{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R6SNZHT4KPZ5XXQO5T54F5BZGS","short_pith_number":"pith:R6SNZHT4","schema_version":"1.0","canonical_sha256":"8fa4dc9e7c53f3dbde0eecfbc2f43934a386e305fac241b511df7b5c1c0fec03","source":{"kind":"arxiv","id":"2312.04944","version":1},"attestation_state":"computed","paper":{"title":"Illicit Darkweb Classification via Natural-language Processing: Classifying Illicit Content of Webpages based on Textual Information","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.IR","authors_text":"Gemma Catolino, Giuseppe Cascavilla, Mirella Sangiovanni","submitted_at":"2023-12-08T10:19:48Z","abstract_excerpt":"This work aims at expanding previous works done in the context of illegal activities classification, performing three different steps. First, we created a heterogeneous dataset of 113995 onion sites and dark marketplaces. Then, we compared pre-trained transferable models, i.e., ULMFit (Universal Language Model Fine-tuning), Bert (Bidirectional Encoder Representations from Transformers), and RoBERTa (Robustly optimized BERT approach) with a traditional text classification approach like LSTM (Long short-term memory) neural networks. Finally, we developed two illegal activities classification app"},"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":"2312.04944","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2023-12-08T10:19:48Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"b6074283f1c35603c8bda7930a058aed8b4aeb8eb96ea3538ff84952013d8ea3","abstract_canon_sha256":"05192d17f9fe9540dc02cf6b4eaa8f6b9cb3add777bda716e00136d328f4baab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:54.778347Z","signature_b64":"MHDBOJoWpwvgY1ynOex9JdJeuvvXD8YZXlDE6/JS73ZzzvnKh+z8hqR7cJ85p6ObFFUABWM44JXn/YA98Jm9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fa4dc9e7c53f3dbde0eecfbc2f43934a386e305fac241b511df7b5c1c0fec03","last_reissued_at":"2026-07-05T07:21:54.777945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:54.777945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Illicit Darkweb Classification via Natural-language Processing: Classifying Illicit Content of Webpages based on Textual Information","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.IR","authors_text":"Gemma Catolino, Giuseppe Cascavilla, Mirella Sangiovanni","submitted_at":"2023-12-08T10:19:48Z","abstract_excerpt":"This work aims at expanding previous works done in the context of illegal activities classification, performing three different steps. First, we created a heterogeneous dataset of 113995 onion sites and dark marketplaces. Then, we compared pre-trained transferable models, i.e., ULMFit (Universal Language Model Fine-tuning), Bert (Bidirectional Encoder Representations from Transformers), and RoBERTa (Robustly optimized BERT approach) with a traditional text classification approach like LSTM (Long short-term memory) neural networks. Finally, we developed two illegal activities classification app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04944","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/2312.04944/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":"2312.04944","created_at":"2026-07-05T07:21:54.778002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04944v1","created_at":"2026-07-05T07:21:54.778002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04944","created_at":"2026-07-05T07:21:54.778002+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6SNZHT4KPZ5","created_at":"2026-07-05T07:21:54.778002+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6SNZHT4KPZ5XXQO","created_at":"2026-07-05T07:21:54.778002+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6SNZHT4","created_at":"2026-07-05T07:21:54.778002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22912","citing_title":"A Language Model-Driven Semi-Supervised Ensemble Framework for Illicit Market Detection Across Deep/Dark Web and Social Platforms","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R6SNZHT4KPZ5XXQO5T54F5BZGS","json":"https://pith.science/pith/R6SNZHT4KPZ5XXQO5T54F5BZGS.json","graph_json":"https://pith.science/api/pith-number/R6SNZHT4KPZ5XXQO5T54F5BZGS/graph.json","events_json":"https://pith.science/api/pith-number/R6SNZHT4KPZ5XXQO5T54F5BZGS/events.json","paper":"https://pith.science/paper/R6SNZHT4"},"agent_actions":{"view_html":"https://pith.science/pith/R6SNZHT4KPZ5XXQO5T54F5BZGS","download_json":"https://pith.science/pith/R6SNZHT4KPZ5XXQO5T54F5BZGS.json","view_paper":"https://pith.science/paper/R6SNZHT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04944&json=true","fetch_graph":"https://pith.science/api/pith-number/R6SNZHT4KPZ5XXQO5T54F5BZGS/graph.json","fetch_events":"https://pith.science/api/pith-number/R6SNZHT4KPZ5XXQO5T54F5BZGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6SNZHT4KPZ5XXQO5T54F5BZGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6SNZHT4KPZ5XXQO5T54F5BZGS/action/storage_attestation","attest_author":"https://pith.science/pith/R6SNZHT4KPZ5XXQO5T54F5BZGS/action/author_attestation","sign_citation":"https://pith.science/pith/R6SNZHT4KPZ5XXQO5T54F5BZGS/action/citation_signature","submit_replication":"https://pith.science/pith/R6SNZHT4KPZ5XXQO5T54F5BZGS/action/replication_record"}},"created_at":"2026-07-05T07:21:54.778002+00:00","updated_at":"2026-07-05T07:21:54.778002+00:00"}