{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:BJP7KZZIOMNSCKPULGM7ANQKMT","short_pith_number":"pith:BJP7KZZI","canonical_record":{"source":{"id":"2012.10945","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2020-12-20T14:54:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1cd304aef021e985183efe7f929ae2837550fbd4ff00cc5fb086ba1f81593d42","abstract_canon_sha256":"7ed70c5a07fbebef5d89f3c71a3794f58f57440cac4bf91ecb4dfbdaa03872ed"},"schema_version":"1.0"},"canonical_sha256":"0a5ff56728731b2129f45999f0360a64dab8dbda086cff76b8e2d4f832c3fe75","source":{"kind":"arxiv","id":"2012.10945","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.10945","created_at":"2026-07-05T02:38:16Z"},{"alias_kind":"arxiv_version","alias_value":"2012.10945v2","created_at":"2026-07-05T02:38:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.10945","created_at":"2026-07-05T02:38:16Z"},{"alias_kind":"pith_short_12","alias_value":"BJP7KZZIOMNS","created_at":"2026-07-05T02:38:16Z"},{"alias_kind":"pith_short_16","alias_value":"BJP7KZZIOMNSCKPU","created_at":"2026-07-05T02:38:16Z"},{"alias_kind":"pith_short_8","alias_value":"BJP7KZZI","created_at":"2026-07-05T02:38:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:BJP7KZZIOMNSCKPULGM7ANQKMT","target":"record","payload":{"canonical_record":{"source":{"id":"2012.10945","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2020-12-20T14:54:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1cd304aef021e985183efe7f929ae2837550fbd4ff00cc5fb086ba1f81593d42","abstract_canon_sha256":"7ed70c5a07fbebef5d89f3c71a3794f58f57440cac4bf91ecb4dfbdaa03872ed"},"schema_version":"1.0"},"canonical_sha256":"0a5ff56728731b2129f45999f0360a64dab8dbda086cff76b8e2d4f832c3fe75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:38:16.611448Z","signature_b64":"zG/RfwAzbNE7HKfLjbld1pkpCzkBwfCNeG41u3iENZPoR2r99uAx+bVZ2oFLn4N2zhnJ01EFC6/nZ+imsOnFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a5ff56728731b2129f45999f0360a64dab8dbda086cff76b8e2d4f832c3fe75","last_reissued_at":"2026-07-05T02:38:16.610946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:38:16.610946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.10945","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":"2026-07-05T02:38:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fb4pzgw6fM0SpeB95maWhQzsSuRvDpHkATclT2cRmM9lWIbBPxX93f8kH27i0tN/nXGNYuStcJfAV3G3l0FABA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:55:48.721717Z"},"content_sha256":"a0c47d91aa90a40afd6abde28c9571885d2fbedafd82bae1d80f621c72662f52","schema_version":"1.0","event_id":"sha256:a0c47d91aa90a40afd6abde28c9571885d2fbedafd82bae1d80f621c72662f52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:BJP7KZZIOMNSCKPULGM7ANQKMT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SPlit: An Optimal Method for Data Splitting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Akhil Vakayil, V. Roshan Joseph","submitted_at":"2020-12-20T14:54:29Z","abstract_excerpt":"In this article we propose an optimal method referred to as SPlit for splitting a dataset into training and testing sets. SPlit is based on the method of Support Points (SP), which was initially developed for finding the optimal representative points of a continuous distribution. We adapt SP for subsampling from a dataset using a sequential nearest neighbor algorithm. We also extend SP to deal with categorical variables so that SPlit can be applied to both regression and classification problems. The implementation of SPlit on real datasets shows substantial improvement in the worst-case testin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.10945","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.10945/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:38:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Ip48+vapBK3stYwT3Mwg2VUBEQfXe6lROz6exCADEWzE68V6Jb1z5Wxtq1WB+3jTksPvIn6u/lfCNSLcCH2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:55:48.722292Z"},"content_sha256":"33b7488167655009c21d66e50428cb1299a12e05da1463cef6b9b4ecdab0c559","schema_version":"1.0","event_id":"sha256:33b7488167655009c21d66e50428cb1299a12e05da1463cef6b9b4ecdab0c559"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BJP7KZZIOMNSCKPULGM7ANQKMT/bundle.json","state_url":"https://pith.science/