{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6N5RDBOAUDELGFVWM2BQQ6KYPF","short_pith_number":"pith:6N5RDBOA","schema_version":"1.0","canonical_sha256":"f37b1185c0a0c8b316b666830879587955b188277e3b10dcc55f3051c127b861","source":{"kind":"arxiv","id":"2006.16993","version":2},"attestation_state":"computed","paper":{"title":"Feature Extraction for Novelty Detection in Network Traffic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NI","authors_text":"Kun Yang, Nick Feamster, Samory Kpotufe","submitted_at":"2020-06-30T17:53:59Z","abstract_excerpt":"Data representation plays a critical role in the performance of novelty detection (or ``anomaly detection'') methods in machine learning. The data representation of network traffic often determines the effectiveness of these models as much as the model itself. The wide range of novel events that network operators need to detect (e.g., attacks, malware, new applications, changes in traffic demands) introduces the possibility for a broad range of possible models and data representations. In each scenario, practitioners must spend significant effort extracting and engineering features that are mo"},"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":"2006.16993","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NI","submitted_at":"2020-06-30T17:53:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"157ce09b7064d5317f76dc216c1d1624fa6729bb73615af961e78974458f219d","abstract_canon_sha256":"b337efcc465f904467371534756586283c36d9a9943d9eeb2f9ad9663d5622bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:09.098447Z","signature_b64":"44QmpKHaXsjwk641JmHdgjeiE0TwYAzf70C9YZDRBPhaCuIYGjPybWSOHmDVoTkTz2cGrEpN6XRtbn9W+y8SDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f37b1185c0a0c8b316b666830879587955b188277e3b10dcc55f3051c127b861","last_reissued_at":"2026-07-05T02:48:09.097982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:09.097982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Extraction for Novelty Detection in Network Traffic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NI","authors_text":"Kun Yang, Nick Feamster, Samory Kpotufe","submitted_at":"2020-06-30T17:53:59Z","abstract_excerpt":"Data representation plays a critical role in the performance of novelty detection (or ``anomaly detection'') methods in machine learning. The data representation of network traffic often determines the effectiveness of these models as much as the model itself. The wide range of novel events that network operators need to detect (e.g., attacks, malware, new applications, changes in traffic demands) introduces the possibility for a broad range of possible models and data representations. In each scenario, practitioners must spend significant effort extracting and engineering features that are mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.16993","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/2006.16993/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":"2006.16993","created_at":"2026-07-05T02:48:09.098040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.16993v2","created_at":"2026-07-05T02:48:09.098040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.16993","created_at":"2026-07-05T02:48:09.098040+00:00"},{"alias_kind":"pith_short_12","alias_value":"6N5RDBOAUDEL","created_at":"2026-07-05T02:48:09.098040+00:00"},{"alias_kind":"pith_short_16","alias_value":"6N5RDBOAUDELGFVW","created_at":"2026-07-05T02:48:09.098040+00:00"},{"alias_kind":"pith_short_8","alias_value":"6N5RDBOA","created_at":"2026-07-05T02:48:09.098040+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.17025","citing_title":"netFound: Principled Design for Network Foundation Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2508.11742","citing_title":"Cross-Flow Correlations Survive Synthesis: Measuring Source-Level Privacy Leakage in Synthetic Network Traces","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6N5RDBOAUDELGFVWM2BQQ6KYPF","json":"https://pith.science/pith/6N5RDBOAUDELGFVWM2BQQ6KYPF.json","graph_json":"https://pith.science/api/pith-number/6N5RDBOAUDELGFVWM2BQQ6KYPF/graph.json","events_json":"https://pith.science/api/pith-number/6N5RDBOAUDELGFVWM2BQQ6KYPF/events.json","paper":"https://pith.science/paper/6N5RDBOA"},"agent_actions":{"view_html":"https://pith.science/pith/6N5RDBOAUDELGFVWM2BQQ6KYPF","download_json":"https://pith.science/pith/6N5RDBOAUDELGFVWM2BQQ6KYPF.json","view_paper":"https://pith.science/paper/6N5RDBOA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.16993&json=true","fetch_graph":"https://pith.science/api/pith-number/6N5RDBOAUDELGFVWM2BQQ6KYPF/graph.json","fetch_events":"https://pith.science/api/pith-number/6N5RDBOAUDELGFVWM2BQQ6KYPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6N5RDBOAUDELGFVWM2BQQ6KYPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6N5RDBOAUDELGFVWM2BQQ6KYPF/action/storage_attestation","attest_author":"https://pith.science/pith/6N5RDBOAUDELGFVWM2BQQ6KYPF/action/author_attestation","sign_citation":"https://pith.science/pith/6N5RDBOAUDELGFVWM2BQQ6KYPF/action/citation_signature","submit_replication":"https://pith.science/pith/6N5RDBOAUDELGFVWM2BQQ6KYPF/action/replication_record"}},"created_at":"2026-07-05T02:48:09.098040+00:00","updated_at":"2026-07-05T02:48:09.098040+00:00"}