{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CXGLDZWQKTOAH5OMYJLY5BKXBF","short_pith_number":"pith:CXGLDZWQ","canonical_record":{"source":{"id":"2502.04372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T12:59:15Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"439e49c5b9ff33937f339ddda35ac4b23063cfa9a112d79aaec447d4c4f501ed","abstract_canon_sha256":"962dc5bd1e357e307cdd1d3cfc54442f2bbea5f635b77f2c1651d2db40f477e7"},"schema_version":"1.0"},"canonical_sha256":"15ccb1e6d054dc03f5ccc2578e8557096cf355f4ee3d1340886f4e5f1f10beea","source":{"kind":"arxiv","id":"2502.04372","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04372","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04372v1","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04372","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_12","alias_value":"CXGLDZWQKTOA","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_16","alias_value":"CXGLDZWQKTOAH5OM","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_8","alias_value":"CXGLDZWQ","created_at":"2026-07-05T10:10:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CXGLDZWQKTOAH5OMYJLY5BKXBF","target":"record","payload":{"canonical_record":{"source":{"id":"2502.04372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T12:59:15Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"439e49c5b9ff33937f339ddda35ac4b23063cfa9a112d79aaec447d4c4f501ed","abstract_canon_sha256":"962dc5bd1e357e307cdd1d3cfc54442f2bbea5f635b77f2c1651d2db40f477e7"},"schema_version":"1.0"},"canonical_sha256":"15ccb1e6d054dc03f5ccc2578e8557096cf355f4ee3d1340886f4e5f1f10beea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:50.566699Z","signature_b64":"5qfOBhcGrb31Nal7k/65XeQPmCFsScnx1eilLLfw4sudcywBH2URQJZ1ykGKJzUSJv4aNokMdMHzj4BCeWGjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15ccb1e6d054dc03f5ccc2578e8557096cf355f4ee3d1340886f4e5f1f10beea","last_reissued_at":"2026-07-05T10:10:50.566118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:50.566118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.04372","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":"2026-07-05T10:10:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XUXepMjMazWFxOO8ZeRN2HArM5MHtyr5g+QmWix9ucaXS9Ya0Vd9KH5lfDEz96HB/OXeUcbMTw7NrExFm5fzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:51:16.375171Z"},"content_sha256":"28cc689bc68b975481f6c410dbeb242d3a0ff40debf50c13f31e7c3ea0250889","schema_version":"1.0","event_id":"sha256:28cc689bc68b975481f6c410dbeb242d3a0ff40debf50c13f31e7c3ea0250889"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CXGLDZWQKTOAH5OMYJLY5BKXBF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mining Unstructured Medical Texts With Conformal Active Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Guilherme Tegoni Goedert, Juliano Genari","submitted_at":"2025-02-05T12:59:15Z","abstract_excerpt":"The extraction of relevant data from Electronic Health Records (EHRs) is crucial to identifying symptoms and automating epidemiological surveillance processes. By harnessing the vast amount of unstructured text in EHRs, we can detect patterns that indicate the onset of disease outbreaks, enabling faster, more targeted public health responses. Our proposed framework provides a flexible and efficient solution for mining data from unstructured texts, significantly reducing the need for extensive manual labeling by specialists. Experiments show that our framework achieving strong performance with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04372","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/2502.04372/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":"2026-07-05T10:10:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LvpR7LVbguvWK9d6DKVaRD3+qqBYyFD3kLcLKTUIo/TUp77usa4goXl1df1ePEfouYxYKHKYi5p5kOxkujkoAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:51:16.375881Z"},"content_sha256":"13a3ab5bb105975e372552e1e06805000df9ea5134b0b3aa2dd6db1b21e82813","schema_version":"1.0","event_id":"sha256:13a3ab5bb105975e372552e1e06805000df9ea5134b0b3aa2dd6db1b21e82813"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CXGLDZWQKTOAH5OMYJLY5BKXBF/bundle.json","state_url":"https://pith.