{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:P4BY4YZKZJOJUIE42MGAZJLMGP","short_pith_number":"pith:P4BY4YZK","canonical_record":{"source":{"id":"2605.13922","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-13T14:08:36Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"a492f4d6d48a7f8c27a80be80853ba8d0a4793f2304ef70025e0c2069f305d5f","abstract_canon_sha256":"3dca79007eb424612b7ce8c65bb9c55631c1965c543027c830b8921f7c682697"},"schema_version":"1.0"},"canonical_sha256":"7f038e632aca5c9a209cd30c0ca56c33c2540eb5e3df4ddac3959e1663fd8f04","source":{"kind":"arxiv","id":"2605.13922","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13922","created_at":"2026-05-17T23:39:15Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13922v1","created_at":"2026-05-17T23:39:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13922","created_at":"2026-05-17T23:39:15Z"},{"alias_kind":"pith_short_12","alias_value":"P4BY4YZKZJOJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"P4BY4YZKZJOJUIE4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"P4BY4YZK","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:P4BY4YZKZJOJUIE42MGAZJLMGP","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13922","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-13T14:08:36Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"a492f4d6d48a7f8c27a80be80853ba8d0a4793f2304ef70025e0c2069f305d5f","abstract_canon_sha256":"3dca79007eb424612b7ce8c65bb9c55631c1965c543027c830b8921f7c682697"},"schema_version":"1.0"},"canonical_sha256":"7f038e632aca5c9a209cd30c0ca56c33c2540eb5e3df4ddac3959e1663fd8f04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:15.562344Z","signature_b64":"Io5+ndyB4VGfPRjiMuiE7t3C7orH5fsybK1UnT2Mnvvu7BzLZsU4dKbArEFcdysAOMyDgNnqmWW+BYi2WtRfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f038e632aca5c9a209cd30c0ca56c33c2540eb5e3df4ddac3959e1663fd8f04","last_reissued_at":"2026-05-17T23:39:15.561224Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:15.561224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13922","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":"2026-05-17T23:39:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zQQo7WsZBce/y01WSoUCX9/sssVI2IfgoRzki7fsjcvD9x1Y1xttBo8TrEJ/9LKVYrDHlwce9TqDxglTv7sBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T17:52:33.161914Z"},"content_sha256":"bd39b4d976f4de37382a17d56f409579a4d844154b388d63e47e63c6755bcdd6","schema_version":"1.0","event_id":"sha256:bd39b4d976f4de37382a17d56f409579a4d844154b388d63e47e63c6755bcdd6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:P4BY4YZKZJOJUIE42MGAZJLMGP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"XAI and Statistical Analysis for Reliable Intrusion Detection in the UAVIDS-2025 Dataset: From Tree to Hybrid and Tabular DNN Ensembles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"XGBoost with SHAP and statistical tests shows density support intersections cause misclassifications in Wormhole and Blackhole attacks on UAVIDS-2025","cross_cats":["cs.LG","stat.CO"],"primary_cat":"cs.CR","authors_text":"Christos Douligeris, Iakovos-Christos Zarkadis","submitted_at":"2026-05-13T14:08:36Z","abstract_excerpt":"During the last few years, the term Mechanistic Interpretability, a specific area, under the umbrella of explainable artificial intelligence (XAI), has been introduced, to explain the decisions made by complex machine learning (ML) models in critical systems like UAV intrusion detection systems (UAVIDS). In this paper, we apply best-practices for data pre-processing and examine a wide range of tree-ensembles, deep neural networks, hybrid stacking models and the latest ensemble neural networks to detect intrusions in UAV, with stratified 10-fold cross validation. With our top-performing model, "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"With our top-performing model, XGBoost, we proceed to Shapley Additive explanations (SHAP), to analyze the global and local feature importances and understand which features, each attack targets, to mimic normal traffic and where the misclassifications occur. ... we discover the true causes of false predictions, observed in Wormhole and Blackhole attacks in UAVIDS-2025.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The UAVIDS-2025 dataset accurately represents real-world UAV traffic distributions and that the chosen statistical tests (Westfall-Young, Jensen-Shannon on KDEs) correctly attribute misclassifications to density support intersection rather than model or preprocessing artifacts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"XGBoost with SHAP and statistical distribution analysis on UAVIDS-2025 identifies density support intersection as the cause of false predictions for Wormhole and Blackhole attacks in UAV intrusion detection.