{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BTJRS7L5U2ZLKWGLBRIZQSBPAK","short_pith_number":"pith:BTJRS7L5","schema_version":"1.0","canonical_sha256":"0cd3197d7da6b2b558cb0c5198482f02afa83aed808ea44c392d96880ed679a7","source":{"kind":"arxiv","id":"2605.15242","version":1},"attestation_state":"computed","paper":{"title":"Logical Grammar Induction via Graph Kolmogorov Complexity: A Neuro-Symbolic Framework for Self-Healing Clinical Data Integrity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Clinical records form a logical grammar whose violations expand graph Kolmogorov complexity and reveal data corruption.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abolfazl Zarghani, Amir Malekesfandiari","submitted_at":"2026-05-14T06:19:43Z","abstract_excerpt":"The reliability of Healthcare Information Systems (HIS) is frequently compromised by human-induced data entry errors, which existing statistical anomaly detection methods fail to distinguish from legitimate clinical extremes. This paper proposes Logic-GNN, a novel neuro-symbolic framework that treats clinical records as a structured ``private language'' governed by latent logical games. By integrating Temporal Graph Neural Networks (TGNN) with Graph Kolmogorov Complexity, we induce a symbolic grammar that represents the underlying logic of medical interactions. We define anomalies as ``grammat"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.15242","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T06:19:43Z","cross_cats_sorted":[],"title_canon_sha256":"296768a486d8e0d0ae5964a9eda4bc284ab2d80a983edaadea500c7525239624","abstract_canon_sha256":"7e089236436c01cb4544a472bead391cadca6728fc09ca44a4f93c77b700e4e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:48.089521Z","signature_b64":"WnhbiBq1Ug80UatTfRngek8FPh/Bvm2GeYfcczcK1ZkPEEt9oHnaeToZZlSsmOjQHJeTIj+NpxkT6H7rXwyDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cd3197d7da6b2b558cb0c5198482f02afa83aed808ea44c392d96880ed679a7","last_reissued_at":"2026-05-20T00:00:48.088724Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:48.088724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Logical Grammar Induction via Graph Kolmogorov Complexity: A Neuro-Symbolic Framework for Self-Healing Clinical Data Integrity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Clinical records form a logical grammar whose violations expand graph Kolmogorov complexity and reveal data corruption.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abolfazl Zarghani, Amir Malekesfandiari","submitted_at":"2026-05-14T06:19:43Z","abstract_excerpt":"The reliability of Healthcare Information Systems (HIS) is frequently compromised by human-induced data entry errors, which existing statistical anomaly detection methods fail to distinguish from legitimate clinical extremes. This paper proposes Logic-GNN, a novel neuro-symbolic framework that treats clinical records as a structured ``private language'' governed by latent logical games. By integrating Temporal Graph Neural Networks (TGNN) with Graph Kolmogorov Complexity, we induce a symbolic grammar that represents the underlying logic of medical interactions. We define anomalies as ``grammat"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Logic-GNN achieves an F1-score of 0.94, outperforming state-of-the-art baselines by 12% in distinguishing between life-threatening medical outliers and data corruption on the Sina System dataset (2M+ records).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Clinical records can be productively modeled as a structured 'private language' governed by latent logical games whose violations are reliably detected by expansion in graph Kolmogorov complexity / MDL (stated in the abstract as the basis for anomaly definition).","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Logic-GNN induces symbolic grammars from clinical graphs via TGNN and Graph Kolmogorov Complexity, defining anomalies as MDL-expanding grammatical violations and reporting 0.94 F1 on the Sina dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Clinical records form a logical grammar whose violations expand graph Kolmogorov complexity and reveal data corruption.