{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:L6SDIVYS65NPM5T54ZH2F4W67R","short_pith_number":"pith:L6SDIVYS","canonical_record":{"source":{"id":"1406.3781","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-14T23:25:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"007a2f4c8a7865a4790163abbe0a474b4f29383950a9a428026a8922b3908cbe","abstract_canon_sha256":"7bc5241dd4347cf33be0d44bcdc1389b781f1c2f8ea709ce5c44bc6c5f3d0958"},"schema_version":"1.0"},"canonical_sha256":"5fa4345712f75af6767de64fa2f2defc4a415ab1de9df0c0b79afccee6b7d603","source":{"kind":"arxiv","id":"1406.3781","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.3781","created_at":"2026-05-18T02:33:01Z"},{"alias_kind":"arxiv_version","alias_value":"1406.3781v2","created_at":"2026-05-18T02:33:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.3781","created_at":"2026-05-18T02:33:01Z"},{"alias_kind":"pith_short_12","alias_value":"L6SDIVYS65NP","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"L6SDIVYS65NPM5T5","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"L6SDIVYS","created_at":"2026-05-18T12:28:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:L6SDIVYS65NPM5T54ZH2F4W67R","target":"record","payload":{"canonical_record":{"source":{"id":"1406.3781","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-14T23:25:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"007a2f4c8a7865a4790163abbe0a474b4f29383950a9a428026a8922b3908cbe","abstract_canon_sha256":"7bc5241dd4347cf33be0d44bcdc1389b781f1c2f8ea709ce5c44bc6c5f3d0958"},"schema_version":"1.0"},"canonical_sha256":"5fa4345712f75af6767de64fa2f2defc4a415ab1de9df0c0b79afccee6b7d603","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:33:01.137138Z","signature_b64":"VWsPz/KUGnj3S6xJWwSCqyQfpRjeSlvEKQucLw0URi4m/c2pia8BcPq1A1bnIpLiOt0zGRQx5gBPc8sS1mfODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fa4345712f75af6767de64fa2f2defc4a415ab1de9df0c0b79afccee6b7d603","last_reissued_at":"2026-05-18T02:33:01.136812Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:33:01.136812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1406.3781","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":"2026-05-18T02:33:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JxInelwgRpb82kqRnPaN8qRRRQW5R+XyBH/tPfGChC1xJAq1kevgqrYiiuyLuB3UQlR+qRiwpEamwUvLEuahAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:22:10.929780Z"},"content_sha256":"1e4b7203fb7ca497b6e0cdb73ae88d93b434ea3a2a829e03cdad60239ae1eadc","schema_version":"1.0","event_id":"sha256:1e4b7203fb7ca497b6e0cdb73ae88d93b434ea3a2a829e03cdad60239ae1eadc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:L6SDIVYS65NPM5T54ZH2F4W67R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Stochastic Mixability to Fast Rates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nishant A. Mehta, Robert C. Williamson","submitted_at":"2014-06-14T23:25:05Z","abstract_excerpt":"Empirical risk minimization (ERM) is a fundamental learning rule for statistical learning problems where the data is generated according to some unknown distribution $\\mathsf{P}$ and returns a hypothesis $f$ chosen from a fixed class $\\mathcal{F}$ with small loss $\\ell$. In the parametric setting, depending upon $(\\ell, \\mathcal{F},\\mathsf{P})$ ERM can have slow $(1/\\sqrt{n})$ or fast $(1/n)$ rates of convergence of the excess risk as a function of the sample size $n$. There exist several results that give sufficient conditions for fast rates in terms of joint properties of $\\ell$, $\\mathcal{F"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.3781","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":""},"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":"2026-05-18T02:33:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o/fNqSoR19QUjCfrSoqDq2bX6m9K5JOZ8forGnIBqxHi6n9opiI4T4ZU7E26oSdQ4syYUpu8sfswfGGfeE6xAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:22:10.930301Z"},"content_sha256":"0135fb3daebf00cee81f0d7c4bfaced216017cf5c80eb83c7050a7970f7df7cc","schema_version":"1.0","event_id":"sha256:0135fb3daebf00cee81f0d7c4bfaced216017cf5c80eb83c7050a7970f7df7cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L6SDIVYS65NPM5T54ZH2F4W67R/bundle.json","state