pith/BJP7KZZIOMNSCKPULGM7ANQKMT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BJP7KZZIOMNSCKPULGM7ANQKMT/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":"2026-08-19T04:55:48Z","links":{"resolver":"https://pith.science/pith/BJP7KZZIOMNSCKPULGM7ANQKMT","bundle":"https://pith.science/pith/BJP7KZZIOMNSCKPULGM7ANQKMT/bundle.json","state":"https://pith.science/pith/BJP7KZZIOMNSCKPULGM7ANQKMT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BJP7KZZIOMNSCKPULGM7ANQKMT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BJP7KZZIOMNSCKPULGM7ANQKMT","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":"7ed70c5a07fbebef5d89f3c71a3794f58f57440cac4bf91ecb4dfbdaa03872ed","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2020-12-20T14:54:29Z","title_canon_sha256":"1cd304aef021e985183efe7f929ae2837550fbd4ff00cc5fb086ba1f81593d42"},"schema_version":"1.0","source":{"id":"2012.10945","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.10945","created_at":"2026-07-05T02:38:16Z"},{"alias_kind":"arxiv_version","alias_value":"2012.10945v2","created_at":"2026-07-05T02:38:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.10945","created_at":"2026-07-05T02:38:16Z"},{"alias_kind":"pith_short_12","alias_value":"BJP7KZZIOMNS","created_at":"2026-07-05T02:38:16Z"},{"alias_kind":"pith_short_16","alias_value":"BJP7KZZIOMNSCKPU","created_at":"2026-07-05T02:38:16Z"},{"alias_kind":"pith_short_8","alias_value":"BJP7KZZI","created_at":"2026-07-05T02:38:16Z"}],"graph_snapshots":[{"event_id":"sha256:33b7488167655009c21d66e50428cb1299a12e05da1463cef6b9b4ecdab0c559","target":"graph","created_at":"2026-07-05T02:38:16Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2012.10945/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this article we propose an optimal method referred to as SPlit for splitting a dataset into training and testing sets. SPlit is based on the method of Support Points (SP), which was initially developed for finding the optimal representative points of a continuous distribution. We adapt SP for subsampling from a dataset using a sequential nearest neighbor algorithm. We also extend SP to deal with categorical variables so that SPlit can be applied to both regression and classification problems. The implementation of SPlit on real datasets shows substantial improvement in the worst-case testin","authors_text":"Akhil Vakayil, V. Roshan Joseph","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2020-12-20T14:54:29Z","title":"SPlit: An Optimal Method for Data Splitting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.10945","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:a0c47d91aa90a40afd6abde28c9571885d2fbedafd82bae1d80f621c72662f52","target":"record","created_at":"2026-07-05T02:38:16Z","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":"7ed70c5a07fbebef5d89f3c71a3794f58f57440cac4bf91ecb4dfbdaa03872ed","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2020-12-20T14:54:29Z","title_canon_sha256":"1cd304aef021e985183efe7f929ae2837550fbd4ff00cc5fb086ba1f81593d42"},"schema_version":"1.0","source":{"id":"2012.10945","kind":"arxiv","version":2}},"canonical_sha256":"0a5ff56728731b2129f45999f0360a64dab8dbda086cff76b8e2d4f832c3fe75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a5ff56728731b2129f45999f0360a64dab8dbda086cff76b8e2d4f832c3fe75","first_computed_at":"2026-07-05T02:38:16.610946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:38:16.610946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zG/RfwAzbNE7HKfLjbld1pkpCzkBwfCNeG41u3iENZPoR2r99uAx+bVZ2oFLn4N2zhnJ01EFC6/nZ+imsOnFDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:38:16.611448Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.10945","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0c47d91aa90a40afd6abde28c9571885d2fbedafd82bae1d80f621c72662f52","sha256:33b7488167655009c21d66e50428cb1299a12e05da1463cef6b9b4ecdab0c559"],"state_sha256":"b57ac3461202dbbc74ba43d35608feb071e757fafcfbb2ad74f756c9e210b53a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gHTSShGFCBAXRFibFFeZ4/QwsE21bFWPJ7uUg1nv5pFgPMjJ//898DeGeXqpeH/Md5Sa5g48fK4i5b+QzWz3CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T04:55:48.726512Z","bundle_sha256":"0acf0581da6b7427a50ea0e8c96146d31100f173a3721d5d3c9e4e14ffabc98f"}}