{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JW6JBM5IH2S22I2Z4OOWDHB7KT","short_pith_number":"pith:JW6JBM5I","schema_version":"1.0","canonical_sha256":"4dbc90b3a83ea5ad2359e39d619c3f54da18f6fcc2e1b374e212c53678497ea2","source":{"kind":"arxiv","id":"2209.03188","version":1},"attestation_state":"computed","paper":{"title":"Avast-CTU Public CAPE Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Branislav Bosansky, Dominik Kouba, Jakub Kroustek, Ondrej Manhal, Petr Somol, Thorsten Sick, Viliam Lisy","submitted_at":"2022-09-06T13:22:27Z","abstract_excerpt":"There is a limited amount of publicly available data to support research in malware analysis technology. Particularly, there are virtually no publicly available datasets generated from rich sandboxes such as Cuckoo/CAPE. The benefit of using dynamic sandboxes is the realistic simulation of file execution in the target machine and obtaining a log of such execution. The machine can be infected by malware hence there is a good chance of capturing the malicious behavior in the execution logs, thus allowing researchers to study such behavior in detail. Although the subsequent analysis of log inform"},"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":"2209.03188","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2022-09-06T13:22:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"43c6ca0d2e7066310b88faf4d56ef4ecd1924a60d524b8c1535696c571c6a543","abstract_canon_sha256":"2d9d3ad915e7ac6d5442150ead873eaf9227f1bac132527a30ed9e3e0e64c532"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:55:32.580497Z","signature_b64":"jMSf7tEUERaLqVtVTaYiM4c5a23Sd8kNmmvkJHe1Nxdn2+Gy6EmBmNQRIvUtgtEHuRxAeImYWZ/QhAdTuj2YDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dbc90b3a83ea5ad2359e39d619c3f54da18f6fcc2e1b374e212c53678497ea2","last_reissued_at":"2026-07-05T04:55:32.580149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:55:32.580149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Avast-CTU Public CAPE Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Branislav Bosansky, Dominik Kouba, Jakub Kroustek, Ondrej Manhal, Petr Somol, Thorsten Sick, Viliam Lisy","submitted_at":"2022-09-06T13:22:27Z","abstract_excerpt":"There is a limited amount of publicly available data to support research in malware analysis technology. Particularly, there are virtually no publicly available datasets generated from rich sandboxes such as Cuckoo/CAPE. The benefit of using dynamic sandboxes is the realistic simulation of file execution in the target machine and obtaining a log of such execution. The machine can be infected by malware hence there is a good chance of capturing the malicious behavior in the execution logs, thus allowing researchers to study such behavior in detail. Although the subsequent analysis of log inform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.03188","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/2209.03188/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":"2209.03188","created_at":"2026-07-05T04:55:32.580205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.03188v1","created_at":"2026-07-05T04:55:32.580205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.03188","created_at":"2026-07-05T04:55:32.580205+00:00"},{"alias_kind":"pith_short_12","alias_value":"JW6JBM5IH2S2","created_at":"2026-07-05T04:55:32.580205+00:00"},{"alias_kind":"pith_short_16","alias_value":"JW6JBM5IH2S22I2Z","created_at":"2026-07-05T04:55:32.580205+00:00"},{"alias_kind":"pith_short_8","alias_value":"JW6JBM5I","created_at":"2026-07-05T04:55:32.580205+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00297","citing_title":"Trident: Improving Malware Detection with LLMs and Behavioral Features","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JW6JBM5IH2S22I2Z4OOWDHB7KT","json":"https://pith.science/pith/JW6JBM5IH2S22I2Z4OOWDHB7KT.json","graph_json":"https://pith.science/api/pith-number/JW6JBM5IH2S22I2Z4OOWDHB7KT/graph.json","events_json":"https://pith.science/api/pith-number/JW6JBM5IH2S22I2Z4OOWDHB7KT/events.json","paper":"https://pith.science/paper/JW6JBM5I"},"agent_actions":{"view_html":"https://pith.science/pith/JW6JBM5IH2S22I2Z4OOWDHB7KT","download_json":"https://pith.science/pith/JW6JBM5IH2S22I2Z4OOWDHB7KT.json","view_paper":"https://pith.science/paper/JW6JBM5I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.03188&json=true","fetch_graph":"https://pith.science/api/pith-number/JW6JBM5IH2S22I2Z4OOWDHB7KT/graph.json","fetch_events":"https://pith.science/api/pith-number/JW6JBM5IH2S22I2Z4OOWDHB7KT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JW6JBM5IH2S22I2Z4OOWDHB7KT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JW6JBM5IH2S22I2Z4OOWDHB7KT/action/storage_attestation","attest_author":"https://pith.science/pith/JW6JBM5IH2S22I2Z4OOWDHB7KT/action/author_attestation","sign_citation":"https://pith.science/pith/JW6JBM5IH2S22I2Z4OOWDHB7KT/action/citation_signature","submit_replication":"https://pith.science/pith/JW6JBM5IH2S22I2Z4OOWDHB7KT/action/replication_record"}},"created_at":"2026-07-05T04:55:32.580205+00:00","updated_at":"2026-07-05T04:55:32.580205+00:00"}