{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:7LF5CAADC33QKWLMUXDJ6TNSQT","short_pith_number":"pith:7LF5CAAD","canonical_record":{"source":{"id":"2111.15633","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SI","submitted_at":"2021-11-28T04:34:48Z","cross_cats_sorted":[],"title_canon_sha256":"3d97472865be8ca8875f46053f741742fc7558be7286b440f59dccd091598933","abstract_canon_sha256":"bb942285e930a6c6eb8dd1fe804044158a7fccf5b9f2b1e44f2936a55981c2dc"},"schema_version":"1.0"},"canonical_sha256":"facbd1000316f705596ca5c69f4db284c4f77f44da024d5c23a9c5839404e204","source":{"kind":"arxiv","id":"2111.15633","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.15633","created_at":"2026-07-05T03:36:28Z"},{"alias_kind":"arxiv_version","alias_value":"2111.15633v1","created_at":"2026-07-05T03:36:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.15633","created_at":"2026-07-05T03:36:28Z"},{"alias_kind":"pith_short_12","alias_value":"7LF5CAADC33Q","created_at":"2026-07-05T03:36:28Z"},{"alias_kind":"pith_short_16","alias_value":"7LF5CAADC33QKWLM","created_at":"2026-07-05T03:36:28Z"},{"alias_kind":"pith_short_8","alias_value":"7LF5CAAD","created_at":"2026-07-05T03:36:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:7LF5CAADC33QKWLMUXDJ6TNSQT","target":"record","payload":{"canonical_record":{"source":{"id":"2111.15633","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SI","submitted_at":"2021-11-28T04:34:48Z","cross_cats_sorted":[],"title_canon_sha256":"3d97472865be8ca8875f46053f741742fc7558be7286b440f59dccd091598933","abstract_canon_sha256":"bb942285e930a6c6eb8dd1fe804044158a7fccf5b9f2b1e44f2936a55981c2dc"},"schema_version":"1.0"},"canonical_sha256":"facbd1000316f705596ca5c69f4db284c4f77f44da024d5c23a9c5839404e204","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:28.460683Z","signature_b64":"1fPxGJefLGnrv5UQL3617cfcU1VnzwFYwRqHCP1vNjHmY1JyqBS0pxgj29SZ8bcI+PhFvBLVaW+S4uBqjJYeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"facbd1000316f705596ca5c69f4db284c4f77f44da024d5c23a9c5839404e204","last_reissued_at":"2026-07-05T03:36:28.458131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:28.458131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.15633","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":"2026-07-05T03:36:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OCRayfk10jZRuEZLoFaEkGUa/8UnmvGgdqRrMkL/22JRTMOWslATejGymH5m/2aIGUTZitMmpnGR2QjOnD2dCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:03:17.502532Z"},"content_sha256":"c733944cc600c80886265889b09cebdb25a69f01e7d5e3352d432a43ccedbe8c","schema_version":"1.0","event_id":"sha256:c733944cc600c80886265889b09cebdb25a69f01e7d5e3352d432a43ccedbe8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:7LF5CAADC33QKWLMUXDJ6TNSQT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable Community Extraction of Text Networks for Automated Grouping in Medical Databases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SI","authors_text":"Allan Fong, Srijan Sengupta, Tomilayo Komolafe","submitted_at":"2021-11-28T04:34:48Z","abstract_excerpt":"Networks are ubiquitous in today's world. Community structure is a well-known feature of many empirical networks, and a lot of statistical methods have been developed for community detection. In this paper, we consider the problem of community structure in text networks,which is greatly relevant in medical errors and patient safety databases. We adapt a well-known community extraction method to develop a scalable algorithm for community extraction in large text databases. The application of our method on a real-world patient safety report database demonstrates that the groups generated from co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.15633","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/2111.15633/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":"2026-07-05T03:36:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fmrwc7rspBWT4dfDboG3YkqIYfHWuLXzyQIPSDIILN+TC/6dUoP38yexs5hYVhz3vei9IKedqpKJ7XYmiK3fDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:03:17.503220Z"},"content_sha256":"e3a1ce11c9e60bbdb74d23049babc867c046710624e1b5d8f73b870c572ccf4a","schema_version":"1.0","event_id":"sha256:e3a1ce11c9e60bbdb74d23049babc867c046710624e1b5d8f73b870c572ccf4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7LF5CAADC33QKWLMUXDJ6TNSQT/bundle.json","state_url":"https://pith.science