{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WVJ3SUX5L2NFQPBTJOJ5HBYDHP","short_pith_number":"pith:WVJ3SUX5","canonical_record":{"source":{"id":"1812.07738","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-19T02:58:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"de028f3e88ace498c7aacd4dcf7fe09746ff427e8d406c7d402480ff97e11c02","abstract_canon_sha256":"493733f4c4a4c5345ee88ded6a14c66df37e4e58bf485040be6f0e995685b9d3"},"schema_version":"1.0"},"canonical_sha256":"b553b952fd5e9a583c334b93d387033bfe376a7302c8009cd6b34ef3afc9092d","source":{"kind":"arxiv","id":"1812.07738","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.07738","created_at":"2026-05-17T23:56:04Z"},{"alias_kind":"arxiv_version","alias_value":"1812.07738v2","created_at":"2026-05-17T23:56:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07738","created_at":"2026-05-17T23:56:04Z"},{"alias_kind":"pith_short_12","alias_value":"WVJ3SUX5L2NF","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WVJ3SUX5L2NFQPBT","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WVJ3SUX5","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WVJ3SUX5L2NFQPBTJOJ5HBYDHP","target":"record","payload":{"canonical_record":{"source":{"id":"1812.07738","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-19T02:58:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"de028f3e88ace498c7aacd4dcf7fe09746ff427e8d406c7d402480ff97e11c02","abstract_canon_sha256":"493733f4c4a4c5345ee88ded6a14c66df37e4e58bf485040be6f0e995685b9d3"},"schema_version":"1.0"},"canonical_sha256":"b553b952fd5e9a583c334b93d387033bfe376a7302c8009cd6b34ef3afc9092d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:05.000294Z","signature_b64":"4yaw2rclOh7Zb+O4isHQLrHqJ3bzrwNHoIxRn5rLpUiM8kzMmU/e3q1fua2i0aKa4Je8RWQ3+oxVjqX5L1wmDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b553b952fd5e9a583c334b93d387033bfe376a7302c8009cd6b34ef3afc9092d","last_reissued_at":"2026-05-17T23:56:04.999724Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:04.999724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.07738","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":"2026-05-17T23:56:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K/Pj9ZboczZrUdHeQVT2fIUtIc6Dg2BRT5Q7meawACbkYhP+3yJQvDKhnfY9zR2tZnfET0E8/sWX4je3mghrAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:29:16.284114Z"},"content_sha256":"c24c885219abf4a1f88051669ac870d379a88f127f62369dbd206a6c9965fd15","schema_version":"1.0","event_id":"sha256:c24c885219abf4a1f88051669ac870d379a88f127f62369dbd206a6c9965fd15"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WVJ3SUX5L2NFQPBTJOJ5HBYDHP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Max-Diversity Distributed Learning: Theory and Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jian Li, Weiping Wang, Yong Liu","submitted_at":"2018-12-19T02:58:43Z","abstract_excerpt":"We study the risk performance of distributed learning for the regularization empirical risk minimization with fast convergence rate, substantially improving the error analysis of the existing divide-and-conquer based distributed learning. An interesting theoretical finding is that the larger the diversity of each local estimate is, the tighter the risk bound is. This theoretical analysis motivates us to devise an effective maxdiversity distributed learning algorithm (MDD). Experimental results show that MDD can outperform the existing divide-andconquer methods but with a bit more time. Theoret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07738","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":"2026-05-17T23:56:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9o89U4XuzdFtsNnmsqjvAu+86g8sJV8s/2/2XcpB0AAJTeGyF7aJSFvl5uCyYxUVmQFP3yHO4lLsypUXL/5+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:29:16.284477Z"},"content_sha256":"ee220c92eb75ff3d5ee73c02e4fcee90fea4ba2b1b8110639cb1b7731daff589","schema_version":"1.0","event_id":"sha256:ee220c92eb75ff3d5ee73c02e4fcee90fea4ba2b1b8110639cb1b7731daff589"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WVJ3SUX5L2NFQPBTJOJ5HBYDHP/bundle.json","state_url":"https://pith