{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IW3PVAK5M5CVFFCT5XFUNY5KR3","short_pith_number":"pith:IW3PVAK5","schema_version":"1.0","canonical_sha256":"45b6fa815d6745529453edcb46e3aa8ee2a02853da4b55fb3490d192160906de","source":{"kind":"arxiv","id":"2308.02581","version":1},"attestation_state":"computed","paper":{"title":"Cream Skimming the Underground: Identifying Relevant Information Points from Online Forums","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Anton Kocheturov, Ashton Woiwood, Cain\\~a Figueiredo, Daniel Sadoc Menasch\\'e, Enrico Lovat, Felipe Moreno-Vera, Leandro Pfleger de Aguiar, Mateus Nogueira, Miguel Bicudo","submitted_at":"2023-08-03T16:52:42Z","abstract_excerpt":"This paper proposes a machine learning-based approach for detecting the exploitation of vulnerabilities in the wild by monitoring underground hacking forums. The increasing volume of posts discussing exploitation in the wild calls for an automatic approach to process threads and posts that will eventually trigger alarms depending on their content. To illustrate the proposed system, we use the CrimeBB dataset, which contains data scraped from multiple underground forums, and develop a supervised machine learning model that can filter threads citing CVEs and label them as Proof-of-Concept, Weapo"},"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":"2308.02581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-08-03T16:52:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"963712a60ef81829332b719a5132f4336f953d8c3790febcbb41deb09c4ec749","abstract_canon_sha256":"7cc9763d1a2fee56b147f85cabe5cb03479ad9edfc8452240f6293a511e14cdb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:38:04.949178Z","signature_b64":"SWp56H4eaDVlFL7bAjLED1Zao/UPQfNV7hUNjkPk84B9zK8oghLQLDq34SwR83cpINwabq3A7CWZfkIiJv76BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45b6fa815d6745529453edcb46e3aa8ee2a02853da4b55fb3490d192160906de","last_reissued_at":"2026-07-05T06:38:04.948608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:38:04.948608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cream Skimming the Underground: Identifying Relevant Information Points from Online Forums","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Anton Kocheturov, Ashton Woiwood, Cain\\~a Figueiredo, Daniel Sadoc Menasch\\'e, Enrico Lovat, Felipe Moreno-Vera, Leandro Pfleger de Aguiar, Mateus Nogueira, Miguel Bicudo","submitted_at":"2023-08-03T16:52:42Z","abstract_excerpt":"This paper proposes a machine learning-based approach for detecting the exploitation of vulnerabilities in the wild by monitoring underground hacking forums. The increasing volume of posts discussing exploitation in the wild calls for an automatic approach to process threads and posts that will eventually trigger alarms depending on their content. To illustrate the proposed system, we use the CrimeBB dataset, which contains data scraped from multiple underground forums, and develop a supervised machine learning model that can filter threads citing CVEs and label them as Proof-of-Concept, Weapo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02581","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/2308.02581/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":"2308.02581","created_at":"2026-07-05T06:38:04.948669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.02581v1","created_at":"2026-07-05T06:38:04.948669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02581","created_at":"2026-07-05T06:38:04.948669+00:00"},{"alias_kind":"pith_short_12","alias_value":"IW3PVAK5M5CV","created_at":"2026-07-05T06:38:04.948669+00:00"},{"alias_kind":"pith_short_16","alias_value":"IW3PVAK5M5CVFFCT","created_at":"2026-07-05T06:38:04.948669+00:00"},{"alias_kind":"pith_short_8","alias_value":"IW3PVAK5","created_at":"2026-07-05T06:38:04.948669+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09762","citing_title":"EventHunter: Dynamic Clustering and Ranking of Security Events from Hacker Forum Discussions","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IW3PVAK5M5CVFFCT5XFUNY5KR3","json":"https://pith.science/pith/IW3PVAK5M5CVFFCT5XFUNY5KR3.json","graph_json":"https://pith.science/api/pith-number/IW3PVAK5M5CVFFCT5XFUNY5KR3/graph.json","events_json":"https://pith.science/api/pith-number/IW3PVAK5M5CVFFCT5XFUNY5KR3/events.json","paper":"https://pith.science/paper/IW3PVAK5"},"agent_actions":{"view_html":"https://pith.science/pith/IW3PVAK5M5CVFFCT5XFUNY5KR3","download_json":"https://pith.science/pith/IW3PVAK5M5CVFFCT5XFUNY5KR3.json","view_paper":"https://pith.science/paper/IW3PVAK5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.02581&json=true","fetch_graph":"https://pith.science/api/pith-number/IW3PVAK5M5CVFFCT5XFUNY5KR3/graph.json","fetch_events":"https://pith.science/api/pith-number/IW3PVAK5M5CVFFCT5XFUNY5KR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IW3PVAK5M5CVFFCT5XFUNY5KR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IW3PVAK5M5CVFFCT5XFUNY5KR3/action/storage_attestation","attest_author":"https://pith.science/pith/IW3PVAK5M5CVFFCT5XFUNY5KR3/action/author_attestation","sign_citation":"https://pith.science/pith/IW3PVAK5M5CVFFCT5XFUNY5KR3/action/citation_signature","submit_replication":"https://pith.science/pith/IW3PVAK5M5CVFFCT5XFUNY5KR3/action/replication_record"}},"created_at":"2026-07-05T06:38:04.948669+00:00","updated_at":"2026-07-05T06:38:04.948669+00:00"}