{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:6H2C5KSJP6LXRR5RD4CWZVKSRA","short_pith_number":"pith:6H2C5KSJ","canonical_record":{"source":{"id":"2012.09597","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-17T14:11:03Z","cross_cats_sorted":[],"title_canon_sha256":"f6edc486374a2b5515edb1d5a19fbf778a94ee449c01fed8b94406e6a83ba409","abstract_canon_sha256":"827461db4f8e6e0c7ecd6a5aabd640fa372edb722acbb6ed6002d563176024dd"},"schema_version":"1.0"},"canonical_sha256":"f1f42eaa497f9778c7b11f056cd5528830938f22e52147390c8a85dfec3103ff","source":{"kind":"arxiv","id":"2012.09597","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.09597","created_at":"2026-07-05T02:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"2012.09597v1","created_at":"2026-07-05T02:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.09597","created_at":"2026-07-05T02:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"6H2C5KSJP6LX","created_at":"2026-07-05T02:00:19Z"},{"alias_kind":"pith_short_16","alias_value":"6H2C5KSJP6LXRR5R","created_at":"2026-07-05T02:00:19Z"},{"alias_kind":"pith_short_8","alias_value":"6H2C5KSJ","created_at":"2026-07-05T02:00:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:6H2C5KSJP6LXRR5RD4CWZVKSRA","target":"record","payload":{"canonical_record":{"source":{"id":"2012.09597","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-17T14:11:03Z","cross_cats_sorted":[],"title_canon_sha256":"f6edc486374a2b5515edb1d5a19fbf778a94ee449c01fed8b94406e6a83ba409","abstract_canon_sha256":"827461db4f8e6e0c7ecd6a5aabd640fa372edb722acbb6ed6002d563176024dd"},"schema_version":"1.0"},"canonical_sha256":"f1f42eaa497f9778c7b11f056cd5528830938f22e52147390c8a85dfec3103ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:19.259600Z","signature_b64":"enAyn1CRzlAkZHFJILeHki8ClAP/nqK/9NW4MSsqXh+TAy5H/x2ywIidFpG3zoxo1Ex4S0Yr6qsbqXYecNXLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1f42eaa497f9778c7b11f056cd5528830938f22e52147390c8a85dfec3103ff","last_reissued_at":"2026-07-05T02:00:19.259173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:19.259173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.09597","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":"2026-07-05T02:00:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oISAXVYlcgysKgpqG1T7g/KD86Q/HnG8gPbIZmLY2VWWL6KXfh8xv05c7sfZ/u49pPhXyWyg/1/AMXvYGmGqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T21:27:16.736770Z"},"content_sha256":"cf13457a4c1381f021abcbc43d3192ba8b6d93f8af1b4103bbd6dd73f6bc88f2","schema_version":"1.0","event_id":"sha256:cf13457a4c1381f021abcbc43d3192ba8b6d93f8af1b4103bbd6dd73f6bc88f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:6H2C5KSJP6LXRR5RD4CWZVKSRA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sensitive Data Detection with High-Throughput Neural Network Models for Financial Institutions","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anh Truong, Austin Walters, Jeremy Goodsitt","submitted_at":"2020-12-17T14:11:03Z","abstract_excerpt":"Named Entity Recognition has been extensively investigated in many fields. However, the application of sensitive entity detection for production systems in financial institutions has not been well explored due to the lack of publicly available, labeled datasets. In this paper, we use internal and synthetic datasets to evaluate various methods of detecting NPI (Nonpublic Personally Identifiable) information commonly found within financial institutions, in both unstructured and structured data formats. Character-level neural network models including CNN, LSTM, BiLSTM-CRF, and CNN-CRF are investi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.09597","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/2012.09597/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":"2026-07-05T02:00:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"079/ArgU4Tmswf4A2WpK+DSyqv86FezoTlzAflpF8lhVYYJpCDqGKYHuuGsVlin414tgeUkt+lO8UNBbK3GXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T21:27:16.737268Z"},"content_sha256":"a0055050a9f1fb51bcdcd245466210abeb016a0748cc5145010774e4bee3804d","schema_version":"1.0","event_id":"sha256:a0055050a9f1fb51bcdcd245466210abeb016a0748cc5145010774e4bee3804d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6H2C5KSJP6LXRR5RD4CWZVKSRA/bundle.json","state_url":"https://pith.science/pith/6H2C5KSJP6LXRR5RD4CWZVKSRA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6H2C5KSJP6LXRR5RD4CWZVKSRA/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":"2026-08-23T21:27:16Z","links":{"resolver":"https://pith.science/pith/6H2C5KSJP6LXRR5RD4CWZVKSRA","bundle":"https://pith.science/pith/6H2C5KSJP6LXRR5RD4CWZVKSRA/bundle.json","state":"https://pith.science/pith/6H2C5KSJP6LXRR5RD4CWZVKSRA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6H2C5KSJP6LXRR5RD4CWZVKSRA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6H2C5KSJP6LXRR5RD4CWZVKSRA","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":"827461db4f8e6e0c7ecd6a5aabd640fa372edb722acbb6ed6002d563176024dd","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-17T14:11:03Z","title_canon_sha256":"f6edc486374a2b5515edb1d5a19fbf778a94ee449c01fed8b94406e6a83ba409"},"schema_version":"1.0","source":{"id":"2012.09597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.09597","created_at":"2026-07-05T02:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"2012.09597v1","created_at":"2026-07-05T02:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.09597","created_at":"2026-07-05T02:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"6H2C5KSJP6LX","created_at":"2026-07-05T02:00:19Z"},{"alias_kind":"pith_short_16","alias_value":"6H2C5KSJP6LXRR5R","created_at":"2026-07-05T02:00:19Z"},{"alias_kind":"pith_short_8","alias_value":"6H2C5KSJ","created_at":"2026-07-05T02:00:19Z"}],"graph_snapshots":[{"event_id":"sha256:a0055050a9f1fb51bcdcd245466210abeb016a0748cc5145010774e4bee3804d","target":"graph","created_at":"2026-07-05T02:00:19Z","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/2012.09597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Named Entity Recognition has been extensively investigated in many fields. However, the application of sensitive entity detection for production systems in financial institutions has not been well explored due to the lack of publicly available, labeled datasets. In this paper, we use internal and synthetic datasets to evaluate various methods of detecting NPI (Nonpublic Personally Identifiable) information commonly found within financial institutions, in both unstructured and structured data formats. Character-level neural network models including CNN, LSTM, BiLSTM-CRF, and CNN-CRF are investi","authors_text":"Anh Truong, Austin Walters, Jeremy Goodsitt","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-17T14:11:03Z","title":"Sensitive Data Detection with High-Throughput Neural Network Models for Financial Institutions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.09597","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:cf13457a4c1381f021abcbc43d3192ba8b6d93f8af1b4103bbd6dd73f6bc88f2","target":"record","created_at":"2026-07-05T02:00:19Z","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":"827461db4f8e6e0c7ecd6a5aabd640fa372edb722acbb6ed6002d563176024dd","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-17T14:11:03Z","title_canon_sha256":"f6edc486374a2b5515edb1d5a19fbf778a94ee449c01fed8b94406e6a83ba409"},"schema_version":"1.0","source":{"id":"2012.09597","kind":"arxiv","version":1}},"canonical_sha256":"f1f42eaa497f9778c7b11f056cd5528830938f22e52147390c8a85dfec3103ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1f42eaa497f9778c7b11f056cd5528830938f22e52147390c8a85dfec3103ff","first_computed_at":"2026-07-05T02:00:19.259173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:00:19.259173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"enAyn1CRzlAkZHFJILeHki8ClAP/nqK/9NW4MSsqXh+TAy5H/x2ywIidFpG3zoxo1Ex4S0Yr6qsbqXYecNXLCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:00:19.259600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.09597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf13457a4c1381f021abcbc43d3192ba8b6d93f8af1b4103bbd6dd73f6bc88f2","sha256:a0055050a9f1fb51bcdcd245466210abeb016a0748cc5145010774e4bee3804d"],"state_sha256":"4f95294252606d8f3f723232435762ea3e49978a9388cf5cdc92452ba7af87ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zQCYFamNr25trr3qv2tASVCCJsZ91tZbTkxEbbd7KfToS7woefxgyXZb55DgRA1dMRVr3nCnN9L30fx4fdiLCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T21:27:16.740925Z","bundle_sha256":"f4fe9d7c472da9cb6894cbf4b151ed2ede16fb06040472e68e1ca2708750c671"}}