science/pith/CXGLDZWQKTOAH5OMYJLY5BKXBF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CXGLDZWQKTOAH5OMYJLY5BKXBF/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":"2026-08-03T15:51:16Z","links":{"resolver":"https://pith.science/pith/CXGLDZWQKTOAH5OMYJLY5BKXBF","bundle":"https://pith.science/pith/CXGLDZWQKTOAH5OMYJLY5BKXBF/bundle.json","state":"https://pith.science/pith/CXGLDZWQKTOAH5OMYJLY5BKXBF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CXGLDZWQKTOAH5OMYJLY5BKXBF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CXGLDZWQKTOAH5OMYJLY5BKXBF","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":"962dc5bd1e357e307cdd1d3cfc54442f2bbea5f635b77f2c1651d2db40f477e7","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T12:59:15Z","title_canon_sha256":"439e49c5b9ff33937f339ddda35ac4b23063cfa9a112d79aaec447d4c4f501ed"},"schema_version":"1.0","source":{"id":"2502.04372","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04372","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04372v1","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04372","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_12","alias_value":"CXGLDZWQKTOA","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_16","alias_value":"CXGLDZWQKTOAH5OM","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_8","alias_value":"CXGLDZWQ","created_at":"2026-07-05T10:10:50Z"}],"graph_snapshots":[{"event_id":"sha256:13a3ab5bb105975e372552e1e06805000df9ea5134b0b3aa2dd6db1b21e82813","target":"graph","created_at":"2026-07-05T10:10:50Z","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/2502.04372/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The extraction of relevant data from Electronic Health Records (EHRs) is crucial to identifying symptoms and automating epidemiological surveillance processes. By harnessing the vast amount of unstructured text in EHRs, we can detect patterns that indicate the onset of disease outbreaks, enabling faster, more targeted public health responses. Our proposed framework provides a flexible and efficient solution for mining data from unstructured texts, significantly reducing the need for extensive manual labeling by specialists. Experiments show that our framework achieving strong performance with ","authors_text":"Guilherme Tegoni Goedert, Juliano Genari","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T12:59:15Z","title":"Mining Unstructured Medical Texts With Conformal Active Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04372","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":"sha256:28cc689bc68b975481f6c410dbeb242d3a0ff40debf50c13f31e7c3ea0250889","target":"record","created_at":"2026-07-05T10:10:50Z","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":"962dc5bd1e357e307cdd1d3cfc54442f2bbea5f635b77f2c1651d2db40f477e7","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T12:59:15Z","title_canon_sha256":"439e49c5b9ff33937f339ddda35ac4b23063cfa9a112d79aaec447d4c4f501ed"},"schema_version":"1.0","source":{"id":"2502.04372","kind":"arxiv","version":1}},"canonical_sha256":"15ccb1e6d054dc03f5ccc2578e8557096cf355f4ee3d1340886f4e5f1f10beea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15ccb1e6d054dc03f5ccc2578e8557096cf355f4ee3d1340886f4e5f1f10beea","first_computed_at":"2026-07-05T10:10:50.566118Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:50.566118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5qfOBhcGrb31Nal7k/65XeQPmCFsScnx1eilLLfw4sudcywBH2URQJZ1ykGKJzUSJv4aNokMdMHzj4BCeWGjCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:50.566699Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04372","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28cc689bc68b975481f6c410dbeb242d3a0ff40debf50c13f31e7c3ea0250889","sha256:13a3ab5bb105975e372552e1e06805000df9ea5134b0b3aa2dd6db1b21e82813"],"state_sha256":"6d5241f101a4ed0b5414401cc39d15a6859dd269e817afa33d76580627cdc4ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UtGnkwKARymBs7hNtlSClu71lhGSbKfqr2766jBVaZ2IrA/SDz8GhjtgojZz2Z1pcVFg0nEKlwVyRk11oYtBDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:51:16.381330Z","bundle_sha256":"a60e848428157046fdf2567457ea3bce9f6bbca69ef18fa2ca8a9befb2addb27"}}