_url":"https://pith.science/pith/L6SDIVYS65NPM5T54ZH2F4W67R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L6SDIVYS65NPM5T54ZH2F4W67R/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":"2026-05-26T08:22:10Z","links":{"resolver":"https://pith.science/pith/L6SDIVYS65NPM5T54ZH2F4W67R","bundle":"https://pith.science/pith/L6SDIVYS65NPM5T54ZH2F4W67R/bundle.json","state":"https://pith.science/pith/L6SDIVYS65NPM5T54ZH2F4W67R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L6SDIVYS65NPM5T54ZH2F4W67R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:L6SDIVYS65NPM5T54ZH2F4W67R","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":"7bc5241dd4347cf33be0d44bcdc1389b781f1c2f8ea709ce5c44bc6c5f3d0958","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-14T23:25:05Z","title_canon_sha256":"007a2f4c8a7865a4790163abbe0a474b4f29383950a9a428026a8922b3908cbe"},"schema_version":"1.0","source":{"id":"1406.3781","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.3781","created_at":"2026-05-18T02:33:01Z"},{"alias_kind":"arxiv_version","alias_value":"1406.3781v2","created_at":"2026-05-18T02:33:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.3781","created_at":"2026-05-18T02:33:01Z"},{"alias_kind":"pith_short_12","alias_value":"L6SDIVYS65NP","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"L6SDIVYS65NPM5T5","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"L6SDIVYS","created_at":"2026-05-18T12:28:35Z"}],"graph_snapshots":[{"event_id":"sha256:0135fb3daebf00cee81f0d7c4bfaced216017cf5c80eb83c7050a7970f7df7cc","target":"graph","created_at":"2026-05-18T02:33:01Z","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":"Empirical risk minimization (ERM) is a fundamental learning rule for statistical learning problems where the data is generated according to some unknown distribution $\\mathsf{P}$ and returns a hypothesis $f$ chosen from a fixed class $\\mathcal{F}$ with small loss $\\ell$. In the parametric setting, depending upon $(\\ell, \\mathcal{F},\\mathsf{P})$ ERM can have slow $(1/\\sqrt{n})$ or fast $(1/n)$ rates of convergence of the excess risk as a function of the sample size $n$. There exist several results that give sufficient conditions for fast rates in terms of joint properties of $\\ell$, $\\mathcal{F","authors_text":"Nishant A. Mehta, Robert C. Williamson","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-14T23:25:05Z","title":"From Stochastic Mixability to Fast Rates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.3781","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":"sha256:1e4b7203fb7ca497b6e0cdb73ae88d93b434ea3a2a829e03cdad60239ae1eadc","target":"record","created_at":"2026-05-18T02:33:01Z","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":"7bc5241dd4347cf33be0d44bcdc1389b781f1c2f8ea709ce5c44bc6c5f3d0958","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-14T23:25:05Z","title_canon_sha256":"007a2f4c8a7865a4790163abbe0a474b4f29383950a9a428026a8922b3908cbe"},"schema_version":"1.0","source":{"id":"1406.3781","kind":"arxiv","version":2}},"canonical_sha256":"5fa4345712f75af6767de64fa2f2defc4a415ab1de9df0c0b79afccee6b7d603","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fa4345712f75af6767de64fa2f2defc4a415ab1de9df0c0b79afccee6b7d603","first_computed_at":"2026-05-18T02:33:01.136812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:33:01.136812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VWsPz/KUGnj3S6xJWwSCqyQfpRjeSlvEKQucLw0URi4m/c2pia8BcPq1A1bnIpLiOt0zGRQx5gBPc8sS1mfODQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:33:01.137138Z","signed_message":"canonical_sha256_bytes"},"source_id":"1406.3781","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e4b7203fb7ca497b6e0cdb73ae88d93b434ea3a2a829e03cdad60239ae1eadc","sha256:0135fb3daebf00cee81f0d7c4bfaced216017cf5c80eb83c7050a7970f7df7cc"],"state_sha256":"e61c540de6cc118813a78358f9e49dcde820f06683a33183a47c863d5f1c430e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qwje+8MKSCSdKb5UAf61Jn+8BsOOWVuJB4I5wYvBv+ilTAXfO/N6omR4H0FMDkSy8GCrCj4peRkCtAt/rEEwAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T08:22:10.933572Z","bundle_sha256":"7f37d896aae3977b645a966586c96240d29604f825f93d46e3471b073a0d2d7b"}}