{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QPRGIAAYAGUAWZNL5VQNJM3VYH","short_pith_number":"pith:QPRGIAAY","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"},"canonical_sha256":"83e264001801a80b65abed60d4b375c1cd5b0469bb303b0798d7288b45836581","source":{"kind":"arxiv","id":"2603.10742","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.10742","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"2603.10742v4","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10742","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"QPRGIAAYAGUA","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"pith_short_16","alias_value":"QPRGIAAYAGUAWZNL","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"pith_short_8","alias_value":"QPRGIAAY","created_at":"2026-06-02T01:03:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QPRGIAAYAGUAWZNL5VQNJM3VYH","target":"record","payload":{"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"},"canonical_sha256":"83e264001801a80b65abed60d4b375c1cd5b0469bb303b0798d7288b45836581","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"},"source_kind":"arxiv","source_id":"2603.10742","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rKGjyX7ln1+rj37XNl2HUXyqu7oY5cP/tZFV9FHdOir6T/l1wSYytjTqY+GoupeMEyi97NAm7eReKcLSWzS8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T08:26:52.021004Z"},"content_sha256":"a4b0c8362bf60d5b2dddf1d3028fd6e5695dc215cc97485bc576e6f16f7c3a06","schema_version":"1.0","event_id":"sha256:a4b0c8362bf60d5b2dddf1d3028fd6e5695dc215cc97485bc576e6f16f7c3a06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QPRGIAAYAGUAWZNL5VQNJM3VYH","target":"graph","payload":{"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"},"verdict_id":"66d5934c-ac97-4ea8-ba63-bff7a712dbd9"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H0wC3nTvYGltqucM5GfcWX2c/oRDRjiCWYIk5wQETpY+Pt6vsgKTyeXRkKDbsLMT07M1JcwXINZF37Nro9ONCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T08:26:52.021910Z"},"content_sha256":"89fc9c026761c8ebf2ba52b7cd67b212f252450769fcb273f7ceeda666b0b3df","schema_version":"1.0","event_id":"sha256:89fc9c026761c8ebf2ba52b7cd67b212f252450769fcb273f7ceeda666b0b3df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QPRGIAAYAGUAWZNL5VQNJM3VYH/bundle.json","state_url":"https://pith.science/pith/QPRGIAAYAGUAWZNL5VQNJM3VYH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QPRGIAAYAGUAWZNL5VQNJM3VYH/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":"2026-06-10T08:26:52Z","links":{"resolver":"https://pith.science/pith/QPRGIAAYAGUAWZNL5VQNJM3VYH","bundle":"https://pith.science/pith/QPRGIAAYAGUAWZNL5VQNJM3VYH/bundle.json","state":"https://pith.science/pith/QPRGIAAYAGUAWZNL5VQNJM3VYH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QPRGIAAYAGUAWZNL5VQNJM3VYH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QPRGIAAYAGUAWZNL5VQNJM3VYH","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":"f7b2a51f1b279dc6b76ff9f6899fb610e8fe4fad69eb9d6bc777adf8ea73ad2b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-11T13:15:33Z","title_canon_sha256":"48f12eded636e225f1591a7db43b33bdf4752a6e951ed8bd35919e7e0c07d05a"},"schema_version":"1.0","source":{"id":"2603.10742","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.10742","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"2603.10742v4","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10742","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"QPRGIAAYAGUA","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"pith_short_16","alias_value":"QPRGIAAYAGUAWZNL","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"pith_short_8","alias_value":"QPRGIAAY","created_at":"2026-06-02T01:03:45Z"}],"graph_snapshots":[{"event_id":"sha256:89fc9c026761c8ebf2ba52b7cd67b212f252450769fcb273f7ceeda666b0b3df","target":"graph","created_at":"2026-06-02T01:03:45Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"2a2f964aa01480e8387c4bc9efc7cdb2da49b32640b5314caaf9fab0c109ed50"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"a1433eb4cf9c0f589123c5c5100b804eab4e49b1d2e194ef855ce2b9ea34226e"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.10742/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Simon Roth","cross_cats":[],"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.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-11T13:15:33Z","title":"A Grammar of Machine Learning Workflows: Rejecting Data Leakage at Call Time"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.10742","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-15T12:33:42.415116Z","id":"66d5934c-ac97-4ea8-ba63-bff7a712dbd9","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"66d5934c-ac97-4ea8-ba63-bff7a712dbd9"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a4b0c8362bf60d5b2dddf1d3028fd6e5695dc215cc97485bc576e6f16f7c3a06","target":"record","created_at":"2026-06-02T01:03:45Z","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":"f7b2a51f1b279dc6b76ff9f6899fb610e8fe4fad69eb9d6bc777adf8ea73ad2b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-11T13:15:33Z","title_canon_sha256":"48f12eded636e225f1591a7db43b33bdf4752a6e951ed8bd35919e7e0c07d05a"},"schema_version":"1.0","source":{"id":"2603.10742","kind":"arxiv","version":4}},"canonical_sha256":"83e264001801a80b65abed60d4b375c1cd5b0469bb303b0798d7288b45836581","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83e264001801a80b65abed60d4b375c1cd5b0469bb303b0798d7288b45836581","first_computed_at":"2026-06-02T01:03:45.350814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:45.350814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ndeciIIjDM+OoOiA0vwQ+lmcnyjeZRiGs8NqrO5bkPCpSHZwR4nNL/CrwFHE3BDDCmovKnr+gf1Sn+h7lJEyDw==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:45.351448Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.10742","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4b0c8362bf60d5b2dddf1d3028fd6e5695dc215cc97485bc576e6f16f7c3a06","sha256:89fc9c026761c8ebf2ba52b7cd67b212f252450769fcb273f7ceeda666b0b3df"],"state_sha256":"f15b02f3afc4e880c84eaee0c06c2f0a8be6952507fff281789fcfa77b746707"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TCKOv6R80MHtn57/6OJNGyORkDHXNUyvYAOh1o84F8rVDttYdY5Ppq/Sv3dJIOMSN8Guf7HTvDxhnPaVapGEAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T08:26:52.026509Z","bundle_sha256":"ae034c1cf89463a283824eabbcbb9195957ca60ac295f7216da34a35eadff769"}}