{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:3KKWRSB5VMTUYFX35WVTBZUYKB","short_pith_number":"pith:3KKWRSB5","canonical_record":{"source":{"id":"1103.2068","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-03-10T16:15:42Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"bff412e6205a0d43dd5cd6e885d67dba6d23acc7892d501b5b6ac9b5f050913b","abstract_canon_sha256":"2b1cb463775865cbe1e27920e3dae53829d6edf4761450ed731af8b1c96d9dfa"},"schema_version":"1.0"},"canonical_sha256":"da9568c83dab274c16fbedab30e698506143e001add0c58cb5b404897f576ef4","source":{"kind":"arxiv","id":"1103.2068","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1103.2068","created_at":"2026-05-18T03:31:54Z"},{"alias_kind":"arxiv_version","alias_value":"1103.2068v2","created_at":"2026-05-18T03:31:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1103.2068","created_at":"2026-05-18T03:31:54Z"},{"alias_kind":"pith_short_12","alias_value":"3KKWRSB5VMTU","created_at":"2026-05-18T12:26:18Z"},{"alias_kind":"pith_short_16","alias_value":"3KKWRSB5VMTUYFX3","created_at":"2026-05-18T12:26:18Z"},{"alias_kind":"pith_short_8","alias_value":"3KKWRSB5","created_at":"2026-05-18T12:26:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:3KKWRSB5VMTUYFX35WVTBZUYKB","target":"record","payload":{"canonical_record":{"source":{"id":"1103.2068","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-03-10T16:15:42Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"bff412e6205a0d43dd5cd6e885d67dba6d23acc7892d501b5b6ac9b5f050913b","abstract_canon_sha256":"2b1cb463775865cbe1e27920e3dae53829d6edf4761450ed731af8b1c96d9dfa"},"schema_version":"1.0"},"canonical_sha256":"da9568c83dab274c16fbedab30e698506143e001add0c58cb5b404897f576ef4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:31:54.536628Z","signature_b64":"LyMhsM29C16xLKpbBAFC9VQTMX0ORnirqg7kAf6e7PqBJqOmmqPvzI+ZwXkwoHikz9p2ZVG8wCOeLmXGJbceBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da9568c83dab274c16fbedab30e698506143e001add0c58cb5b404897f576ef4","last_reissued_at":"2026-05-18T03:31:54.535937Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:31:54.535937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1103.2068","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":"2026-05-18T03:31:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CLVoBozd4QYHoqlg6hBYzPJTe0tPL8ALUnFugBvWCEwwAWvBI2f6/4GTrQqOex2TBHJmBl3vPdHUwVRJ3Gl8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T02:33:44.201116Z"},"content_sha256":"7d052c48527fd437592414e576d8d7157c14aab35289a1da1460a295c5328c74","schema_version":"1.0","event_id":"sha256:7d052c48527fd437592414e576d8d7157c14aab35289a1da1460a295c5328c74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:3KKWRSB5VMTUYFX35WVTBZUYKB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"COMET: A Recipe for Learning and Using Large Ensembles on Massive Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Justin D. Basilico, Kevin R. Dixon, M. Arthur Munson, Tamara G. Kolda, W. Philip Kegelmeyer","submitted_at":"2011-03-10T16:15:42Z","abstract_excerpt":"COMET is a single-pass MapReduce algorithm for learning on large-scale data. It builds multiple random forest ensembles on distributed blocks of data and merges them into a mega-ensemble. This approach is appropriate when learning from massive-scale data that is too large to fit on a single machine. To get the best accuracy, IVoting should be used instead of bagging to generate the training subset for each decision tree in the random forest. Experiments with two large datasets (5GB and 50GB compressed) show that COMET compares favorably (in both accuracy and training time) to learning on a sub"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1103.2068","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":"2026-05-18T03:31:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0siHUKJFANcXXDZhk0sfHBLYwraNzmwR60XXx+pudmeI2NVkSQCNagBvRJIv7H5u5f26c9w5kYWxrfgl/0SsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T02:33:44.201732Z"},"content_sha256":"664448739f8f8bdb40804f25f976a33605c6e383efa17e5c14de3dfbfeb3a060","schema_version":"1.0","event_id":"sha256:664448739f8f8bdb40804f25f976a33605c6e383efa17e5c14de3dfbfeb3a060"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3KKWRSB5VMTUYFX35WVTBZUYKB/bundle.json","state_url":"https://pith.science/pith/3KKWRSB5VMTUYFX35WVTBZUYKB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3KKWRSB5VMTUYFX35WVTBZUYKB/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":"2026-05-28T02:33:44Z","links":{"resolver":"https://pith.science/pith/3KKWRSB5VMTUYFX35WVTBZUYKB","bundle":"https://pith.science/pith/3KKWRSB5VMTUYFX35WVTBZUYKB/bundle.json","state":"https://pith.science/pith/3KKWRSB5VMTUYFX35WVTBZUYKB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3KKWRSB5VMTUYFX35WVTBZUYKB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:3KKWRSB5VMTUYFX35WVTBZUYKB","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":"2b1cb463775865cbe1e27920e3dae53829d6edf4761450ed731af8b1c96d9dfa","cross_cats_sorted":["cs.DC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-03-10T16:15:42Z","title_canon_sha256":"bff412e6205a0d43dd5cd6e885d67dba6d23acc7892d501b5b6ac9b5f050913b"},"schema_version":"1.0","source":{"id":"1103.2068","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1103.2068","created_at":"2026-05-18T03:31:54Z"},{"alias_kind":"arxiv_version","alias_value":"1103.2068v2","created_at":"2026-05-18T03:31:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1103.2068","created_at":"2026-05-18T03:31:54Z"},{"alias_kind":"pith_short_12","alias_value":"3KKWRSB5VMTU","created_at":"2026-05-18T12:26:18Z"},{"alias_kind":"pith_short_16","alias_value":"3KKWRSB5VMTUYFX3","created_at":"2026-05-18T12:26:18Z"},{"alias_kind":"pith_short_8","alias_value":"3KKWRSB5","created_at":"2026-05-18T12:26:18Z"}],"graph_snapshots":[{"event_id":"sha256:664448739f8f8bdb40804f25f976a33605c6e383efa17e5c14de3dfbfeb3a060","target":"graph","created_at":"2026-05-18T03:31:54Z","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":"COMET is a single-pass MapReduce algorithm for learning on large-scale data. It builds multiple random forest ensembles on distributed blocks of data and merges them into a mega-ensemble. This approach is appropriate when learning from massive-scale data that is too large to fit on a single machine. To get the best accuracy, IVoting should be used instead of bagging to generate the training subset for each decision tree in the random forest. Experiments with two large datasets (5GB and 50GB compressed) show that COMET compares favorably (in both accuracy and training time) to learning on a sub","authors_text":"Justin D. Basilico, Kevin R. Dixon, M. Arthur Munson, Tamara G. Kolda, W. Philip Kegelmeyer","cross_cats":["cs.DC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-03-10T16:15:42Z","title":"COMET: A Recipe for Learning and Using Large Ensembles on Massive Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1103.2068","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":"sha256:7d052c48527fd437592414e576d8d7157c14aab35289a1da1460a295c5328c74","target":"record","created_at":"2026-05-18T03:31:54Z","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":"2b1cb463775865cbe1e27920e3dae53829d6edf4761450ed731af8b1c96d9dfa","cross_cats_sorted":["cs.DC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-03-10T16:15:42Z","title_canon_sha256":"bff412e6205a0d43dd5cd6e885d67dba6d23acc7892d501b5b6ac9b5f050913b"},"schema_version":"1.0","source":{"id":"1103.2068","kind":"arxiv","version":2}},"canonical_sha256":"da9568c83dab274c16fbedab30e698506143e001add0c58cb5b404897f576ef4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da9568c83dab274c16fbedab30e698506143e001add0c58cb5b404897f576ef4","first_computed_at":"2026-05-18T03:31:54.535937Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:31:54.535937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LyMhsM29C16xLKpbBAFC9VQTMX0ORnirqg7kAf6e7PqBJqOmmqPvzI+ZwXkwoHikz9p2ZVG8wCOeLmXGJbceBw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:31:54.536628Z","signed_message":"canonical_sha256_bytes"},"source_id":"1103.2068","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d052c48527fd437592414e576d8d7157c14aab35289a1da1460a295c5328c74","sha256:664448739f8f8bdb40804f25f976a33605c6e383efa17e5c14de3dfbfeb3a060"],"state_sha256":"418e1a8d4cffbfc59281dd51263fce445408fcfd7e5072e54a51ea5aba55f2aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EWtppo5to82WxtNaH4eXZu2l50ESxzC2CYMkNUsCC/i6U4ivA8gnkfijHWLtFe8VFjmJQ1x7E4S93l2ZdH+yDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T02:33:44.204511Z","bundle_sha256":"ccb6936ab12bb8d8fd67a3bf8488ab28aea0a728128aabf315fdc325e61ac0e3"}}