{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XP5CKQ2ZQI272PD52FE5ZV3WFC","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":"c7067e672bbf9e6cf72aaedc9f1ab0da459734e1355b18be9e93b890b6ad99cb","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-01-24T09:30:21Z","title_canon_sha256":"b734fa8ccd4c4c39f3ac0e0edfe0e99470f3299e975dc9e30d0988da3e8323d7"},"schema_version":"1.0","source":{"id":"2401.13320","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.13320","created_at":"2026-07-05T07:37:03Z"},{"alias_kind":"arxiv_version","alias_value":"2401.13320v1","created_at":"2026-07-05T07:37:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13320","created_at":"2026-07-05T07:37:03Z"},{"alias_kind":"pith_short_12","alias_value":"XP5CKQ2ZQI27","created_at":"2026-07-05T07:37:03Z"},{"alias_kind":"pith_short_16","alias_value":"XP5CKQ2ZQI272PD5","created_at":"2026-07-05T07:37:03Z"},{"alias_kind":"pith_short_8","alias_value":"XP5CKQ2Z","created_at":"2026-07-05T07:37:03Z"}],"graph_snapshots":[{"event_id":"sha256:f9af76a4fef458cab4298cb3adc132e651474ece53e0c4227b7c0f5727c51fb3","target":"graph","created_at":"2026-07-05T07:37:03Z","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/2401.13320/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The dark web has become notorious for its association with illicit activities and there is a growing need for systems to automate the monitoring of this space. This paper proposes an end-to-end scalable architecture for the early identification of new Tor sites and the daily analysis of their content. The solution is built using an Open Source Big Data stack for data serving with Kubernetes, Kafka, Kubeflow, and MinIO, continuously discovering onion addresses in different sources (threat intelligence, code repositories, web-Tor gateways, and Tor repositories), downloading the HTML from Tor and","authors_text":"F\\'elix G\\'omez M\\'armol, G\\'er\\^ome Bovet, Gregorio Mart\\'inez P\\'erez, H\\^ong-\\^An Sandlin, Javier Pastor-Galindo","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-01-24T09:30:21Z","title":"A Big Data Architecture for Early Identification and Categorization of Dark Web Sites"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13320","kind":"arxiv","version":1},"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:bf6b3eff541e3db973ffa1b0350fa9e058bc18590603947ddffae09e9a498e85","target":"record","created_at":"2026-07-05T07:37:03Z","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":"c7067e672bbf9e6cf72aaedc9f1ab0da459734e1355b18be9e93b890b6ad99cb","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-01-24T09:30:21Z","title_canon_sha256":"b734fa8ccd4c4c39f3ac0e0edfe0e99470f3299e975dc9e30d0988da3e8323d7"},"schema_version":"1.0","source":{"id":"2401.13320","kind":"arxiv","version":1}},"canonical_sha256":"bbfa2543598235fd3c7dd149dcd776289ea0587ecc8aeed1b9fd3db2873a1934","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbfa2543598235fd3c7dd149dcd776289ea0587ecc8aeed1b9fd3db2873a1934","first_computed_at":"2026-07-05T07:37:03.902254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:37:03.902254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jtYXFtjZWfaDi0JMWwOS5qP5di5aytCCHd0DdyiFZievb9kknWPH6+YRiNlnzMyZsN8ZTtIcYgR/I90Jnmu8BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:37:03.902877Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.13320","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf6b3eff541e3db973ffa1b0350fa9e058bc18590603947ddffae09e9a498e85","sha256:f9af76a4fef458cab4298cb3adc132e651474ece53e0c4227b7c0f5727c51fb3"],"state_sha256":"87c8c5bbc0226583bc0f8c9567fa7f688ada10563993b6fa4e45d78b9bd9638c"}