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"XGBoost with SHAP and statistical tests shows density support intersections cause misclassifications in Wormhole and Blackhole attacks on UAVIDS-2025","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9bd1a71e9d10ed330225d2bf61999c4c5e683f7cb71c3a867b3075cc0ea0709d"},"source":{"id":"2605.13922","kind":"arxiv","version":1},"verdict":{"id":"845b8557-8d5a-4f87-8271-c0865e28cf9d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:45:30.706945Z","strongest_claim":"With our top-performing model, XGBoost, we proceed to Shapley Additive explanations (SHAP), to analyze the global and local feature importances and understand which features, each attack targets, to mimic normal traffic and where the misclassifications occur. ... we discover the true causes of false predictions, observed in Wormhole and Blackhole attacks in UAVIDS-2025.","one_line_summary":"XGBoost with SHAP and statistical distribution analysis on UAVIDS-2025 identifies density support intersection as the cause of false predictions for Wormhole and Blackhole attacks in UAV intrusion detection.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The UAVIDS-2025 dataset accurately represents real-world UAV traffic distributions and that the chosen statistical tests (Westfall-Young, Jensen-Shannon on KDEs) correctly attribute misclassifications to density support intersection rather than model or preprocessing artifacts.","pith_extraction_headline":"XGBoost with SHAP and statistical tests shows density support intersections cause misclassifications in Wormhole and Blackhole attacks on UAVIDS-2025"},"references":{"count":29,"sample":[{"doi":"10.1109/icoei.2019.8862784","year":2019,"title":"Machine Learning Based In- trusion Detection System","work_id":"a52b7ca2-91ec-4d05-b9e7-d4aa4d1e1a10","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/jiot.2021.3126811","year":2021,"title":"A Taxonomy of Machine-Learning-Based Intrusion Detection Systems for the Internet of Things: A Survey","work_id":"50b3b910-65a0-43d6-b878-04e2bb5cca76","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.3390/drones10020125","year":null,"title":"Securing UA V Swarms with Vision Transform- ers: A Byzantine-Robust Federated Learning Framework for Cross- Modal Intrusion Detection","work_id":"f7217d53-06dc-41db-9d56-f428ad3cd2be","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Better by default: Strong Pre-Tuned MLPs and Boosted Trees on Tabular Data","work_id":"6df4af78-801d-4e44-a9d7-ae2e7ec61176","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/ccnc51664.2024.10454862","year":2024,"title":"In: 2024 IEEE Inter- national Conference on Cyber Security and Resilience (CSR)","work_id":"df65feb7-b1ed-4bf4-85d2-b5d894f07df8","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":29,"snapshot_sha256":"46318ec8b28a18495fcd6be8c93a9426c9226c2a4345467c659b9014799d4579","internal_anchors":2},"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":"845b8557-8d5a-4f87-8271-c0865e28cf9d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dlGY1rIxeYXRL0yNJ3xLd//lCH95LgOyBXYwA5KiUr2/r5P8EpJVJjMoAKiZUMX59Om4sU2SUrGv2nYZ4Ky/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T17:52:33.162499Z"},"content_sha256":"dfd3aecc3c11ef4fc3effee57db3cf741135ca9fe27aac7e0e91eaae25c0e3ca","schema_version":"1.0","event_id":"sha256:dfd3aecc3c11ef4fc3effee57db3cf741135ca9fe27aac7e0e91eaae25c0e3ca"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:P4BY4YZKZJOJUIE42MGAZJLMGP","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1007/s11370–022-00452-4) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"S. A. H. Mohsan, N. Q. H. Othman, Y . Li, M. H. Alsharif, and M. A. Khan, “Unmanned aerial vehicles (UA Vs): practical aspects, applications, open challenges, security issues, and future trends”, In- telligent Service Robotics, vol. 16, no.","arxiv_id":"2605.13922","detector":"doi_compliance","evidence":{"ref_index":19,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"S. A. H. Mohsan, N. Q. H. Othman, Y . Li, M. H. Alsharif, and M. A. Khan, “Unmanned aerial vehicles (UA Vs): practical aspects, applications, open challenges, security issues, and future trends”, In- telligent Service Robotics, vol. 