{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FY3TMW3GIV3ZDLX3WAS4EHQE3G","short_pith_number":"pith:FY3TMW3G","canonical_record":{"source":{"id":"2506.16628","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T21:55:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a5ced6205e74885bcb02b9528c80f155d046fcd8ecc3f3527221eecd1076d4d5","abstract_canon_sha256":"3774c595fde3f3dbe73a99640983b05ff332cb8ea96fc0a34b60337c717563e3"},"schema_version":"1.0"},"canonical_sha256":"2e37365b66457791aefbb025c21e04d9831e3903db3fd18fa1286f0cf026960f","source":{"kind":"arxiv","id":"2506.16628","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16628","created_at":"2026-07-05T11:24:39Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16628v1","created_at":"2026-07-05T11:24:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16628","created_at":"2026-07-05T11:24:39Z"},{"alias_kind":"pith_short_12","alias_value":"FY3TMW3GIV3Z","created_at":"2026-07-05T11:24:39Z"},{"alias_kind":"pith_short_16","alias_value":"FY3TMW3GIV3ZDLX3","created_at":"2026-07-05T11:24:39Z"},{"alias_kind":"pith_short_8","alias_value":"FY3TMW3G","created_at":"2026-07-05T11:24:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FY3TMW3GIV3ZDLX3WAS4EHQE3G","target":"record","payload":{"canonical_record":{"source":{"id":"2506.16628","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T21:55:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a5ced6205e74885bcb02b9528c80f155d046fcd8ecc3f3527221eecd1076d4d5","abstract_canon_sha256":"3774c595fde3f3dbe73a99640983b05ff332cb8ea96fc0a34b60337c717563e3"},"schema_version":"1.0"},"canonical_sha256":"2e37365b66457791aefbb025c21e04d9831e3903db3fd18fa1286f0cf026960f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:39.802567Z","signature_b64":"Q2N4H3msigobGbEgOQmwcASAl6dtjAx0v+fmwrIGUvqMT6O3jqevxJ84cpeM2m/oHfAg13PE/fwFPZmGJurqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e37365b66457791aefbb025c21e04d9831e3903db3fd18fa1286f0cf026960f","last_reissued_at":"2026-07-05T11:24:39.802090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:39.802090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.16628","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":"2026-07-05T11:24:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cqNGXyRl+GUCkHR7qvbDZVzG9fDRYd5IbNW3PmfzawW67UqyL1fAPyRWOaKFsgFx/3ecxcJ0KVD0x51j1dhOAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:29:42.824668Z"},"content_sha256":"ea592ad7d018de896749e80e64cb8c750f8583381302116a4e560470db3d8026","schema_version":"1.0","event_id":"sha256:ea592ad7d018de896749e80e64cb8c750f8583381302116a4e560470db3d8026"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FY3TMW3GIV3ZDLX3WAS4EHQE3G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Initial Investigation of LLM-Assisted Development of Rule-Based Clinical NLP System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Brian T. Bucher, Jianlin Shi","submitted_at":"2025-06-19T21:55:33Z","abstract_excerpt":"Despite advances in machine learning (ML) and large language models (LLMs), rule-based natural language processing (NLP) systems remain active in clinical settings due to their interpretability and operational efficiency. However, their manual development and maintenance are labor-intensive, particularly in tasks with large linguistic variability. To overcome these limitations, we proposed a novel approach employing LLMs solely during the rule-based systems development phase. We conducted the initial experiments focusing on the first two steps of developing a rule-based NLP pipeline: find rele"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16628","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/2506.16628/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":"2026-07-05T11:24:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xm5zIGk15INm6QLJdrFfaXT6EKSQYAnDJigM46ziMmGyhnYIvretE6XDc/CqFvF0maHvFaVEKTffn5/zZf/HDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:29:42.825252Z"},"content_sha256":"9a7a3c2a180f7dd6055e2364e7ff90bb0658e6d9720e62d6346a125b1649d2e5","schema_version":"1.0","event_id":"sha256:9a7a3c2a180f7dd6055e2364e7ff90bb0658e6d9720e62d6346a125b1649d2e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FY3TMW3GIV3ZDLX3WAS4EHQE3G/bundle.json","state_url":"https