{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GVU63KP3RXN4HNE7TS6YHYRVDQ","short_pith_number":"pith:GVU63KP3","canonical_record":{"source":{"id":"2605.14374","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T04:53:18Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"5ad009ce76e93359dc96279348563a873e6e02d60dc728c940382334a0d44cb3","abstract_canon_sha256":"0c2601cbcbb91a267557b197a6d097af0e1e1c6d6e3288db0698bb66d83d529a"},"schema_version":"1.0"},"canonical_sha256":"3569eda9fb8ddbc3b49f9cbd83e2351c262bc4d9d7e70cc01c2e8dd9b18145d4","source":{"kind":"arxiv","id":"2605.14374","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14374","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14374v1","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14374","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"GVU63KP3RXN4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"GVU63KP3RXN4HNE7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"GVU63KP3","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GVU63KP3RXN4HNE7TS6YHYRVDQ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14374","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T04:53:18Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"5ad009ce76e93359dc96279348563a873e6e02d60dc728c940382334a0d44cb3","abstract_canon_sha256":"0c2601cbcbb91a267557b197a6d097af0e1e1c6d6e3288db0698bb66d83d529a"},"schema_version":"1.0"},"canonical_sha256":"3569eda9fb8ddbc3b49f9cbd83e2351c262bc4d9d7e70cc01c2e8dd9b18145d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:07.793905Z","signature_b64":"aZjBYvaSMZ38nQVlYMO1KtBGqjWqJM9jgbER4mont4wsRRKtTQfJhQANiWI0iHHrO6NMrM/MKeyjeHmye0w4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3569eda9fb8ddbc3b49f9cbd83e2351c262bc4d9d7e70cc01c2e8dd9b18145d4","last_reissued_at":"2026-05-17T23:39:07.793266Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:07.793266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14374","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":"2026-05-17T23:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SXNl/bm5Ik0gd6tX7aznkIiH7kMa9CEbYPPutvbggMnruWrFW3zW7QIWi7XKk/V3EXArq66+7Jcciz9zk5qlBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T12:21:51.178333Z"},"content_sha256":"1fc5507085c836304887b192bcc3c224cdba0f3539b0ec3b51e804be4377f466","schema_version":"1.0","event_id":"sha256:1fc5507085c836304887b192bcc3c224cdba0f3539b0ec3b51e804be4377f466"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GVU63KP3RXN4HNE7TS6YHYRVDQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Pattern Detection Tree for Symbolic Rule-Based Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The Optimal Pattern Detection Tree uses mixed-integer programming to identify a single optimal symbolic rule that maximizes coverage while minimizing false positives in binary classification.","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Yangho Chen, Young-Chae Hong","submitted_at":"2026-05-14T04:53:18Z","abstract_excerpt":"Pattern discovery in data plays a crucial role across diverse domains, including healthcare, risk assessment, and machinery maintenance. In contrast to black-box deep learning models, symbolic rule discovery emerges as a key data mining task, generating human-interpretable rules that offer both transparency and intuitive explainability. This paper introduces the Optimal Pattern Detection Tree (OPDT), a rule-based machine learning model based on novel mixed-integer programming to discover a single optimal pattern in data through binary classification. To incorporate prior knowledge and complian"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"This optimization-based approach discovers a hidden underlying pattern in datasets, when it exists, by identifying an optimal rule that maximizes coverage while minimizing the false positive rate due to misclassification. Our computational experiments show that OPDT discovers a pattern with optimality guarantees on moderately sized datasets within reasonable runtime.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a single hidden optimal pattern exists in the data and that the mixed-integer programming formulation can locate it with optimality guarantees on moderately sized datasets without excessive computational cost or formulation gaps.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"OPDT uses mixed-integer programming to identify an optimal symbolic rule that maximizes coverage while minimizing false positives for binary classification, with support for domain constraints via Branching Structure Constraints.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The Optimal Pattern Detection Tree uses mixed-integer programming to identify a single optimal symbolic rule that maximizes coverage while minimizing false positives in binary classification.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"217353173c988eabdcc129fa2b5e990933fca026e9d87ed4f760a53335d1e4c5"},"source":{"id":"2605.14374","kind":"arxiv","version":1},"verdict":{"id":"81e0ce8a-c167-49ab-a8c0-555f839d1c28","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:41:29.876680Z","strongest_claim":"This optimization-based approach discovers a hidden underlying pattern in datasets, when it exists, by identifying an optimal rule that maximizes coverage while minimizing the false positive rate due to misclassification. Our computational experiments show that OPDT discovers a pattern with optimality guarantees on moderately sized datasets within reasonable runtime.","one_line_summary":"OPDT uses mixed-integer programming to identify an optimal symbolic rule that maximizes coverage while minimizing false positives for binary classification, with support for domain constraints via Branching Structure Constraints.