{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VJC2E7E4IUJXKCTTATI2G2DPQI","short_pith_number":"pith:VJC2E7E4","canonical_record":{"source":{"id":"2105.10041","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2021-05-20T21:31:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c22aad35e526d8c1db3d8cbdeb25ec70be4c5059d116da151081a23ad2dad1c","abstract_canon_sha256":"c708eaed79a0cf8a5363beab5ab41e476506fea57ca745ba69192d152a09c887"},"schema_version":"1.0"},"canonical_sha256":"aa45a27c9c4513750a7304d1a3686f8234cf8c55fda4efd90166f68d4eaf2fa2","source":{"kind":"arxiv","id":"2105.10041","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.10041","created_at":"2026-07-05T02:42:06Z"},{"alias_kind":"arxiv_version","alias_value":"2105.10041v1","created_at":"2026-07-05T02:42:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.10041","created_at":"2026-07-05T02:42:06Z"},{"alias_kind":"pith_short_12","alias_value":"VJC2E7E4IUJX","created_at":"2026-07-05T02:42:06Z"},{"alias_kind":"pith_short_16","alias_value":"VJC2E7E4IUJXKCTT","created_at":"2026-07-05T02:42:06Z"},{"alias_kind":"pith_short_8","alias_value":"VJC2E7E4","created_at":"2026-07-05T02:42:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VJC2E7E4IUJXKCTTATI2G2DPQI","target":"record","payload":{"canonical_record":{"source":{"id":"2105.10041","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2021-05-20T21:31:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c22aad35e526d8c1db3d8cbdeb25ec70be4c5059d116da151081a23ad2dad1c","abstract_canon_sha256":"c708eaed79a0cf8a5363beab5ab41e476506fea57ca745ba69192d152a09c887"},"schema_version":"1.0"},"canonical_sha256":"aa45a27c9c4513750a7304d1a3686f8234cf8c55fda4efd90166f68d4eaf2fa2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:06.809370Z","signature_b64":"26LRJKUmO9Z8B227IHc46ISPePVrlv5Dy5l5Afbj/coJZl8X7s19LtZhOQE7N+Nrz1rR7RiDYtJ5MX3rJf1wDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa45a27c9c4513750a7304d1a3686f8234cf8c55fda4efd90166f68d4eaf2fa2","last_reissued_at":"2026-07-05T02:42:06.808945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:06.808945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.10041","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:42:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NZjQGJSH7jHQsSM1Ax4RTIkGt7VN88BKMYCdhrdpQj5oNO+/p93Q+Wdda/MI5ebYALV0pVKaJViKnXXvHmmKBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T10:14:58.567283Z"},"content_sha256":"da16e119bcede54da183b3e6015cf845eb2f9792a0b0fff5c5350b7695bd19d2","schema_version":"1.0","event_id":"sha256:da16e119bcede54da183b3e6015cf845eb2f9792a0b0fff5c5350b7695bd19d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VJC2E7E4IUJXKCTTATI2G2DPQI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Curation and Quality Assurance for Machine Learning-based Cyber Intrusion Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Anand Sagar Thumati, Haihua Chen, Jay Bhuyan, Junhua Ding, Ngan Tran","submitted_at":"2021-05-20T21:31:46Z","abstract_excerpt":"Intrusion detection is an essential task in the cyber threat environment. Machine learning and deep learning techniques have been applied for intrusion detection. However, most of the existing research focuses on the model work but ignores the fact that poor data quality has a direct impact on the performance of a machine learning system. More attention should be paid to the data work when building a machine learning-based intrusion detection system. This article first summarizes existing machine learning-based intrusion detection systems and the datasets used for building these systems. Then "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.10041","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/2105.10041/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":"2026-07-05T02:42:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EpTLvr0t64zR5Kpn+a9Oic+K+U/J/kMxD3aKJhjixljxQJRfp9AzJWKszJO51Pr2eOAyKUf2shEBXBGDHl39BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T10:14:58.567694Z"},"content_sha256":"b5c90ed077192c358554e1c1e3cae0cb8dcfc9f36408964a2f5fcd67f4122088","schema_version":"1.0","event_id":"sha256:b5c90ed077192c358554e1c1e3cae0cb8dcfc9f36408964a2f5fcd67f4122088"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VJC2E7E4IUJXKCTTATI2G2DPQI/bundle.json","state_url":"https://pith.science/pith/VJC2E7E4IUJXKCTTATI2G2DPQI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VJC2E7E4IUJXKCTTATI2G2DPQI/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":"2026-07-27T10:14:58Z","links":{"resolver":"https://pith.science/pith/VJC2E7E4IUJXKCTTATI2G2DPQI","bundle":"https://pith.science/pith/VJC2E7E4IUJXKCTTATI2G2DPQI/bundle.json","state":"https://pith.science/pith/VJC2E7E4IUJXKCTTATI2G2DPQI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VJC2E7E4IUJXKCTTATI2G2DPQI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VJC2E7E4IUJXKCTTATI2G2DPQI","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":"c708eaed79a0cf8a5363beab5ab41e476506fea57ca745ba69192d152a09c887","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2021-05-20T21:31:46Z","title_canon_sha256":"5c22aad35e526d8c1db3d8cbdeb25ec70be4c5059d116da151081a23ad2dad1c"},"schema_version":"1.0","source":{"id":"2105.10041","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.10041","created_at":"2026-07-05T02:42:06Z"},{"alias_kind":"arxiv_version","alias_value":"2105.10041v1","created_at":"2026-07-05T02:42:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.10041","created_at":"2026-07-05T02:42:06Z"},{"alias_kind":"pith_short_12","alias_value":"VJC2E7E4IUJX","created_at":"2026-07-05T02:42:06Z"},{"alias_kind":"pith_short_16","alias_value":"VJC2E7E4IUJXKCTT","created_at":"2026-07-05T02:42:06Z"},{"alias_kind":"pith_short_8","alias_value":"VJC2E7E4","created_at":"2026-07-05T02:42:06Z"}],"graph_snapshots":[{"event_id":"sha256:b5c90ed077192c358554e1c1e3cae0cb8dcfc9f36408964a2f5fcd67f4122088","target":"graph","created_at":"2026-07-05T02:42:06Z","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/2105.10041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Intrusion detection is an essential task in the cyber threat environment. Machine learning and deep learning techniques have been applied for intrusion detection. However, most of the existing research focuses on the model work but ignores the fact that poor data quality has a direct impact on the performance of a machine learning system. More attention should be paid to the data work when building a machine learning-based intrusion detection system. This article first summarizes existing machine learning-based intrusion detection systems and the datasets used for building these systems. Then ","authors_text":"Anand Sagar Thumati, Haihua Chen, Jay Bhuyan, Junhua Ding, Ngan Tran","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2021-05-20T21:31:46Z","title":"Data Curation and Quality Assurance for Machine Learning-based Cyber Intrusion Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.10041","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:da16e119bcede54da183b3e6015cf845eb2f9792a0b0fff5c5350b7695bd19d2","target":"record","created_at":"2026-07-05T02:42:06Z","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":"c708eaed79a0cf8a5363beab5ab41e476506fea57ca745ba69192d152a09c887","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2021-05-20T21:31:46Z","title_canon_sha256":"5c22aad35e526d8c1db3d8cbdeb25ec70be4c5059d116da151081a23ad2dad1c"},"schema_version":"1.0","source":{"id":"2105.10041","kind":"arxiv","version":1}},"canonical_sha256":"aa45a27c9c4513750a7304d1a3686f8234cf8c55fda4efd90166f68d4eaf2fa2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa45a27c9c4513750a7304d1a3686f8234cf8c55fda4efd90166f68d4eaf2fa2","first_computed_at":"2026-07-05T02:42:06.808945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:42:06.808945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"26LRJKUmO9Z8B227IHc46ISPePVrlv5Dy5l5Afbj/coJZl8X7s19LtZhOQE7N+Nrz1rR7RiDYtJ5MX3rJf1wDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:42:06.809370Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.10041","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da16e119bcede54da183b3e6015cf845eb2f9792a0b0fff5c5350b7695bd19d2","sha256:b5c90ed077192c358554e1c1e3cae0cb8dcfc9f36408964a2f5fcd67f4122088"],"state_sha256":"47ee301d0ea87f1b892bf4ee9196edfcd51c9251d1468d9238a308873b30b003"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hrjO7qPsCCLaSWnWOC8yOaQUTY0jfzjVe2hJsReoPoBzdZM4XTKBowbnFrlva5lMHLl9pxZq/BMywd8JOO9aBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T10:14:58.569945Z","bundle_sha256":"8f0243046daf4fa5679196123e6361732ad5d175b611b1cdbacc5726901aec44"}}