://pith.science/pith/FY3TMW3GIV3ZDLX3WAS4EHQE3G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FY3TMW3GIV3ZDLX3WAS4EHQE3G/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":"2026-08-07T08:29:42Z","links":{"resolver":"https://pith.science/pith/FY3TMW3GIV3ZDLX3WAS4EHQE3G","bundle":"https://pith.science/pith/FY3TMW3GIV3ZDLX3WAS4EHQE3G/bundle.json","state":"https://pith.science/pith/FY3TMW3GIV3ZDLX3WAS4EHQE3G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FY3TMW3GIV3ZDLX3WAS4EHQE3G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FY3TMW3GIV3ZDLX3WAS4EHQE3G","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":"3774c595fde3f3dbe73a99640983b05ff332cb8ea96fc0a34b60337c717563e3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T21:55:33Z","title_canon_sha256":"a5ced6205e74885bcb02b9528c80f155d046fcd8ecc3f3527221eecd1076d4d5"},"schema_version":"1.0","source":{"id":"2506.16628","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16628","created_at":"2026-07-05T11:24:39Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16628v1","created_at":"2026-07-05T11:24:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16628","created_at":"2026-07-05T11:24:39Z"},{"alias_kind":"pith_short_12","alias_value":"FY3TMW3GIV3Z","created_at":"2026-07-05T11:24:39Z"},{"alias_kind":"pith_short_16","alias_value":"FY3TMW3GIV3ZDLX3","created_at":"2026-07-05T11:24:39Z"},{"alias_kind":"pith_short_8","alias_value":"FY3TMW3G","created_at":"2026-07-05T11:24:39Z"}],"graph_snapshots":[{"event_id":"sha256:9a7a3c2a180f7dd6055e2364e7ff90bb0658e6d9720e62d6346a125b1649d2e5","target":"graph","created_at":"2026-07-05T11:24:39Z","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/2506.16628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite advances in machine learning (ML) and large language models (LLMs), rule-based natural language processing (NLP) systems remain active in clinical settings due to their interpretability and operational efficiency. However, their manual development and maintenance are labor-intensive, particularly in tasks with large linguistic variability. To overcome these limitations, we proposed a novel approach employing LLMs solely during the rule-based systems development phase. We conducted the initial experiments focusing on the first two steps of developing a rule-based NLP pipeline: find rele","authors_text":"Brian T. Bucher, Jianlin Shi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T21:55:33Z","title":"Initial Investigation of LLM-Assisted Development of Rule-Based Clinical NLP System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16628","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:ea592ad7d018de896749e80e64cb8c750f8583381302116a4e560470db3d8026","target":"record","created_at":"2026-07-05T11:24:39Z","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":"3774c595fde3f3dbe73a99640983b05ff332cb8ea96fc0a34b60337c717563e3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T21:55:33Z","title_canon_sha256":"a5ced6205e74885bcb02b9528c80f155d046fcd8ecc3f3527221eecd1076d4d5"},"schema_version":"1.0","source":{"id":"2506.16628","kind":"arxiv","version":1}},"canonical_sha256":"2e37365b66457791aefbb025c21e04d9831e3903db3fd18fa1286f0cf026960f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e37365b66457791aefbb025c21e04d9831e3903db3fd18fa1286f0cf026960f","first_computed_at":"2026-07-05T11:24:39.802090Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:39.802090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q2N4H3msigobGbEgOQmwcASAl6dtjAx0v+fmwrIGUvqMT6O3jqevxJ84cpeM2m/oHfAg13PE/fwFPZmGJurqAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:39.802567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16628","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea592ad7d018de896749e80e64cb8c750f8583381302116a4e560470db3d8026","sha256:9a7a3c2a180f7dd6055e2364e7ff90bb0658e6d9720e62d6346a125b1649d2e5"],"state_sha256":"f9279db79472abf08bab41980f89243c68830383ce96f93ee6ce82bcdc589bab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ksIl9Bn6pQ37iGdL0jqZ0/i+3YHy2FTpsUi8K77jNEioidRxRH6OBKCYMw1LbgHixUzvB0qYXwuLbANzOdw6Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T08:29:42.831078Z","bundle_sha256":"bfe44ab0efa7ca24801f67c4e7d80378cc5b23ae9cf751aed687d1f052a79808"}}