{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:S7CJ5HIQEVZTMW225ROHDOH4G6","short_pith_number":"pith:S7CJ5HIQ","canonical_record":{"source":{"id":"1501.02629","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-01-12T12:58:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"608794777306b59080d6e54a261157aeca6a5f947a26574ee6488a6768b31a48","abstract_canon_sha256":"a8bbab94754415f57f0a678b27d271e069e2461c933d91a222021dad09ecd9da"},"schema_version":"1.0"},"canonical_sha256":"97c49e9d102573365b5aec5c71b8fc37bb78f3f0759f61fbfa68ad800f5880c6","source":{"kind":"arxiv","id":"1501.02629","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1501.02629","created_at":"2026-05-17T23:55:39Z"},{"alias_kind":"arxiv_version","alias_value":"1501.02629v4","created_at":"2026-05-17T23:55:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.02629","created_at":"2026-05-17T23:55:39Z"},{"alias_kind":"pith_short_12","alias_value":"S7CJ5HIQEVZT","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"S7CJ5HIQEVZTMW22","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"S7CJ5HIQ","created_at":"2026-05-18T12:29:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:S7CJ5HIQEVZTMW225ROHDOH4G6","target":"record","payload":{"canonical_record":{"source":{"id":"1501.02629","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-01-12T12:58:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"608794777306b59080d6e54a261157aeca6a5f947a26574ee6488a6768b31a48","abstract_canon_sha256":"a8bbab94754415f57f0a678b27d271e069e2461c933d91a222021dad09ecd9da"},"schema_version":"1.0"},"canonical_sha256":"97c49e9d102573365b5aec5c71b8fc37bb78f3f0759f61fbfa68ad800f5880c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:39.159568Z","signature_b64":"rD/Td0OsCd/iGn+gkA1XO3Mmza304zD67MdhP9+HQ9KvHvICJ8dbMKk/+LOUzipUlN0IQghE7/Rm4/xvYMNODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97c49e9d102573365b5aec5c71b8fc37bb78f3f0759f61fbfa68ad800f5880c6","last_reissued_at":"2026-05-17T23:55:39.159117Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:39.159117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1501.02629","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:55:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p2JSDZlBF+BTMKPU4QThyJ3t2I3aSVmWbgVjZM3GH3I/IsgBUjVku2GV9s9AkORN/EL89c0wGEGEsYEi5aJsCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:03:28.199279Z"},"content_sha256":"4d76285a779a0a115cc6b365c17ba731fba326416513865e441f293d5466f1bc","schema_version":"1.0","event_id":"sha256:4d76285a779a0a115cc6b365c17ba731fba326416513865e441f293d5466f1bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:S7CJ5HIQEVZTMW225ROHDOH4G6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling-up Empirical Risk Minimization: Optimization of Incomplete U-statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Aur\\'elien Bellet, Igor Colin, St\\'ephan Cl\\'emen\\c{c}on","submitted_at":"2015-01-12T12:58:45Z","abstract_excerpt":"In a wide range of statistical learning problems such as ranking, clustering or metric learning among others, the risk is accurately estimated by $U$-statistics of degree $d\\geq 1$, i.e. functionals of the training data with low variance that take the form of averages over $k$-tuples. From a computational perspective, the calculation of such statistics is highly expensive even for a moderate sample size $n$, as it requires averaging $O(n^d)$ terms. This makes learning procedures relying on the optimization of such data functionals hardly feasible in practice. It is the major goal of this paper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1501.02629","kind":"arxiv","version":4},"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":"2026-05-17T23:55:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ysEIs92/Lfi4wmS6X6zrkiVhxkRQwWzpv/lSX9y4VeI7cRVEWcB1KdPggrIcLERO1BRQjT1VvR8DJWUxfzLWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:03:28.199655Z"},"content_sha256":"6b69cd492826e385ce0899983b3ee5dab64b6a688531c8966c817cca7930c41e","schema_version":"1.0","event_id":"sha256:6b69cd492826e385ce0899983b3ee5dab64b6a688531c8966c817cca7930c41e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S7CJ5HIQEVZTMW225ROHDOH4G6/bundle.json","state_url":"https://pith.science/pith/S7CJ5HIQEVZTMW225ROHDOH4G6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S7CJ5HIQEVZTMW225ROHDOH4G6/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":"2026-06-02T22:03:28Z","links":{"resolver":"https://pith.science/pith/S7CJ5HIQEVZTMW225ROHDOH4G6","bundle":"https://pith.science/pith/S7CJ5HIQEVZTMW225ROHDOH4G6/bundle.json","state":"https://pith.science/pith/S7CJ5HIQEVZTMW225ROHDOH4G6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S7CJ5HIQEVZTMW225ROHDOH4G6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:S7CJ5HIQEVZTMW225ROHDOH4G6","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":"a8bbab94754415f57f0a678b27d271e069e2461c933d91a222021dad09ecd9da","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-01-12T12:58:45Z","title_canon_sha256":"608794777306b59080d6e54a261157aeca6a5f947a26574ee6488a6768b31a48"},"schema_version":"1.0","source":{"id":"1501.02629","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1501.02629","created_at":"2026-05-17T23:55:39Z"},{"alias_kind":"arxiv_version","alias_value":"1501.02629v4","created_at":"2026-05-17T23:55:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.02629","created_at":"2026-05-17T23:55:39Z"},{"alias_kind":"pith_short_12","alias_value":"S7CJ5HIQEVZT","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"S7CJ5HIQEVZTMW22","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"S7CJ5HIQ","created_at":"2026-05-18T12:29:39Z"}],"graph_snapshots":[{"event_id":"sha256:6b69cd492826e385ce0899983b3ee5dab64b6a688531c8966c817cca7930c41e","target":"graph","created_at":"2026-05-17T23:55:39Z","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":"In a wide range of statistical learning problems such as ranking, clustering or metric learning among others, the risk is accurately estimated by $U$-statistics of degree $d\\geq 1$, i.e. functionals of the training data with low variance that take the form of averages over $k$-tuples. From a computational perspective, the calculation of such statistics is highly expensive even for a moderate sample size $n$, as it requires averaging $O(n^d)$ terms. This makes learning procedures relying on the optimization of such data functionals hardly feasible in practice. It is the major goal of this paper","authors_text":"Aur\\'elien Bellet, Igor Colin, St\\'ephan Cl\\'emen\\c{c}on","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-01-12T12:58:45Z","title":"Scaling-up Empirical Risk Minimization: Optimization of Incomplete U-statistics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1501.02629","kind":"arxiv","version":4},"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":"sha256:4d76285a779a0a115cc6b365c17ba731fba326416513865e441f293d5466f1bc","target":"record","created_at":"2026-05-17T23:55:39Z","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":"a8bbab94754415f57f0a678b27d271e069e2461c933d91a222021dad09ecd9da","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-01-12T12:58:45Z","title_canon_sha256":"608794777306b59080d6e54a261157aeca6a5f947a26574ee6488a6768b31a48"},"schema_version":"1.0","source":{"id":"1501.02629","kind":"arxiv","version":4}},"canonical_sha256":"97c49e9d102573365b5aec5c71b8fc37bb78f3f0759f61fbfa68ad800f5880c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97c49e9d102573365b5aec5c71b8fc37bb78f3f0759f61fbfa68ad800f5880c6","first_computed_at":"2026-05-17T23:55:39.159117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:39.159117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rD/Td0OsCd/iGn+gkA1XO3Mmza304zD67MdhP9+HQ9KvHvICJ8dbMKk/+LOUzipUlN0IQghE7/Rm4/xvYMNODA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:39.159568Z","signed_message":"canonical_sha256_bytes"},"source_id":"1501.02629","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d76285a779a0a115cc6b365c17ba731fba326416513865e441f293d5466f1bc","sha256:6b69cd492826e385ce0899983b3ee5dab64b6a688531c8966c817cca7930c41e"],"state_sha256":"923c138e406d8855c67c827dab408158eb12f1128f6f0c83ab5cc5661944dc79"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WzJQ6wcfXuNl0BRjKqrH69IXDeJ1c6kuCFUESzkvoF104Yk0MvBQdjMEePbrLe2edkwPbGDVumv5lOJ0Ifq4Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T22:03:28.201778Z","bundle_sha256":"6e540f1f01e4edc668ac7aa380a907c633dd13f101d2b0da349bcb4c0a9cc238"}}