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ee49fb3ef835815fec3f19df331cb164af81145ad0771dd4c5f516e245214a76"},"source":{"id":"2605.15242","kind":"arxiv","version":1},"verdict":{"id":"f0f35afd-60b8-44fa-a818-3530f0a4d795","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T16:23:29.817650Z","strongest_claim":"Logic-GNN achieves an F1-score of 0.94, outperforming state-of-the-art baselines by 12% in distinguishing between life-threatening medical outliers and data corruption on the Sina System dataset (2M+ records).","one_line_summary":"Logic-GNN induces symbolic grammars from clinical graphs via TGNN and Graph Kolmogorov Complexity, defining anomalies as MDL-expanding grammatical violations and reporting 0.94 F1 on the Sina dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Clinical records can be productively modeled as a structured 'private language' governed by latent logical games whose violations are reliably detected by expansion in graph Kolmogorov complexity / MDL (stated in the abstract as the basis for anomaly definition).","pith_extraction_headline":"Clinical records form a logical grammar whose violations expand graph Kolmogorov complexity and reveal data corruption."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15242/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T16:36:29.089954Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T16:31:18.458484Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T16:01:54.828497Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.822091Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"9119ea744d996efc37e1b54f05009ec7e79aa156542a270fafab479fd4fa5163"},"references":{"count":13,"sample":[{"doi":"","year":2024,"title":"A Novel Anomaly Detection Using Autoencoders on Contaminated Data,","work_id":"5bdee3e3-8a77-4982-a8ea-af2020ef760f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"L. Wu, P . Cui, J. Pei, and L. Zhao,Graph Neural Networks: Founda- tions, Frontiers, and Applications, Springer, 2022","work_id":"11b7039e-c4e4-4231-bdc8-932acfbe67e8","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Interpretability in Graph Neural Networks,","work_id":"252e8bf7-f0ca-4d22-92b0-95901ba94ac8","ref_index":6,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2008,"title":"M. Li and P . Vit ´anyi,An Introduction to Kolmogorov Complexity and Its Applications, 3rd ed., Springer, 2008","work_id":"afe5977b-9d93-4241-9e48-548fbf1d957d","ref_index":7,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Adaptive Sliding Window Optimization for Multi- Dimensional Data Streams Using Reinforcement Learning,","work_id":"4001c723-5963-4915-b300-c2d4af3c442d","ref_index":8,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":13,"snapshot_sha256":"649e31a513a64e3f7f2b5d55187e4f26167c6ee37504f90a5d2478d087fae30e","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bb80c6150c2f2342424ae79132c9339366886bf100d52199c611b8eef1e11575"},"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":"2605.15242","created_at":"2026-05-20T00:00:48.088830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15242v1","created_at":"2026-05-20T00:00:48.088830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15242","created_at":"2026-05-20T00:00:48.088830+00:00"},{"alias_kind":"pith_short_12","alias_value":"BTJRS7L5U2ZL","created_at":"2026-05-20T00:00:48.088830+00:00"},{"alias_kind":"pith_short_16","alias_value":"BTJRS7L5U2ZLKWGL","created_at":"2026-05-20T00:00:48.088830+00:00"},{"alias_kind":"pith_short_8","alias_value":"BTJRS7L5","created_at":"2026-05-20T00:00:48.088830+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/BTJRS7L5U2ZLKWGLBRIZQSBPAK","json":"https://pith.science/pith/BTJRS7L5U2ZLKWGLBRIZQSBPAK.json","graph_json":"https://pith.science/api/pith-number/BTJRS7L5U2ZLKWGLBRIZQSBPAK/graph.json","events_json":"https://pith.science/api/pith-number/BTJRS7L5U2ZLKWGLBRIZQSBPAK/events.json","paper":"https://pith.science/paper/BTJRS7L5"},"agent_actions":{"view_html":"https://pith.science/pith/BTJRS7L5U2ZLKWGLBRIZQSBPAK","download_json":"https://pith.science/pith/BTJRS7L5U2ZLKWGLBRIZQSBPAK.json","view_paper":"https://pith.science/paper/BTJRS7L5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15242&json=true","fetch_graph":"https://pith.science/api/pith-number/BTJRS7L5U2ZLKWGLBRIZQSBPAK/graph.json","fetch_events":"https://pith.science/api/pith-number/BTJRS7L5U2ZLKWGLBRIZQSBPAK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BTJRS7L5U2ZLKWGLBRIZQSBPAK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BTJRS7L5U2ZLKWGLBRIZQSBPAK/action/storage_attestation","attest_author":"https://pith.science/pith/BTJRS7L5U2ZLKWGLBRIZQSBPAK/action/author_attestation","sign_citation":"https://pith.science/pith/BTJRS7L5U2ZLKWGLBRIZQSBPAK/action/citation_signature","submit_replication":"https://pith.science/pith/BTJRS7L5U2ZLKWGLBRIZQSBPAK/action/replication_record"}},"created_at":"2026-05-20T00:00:48.088830+00:00","updated_at":"2026-05-20T00:00:48.088830+00:00"}