/pith/7LF5CAADC33QKWLMUXDJ6TNSQT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7LF5CAADC33QKWLMUXDJ6TNSQT/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":"2026-08-11T19:03:17Z","links":{"resolver":"https://pith.science/pith/7LF5CAADC33QKWLMUXDJ6TNSQT","bundle":"https://pith.science/pith/7LF5CAADC33QKWLMUXDJ6TNSQT/bundle.json","state":"https://pith.science/pith/7LF5CAADC33QKWLMUXDJ6TNSQT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7LF5CAADC33QKWLMUXDJ6TNSQT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7LF5CAADC33QKWLMUXDJ6TNSQT","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":"bb942285e930a6c6eb8dd1fe804044158a7fccf5b9f2b1e44f2936a55981c2dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SI","submitted_at":"2021-11-28T04:34:48Z","title_canon_sha256":"3d97472865be8ca8875f46053f741742fc7558be7286b440f59dccd091598933"},"schema_version":"1.0","source":{"id":"2111.15633","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.15633","created_at":"2026-07-05T03:36:28Z"},{"alias_kind":"arxiv_version","alias_value":"2111.15633v1","created_at":"2026-07-05T03:36:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.15633","created_at":"2026-07-05T03:36:28Z"},{"alias_kind":"pith_short_12","alias_value":"7LF5CAADC33Q","created_at":"2026-07-05T03:36:28Z"},{"alias_kind":"pith_short_16","alias_value":"7LF5CAADC33QKWLM","created_at":"2026-07-05T03:36:28Z"},{"alias_kind":"pith_short_8","alias_value":"7LF5CAAD","created_at":"2026-07-05T03:36:28Z"}],"graph_snapshots":[{"event_id":"sha256:e3a1ce11c9e60bbdb74d23049babc867c046710624e1b5d8f73b870c572ccf4a","target":"graph","created_at":"2026-07-05T03:36:28Z","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/2111.15633/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Networks are ubiquitous in today's world. Community structure is a well-known feature of many empirical networks, and a lot of statistical methods have been developed for community detection. In this paper, we consider the problem of community structure in text networks,which is greatly relevant in medical errors and patient safety databases. We adapt a well-known community extraction method to develop a scalable algorithm for community extraction in large text databases. The application of our method on a real-world patient safety report database demonstrates that the groups generated from co","authors_text":"Allan Fong, Srijan Sengupta, Tomilayo Komolafe","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SI","submitted_at":"2021-11-28T04:34:48Z","title":"Scalable Community Extraction of Text Networks for Automated Grouping in Medical Databases"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.15633","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:c733944cc600c80886265889b09cebdb25a69f01e7d5e3352d432a43ccedbe8c","target":"record","created_at":"2026-07-05T03:36:28Z","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":"bb942285e930a6c6eb8dd1fe804044158a7fccf5b9f2b1e44f2936a55981c2dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SI","submitted_at":"2021-11-28T04:34:48Z","title_canon_sha256":"3d97472865be8ca8875f46053f741742fc7558be7286b440f59dccd091598933"},"schema_version":"1.0","source":{"id":"2111.15633","kind":"arxiv","version":1}},"canonical_sha256":"facbd1000316f705596ca5c69f4db284c4f77f44da024d5c23a9c5839404e204","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"facbd1000316f705596ca5c69f4db284c4f77f44da024d5c23a9c5839404e204","first_computed_at":"2026-07-05T03:36:28.458131Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:36:28.458131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1fPxGJefLGnrv5UQL3617cfcU1VnzwFYwRqHCP1vNjHmY1JyqBS0pxgj29SZ8bcI+PhFvBLVaW+S4uBqjJYeBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:36:28.460683Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.15633","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c733944cc600c80886265889b09cebdb25a69f01e7d5e3352d432a43ccedbe8c","sha256:e3a1ce11c9e60bbdb74d23049babc867c046710624e1b5d8f73b870c572ccf4a"],"state_sha256":"149c4f93c88aea74adc024bdf9e2ab09fa9f5d75a304d670ea1f198d6e65c95c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IvzWXvOf2O9eW1Yhv40ofYigq1cbkCgt8tqJw07rrVSExbw5NXnCLjUUDDdj2qgsnk4fqA3YJW9Uli4Ig3kNBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T19:03:17.507204Z","bundle_sha256":"528641b8dbdbd60f15c28302842d7216ac2867e3a0dc1b06488f4e8cfcf45b94"}}