{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZZBHOGRJYGYDFOFVHJ3VZJSSBB","short_pith_number":"pith:ZZBHOGRJ","schema_version":"1.0","canonical_sha256":"ce42771a29c1b032b8b53a775ca6520841ecf78ce6625f21bfcdd655dcdead72","source":{"kind":"arxiv","id":"2405.03489","version":3},"attestation_state":"computed","paper":{"title":"On the Influence of Data Resampling for Deep Learning-Based Log Anomaly Detection: Insights and Recommendations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Federica Sarro, Huiqi Zou, Jacky Keung, Pinjia He, Xiaoxue Ma, Xiao Yu, Yishu Li","submitted_at":"2024-05-06T14:01:05Z","abstract_excerpt":"Numerous Deep Learning (DL)-based approaches have gained attention in software Log Anomaly Detection (LAD), yet class imbalance in training data remains a challenge, with anomalies often comprising less than 1% of datasets like Thunderbird. Existing DLLAD methods may underperform in severely imbalanced datasets. Although data resampling has proven effective in other software engineering tasks, it has not been explored in LAD. This study aims to fill this gap by providing an in-depth analysis of the impact of diverse data resampling methods on existing DLLAD approaches from two distinct perspec"},"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":"2405.03489","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2024-05-06T14:01:05Z","cross_cats_sorted":[],"title_canon_sha256":"a4d45a9e939e0736bbc99a7b4c467d8b16492b4294f36f0ef88cc78e6925068b","abstract_canon_sha256":"a3fd661403a4c556ab413e4fb9bea5f2134937e1919ee4412be51577bc0f65d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:11.965076Z","signature_b64":"PhiLO90QDJhDsxcUSwghnozbq+L/z574LoBgdeYxMj22WJ3m1DKFv47Rw7oSiAckGFgpSjttHcwmtZ1R3CztDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce42771a29c1b032b8b53a775ca6520841ecf78ce6625f21bfcdd655dcdead72","last_reissued_at":"2026-07-05T09:28:11.964632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:11.964632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Influence of Data Resampling for Deep Learning-Based Log Anomaly Detection: Insights and Recommendations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Federica Sarro, Huiqi Zou, Jacky Keung, Pinjia He, Xiaoxue Ma, Xiao Yu, Yishu Li","submitted_at":"2024-05-06T14:01:05Z","abstract_excerpt":"Numerous Deep Learning (DL)-based approaches have gained attention in software Log Anomaly Detection (LAD), yet class imbalance in training data remains a challenge, with anomalies often comprising less than 1% of datasets like Thunderbird. Existing DLLAD methods may underperform in severely imbalanced datasets. Although data resampling has proven effective in other software engineering tasks, it has not been explored in LAD. This study aims to fill this gap by providing an in-depth analysis of the impact of diverse data resampling methods on existing DLLAD approaches from two distinct perspec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03489","kind":"arxiv","version":3},"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/2405.03489/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":"2405.03489","created_at":"2026-07-05T09:28:11.964694+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.03489v3","created_at":"2026-07-05T09:28:11.964694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03489","created_at":"2026-07-05T09:28:11.964694+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZZBHOGRJYGYD","created_at":"2026-07-05T09:28:11.964694+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZZBHOGRJYGYDFOFV","created_at":"2026-07-05T09:28:11.964694+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZZBHOGRJ","created_at":"2026-07-05T09:28:11.964694+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.11031","citing_title":"AdaptiveLog: An Adaptive Log Analysis Framework with the Collaboration of Large and Small Language Model","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZZBHOGRJYGYDFOFVHJ3VZJSSBB","json":"https://pith.science/pith/ZZBHOGRJYGYDFOFVHJ3VZJSSBB.json","graph_json":"https://pith.science/api/pith-number/ZZBHOGRJYGYDFOFVHJ3VZJSSBB/graph.json","events_json":"https://pith.science/api/pith-number/ZZBHOGRJYGYDFOFVHJ3VZJSSBB/events.json","paper":"https://pith.science/paper/ZZBHOGRJ"},"agent_actions":{"view_html":"https://pith.science/pith/ZZBHOGRJYGYDFOFVHJ3VZJSSBB","download_json":"https://pith.science/pith/ZZBHOGRJYGYDFOFVHJ3VZJSSBB.json","view_paper":"https://pith.science/paper/ZZBHOGRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.03489&json=true","fetch_graph":"https://pith.science/api/pith-number/ZZBHOGRJYGYDFOFVHJ3VZJSSBB/graph.json","fetch_events":"https://pith.science/api/pith-number/ZZBHOGRJYGYDFOFVHJ3VZJSSBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZZBHOGRJYGYDFOFVHJ3VZJSSBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZZBHOGRJYGYDFOFVHJ3VZJSSBB/action/storage_attestation","attest_author":"https://pith.science/pith/ZZBHOGRJYGYDFOFVHJ3VZJSSBB/action/author_attestation","sign_citation":"https://pith.science/pith/ZZBHOGRJYGYDFOFVHJ3VZJSSBB/action/citation_signature","submit_replication":"https://pith.science/pith/ZZBHOGRJYGYDFOFVHJ3VZJSSBB/action/replication_record"}},"created_at":"2026-07-05T09:28:11.964694+00:00","updated_at":"2026-07-05T09:28:11.964694+00:00"}