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a single hidden optimal pattern exists in the data and that the mixed-integer programming formulation can locate it with optimality guarantees on moderately sized datasets without excessive computational cost or formulation gaps.","pith_extraction_headline":"The Optimal Pattern Detection Tree uses mixed-integer programming to identify a single optimal symbolic rule that maximizes coverage while minimizing false positives in binary classification."},"references":{"count":59,"sample":[{"doi":"","year":null,"title":"Advances in neural information processing systems , volume =","work_id":"5dc19876-824e-42a6-8c48-04b998fa3eae","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Applied Sciences , volume =","work_id":"efe03fe0-08ac-4cad-9d0f-5d6e0f79f66f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1999,"title":"Proceedings of the 1999 IEEE symposium on security and privacy (Cat","work_id":"0de95f36-1b7a-460e-aded-0e5decc53506","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2009,"title":"2009 Second International Conference on Intelligent Computation Technology and Automation , volume =","work_id":"a512a873-5abf-4e04-8b76-164cf5c963ce","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Journal of statistical software , volume =","work_id":"990415dc-beb6-4dab-ac25-2fe3fabd802d","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":59,"snapshot_sha256":"8b475d733ea2feb3185bca663fe1234ff74229cbd01919451f34b5ccf3c04ec4","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"21ae057da8609bfbaf8cc113566981370ec698d7bb5dd21c0e758abbb3a9b6d0"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"81e0ce8a-c167-49ab-a8c0-555f839d1c28"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lnrnLZx7RIgEl7bOUc+NXDG5UzZZBevErTnKrh4dTxleTCsqb0qWUNEJtfwyyh2kL4tGF7F7hENvxJwEGWISDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T12:21:51.178876Z"},"content_sha256":"68b8b1b10e29b79dbb6307230c2ba9f22e9b0ba19051486b27a8322665ef005e","schema_version":"1.0","event_id":"sha256:68b8b1b10e29b79dbb6307230c2ba9f22e9b0ba19051486b27a8322665ef005e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GVU63KP3RXN4HNE7TS6YHYRVDQ/bundle.json","state_url":"https://pith.science/pith/GVU63KP3RXN4HNE7TS6YHYRVDQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GVU63KP3RXN4HNE7TS6YHYRVDQ/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":"2026-06-11T12:21:51Z","links":{"resolver":"https://pith.science/pith/GVU63KP3RXN4HNE7TS6YHYRVDQ","bundle":"https://pith.science/pith/GVU63KP3RXN4HNE7TS6YHYRVDQ/bundle.json","state":"https://pith.science/pith/GVU63KP3RXN4HNE7TS6YHYRVDQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GVU63KP3RXN4HNE7TS6YHYRVDQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GVU63KP3RXN4HNE7TS6YHYRVDQ","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":"0c2601cbcbb91a267557b197a6d097af0e1e1c6d6e3288db0698bb66d83d529a","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T04:53:18Z","title_canon_sha256":"5ad009ce76e93359dc96279348563a873e6e02d60dc728c940382334a0d44cb3"},"schema_version":"1.0","source":{"id":"2605.14374","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14374","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14374v1","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14374","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"GVU63KP3RXN4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"GVU63KP3RXN4HNE7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"GVU63KP3","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:68b8b1b10e29b79dbb6307230c2ba9f22e9b0ba19051486b27a8322665ef005e","target":"graph","created_at":"2026-05-17T23:39:07Z","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 optimization-based approach discovers a hidden underlying pattern in datasets, when it exists, by identifying an optimal rule that maximizes coverage while minimizing the false positive rate due to misclassification. Our computational experiments show that OPDT discovers a pattern with optimality guarantees on moderately sized datasets within reasonable runtime."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a single hidden optimal pattern exists in the data and that the mixed-integer programming formulation can locate it with optimality guarantees on moderately sized datasets without excessive computational cost or formulation gaps."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"OPDT uses mixed-integer programming to identify an optimal symbolic rule that maximizes coverage while minimizing false positives for binary classification, with support for domain constraints via Branching Structure Constraints."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"The Optimal Pattern Detection Tree uses mixed-integer programming to identify a single optimal symbolic rule that maximizes coverage while minimizing false positives in binary classification."