{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KC5DXJWVJ34QATAI6FH2THCVC3","short_pith_number":"pith:KC5DXJWV","canonical_record":{"source":{"id":"2204.06885","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-14T11:17:22Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"7f3f560544466ba32bbe3f58c6f967655b0ef7ec6d1b002c70dc5c3bb304510b","abstract_canon_sha256":"ca5897c4f2515a9c578a10ff329e0990ada4857a55dfb4416c3570eefac737ee"},"schema_version":"1.0"},"canonical_sha256":"50ba3ba6d54ef9004c08f14fa99c5516e1cb95400d3482a1f27bfb027234327e","source":{"kind":"arxiv","id":"2204.06885","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.06885","created_at":"2026-07-05T04:20:19Z"},{"alias_kind":"arxiv_version","alias_value":"2204.06885v2","created_at":"2026-07-05T04:20:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.06885","created_at":"2026-07-05T04:20:19Z"},{"alias_kind":"pith_short_12","alias_value":"KC5DXJWVJ34Q","created_at":"2026-07-05T04:20:19Z"},{"alias_kind":"pith_short_16","alias_value":"KC5DXJWVJ34QATAI","created_at":"2026-07-05T04:20:19Z"},{"alias_kind":"pith_short_8","alias_value":"KC5DXJWV","created_at":"2026-07-05T04:20:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KC5DXJWVJ34QATAI6FH2THCVC3","target":"record","payload":{"canonical_record":{"source":{"id":"2204.06885","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-14T11:17:22Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"7f3f560544466ba32bbe3f58c6f967655b0ef7ec6d1b002c70dc5c3bb304510b","abstract_canon_sha256":"ca5897c4f2515a9c578a10ff329e0990ada4857a55dfb4416c3570eefac737ee"},"schema_version":"1.0"},"canonical_sha256":"50ba3ba6d54ef9004c08f14fa99c5516e1cb95400d3482a1f27bfb027234327e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:19.759460Z","signature_b64":"xaI0nOhlBQPYWbYEJjhp4lkwnttcX/nghQjdCj1LRdeUZ2m+11+CRu/+/WOuf04mLQl11Npj/8Jq246lQn+WBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50ba3ba6d54ef9004c08f14fa99c5516e1cb95400d3482a1f27bfb027234327e","last_reissued_at":"2026-07-05T04:20:19.759021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:19.759021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.06885","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:20:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X89Eak96rS8b4O+8TQ2U12J+bQ83QksYzD0J6dSuyxtwr6Rl8WQE4GkcgbNhFUPV2xXbpPlGkrZPovXcmOKqAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T14:19:41.250044Z"},"content_sha256":"c956aa7b9bc0b0d9876254448c279bd899c9dbece3c61a3a4c0979e35d735565","schema_version":"1.0","event_id":"sha256:c956aa7b9bc0b0d9876254448c279bd899c9dbece3c61a3a4c0979e35d735565"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KC5DXJWVJ34QATAI6FH2THCVC3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Shedding New Light on the Language of the Dark Web","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Eugene Jang, Jin-Woo Chung, Seungwon Shin, Yongjae Lee, Youngjin Jin","submitted_at":"2022-04-14T11:17:22Z","abstract_excerpt":"The hidden nature and the limited accessibility of the Dark Web, combined with the lack of public datasets in this domain, make it difficult to study its inherent characteristics such as linguistic properties. Previous works on text classification of Dark Web domain have suggested that the use of deep neural models may be ineffective, potentially due to the linguistic differences between the Dark and Surface Webs. However, not much work has been done to uncover the linguistic characteristics of the Dark Web. This paper introduces CoDA, a publicly available Dark Web dataset consisting of 10000 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.06885","kind":"arxiv","version":2},"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/2204.06885/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:20:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"73NgVYNWbV+9wVgp+9FJH8aPRSu4PK2Sf+sEAOL2t7vMVBRPASAQo4/Sfrz4vS0It7ff14Ph/S5MuwiHAIePAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T14:19:41.250556Z"},"content_sha256":"78b660a0b9110f300e81dc9d716a45b0ffda20fa7e3e72ae99a991befe9ee397","schema_version":"1.0","event_id":"sha256:78b660a0b9110f300e81dc9d716a45b0ffda20fa7e3e72ae99a991befe9ee397"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KC5DXJWVJ34QATAI6FH2THCVC3/bundle.json","state_url":"https