{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VOV7WFQF23XJF2E4AN7GHBYKP7","short_pith_number":"pith:VOV7WFQF","schema_version":"1.0","canonical_sha256":"ababfb1605d6ee92e89c037e63870a7ff179033223ed1a0ec50807343be7eda8","source":{"kind":"arxiv","id":"2404.07765","version":1},"attestation_state":"computed","paper":{"title":"AnnoCTR: A Dataset for Detecting and Linking Entities, Tactics, and Techniques in Cyber Threat Reports","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Annemarie Friedrich, Dragan Milchevski, Ghazaleh Haratinezhad Torbati, Lukas Lange, Marc M\\\"uller, Patrick Grau, Subhash Pujari","submitted_at":"2024-04-11T14:04:36Z","abstract_excerpt":"Monitoring the threat landscape to be aware of actual or potential attacks is of utmost importance to cybersecurity professionals. Information about cyber threats is typically distributed using natural language reports. Natural language processing can help with managing this large amount of unstructured information, yet to date, the topic has received little attention. With this paper, we present AnnoCTR, a new CC-BY-SA-licensed dataset of cyber threat reports. The reports have been annotated by a domain expert with named entities, temporal expressions, and cybersecurity-specific concepts incl"},"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":"2404.07765","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T14:04:36Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"title_canon_sha256":"0be72c237523f3ab3147dfebe0c5024aea14f43ca65ffbe41cf8982bb6e12d94","abstract_canon_sha256":"bbed601f01b7407c5640b1377e9b0ee23f2dbbf1d6afe97d3bd10221cdce39d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:57.400815Z","signature_b64":"bsopGHCOhKU/4s9SVmjPqOOAbYprWREGPumvQ6vjpDQXkUVowxh6m/4oI8Pg7yhCm/z9RdGeH6T027Pj2Q7CCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ababfb1605d6ee92e89c037e63870a7ff179033223ed1a0ec50807343be7eda8","last_reissued_at":"2026-07-05T08:06:57.400299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:57.400299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnnoCTR: A Dataset for Detecting and Linking Entities, Tactics, and Techniques in Cyber Threat Reports","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Annemarie Friedrich, Dragan Milchevski, Ghazaleh Haratinezhad Torbati, Lukas Lange, Marc M\\\"uller, Patrick Grau, Subhash Pujari","submitted_at":"2024-04-11T14:04:36Z","abstract_excerpt":"Monitoring the threat landscape to be aware of actual or potential attacks is of utmost importance to cybersecurity professionals. Information about cyber threats is typically distributed using natural language reports. Natural language processing can help with managing this large amount of unstructured information, yet to date, the topic has received little attention. With this paper, we present AnnoCTR, a new CC-BY-SA-licensed dataset of cyber threat reports. The reports have been annotated by a domain expert with named entities, temporal expressions, and cybersecurity-specific concepts incl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07765","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/2404.07765/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":"2404.07765","created_at":"2026-07-05T08:06:57.400373+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07765v1","created_at":"2026-07-05T08:06:57.400373+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07765","created_at":"2026-07-05T08:06:57.400373+00:00"},{"alias_kind":"pith_short_12","alias_value":"VOV7WFQF23XJ","created_at":"2026-07-05T08:06:57.400373+00:00"},{"alias_kind":"pith_short_16","alias_value":"VOV7WFQF23XJF2E4","created_at":"2026-07-05T08:06:57.400373+00:00"},{"alias_kind":"pith_short_8","alias_value":"VOV7WFQF","created_at":"2026-07-05T08:06:57.400373+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07470","citing_title":"Beyond Single Reports: Evaluating Automated ATT&CK Technique Extraction in Multi-Report Campaign Settings","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VOV7WFQF23XJF2E4AN7GHBYKP7","json":"https://pith.science/pith/VOV7WFQF23XJF2E4AN7GHBYKP7.json","graph_json":"https://pith.science/api/pith-number/VOV7WFQF23XJF2E4AN7GHBYKP7/graph.json","events_json":"https://pith.science/api/pith-number/VOV7WFQF23XJF2E4AN7GHBYKP7/events.json","paper":"https://pith.science/paper/VOV7WFQF"},"agent_actions":{"view_html":"https://pith.science/pith/VOV7WFQF23XJF2E4AN7GHBYKP7","download_json":"https://pith.science/pith/VOV7WFQF23XJF2E4AN7GHBYKP7.json","view_paper":"https://pith.science/paper/VOV7WFQF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07765&json=true","fetch_graph":"https://pith.science/api/pith-number/VOV7WFQF23XJF2E4AN7GHBYKP7/graph.json","fetch_events":"https://pith.science/api/pith-number/VOV7WFQF23XJF2E4AN7GHBYKP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VOV7WFQF23XJF2E4AN7GHBYKP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VOV7WFQF23XJF2E4AN7GHBYKP7/action/storage_attestation","attest_author":"https://pith.science/pith/VOV7WFQF23XJF2E4AN7GHBYKP7/action/author_attestation","sign_citation":"https://pith.science/pith/VOV7WFQF23XJF2E4AN7GHBYKP7/action/citation_signature","submit_replication":"https://pith.science/pith/VOV7WFQF23XJF2E4AN7GHBYKP7/action/replication_record"}},"created_at":"2026-07-05T08:06:57.400373+00:00","updated_at":"2026-07-05T08:06:57.400373+00:00"}