16, no.","reconstructed_doi":"10.1007/s11370–022-00452-4"},"severity":"advisory","ref_index":19,"audited_at":"2026-05-19T06:24:57.596340Z","event_type":"pith.integrity.v1","detected_doi":"10.1007/s11370–022-00452-4","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"29627de67757c030d1d08a0f288f670aebd92ddfb4f8cb514be48831dc4b1aa6","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":138,"payload_sha256":"bffca635cc01fc8e3069ec65ab0b0fc48ecc8a6d95301447d5ac1ec5b341135d","signature_b64":"rZ1OFKKss6NVVAhIKg/EhaRL/yVdfoa49wgzeus+m0AQjKV2QaTJy+IapHTuTuIUEz5GnmJw7kTMArVs88tJBw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T06:26:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eH+vOJ+ctxeMrpDKEKukiLmrYU/Gjzu/BfdeEGn95NsP2IKEpCWj8F8rPN7C7o46TkxUVUuOoGXI9oYevilCAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T17:52:33.163514Z"},"content_sha256":"82744e8e56a3f4476b76ace6d8206b46516fbe6baddc9c6afac11409ff782b89","schema_version":"1.0","event_id":"sha256:82744e8e56a3f4476b76ace6d8206b46516fbe6baddc9c6afac11409ff782b89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P4BY4YZKZJOJUIE42MGAZJLMGP/bundle.json","state_url":"https://pith.science/pith/P4BY4YZKZJOJUIE42MGAZJLMGP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P4BY4YZKZJOJUIE42MGAZJLMGP/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":"2026-05-21T17:52:33Z","links":{"resolver":"https://pith.science/pith/P4BY4YZKZJOJUIE42MGAZJLMGP","bundle":"https://pith.science/pith/P4BY4YZKZJOJUIE42MGAZJLMGP/bundle.json","state":"https://pith.science/pith/P4BY4YZKZJOJUIE42MGAZJLMGP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P4BY4YZKZJOJUIE42MGAZJLMGP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P4BY4YZKZJOJUIE42MGAZJLMGP","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3dca79007eb424612b7ce8c65bb9c55631c1965c543027c830b8921f7c682697","cross_cats_sorted":["cs.LG","stat.CO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-13T14:08:36Z","title_canon_sha256":"a492f4d6d48a7f8c27a80be80853ba8d0a4793f2304ef70025e0c2069f305d5f"},"schema_version":"1.0","source":{"id":"2605.13922","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13922","created_at":"2026-05-17T23:39:15Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13922v1","created_at":"2026-05-17T23:39:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13922","created_at":"2026-05-17T23:39:15Z"},{"alias_kind":"pith_short_12","alias_value":"P4BY4YZKZJOJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"P4BY4YZKZJOJUIE4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"P4BY4YZK","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:dfd3aecc3c11ef4fc3effee57db3cf741135ca9fe27aac7e0e91eaae25c0e3ca","target":"graph","created_at":"2026-05-17T23:39:15Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"With our top-performing model, XGBoost, we proceed to Shapley Additive explanations (SHAP), to analyze the global and local feature importances and understand which features, each attack targets, to mimic normal traffic and where the misclassifications occur. ... we discover the true causes of false predictions, observed in Wormhole and Blackhole attacks in UAVIDS-2025."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The UAVIDS-2025 dataset accurately represents real-world UAV traffic distributions and that the chosen statistical tests (Westfall-Young, Jensen-Shannon on KDEs) correctly attribute misclassifications to density support intersection rather than model or preprocessing artifacts."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"XGBoost with SHAP and statistical distribution analysis on UAVIDS-2025 identifies density support intersection as the cause of false predictions for Wormhole and Blackhole attacks in UAV intrusion detection."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"XGBoost with SHAP and statistical tests shows density support intersections cause misclassifications in Wormhole and Blackhole attacks on UAVIDS-2025"}],"snapshot_sha256":"9bd1a71e9d10ed330225d2bf61999c4c5e683f7cb71c3a867b3075cc0ea0709d"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"During the last few years, the term Mechanistic Interpretability, a specific area, under the umbrella of explainable artificial intelligence (XAI), has been introduced, to explain the decisions made by complex machine learning (ML) models in critical systems like UAV intrusion detection systems (UAVIDS). In this paper, we apply best-practices for data pre-processing and examine a wide range of tree-ensembles, deep neural networks, hybrid stacking models and the latest ensemble neural networks to detect intrusions in UAV, with stratified 10-fold cross validation. With our top-performing model, ","authors_text":"Christos Douligeris, Iakovos-Christos Zarkadis","cross_cats":["cs.LG","stat.CO"],"headline":"XGBoost with SHAP and statistical tests shows density support intersections cause misclassifications in Wormhole and Blackhole attacks on UAVIDS-2025","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-13T14:08:36Z","title":"XAI