://pith.science/pith/KC5DXJWVJ34QATAI6FH2THCVC3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KC5DXJWVJ34QATAI6FH2THCVC3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-16T14:19:41Z","links":{"resolver":"https://pith.science/pith/KC5DXJWVJ34QATAI6FH2THCVC3","bundle":"https://pith.science/pith/KC5DXJWVJ34QATAI6FH2THCVC3/bundle.json","state":"https://pith.science/pith/KC5DXJWVJ34QATAI6FH2THCVC3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KC5DXJWVJ34QATAI6FH2THCVC3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KC5DXJWVJ34QATAI6FH2THCVC3","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":"ca5897c4f2515a9c578a10ff329e0990ada4857a55dfb4416c3570eefac737ee","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-14T11:17:22Z","title_canon_sha256":"7f3f560544466ba32bbe3f58c6f967655b0ef7ec6d1b002c70dc5c3bb304510b"},"schema_version":"1.0","source":{"id":"2204.06885","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.06885","created_at":"2026-07-05T04:20:19Z"},{"alias_kind":"arxiv_version","alias_value":"2204.06885v2","created_at":"2026-07-05T04:20:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.06885","created_at":"2026-07-05T04:20:19Z"},{"alias_kind":"pith_short_12","alias_value":"KC5DXJWVJ34Q","created_at":"2026-07-05T04:20:19Z"},{"alias_kind":"pith_short_16","alias_value":"KC5DXJWVJ34QATAI","created_at":"2026-07-05T04:20:19Z"},{"alias_kind":"pith_short_8","alias_value":"KC5DXJWV","created_at":"2026-07-05T04:20:19Z"}],"graph_snapshots":[{"event_id":"sha256:78b660a0b9110f300e81dc9d716a45b0ffda20fa7e3e72ae99a991befe9ee397","target":"graph","created_at":"2026-07-05T04:20:19Z","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/2204.06885/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The hidden nature and the limited accessibility of the Dark Web, combined with the lack of public datasets in this domain, make it difficult to study its inherent characteristics such as linguistic properties. Previous works on text classification of Dark Web domain have suggested that the use of deep neural models may be ineffective, potentially due to the linguistic differences between the Dark and Surface Webs. However, not much work has been done to uncover the linguistic characteristics of the Dark Web. This paper introduces CoDA, a publicly available Dark Web dataset consisting of 10000 ","authors_text":"Eugene Jang, Jin-Woo Chung, Seungwon Shin, Yongjae Lee, Youngjin Jin","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-14T11:17:22Z","title":"Shedding New Light on the Language of the Dark Web"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.06885","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:c956aa7b9bc0b0d9876254448c279bd899c9dbece3c61a3a4c0979e35d735565","target":"record","created_at":"2026-07-05T04:20:19Z","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":"ca5897c4f2515a9c578a10ff329e0990ada4857a55dfb4416c3570eefac737ee","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-14T11:17:22Z","title_canon_sha256":"7f3f560544466ba32bbe3f58c6f967655b0ef7ec6d1b002c70dc5c3bb304510b"},"schema_version":"1.0","source":{"id":"2204.06885","kind":"arxiv","version":2}},"canonical_sha256":"50ba3ba6d54ef9004c08f14fa99c5516e1cb95400d3482a1f27bfb027234327e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50ba3ba6d54ef9004c08f14fa99c5516e1cb95400d3482a1f27bfb027234327e","first_computed_at":"2026-07-05T04:20:19.759021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:20:19.759021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xaI0nOhlBQPYWbYEJjhp4lkwnttcX/nghQjdCj1LRdeUZ2m+11+CRu/+/WOuf04mLQl11Npj/8Jq246lQn+WBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:20:19.759460Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.06885","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c956aa7b9bc0b0d9876254448c279bd899c9dbece3c61a3a4c0979e35d735565","sha256:78b660a0b9110f300e81dc9d716a45b0ffda20fa7e3e72ae99a991befe9ee397"],"state_sha256":"bc6183acd536436849474dfbba4c0b5b371cd996379f7644cf2a3f51a922df03"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nwpHqsKK63ainJbUVS0CU88Ei/A1Nf7UatAPvbjvzLVmKW2DtclNHijZfN2NDi/2y+FVauTQuEkSEbcCD4OQAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T14:19:41.256150Z","bundle_sha256":"de8879be09092db05cac37ff1d30eff9efc1639997d21e07ab62ebe79b57985c"}}