{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7EAEKBC543ADP5QQZP3GNQJ4G4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cb0384d555827176ec85a8dcdbed90ffdd2d5600b41f45e5ab87a45e9de29192","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-15T12:23:10Z","title_canon_sha256":"d5ff5f5710cb9c1527d0e21fbbace60287382d063290be93ebd9b002faab58a2"},"schema_version":"1.0","source":{"id":"2305.08596","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.08596","created_at":"2026-07-05T06:11:21Z"},{"alias_kind":"arxiv_version","alias_value":"2305.08596v2","created_at":"2026-07-05T06:11:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08596","created_at":"2026-07-05T06:11:21Z"},{"alias_kind":"pith_short_12","alias_value":"7EAEKBC543AD","created_at":"2026-07-05T06:11:21Z"},{"alias_kind":"pith_short_16","alias_value":"7EAEKBC543ADP5QQ","created_at":"2026-07-05T06:11:21Z"},{"alias_kind":"pith_short_8","alias_value":"7EAEKBC5","created_at":"2026-07-05T06:11:21Z"}],"graph_snapshots":[{"event_id":"sha256:fd9609e87c372aacec359cf5742125ccc3ea4511462289c950b9a90b925a0126","target":"graph","created_at":"2026-07-05T06:11:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.08596/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research has suggested that there are clear differences in the language used in the Dark Web compared to that of the Surface Web. As studies on the Dark Web commonly require textual analysis of the domain, language models specific to the Dark Web may provide valuable insights to researchers. In this work, we introduce DarkBERT, a language model pretrained on Dark Web data. We describe the steps taken to filter and compile the text data used to train DarkBERT to combat the extreme lexical and structural diversity of the Dark Web that may be detrimental to building a proper representation","authors_text":"Eugene Jang, Jian Cui, Jin-Woo Chung, Seungwon Shin, Yongjae Lee, Youngjin Jin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-15T12:23:10Z","title":"DarkBERT: A Language Model for the Dark Side of the Internet"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08596","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ecfe075d99e7eef3fc23117f00bdb9e7aeaf3e08d674a3a06b3be18017e8cd0a","target":"record","created_at":"2026-07-05T06:11:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cb0384d555827176ec85a8dcdbed90ffdd2d5600b41f45e5ab87a45e9de29192","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-15T12:23:10Z","title_canon_sha256":"d5ff5f5710cb9c1527d0e21fbbace60287382d063290be93ebd9b002faab58a2"},"schema_version":"1.0","source":{"id":"2305.08596","kind":"arxiv","version":2}},"canonical_sha256":"f90045045de6c037f610cbf666c13c37326c7cd3aec134d80771aea616330ff3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f90045045de6c037f610cbf666c13c37326c7cd3aec134d80771aea616330ff3","first_computed_at":"2026-07-05T06:11:21.396146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:21.396146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ne+XMQC3Mv6q20uXv5vfLKSWUdhvN6qVjTulNrkm1gN8TYiz1zyWxFwtYnpfpqMb83vsfrst8asZYgxp7rudAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:21.396548Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.08596","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecfe075d99e7eef3fc23117f00bdb9e7aeaf3e08d674a3a06b3be18017e8cd0a","sha256:fd9609e87c372aacec359cf5742125ccc3ea4511462289c950b9a90b925a0126"],"state_sha256":"5781eb5cb0b56889a46847a23d6b23fd77e60f969e0844ac798cb2ebde547180"}