{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:27D24I4WJMUCBHN2R7KSIFVTLV","short_pith_number":"pith:27D24I4W","canonical_record":{"source":{"id":"1907.02437","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-04T14:55:02Z","cross_cats_sorted":["cs.LG","stat.CO","stat.ME"],"title_canon_sha256":"34d7b225b0fc3bb188eef59892ee7fc4792de98d722fa94dcd4f1e7ade460d46","abstract_canon_sha256":"e877bfc806aa62ed5752b9340133537d2f4ee77ebb42b4a50e54f844a14bad82"},"schema_version":"1.0"},"canonical_sha256":"d7c7ae23964b28209dba8fd52416b35d600a0b0264253351bb1f8c0214e8c931","source":{"kind":"arxiv","id":"1907.02437","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.02437","created_at":"2026-05-17T23:41:28Z"},{"alias_kind":"arxiv_version","alias_value":"1907.02437v1","created_at":"2026-05-17T23:41:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02437","created_at":"2026-05-17T23:41:28Z"},{"alias_kind":"pith_short_12","alias_value":"27D24I4WJMUC","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"27D24I4WJMUCBHN2","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"27D24I4W","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:27D24I4WJMUCBHN2R7KSIFVTLV","target":"record","payload":{"canonical_record":{"source":{"id":"1907.02437","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-04T14:55:02Z","cross_cats_sorted":["cs.LG","stat.CO","stat.ME"],"title_canon_sha256":"34d7b225b0fc3bb188eef59892ee7fc4792de98d722fa94dcd4f1e7ade460d46","abstract_canon_sha256":"e877bfc806aa62ed5752b9340133537d2f4ee77ebb42b4a50e54f844a14bad82"},"schema_version":"1.0"},"canonical_sha256":"d7c7ae23964b28209dba8fd52416b35d600a0b0264253351bb1f8c0214e8c931","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:28.613670Z","signature_b64":"XXuzWp1zDkhupTGHyZAJfOUKa1XyUH/fHEd1sOTRg+RmXz7UOAM+sZIvF3+9iPo//DiwNSW16QiVL1Hta5I8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7c7ae23964b28209dba8fd52416b35d600a0b0264253351bb1f8c0214e8c931","last_reissued_at":"2026-05-17T23:41:28.612877Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:28.612877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.02437","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":"2026-05-17T23:41:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G5vwi7TheHRULHRhmhoFb5HC2WDgiwrEsYKCotcOuqN9LYuAeEZoX/10csf3sJ8r5aMa/X+8sgb+Azut5L3xCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:13:52.609860Z"},"content_sha256":"cc568242b6b5bf1b56a07814396724b411c1cb01ff8f78367262cf39521d5610","schema_version":"1.0","event_id":"sha256:cc568242b6b5bf1b56a07814396724b411c1cb01ff8f78367262cf39521d5610"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:27D24I4WJMUCBHN2R7KSIFVTLV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Subsampling Bias and The Best-Discrepancy Systematic Cross Validation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.CO","stat.ME"],"primary_cat":"stat.ML","authors_text":"Jianya Liu, Liang Guo, Ruodan Lu","submitted_at":"2019-07-04T14:55:02Z","abstract_excerpt":"Statistical machine learning models should be evaluated and validated before putting to work. Conventional k-fold Monte Carlo Cross-Validation (MCCV) procedure uses a pseudo-random sequence to partition instances into k subsets, which usually causes subsampling bias, inflates generalization errors and jeopardizes the reliability and effectiveness of cross-validation. Based on ordered systematic sampling theory in statistics and low-discrepancy sequence theory in number theory, we propose a new k-fold cross-validation procedure by replacing a pseudo-random sequence with a best-discrepancy seque"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02437","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":"2026-05-17T23:41:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tHVs0V5q335u6iZQH3g+BnRn7Kk/906M3D+jqeuvxY0S8IKQAAzU2m8UJsblRWNwgKW1sfGsbgHCrqaZxPv9Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:13:52.610483Z"},"content_sha256":"d003945141b1e171d314bead20336dea5ce3c1b40e81587841df65cc07e91a6c","schema_version":"1.0","event_id":"sha256:d003945141b1e171d314bead20336dea5ce3c1b40e81587841df65cc07e91a6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/27D24I4WJMUCBHN2R7KSIFVTLV/bundle.json","state_url":"https://pith.science/pith