{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PSMCY4DQHPHP3QZQPWDLKTOPIC","short_pith_number":"pith:PSMCY4DQ","canonical_record":{"source":{"id":"2310.14429","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-10-22T22:25:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0188b9dc2c1f6cf68694811dfe1c078858ffa30117fddc269c8a42f4bf7ea2be","abstract_canon_sha256":"e67683c8bed36a101c264199ea0d27145e03aab9210b75d71203fd9b8aef1047"},"schema_version":"1.0"},"canonical_sha256":"7c982c70703bcefdc3307d86b54dcf40924e284cb4740cb769eedfbf171aaec1","source":{"kind":"arxiv","id":"2310.14429","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14429","created_at":"2026-07-05T07:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14429v1","created_at":"2026-07-05T07:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14429","created_at":"2026-07-05T07:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"PSMCY4DQHPHP","created_at":"2026-07-05T07:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"PSMCY4DQHPHP3QZQ","created_at":"2026-07-05T07:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"PSMCY4DQ","created_at":"2026-07-05T07:03:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PSMCY4DQHPHP3QZQPWDLKTOPIC","target":"record","payload":{"canonical_record":{"source":{"id":"2310.14429","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-10-22T22:25:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0188b9dc2c1f6cf68694811dfe1c078858ffa30117fddc269c8a42f4bf7ea2be","abstract_canon_sha256":"e67683c8bed36a101c264199ea0d27145e03aab9210b75d71203fd9b8aef1047"},"schema_version":"1.0"},"canonical_sha256":"7c982c70703bcefdc3307d86b54dcf40924e284cb4740cb769eedfbf171aaec1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:44.243346Z","signature_b64":"DQt1anjrYfmTbz64edu89/DIPX7DITaSL09JI5bzvfXNk5XgJ70IKJC63x+poRYIVGfyGhg/7V2ct9BbNPglAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c982c70703bcefdc3307d86b54dcf40924e284cb4740cb769eedfbf171aaec1","last_reissued_at":"2026-07-05T07:03:44.242867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:44.242867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.14429","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":"2026-07-05T07:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qavuOQYzV9QAjQswgR0sq9lY5OKlNAV50TRBXDOUjIrZt/x/sG7eVknfTc3CRc1Eyi6PNct+3MGKJyBfqv+wAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:10:24.534143Z"},"content_sha256":"1db1743c993611835d56db8070611e9930d88dc18ab7a02f41321a5ac79904e1","schema_version":"1.0","event_id":"sha256:1db1743c993611835d56db8070611e9930d88dc18ab7a02f41321a5ac79904e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PSMCY4DQHPHP3QZQPWDLKTOPIC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text generation for dataset augmentation in security classification tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CR","authors_text":"Alexander P. Welsh, Matthew Edwards","submitted_at":"2023-10-22T22:25:14Z","abstract_excerpt":"Security classifiers, designed to detect malicious content in computer systems and communications, can underperform when provided with insufficient training data. In the security domain, it is often easy to find samples of the negative (benign) class, and challenging to find enough samples of the positive (malicious) class to train an effective classifier. This study evaluates the application of natural language text generators to fill this data gap in multiple security-related text classification tasks. We describe a variety of previously-unexamined language-model fine-tuning approaches for t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14429","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/2310.14429/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":"2026-07-05T07:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WTemfKeNaPoP/Vq+UQ4tF/LY6YxKocmN0C/tdKF4x49m6ajezODulOhOldmgTlnlMfg5HIkrijZpg7mlZNUAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:10:24.534639Z"},"content_sha256":"d7a0e2eb7e2a31bb80b1dcad5bafe114d6a2a6c0dbd9cafd3da5e67ff043f03f","schema_version":"1.0","event_id":"sha256:d7a0e2eb7e2a31bb80b1dcad5bafe114d6a2a6c0dbd9cafd3da5e67ff043f03f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PSMCY4DQHPHP3QZQPWDLKTOPIC/bundle.json","state_url":"https://pith