.science/pith/WVJ3SUX5L2NFQPBTJOJ5HBYDHP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WVJ3SUX5L2NFQPBTJOJ5HBYDHP/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":"2026-06-03T20:29:16Z","links":{"resolver":"https://pith.science/pith/WVJ3SUX5L2NFQPBTJOJ5HBYDHP","bundle":"https://pith.science/pith/WVJ3SUX5L2NFQPBTJOJ5HBYDHP/bundle.json","state":"https://pith.science/pith/WVJ3SUX5L2NFQPBTJOJ5HBYDHP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WVJ3SUX5L2NFQPBTJOJ5HBYDHP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WVJ3SUX5L2NFQPBTJOJ5HBYDHP","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":"493733f4c4a4c5345ee88ded6a14c66df37e4e58bf485040be6f0e995685b9d3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-19T02:58:43Z","title_canon_sha256":"de028f3e88ace498c7aacd4dcf7fe09746ff427e8d406c7d402480ff97e11c02"},"schema_version":"1.0","source":{"id":"1812.07738","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.07738","created_at":"2026-05-17T23:56:04Z"},{"alias_kind":"arxiv_version","alias_value":"1812.07738v2","created_at":"2026-05-17T23:56:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07738","created_at":"2026-05-17T23:56:04Z"},{"alias_kind":"pith_short_12","alias_value":"WVJ3SUX5L2NF","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WVJ3SUX5L2NFQPBT","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WVJ3SUX5","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:ee220c92eb75ff3d5ee73c02e4fcee90fea4ba2b1b8110639cb1b7731daff589","target":"graph","created_at":"2026-05-17T23:56:04Z","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":"We study the risk performance of distributed learning for the regularization empirical risk minimization with fast convergence rate, substantially improving the error analysis of the existing divide-and-conquer based distributed learning. An interesting theoretical finding is that the larger the diversity of each local estimate is, the tighter the risk bound is. This theoretical analysis motivates us to devise an effective maxdiversity distributed learning algorithm (MDD). Experimental results show that MDD can outperform the existing divide-andconquer methods but with a bit more time. Theoret","authors_text":"Jian Li, Weiping Wang, Yong Liu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-19T02:58:43Z","title":"Max-Diversity Distributed Learning: Theory and Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07738","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:c24c885219abf4a1f88051669ac870d379a88f127f62369dbd206a6c9965fd15","target":"record","created_at":"2026-05-17T23:56:04Z","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":"493733f4c4a4c5345ee88ded6a14c66df37e4e58bf485040be6f0e995685b9d3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-19T02:58:43Z","title_canon_sha256":"de028f3e88ace498c7aacd4dcf7fe09746ff427e8d406c7d402480ff97e11c02"},"schema_version":"1.0","source":{"id":"1812.07738","kind":"arxiv","version":2}},"canonical_sha256":"b553b952fd5e9a583c334b93d387033bfe376a7302c8009cd6b34ef3afc9092d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b553b952fd5e9a583c334b93d387033bfe376a7302c8009cd6b34ef3afc9092d","first_computed_at":"2026-05-17T23:56:04.999724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:04.999724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4yaw2rclOh7Zb+O4isHQLrHqJ3bzrwNHoIxRn5rLpUiM8kzMmU/e3q1fua2i0aKa4Je8RWQ3+oxVjqX5L1wmDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:05.000294Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.07738","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c24c885219abf4a1f88051669ac870d379a88f127f62369dbd206a6c9965fd15","sha256:ee220c92eb75ff3d5ee73c02e4fcee90fea4ba2b1b8110639cb1b7731daff589"],"state_sha256":"249ca524191680a9c3b163b6259489e53e976ed43ab14d30f070517e13ce006f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qjS3IF2MgKVBwj8+wlE7h1DC2cVfwZZPjYDtE1P3Fg5zqvPTllWTF04yeq0SP8T2NKMHepAans9ymMIXEAWaDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T20:29:16.286406Z","bundle_sha256":"3dd425f969ec71bea405bb287ff8bfdaba8ae3db249f6caf9c63faf2d59aaea6"}}