/27D24I4WJMUCBHN2R7KSIFVTLV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/27D24I4WJMUCBHN2R7KSIFVTLV/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":"2026-05-29T16:13:52Z","links":{"resolver":"https://pith.science/pith/27D24I4WJMUCBHN2R7KSIFVTLV","bundle":"https://pith.science/pith/27D24I4WJMUCBHN2R7KSIFVTLV/bundle.json","state":"https://pith.science/pith/27D24I4WJMUCBHN2R7KSIFVTLV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/27D24I4WJMUCBHN2R7KSIFVTLV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:27D24I4WJMUCBHN2R7KSIFVTLV","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":"e877bfc806aa62ed5752b9340133537d2f4ee77ebb42b4a50e54f844a14bad82","cross_cats_sorted":["cs.LG","stat.CO","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-04T14:55:02Z","title_canon_sha256":"34d7b225b0fc3bb188eef59892ee7fc4792de98d722fa94dcd4f1e7ade460d46"},"schema_version":"1.0","source":{"id":"1907.02437","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.02437","created_at":"2026-05-17T23:41:28Z"},{"alias_kind":"arxiv_version","alias_value":"1907.02437v1","created_at":"2026-05-17T23:41:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02437","created_at":"2026-05-17T23:41:28Z"},{"alias_kind":"pith_short_12","alias_value":"27D24I4WJMUC","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"27D24I4WJMUCBHN2","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"27D24I4W","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:d003945141b1e171d314bead20336dea5ce3c1b40e81587841df65cc07e91a6c","target":"graph","created_at":"2026-05-17T23:41:28Z","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":"Statistical machine learning models should be evaluated and validated before putting to work. Conventional k-fold Monte Carlo Cross-Validation (MCCV) procedure uses a pseudo-random sequence to partition instances into k subsets, which usually causes subsampling bias, inflates generalization errors and jeopardizes the reliability and effectiveness of cross-validation. Based on ordered systematic sampling theory in statistics and low-discrepancy sequence theory in number theory, we propose a new k-fold cross-validation procedure by replacing a pseudo-random sequence with a best-discrepancy seque","authors_text":"Jianya Liu, Liang Guo, Ruodan Lu","cross_cats":["cs.LG","stat.CO","stat.ME"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-04T14:55:02Z","title":"Subsampling Bias and The Best-Discrepancy Systematic Cross Validation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02437","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:cc568242b6b5bf1b56a07814396724b411c1cb01ff8f78367262cf39521d5610","target":"record","created_at":"2026-05-17T23:41:28Z","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":"e877bfc806aa62ed5752b9340133537d2f4ee77ebb42b4a50e54f844a14bad82","cross_cats_sorted":["cs.LG","stat.CO","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-04T14:55:02Z","title_canon_sha256":"34d7b225b0fc3bb188eef59892ee7fc4792de98d722fa94dcd4f1e7ade460d46"},"schema_version":"1.0","source":{"id":"1907.02437","kind":"arxiv","version":1}},"canonical_sha256":"d7c7ae23964b28209dba8fd52416b35d600a0b0264253351bb1f8c0214e8c931","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7c7ae23964b28209dba8fd52416b35d600a0b0264253351bb1f8c0214e8c931","first_computed_at":"2026-05-17T23:41:28.612877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:28.612877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XXuzWp1zDkhupTGHyZAJfOUKa1XyUH/fHEd1sOTRg+RmXz7UOAM+sZIvF3+9iPo//DiwNSW16QiVL1Hta5I8Cg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:28.613670Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.02437","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc568242b6b5bf1b56a07814396724b411c1cb01ff8f78367262cf39521d5610","sha256:d003945141b1e171d314bead20336dea5ce3c1b40e81587841df65cc07e91a6c"],"state_sha256":"7faa117359bf61e452dbe2691f9d206197eff6d3145d228320322df7b5cf363c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PUL8V84IcvA/SJ5h1A3Oj1/RVrVSPVYYXcrUITegRkYdpC45J7l06ZD0W/f/9Vk1abdj7ZFpZhNT0wsGNwk1Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T16:13:52.613824Z","bundle_sha256":"38ca34c9d562aa351bff7ec6923abbb78403ea74fdf7fd0c91b1cc2c40fd0101"}}