.science/pith/PSMCY4DQHPHP3QZQPWDLKTOPIC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PSMCY4DQHPHP3QZQPWDLKTOPIC/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":"2026-08-08T01:10:24Z","links":{"resolver":"https://pith.science/pith/PSMCY4DQHPHP3QZQPWDLKTOPIC","bundle":"https://pith.science/pith/PSMCY4DQHPHP3QZQPWDLKTOPIC/bundle.json","state":"https://pith.science/pith/PSMCY4DQHPHP3QZQPWDLKTOPIC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PSMCY4DQHPHP3QZQPWDLKTOPIC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PSMCY4DQHPHP3QZQPWDLKTOPIC","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":"e67683c8bed36a101c264199ea0d27145e03aab9210b75d71203fd9b8aef1047","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-10-22T22:25:14Z","title_canon_sha256":"0188b9dc2c1f6cf68694811dfe1c078858ffa30117fddc269c8a42f4bf7ea2be"},"schema_version":"1.0","source":{"id":"2310.14429","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14429","created_at":"2026-07-05T07:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14429v1","created_at":"2026-07-05T07:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14429","created_at":"2026-07-05T07:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"PSMCY4DQHPHP","created_at":"2026-07-05T07:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"PSMCY4DQHPHP3QZQ","created_at":"2026-07-05T07:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"PSMCY4DQ","created_at":"2026-07-05T07:03:44Z"}],"graph_snapshots":[{"event_id":"sha256:d7a0e2eb7e2a31bb80b1dcad5bafe114d6a2a6c0dbd9cafd3da5e67ff043f03f","target":"graph","created_at":"2026-07-05T07:03:44Z","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/2310.14429/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Security classifiers, designed to detect malicious content in computer systems and communications, can underperform when provided with insufficient training data. In the security domain, it is often easy to find samples of the negative (benign) class, and challenging to find enough samples of the positive (malicious) class to train an effective classifier. This study evaluates the application of natural language text generators to fill this data gap in multiple security-related text classification tasks. We describe a variety of previously-unexamined language-model fine-tuning approaches for t","authors_text":"Alexander P. Welsh, Matthew Edwards","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-10-22T22:25:14Z","title":"Text generation for dataset augmentation in security classification tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14429","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":"sha256:1db1743c993611835d56db8070611e9930d88dc18ab7a02f41321a5ac79904e1","target":"record","created_at":"2026-07-05T07:03:44Z","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":"e67683c8bed36a101c264199ea0d27145e03aab9210b75d71203fd9b8aef1047","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-10-22T22:25:14Z","title_canon_sha256":"0188b9dc2c1f6cf68694811dfe1c078858ffa30117fddc269c8a42f4bf7ea2be"},"schema_version":"1.0","source":{"id":"2310.14429","kind":"arxiv","version":1}},"canonical_sha256":"7c982c70703bcefdc3307d86b54dcf40924e284cb4740cb769eedfbf171aaec1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c982c70703bcefdc3307d86b54dcf40924e284cb4740cb769eedfbf171aaec1","first_computed_at":"2026-07-05T07:03:44.242867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:44.242867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DQt1anjrYfmTbz64edu89/DIPX7DITaSL09JI5bzvfXNk5XgJ70IKJC63x+poRYIVGfyGhg/7V2ct9BbNPglAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:44.243346Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.14429","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1db1743c993611835d56db8070611e9930d88dc18ab7a02f41321a5ac79904e1","sha256:d7a0e2eb7e2a31bb80b1dcad5bafe114d6a2a6c0dbd9cafd3da5e67ff043f03f"],"state_sha256":"5e037c970527c0d3ac5ca337ae3dc02abdff2329a19bb04e9ca3ebe776cd74df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pU/5Yj1N+krrKF7oxvwrp9pAGY24Uk6Oy7LVwFVJnZ0aa3Mb31wac00eprxot6Xrc7bflvp/A7ltygvtusBsDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:10:24.538552Z","bundle_sha256":"a270d710cbba3ada3ba53f69ff2bd234dc4e3a9c48cf732882c2442a78a45e36"}}