{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QPRGIAAYAGUAWZNL5VQNJM3VYH","short_pith_number":"pith:QPRGIAAY","schema_version":"1.0","canonical_sha256":"83e264001801a80b65abed60d4b375c1cd5b0469bb303b0798d7288b45836581","source":{"kind":"arxiv","id":"2603.10742","version":4},"attestation_state":"computed","paper":{"title":"A Grammar of Machine Learning Workflows: Rejecting Data Leakage at Call Time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A grammar of eight typed primitives, a directed acyclic graph, and four hard constraints makes the most damaging forms of data leakage structurally unrepresentable in machine learning workflows.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Simon Roth","submitted_at":"2026-03-11T13:15:33Z","abstract_excerpt":"Data leakage has been identified in 648 published papers across 30 scientific fields. The knowledge to prevent it has existed for over a decade; the problem persists because the tools do not enforce what the textbooks teach. This paper presents a grammar (eight typed primitives connected by a directed acyclic graph with four hard constraints) that makes the most damaging leakage types structurally unrepresentable within the grammar's scope. The core mechanism is a terminal assessment gate: the first call-time-enforced evaluate/assess boundary documented in the peer-reviewed ML methodology lite"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"canonical_record":{"source":{"id":"2603.10742","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-11T13:15:33Z","cross_cats_sorted":[],"title_canon_sha256":"48f12eded636e225f1591a7db43b33bdf4752a6e951ed8bd35919e7e0c07d05a","abstract_canon_sha256":"f7b2a51f1b279dc6b76ff9f6899fb610e8fe4fad69eb9d6bc777adf8ea73ad2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:45.351448Z","signature_b64":"ndeciIIjDM+OoOiA0vwQ+lmcnyjeZRiGs8NqrO5bkPCpSHZwR4nNL/CrwFHE3BDDCmovKnr+gf1Sn+h7lJEyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83e264001801a80b65abed60d4b375c1cd5b0469bb303b0798d7288b45836581","last_reissued_at":"2026-06-02T01:03:45.350814Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:45.350814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Grammar of Machine Learning Workflows: Rejecting Data Leakage at Call Time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A grammar of eight typed primitives, a directed acyclic graph, and four hard constraints makes the most damaging forms of data leakage structurally unrepresentable in machine learning workflows.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Simon Roth","submitted_at":"2026-03-11T13:15:33Z","abstract_excerpt":"Data leakage has been identified in 648 published papers across 30 scientific fields. The knowledge to prevent it has existed for over a decade; the problem persists because the tools do not enforce what the textbooks teach. This paper presents a grammar (eight typed primitives connected by a directed acyclic graph with four hard constraints) that makes the most damaging leakage types structurally unrepresentable within the grammar's scope. The core mechanism is a terminal assessment gate: the first call-time-enforced evaluate/assess boundary documented in the peer-reviewed ML methodology lite"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"This paper presents a grammar - eight typed primitives, a directed acyclic graph, and four hard constraints - that makes the most damaging leakage types structurally unrepresentable.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the four hard constraints and the terminal assessment gate are sufficient to block all damaging leakage types while remaining practical for real workflows and enforceable at call time.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A grammar of eight typed primitives, a DAG, and four constraints makes the most damaging forms of data leakage in ML workflows structurally unrepresentable.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A grammar of eight typed primitives, a directed acyclic graph, and four hard constraints makes the most damaging forms of data leakage structurally unrepresentable in machine learning workflows.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2a2f964aa01480e8387c4bc9efc7cdb2da49b32640b5314caaf9fab0c109ed50"},"source":{"id":"2603.10742","kind":"arxiv","version":4},"verdict":{"id":"66d5934c-ac97-4ea8-ba63-bff7a712dbd9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T12:33:42.415116Z","strongest_claim":"This paper presents a grammar - eight typed primitives, a directed acyclic graph, and four hard constraints - that makes the most damaging leakage types structurally unrepresentable.","one_line_summary":"A grammar of eight typed primitives, a DAG, and four constraints makes the most damaging forms of data leakage in ML workflows structurally unrepresentable.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the four hard constraints and the terminal assessment gate are sufficient to block all damaging leakage types while remaining practical for real workflows and enforceable at call time.","pith_extraction_headline":"A grammar of eight typed primitives, a directed acyclic graph, and four hard constraints makes the most damaging forms of data leakage structurally unrepresentable in machine learning workflows."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.10742/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":2,"snapshot_sha256":"a1433eb4cf9c0f589123c5c5100b804eab4e49b1d2e194ef855ce2b9ea34226e"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2603.10742","created_at":"2026-06-02T01:03:45.350899+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.10742v4","created_at":"2026-06-02T01:03:45.350899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10742","created_at":"2026-06-02T01:03:45.350899+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPRGIAAYAGUA","created_at":"2026-06-02T01:03:45.350899+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPRGIAAYAGUAWZNL","created_at":"2026-06-02T01:03:45.350899+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPRGIAAY","created_at":"2026-06-02T01:03:45.350899+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QPRGIAAYAGUAWZNL5VQNJM3VYH","json":"https://pith.science/pith/QPRGIAAYAGUAWZNL5VQNJM3VYH.json","graph_json":"https://pith.science/api/pith-number/QPRGIAAYAGUAWZNL5VQNJM3VYH/graph.json","events_json":"https://pith.science/api/pith-number/QPRGIAAYAGUAWZNL5VQNJM3VYH/events.json","paper":"https://pith.science/paper/QPRGIAAY"},"agent_actions":{"view_html":"https://pith.science/pith/QPRGIAAYAGUAWZNL5VQNJM3VYH","download_json":"https://pith.science/pith/QPRGIAAYAGUAWZNL5VQNJM3VYH.json","view_paper":"https://pith.science/paper/QPRGIAAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.10742&json=true","fetch_graph":"https://pith.science/api/pith-number/QPRGIAAYAGUAWZNL5VQNJM3VYH/graph.json","fetch_events":"https://pith.science/api/pith-number/QPRGIAAYAGUAWZNL5VQNJM3VYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPRGIAAYAGUAWZNL5VQNJM3VYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPRGIAAYAGUAWZNL5VQNJM3VYH/action/storage_attestation","attest_author":"https://pith.science/pith/QPRGIAAYAGUAWZNL5VQNJM3VYH/action/author_attestation","sign_citation":"https://pith.science/pith/QPRGIAAYAGUAWZNL5VQNJM3VYH/action/citation_signature","submit_replication":"https://pith.science/pith/QPRGIAAYAGUAWZNL5VQNJM3VYH/action/replication_record"}},"created_at":"2026-06-02T01:03:45.350899+00:00","updated_at":"2026-06-02T01:03:45.350899+00:00"}