\\`o Cesa-Bianchi","submitted_at":"2019-02-05T18:31:23Z","abstract_excerpt":"Gibbs-ERM learning is a natural idealized model of learning with stochastic optimization algorithms (such as Stochastic Gradient Langevin Dynamics and ---to some extent--- Stochastic Gradient Descent), while it also arises in other contexts, including PAC-Bayesian theory, and sampling mechanisms. In this work we study the excess risk suffered by a Gibbs-ERM learner that uses non-convex, regularized empirical risk with the goal to understand the interplay between the data-generating distribution and learning in large hypothesis spaces. Our main results are distribution-dependent upper bounds on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01846","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":""},"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":"2026-05-17T23:54:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dH1kp0AkIKlUPhRmbpfSKNXeXi+VChHTCvJVhka+9OoKw1xiaud2m1jMnzbyZwEfe0Fl+wvN2j69DqhgWN95AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T18:08:58.478347Z"},"content_sha256":"549362eb57f56b87a0a49e52614918c8546f3293f1b47e08a1ff3596caccec6b","schema_version":"1.0","event_id":"sha256:549362eb57f56b87a0a49e52614918c8546f3293f1b47e08a1ff3596caccec6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A3ELVCBMHYW7VJQZMVZUTIB66E/bundle.json","state_url":"https://pith.science/pith/A3ELVCBMHYW7VJQZMVZUTIB66E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A3ELVCBMHYW7VJQZMVZUTIB66E/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":"2026-05-26T18:08:58Z","links":{"resolver":"https://pith.science/pith/A3ELVCBMHYW7VJQZMVZUTIB66E","bundle":"https://pith.science/pith/A3ELVCBMHYW7VJQZMVZUTIB66E/bundle.json","state":"https://pith.science/pith/A3ELVCBMHYW7VJQZMVZUTIB66E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A3ELVCBMHYW7VJQZMVZUTIB66E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:A3ELVCBMHYW7VJQZMVZUTIB66E","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":"a83f435fff18a45e863add21d611a031117a1b50ce08693da9c6f75b1a25d506","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-05T18:31:23Z","title_canon_sha256":"8a9fd44a5d1764c55fcef6837432138559369c3d52a70fb343e1bd0ceee04902"},"schema_version":"1.0","source":{"id":"1902.01846","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.01846","created_at":"2026-05-17T23:54:42Z"},{"alias_kind":"arxiv_version","alias_value":"1902.01846v1","created_at":"2026-05-17T23:54:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01846","created_at":"2026-05-17T23:54:42Z"},{"alias_kind":"pith_short_12","alias_value":"A3ELVCBMHYW7","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"A3ELVCBMHYW7VJQZ","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"A3ELVCBM","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:549362eb57f56b87a0a49e52614918c8546f3293f1b47e08a1ff3596caccec6b","target":"graph","created_at":"2026-05-17T23:54:42Z","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"},"paper":{"abstract_excerpt":"Gibbs-ERM learning is a natural idealized model of learning with stochastic optimization algorithms (such as Stochastic Gradient Langevin Dynamics and ---to some extent--- Stochastic Gradient Descent), while it also arises in other contexts, including PAC-Bayesian theory, and sampling mechanisms. In this work we study the excess risk suffered by a Gibbs-ERM learner that uses non-convex, regularized empirical risk with the goal to understand the interplay between the data-generating distribution and learning in large hypothesis spaces. Our main results are distribution-dependent upper bounds on","authors_text":"Csaba Szepesv\\'ari, Ilja Kuzborskij, Nicol\\`o Cesa-Bianchi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-05T18:31:23Z","title":"Distribution-Dependent Analysis of Gibbs-ERM Principle"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01846","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":"sha256:909a49f04639ad0b450946bbc991446c3cbfa3ed7b927739392c3e2992ad8ab7","target":"record","created_at":"2026-05-17T23:54:42Z","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":"a83f435fff18a45e863add21d611a031117a1b50ce08693da9c6f75b1a25d506","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-05T18:31:23Z","title_canon_sha256":"8a9fd44a5d1764c55fcef6837432138559369c3d52a70fb343e1bd0ceee04902"},"schema_version":"1.0","source":{"id":"1902.01846","kind":"arxiv","version":1}},"canonical_sha256":"06c8ba882c3e2dfaa619657349a03ef139502a995ab96e08eba5877bc274fa57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06c8ba882c3e2dfaa619657349a03ef139502a995ab96e08eba5877bc274fa57","first_computed_at":"2026-05-17T23:54:42.194637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:42.194637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xqhPp0VY7sE7xBFmzHHvuTsPnVIPBKl/NkqbQ+s6Hs3XIB62EFAj0oQZYXUkIS/UUC8KpfOdKWxX0XLaGuACDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:42.195215Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.01846","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:909a49f04639ad0b450946bbc991446c3cbfa3ed7b927739392c3e2992ad8ab7","sha256:549362eb57f56b87a0a49e52614918c8546f3293f1b47e08a1ff3596caccec6b"],"state_sha256":"6364959937efa3dfd807ac445c158e78cc2349c5cb54863cd15b1be8d443f6cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"biTOs4TsW7W6GHc+Lmau00kO2jTrfG4Koduh+dEpe0Z9K4Frc+adozxdOGe1Gn/qF9DouiZ4iuRKYDrGACEFDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T18:08:58.480883Z","bundle_sha256":"296dd8d7c75013b77ba417299ceecbcd14fc18c3fb4e394e635e7181780a7e63"}}