and Statistical Analysis for Reliable Intrusion Detection in the UAVIDS-2025 Dataset: From Tree to Hybrid and Tabular DNN Ensembles"},"references":{"count":29,"internal_anchors":2,"resolved_work":29,"sample":[{"cited_arxiv_id":"","doi":"10.1109/icoei.2019.8862784","is_internal_anchor":false,"ref_index":1,"title":"Machine Learning Based In- trusion Detection System","work_id":"a52b7ca2-91ec-4d05-b9e7-d4aa4d1e1a10","year":2019},{"cited_arxiv_id":"","doi":"10.1109/jiot.2021.3126811","is_internal_anchor":false,"ref_index":2,"title":"A Taxonomy of Machine-Learning-Based Intrusion Detection Systems for the Internet of Things: A Survey","work_id":"50b3b910-65a0-43d6-b878-04e2bb5cca76","year":2021},{"cited_arxiv_id":"","doi":"10.3390/drones10020125","is_internal_anchor":false,"ref_index":3,"title":"Securing UA V Swarms with Vision Transform- ers: A Byzantine-Robust Federated Learning Framework for Cross- Modal Intrusion Detection","work_id":"f7217d53-06dc-41db-9d56-f428ad3cd2be","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Better by default: Strong Pre-Tuned MLPs and Boosted Trees on Tabular Data","work_id":"6df4af78-801d-4e44-a9d7-ae2e7ec61176","year":2024},{"cited_arxiv_id":"","doi":"10.1109/ccnc51664.2024.10454862","is_internal_anchor":false,"ref_index":5,"title":"In: 2024 IEEE Inter- national Conference on Cyber Security and Resilience (CSR)","work_id":"df65feb7-b1ed-4bf4-85d2-b5d894f07df8","year":2024}],"snapshot_sha256":"46318ec8b28a18495fcd6be8c93a9426c9226c2a4345467c659b9014799d4579"},"source":{"id":"2605.13922","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T05:45:30.706945Z","id":"845b8557-8d5a-4f87-8271-c0865e28cf9d","model_set":{"reader":"grok-4.3"},"one_line_summary":"XGBoost with SHAP and statistical distribution analysis on UAVIDS-2025 identifies density support intersection as the cause of false predictions for Wormhole and Blackhole attacks in UAV intrusion detection.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"XGBoost with SHAP and statistical tests shows density support intersections cause misclassifications in Wormhole and Blackhole attacks on UAVIDS-2025","strongest_claim":"With our top-performing model, XGBoost, we proceed to Shapley Additive explanations (SHAP), to analyze the global and local feature importances and understand which features, each attack targets, to mimic normal traffic and where the misclassifications occur. ... we discover the true causes of false predictions, observed in Wormhole and Blackhole attacks in UAVIDS-2025.","weakest_assumption":"The UAVIDS-2025 dataset accurately represents real-world UAV traffic distributions and that the chosen statistical tests (Westfall-Young, Jensen-Shannon on KDEs) correctly attribute misclassifications to density support intersection rather than model or preprocessing artifacts."}},"verdict_id":"845b8557-8d5a-4f87-8271-c0865e28cf9d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bd39b4d976f4de37382a17d56f409579a4d844154b388d63e47e63c6755bcdd6","target":"record","created_at":"2026-05-17T23:39:15Z","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":"3dca79007eb424612b7ce8c65bb9c55631c1965c543027c830b8921f7c682697","cross_cats_sorted":["cs.LG","stat.CO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-13T14:08:36Z","title_canon_sha256":"a492f4d6d48a7f8c27a80be80853ba8d0a4793f2304ef70025e0c2069f305d5f"},"schema_version":"1.0","source":{"id":"2605.13922","kind":"arxiv","version":1}},"canonical_sha256":"7f038e632aca5c9a209cd30c0ca56c33c2540eb5e3df4ddac3959e1663fd8f04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f038e632aca5c9a209cd30c0ca56c33c2540eb5e3df4ddac3959e1663fd8f04","first_computed_at":"2026-05-17T23:39:15.561224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:15.561224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Io5+ndyB4VGfPRjiMuiE7t3C7orH5fsybK1UnT2Mnvvu7BzLZsU4dKbArEFcdysAOMyDgNnqmWW+BYi2WtRfAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:15.562344Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13922","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd39b4d976f4de37382a17d56f409579a4d844154b388d63e47e63c6755bcdd6","sha256:dfd3aecc3c11ef4fc3effee57db3cf741135ca9fe27aac7e0e91eaae25c0e3ca","sha256:82744e8e56a3f4476b76ace6d8206b46516fbe6baddc9c6afac11409ff782b89"],"state_sha256":"d62b3b51ba504314519186839c6af4e5badb0ac57034954f7fb444f36cb3c906"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e3gMo4bxvQcKoAQFFrlCOZlLftn1nNC8Aif9osTktb4ffuFAIuyMzI1x0nOj+TqFA6xRydVakUk7iflRcIb1CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T17:52:33.166122Z","bundle_sha256":"86ac2284d0bfa0a918df5571fa6dc37ee7e7c00b4148bfa321759e0e18b317b4"}}