}],"snapshot_sha256":"217353173c988eabdcc129fa2b5e990933fca026e9d87ed4f760a53335d1e4c5"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"21ae057da8609bfbaf8cc113566981370ec698d7bb5dd21c0e758abbb3a9b6d0"},"paper":{"abstract_excerpt":"Pattern discovery in data plays a crucial role across diverse domains, including healthcare, risk assessment, and machinery maintenance. In contrast to black-box deep learning models, symbolic rule discovery emerges as a key data mining task, generating human-interpretable rules that offer both transparency and intuitive explainability. This paper introduces the Optimal Pattern Detection Tree (OPDT), a rule-based machine learning model based on novel mixed-integer programming to discover a single optimal pattern in data through binary classification. To incorporate prior knowledge and complian","authors_text":"Yangho Chen, Young-Chae Hong","cross_cats":["cs.AI","math.OC"],"headline":"The Optimal Pattern Detection Tree uses mixed-integer programming to identify a single optimal symbolic rule that maximizes coverage while minimizing false positives in binary classification.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T04:53:18Z","title":"Optimal Pattern Detection Tree for Symbolic Rule-Based Classification"},"references":{"count":59,"internal_anchors":0,"resolved_work":59,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Advances in neural information processing systems , volume =","work_id":"5dc19876-824e-42a6-8c48-04b998fa3eae","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Applied Sciences , volume =","work_id":"efe03fe0-08ac-4cad-9d0f-5d6e0f79f66f","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Proceedings of the 1999 IEEE symposium on security and privacy (Cat","work_id":"0de95f36-1b7a-460e-aded-0e5decc53506","year":1999},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"2009 Second International Conference on Intelligent Computation Technology and Automation , volume =","work_id":"a512a873-5abf-4e04-8b76-164cf5c963ce","year":2009},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Journal of statistical software , volume =","work_id":"990415dc-beb6-4dab-ac25-2fe3fabd802d","year":null}],"snapshot_sha256":"8b475d733ea2feb3185bca663fe1234ff74229cbd01919451f34b5ccf3c04ec4"},"source":{"id":"2605.14374","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:41:29.876680Z","id":"81e0ce8a-c167-49ab-a8c0-555f839d1c28","model_set":{"reader":"grok-4.3"},"one_line_summary":"OPDT uses mixed-integer programming to identify an optimal symbolic rule that maximizes coverage while minimizing false positives for binary classification, with support for domain constraints via Branching Structure Constraints.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"The Optimal Pattern Detection Tree uses mixed-integer programming to identify a single optimal symbolic rule that maximizes coverage while minimizing false positives in binary classification.","strongest_claim":"This optimization-based approach discovers a hidden underlying pattern in datasets, when it exists, by identifying an optimal rule that maximizes coverage while minimizing the false positive rate due to misclassification. Our computational experiments show that OPDT discovers a pattern with optimality guarantees on moderately sized datasets within reasonable runtime.","weakest_assumption":"That a single hidden optimal pattern exists in the data and that the mixed-integer programming formulation can locate it with optimality guarantees on moderately sized datasets without excessive computational cost or formulation gaps."}},"verdict_id":"81e0ce8a-c167-49ab-a8c0-555f839d1c28"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1fc5507085c836304887b192bcc3c224cdba0f3539b0ec3b51e804be4377f466","target":"record","created_at":"2026-05-17T23:39:07Z","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":"0c2601cbcbb91a267557b197a6d097af0e1e1c6d6e3288db0698bb66d83d529a","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T04:53:18Z","title_canon_sha256":"5ad009ce76e93359dc96279348563a873e6e02d60dc728c940382334a0d44cb3"},"schema_version":"1.0","source":{"id":"2605.14374","kind":"arxiv","version":1}},"canonical_sha256":"3569eda9fb8ddbc3b49f9cbd83e2351c262bc4d9d7e70cc01c2e8dd9b18145d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3569eda9fb8ddbc3b49f9cbd83e2351c262bc4d9d7e70cc01c2e8dd9b18145d4","first_computed_at":"2026-05-17T23:39:07.793266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:07.793266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aZjBYvaSMZ38nQVlYMO1KtBGqjWqJM9jgbER4mont4wsRRKtTQfJhQANiWI0iHHrO6NMrM/MKeyjeHmye0w4CQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:07.793905Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14374","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fc5507085c836304887b192bcc3c224cdba0f3539b0ec3b51e804be4377f466","sha256:68b8b1b10e29b79dbb6307230c2ba9f22e9b0ba19051486b27a8322665ef005e"],"state_sha256":"df3e9813715393fd784065c1807f7571280925b3194be4e0291a1b2edda2ed4f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UqcL2FK06iIM2H/DTfoc1rY33eSkSfFZCldXUc5X68xYxgZFQrvM5LMU6ic9XatVmmsMIqzGxwlLMueR9TQECQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T12:21:51.181283Z","bundle_sha256":"f3c2eef6715d080963de0ec867858830490ff5c424cc75831235442d39268266"}}