{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CTMIZU464ERVGXS2WERBX4EXID","short_pith_number":"pith:CTMIZU46","schema_version":"1.0","canonical_sha256":"14d88cd39ee123535e5ab1221bf09740db0fc8a4b91dee1e1dc2171264db2bca","source":{"kind":"arxiv","id":"2109.06595","version":2},"attestation_state":"computed","paper":{"title":"GPT-2C: A GPT-2 parser for Cowrie honeypot logs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Dimitris Tsakalidis, Erion Tsani, Fatima Sadiq, Febrian Setianto, Georgios Domalis, Panos Kostakos","submitted_at":"2021-09-14T11:33:04Z","abstract_excerpt":"Deception technologies like honeypots produce comprehensive log reports, but often lack interoperability with EDR and SIEM technologies. A key bottleneck is that existing information transformation plugins perform well on static logs (e.g. geolocation), but face limitations when it comes to parsing dynamic log topics (e.g. user-generated content). In this paper, we present a run-time system (GPT-2C) that leverages large pre-trained models (GPT-2) to parse dynamic logs generate by a Cowrie SSH honeypot. Our fine-tuned model achieves 89\\% inference accuracy in the new domain and demonstrates acc"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2109.06595","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2021-09-14T11:33:04Z","cross_cats_sorted":[],"title_canon_sha256":"0677babc95a879d63a29b37174c24f4c771edfc35d4bec29c1b94417cd4abe0a","abstract_canon_sha256":"b0895dd5d3964a5ee0ac086f4cf39e75d0a3e935af4c33ade0a53a790c741e05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:14:36.812739Z","signature_b64":"8CqazJ0zJOAg+ZmmDoJsjp0DYaV692Pa5vN4I7uSjiPhzBDg82oe9WCPpOTQteOlRX2KKCIgNMK8YL1qZ4eZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14d88cd39ee123535e5ab1221bf09740db0fc8a4b91dee1e1dc2171264db2bca","last_reissued_at":"2026-07-05T03:14:36.812324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:14:36.812324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPT-2C: A GPT-2 parser for Cowrie honeypot logs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Dimitris Tsakalidis, Erion Tsani, Fatima Sadiq, Febrian Setianto, Georgios Domalis, Panos Kostakos","submitted_at":"2021-09-14T11:33:04Z","abstract_excerpt":"Deception technologies like honeypots produce comprehensive log reports, but often lack interoperability with EDR and SIEM technologies. A key bottleneck is that existing information transformation plugins perform well on static logs (e.g. geolocation), but face limitations when it comes to parsing dynamic log topics (e.g. user-generated content). In this paper, we present a run-time system (GPT-2C) that leverages large pre-trained models (GPT-2) to parse dynamic logs generate by a Cowrie SSH honeypot. Our fine-tuned model achieves 89\\% inference accuracy in the new domain and demonstrates acc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06595","kind":"arxiv","version":2},"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/2109.06595/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2109.06595","created_at":"2026-07-05T03:14:36.812384+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.06595v2","created_at":"2026-07-05T03:14:36.812384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06595","created_at":"2026-07-05T03:14:36.812384+00:00"},{"alias_kind":"pith_short_12","alias_value":"CTMIZU464ERV","created_at":"2026-07-05T03:14:36.812384+00:00"},{"alias_kind":"pith_short_16","alias_value":"CTMIZU464ERVGXS2","created_at":"2026-07-05T03:14:36.812384+00:00"},{"alias_kind":"pith_short_8","alias_value":"CTMIZU46","created_at":"2026-07-05T03:14:36.812384+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CTMIZU464ERVGXS2WERBX4EXID","json":"https://pith.science/pith/CTMIZU464ERVGXS2WERBX4EXID.json","graph_json":"https://pith.science/api/pith-number/CTMIZU464ERVGXS2WERBX4EXID/graph.json","events_json":"https://pith.science/api/pith-number/CTMIZU464ERVGXS2WERBX4EXID/events.json","paper":"https://pith.science/paper/CTMIZU46"},"agent_actions":{"view_html":"https://pith.science/pith/CTMIZU464ERVGXS2WERBX4EXID","download_json":"https://pith.science/pith/CTMIZU464ERVGXS2WERBX4EXID.json","view_paper":"https://pith.science/paper/CTMIZU46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.06595&json=true","fetch_graph":"https://pith.science/api/pith-number/CTMIZU464ERVGXS2WERBX4EXID/graph.json","fetch_events":"https://pith.science/api/pith-number/CTMIZU464ERVGXS2WERBX4EXID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CTMIZU464ERVGXS2WERBX4EXID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CTMIZU464ERVGXS2WERBX4EXID/action/storage_attestation","attest_author":"https://pith.science/pith/CTMIZU464ERVGXS2WERBX4EXID/action/author_attestation","sign_citation":"https://pith.science/pith/CTMIZU464ERVGXS2WERBX4EXID/action/citation_signature","submit_replication":"https://pith.science/pith/CTMIZU464ERVGXS2WERBX4EXID/action/replication_record"}},"created_at":"2026-07-05T03:14:36.812384+00:00","updated_at":"2026-07-05T03:14:36.812384+00:00"}