{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QY5DNZAHPBV6XYZPNS4NLLT2HG","short_pith_number":"pith:QY5DNZAH","schema_version":"1.0","canonical_sha256":"863a36e407786bebe32f6cb8d5ae7a399efb357a8c2fb2cac7cbb8c308084356","source":{"kind":"arxiv","id":"2004.13006","version":1},"attestation_state":"computed","paper":{"title":"NetML: A Challenge for Network Traffic Analytics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NI","stat.ML"],"primary_cat":"cs.CR","authors_text":"Onur Barut, Peilong Li, Tong Zhang, Weigang Li, Yan Luo","submitted_at":"2020-04-25T01:12:17Z","abstract_excerpt":"Classifying network traffic is the basis for important network applications. Prior research in this area has faced challenges on the availability of representative datasets, and many of the results cannot be readily reproduced. Such a problem is exacerbated by emerging data-driven machine learning based approaches. To address this issue, we provide three open datasets containing almost 1.3M labeled flows in total, with flow features and anonymized raw packets, for the research community. We focus on broad aspects in network traffic analysis, including both malware detection and application cla"},"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":"2004.13006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2020-04-25T01:12:17Z","cross_cats_sorted":["cs.LG","cs.NI","stat.ML"],"title_canon_sha256":"95e38434f72be73e5400fc8af4370ac53dba32be0ffcd3ed1611c0642fb6da3c","abstract_canon_sha256":"97b9e5a5050dc42b9e721a066e24da3c6725ea32095d48eb89019ed554847cb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:54.705743Z","signature_b64":"PXQF4LBmtxYooRriy4o3fcMQWeuORq5FN1qr5KE1wep8D2AaoJDC7zdx+AmXUqaK35WV1VdwILbvCfpsnFJDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"863a36e407786bebe32f6cb8d5ae7a399efb357a8c2fb2cac7cbb8c308084356","last_reissued_at":"2026-07-05T00:58:54.705371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:54.705371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NetML: A Challenge for Network Traffic Analytics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NI","stat.ML"],"primary_cat":"cs.CR","authors_text":"Onur Barut, Peilong Li, Tong Zhang, Weigang Li, Yan Luo","submitted_at":"2020-04-25T01:12:17Z","abstract_excerpt":"Classifying network traffic is the basis for important network applications. Prior research in this area has faced challenges on the availability of representative datasets, and many of the results cannot be readily reproduced. Such a problem is exacerbated by emerging data-driven machine learning based approaches. To address this issue, we provide three open datasets containing almost 1.3M labeled flows in total, with flow features and anonymized raw packets, for the research community. We focus on broad aspects in network traffic analysis, including both malware detection and application cla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13006","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/2004.13006/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":"2004.13006","created_at":"2026-07-05T00:58:54.705434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.13006v1","created_at":"2026-07-05T00:58:54.705434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13006","created_at":"2026-07-05T00:58:54.705434+00:00"},{"alias_kind":"pith_short_12","alias_value":"QY5DNZAHPBV6","created_at":"2026-07-05T00:58:54.705434+00:00"},{"alias_kind":"pith_short_16","alias_value":"QY5DNZAHPBV6XYZP","created_at":"2026-07-05T00:58:54.705434+00:00"},{"alias_kind":"pith_short_8","alias_value":"QY5DNZAH","created_at":"2026-07-05T00:58:54.705434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06688","citing_title":"Network Intrusion Datasets: A Survey, Limitations, and Recommendations","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QY5DNZAHPBV6XYZPNS4NLLT2HG","json":"https://pith.science/pith/QY5DNZAHPBV6XYZPNS4NLLT2HG.json","graph_json":"https://pith.science/api/pith-number/QY5DNZAHPBV6XYZPNS4NLLT2HG/graph.json","events_json":"https://pith.science/api/pith-number/QY5DNZAHPBV6XYZPNS4NLLT2HG/events.json","paper":"https://pith.science/paper/QY5DNZAH"},"agent_actions":{"view_html":"https://pith.science/pith/QY5DNZAHPBV6XYZPNS4NLLT2HG","download_json":"https://pith.science/pith/QY5DNZAHPBV6XYZPNS4NLLT2HG.json","view_paper":"https://pith.science/paper/QY5DNZAH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.13006&json=true","fetch_graph":"https://pith.science/api/pith-number/QY5DNZAHPBV6XYZPNS4NLLT2HG/graph.json","fetch_events":"https://pith.science/api/pith-number/QY5DNZAHPBV6XYZPNS4NLLT2HG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QY5DNZAHPBV6XYZPNS4NLLT2HG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QY5DNZAHPBV6XYZPNS4NLLT2HG/action/storage_attestation","attest_author":"https://pith.science/pith/QY5DNZAHPBV6XYZPNS4NLLT2HG/action/author_attestation","sign_citation":"https://pith.science/pith/QY5DNZAHPBV6XYZPNS4NLLT2HG/action/citation_signature","submit_replication":"https://pith.science/pith/QY5DNZAHPBV6XYZPNS4NLLT2HG/action/replication_record"}},"created_at":"2026-07-05T00:58:54.705434+00:00","updated_at":"2026-07-05T00:58:54.705434+00:00"}