{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:KJAVQVYV5PTDLRFDX7QI5OGO7C","short_pith_number":"pith:KJAVQVYV","canonical_record":{"source":{"id":"2107.01905","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2021-07-05T09:54:34Z","cross_cats_sorted":[],"title_canon_sha256":"8129fa00311a14d3c1f2d8a784aebdfff03303b595d4ecc11157ef95b67b37d5","abstract_canon_sha256":"3b8dfecdeb11ba960ebe982cd728f571df5d691c0e4c195446b7be887f3f2018"},"schema_version":"1.0"},"canonical_sha256":"5241585715ebe635c4a3bfe08eb8cef8a6e519951cdfaed1f09a22a05091a3c9","source":{"kind":"arxiv","id":"2107.01905","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.01905","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"arxiv_version","alias_value":"2107.01905v1","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01905","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"pith_short_12","alias_value":"KJAVQVYV5PTD","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"pith_short_16","alias_value":"KJAVQVYV5PTDLRFD","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"pith_short_8","alias_value":"KJAVQVYV","created_at":"2026-07-05T02:55:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:KJAVQVYV5PTDLRFDX7QI5OGO7C","target":"record","payload":{"canonical_record":{"source":{"id":"2107.01905","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2021-07-05T09:54:34Z","cross_cats_sorted":[],"title_canon_sha256":"8129fa00311a14d3c1f2d8a784aebdfff03303b595d4ecc11157ef95b67b37d5","abstract_canon_sha256":"3b8dfecdeb11ba960ebe982cd728f571df5d691c0e4c195446b7be887f3f2018"},"schema_version":"1.0"},"canonical_sha256":"5241585715ebe635c4a3bfe08eb8cef8a6e519951cdfaed1f09a22a05091a3c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:55:01.729748Z","signature_b64":"bnKLepZ59eg1RwAiXfaDecVPDyDqW3e1jv4WjxkTTjGebTs2aafnqN9dXQKowPxyHCsGnFtKA22O5BR35uaHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5241585715ebe635c4a3bfe08eb8cef8a6e519951cdfaed1f09a22a05091a3c9","last_reissued_at":"2026-07-05T02:55:01.729399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:55:01.729399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.01905","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":"2026-07-05T02:55:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s5DRbttBuwpU5POmko0AwCZcwtA0GXA43hgr4ZWBkAdejDfDpmQPySa2VpEzrdVc+OaL76K8NeU9tEOF49ixDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:23:23.017846Z"},"content_sha256":"b4ccf89b4b67793ccb9861e1e9b4e4994d3a4510611612409870c353438c84bc","schema_version":"1.0","event_id":"sha256:b4ccf89b4b67793ccb9861e1e9b4e4994d3a4510611612409870c353438c84bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:KJAVQVYV5PTDLRFDX7QI5OGO7C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Creating Unbiased Public Benchmark Datasets with Data Leakage Prevention for Predictive Process Monitoring","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hans Weytjens, Jochen De Weerdt","submitted_at":"2021-07-05T09:54:34Z","abstract_excerpt":"Advances in AI, and especially machine learning, are increasingly drawing research interest and efforts towards predictive process monitoring, the subfield of process mining (PM) that concerns predicting next events, process outcomes and remaining execution times. Unfortunately, researchers use a variety of datasets and ways to split them into training and test sets. The documentation of these preprocessing steps is not always complete. Consequently, research results are hard or even impossible to reproduce and to compare between papers. At times, the use of non-public domain knowledge further"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01905","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.01905/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":"2026-07-05T02:55:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kTECSnYnfFLMG0ysZSE2IrsiM7JO3reNsVQTmR4MHzMMHkwKl4PQWVtBk5D3xSF852AllboMQO3hXZ51ALV2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:23:23.018352Z"},"content_sha256":"69f8601263e7d8be150ef28ce4c328b43fb1d25abb5f6efdc5a935b28efaf44f","schema_version":"1.0","event_id":"sha256:69f8601263e7d8be150ef28ce4c328b43fb1d25abb5f6efdc5a935b28efaf44f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJAVQVYV5PTDLRFDX7QI5OGO7C/bundle.json","state_url":"https://pith.science/pith/KJAVQVYV5PTDLRFDX7QI5OGO7C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJAVQVYV5PTDLRFDX7QI5OGO7C/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":"2026-08-04T07:23:23Z","links":{"resolver":"https://pith.science/pith/KJAVQVYV5PTDLRFDX7QI5OGO7C","bundle":"https://pith.science/pith/KJAVQVYV5PTDLRFDX7QI5OGO7C/bundle.json","state":"https://pith.science/pith/KJAVQVYV5PTDLRFDX7QI5OGO7C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJAVQVYV5PTDLRFDX7QI5OGO7C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KJAVQVYV5PTDLRFDX7QI5OGO7C","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":"3b8dfecdeb11ba960ebe982cd728f571df5d691c0e4c195446b7be887f3f2018","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2021-07-05T09:54:34Z","title_canon_sha256":"8129fa00311a14d3c1f2d8a784aebdfff03303b595d4ecc11157ef95b67b37d5"},"schema_version":"1.0","source":{"id":"2107.01905","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.01905","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"arxiv_version","alias_value":"2107.01905v1","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01905","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"pith_short_12","alias_value":"KJAVQVYV5PTD","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"pith_short_16","alias_value":"KJAVQVYV5PTDLRFD","created_at":"2026-07-05T02:55:01Z"},{"alias_kind":"pith_short_8","alias_value":"KJAVQVYV","created_at":"2026-07-05T02:55:01Z"}],"graph_snapshots":[{"event_id":"sha256:69f8601263e7d8be150ef28ce4c328b43fb1d25abb5f6efdc5a935b28efaf44f","target":"graph","created_at":"2026-07-05T02:55:01Z","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/2107.01905/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advances in AI, and especially machine learning, are increasingly drawing research interest and efforts towards predictive process monitoring, the subfield of process mining (PM) that concerns predicting next events, process outcomes and remaining execution times. Unfortunately, researchers use a variety of datasets and ways to split them into training and test sets. The documentation of these preprocessing steps is not always complete. Consequently, research results are hard or even impossible to reproduce and to compare between papers. At times, the use of non-public domain knowledge further","authors_text":"Hans Weytjens, Jochen De Weerdt","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2021-07-05T09:54:34Z","title":"Creating Unbiased Public Benchmark Datasets with Data Leakage Prevention for Predictive Process Monitoring"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01905","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:b4ccf89b4b67793ccb9861e1e9b4e4994d3a4510611612409870c353438c84bc","target":"record","created_at":"2026-07-05T02:55:01Z","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":"3b8dfecdeb11ba960ebe982cd728f571df5d691c0e4c195446b7be887f3f2018","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2021-07-05T09:54:34Z","title_canon_sha256":"8129fa00311a14d3c1f2d8a784aebdfff03303b595d4ecc11157ef95b67b37d5"},"schema_version":"1.0","source":{"id":"2107.01905","kind":"arxiv","version":1}},"canonical_sha256":"5241585715ebe635c4a3bfe08eb8cef8a6e519951cdfaed1f09a22a05091a3c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5241585715ebe635c4a3bfe08eb8cef8a6e519951cdfaed1f09a22a05091a3c9","first_computed_at":"2026-07-05T02:55:01.729399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:55:01.729399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bnKLepZ59eg1RwAiXfaDecVPDyDqW3e1jv4WjxkTTjGebTs2aafnqN9dXQKowPxyHCsGnFtKA22O5BR35uaHAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:55:01.729748Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.01905","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4ccf89b4b67793ccb9861e1e9b4e4994d3a4510611612409870c353438c84bc","sha256:69f8601263e7d8be150ef28ce4c328b43fb1d25abb5f6efdc5a935b28efaf44f"],"state_sha256":"452170575f8a471869fbf84c899b3ae431ac847c68ea5300056aa598d7245d90"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E8VsA2S9N7EFRB2mX5VY1YKQH2J+bwXOoVO8V2snq4uHnSlgt4ADVwejU3bbItOH9+1qFp9kEtClO3Da1XWrAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:23:23.022098Z","bundle_sha256":"d0e5efb49941f4cae3c8aa3b9ed0d2abb7614ad69b67fc1929d566f79610bb74"}}