{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XCOWMEXECGOA72EOAXIVWBC3XT","short_pith_number":"pith:XCOWMEXE","schema_version":"1.0","canonical_sha256":"b89d6612e4119c0fe88e05d15b045bbcc2240ed0965e3428e9aafed22ff1e910","source":{"kind":"arxiv","id":"2310.06047","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Distillation for Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adrian Alan Pol, Ekaterina Govorkova, Isobel Ojalvo, Maurizio Pierini, Nadezda Chernyavskaya, Peter Elmer, Philip Harris, Sonja Gronroos","submitted_at":"2023-10-09T18:02:38Z","abstract_excerpt":"Unsupervised deep learning techniques are widely used to identify anomalous behaviour. The performance of such methods is a product of the amount of training data and the model size. However, the size is often a limiting factor for the deployment on resource-constrained devices. We present a novel procedure based on knowledge distillation for compressing an unsupervised anomaly detection model into a supervised deployable one and we suggest a set of techniques to improve the detection sensitivity. Compressed models perform comparably to their larger counterparts while significantly reducing th"},"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":"2310.06047","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T18:02:38Z","cross_cats_sorted":[],"title_canon_sha256":"c5d95342bbd84ffd1beaf7dda49c0e3e6ae425d5e220faaa46ab926497e67afa","abstract_canon_sha256":"e727e6c0ef58acb68fce3850b29232c345be393088f25b7d1956e93967a5c6cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:03.480430Z","signature_b64":"H9bwpwKmFdWVaYLDEJ/S94OMBQaTsbVFC/0l6OW7v0Z2vPJgTDf8ClqWGDZCsK9DwhV2IA8WnqjqRcMmR+gaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b89d6612e4119c0fe88e05d15b045bbcc2240ed0965e3428e9aafed22ff1e910","last_reissued_at":"2026-07-05T06:59:03.479993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:03.479993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Distillation for Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adrian Alan Pol, Ekaterina Govorkova, Isobel Ojalvo, Maurizio Pierini, Nadezda Chernyavskaya, Peter Elmer, Philip Harris, Sonja Gronroos","submitted_at":"2023-10-09T18:02:38Z","abstract_excerpt":"Unsupervised deep learning techniques are widely used to identify anomalous behaviour. The performance of such methods is a product of the amount of training data and the model size. However, the size is often a limiting factor for the deployment on resource-constrained devices. We present a novel procedure based on knowledge distillation for compressing an unsupervised anomaly detection model into a supervised deployable one and we suggest a set of techniques to improve the detection sensitivity. Compressed models perform comparably to their larger counterparts while significantly reducing th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06047","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/2310.06047/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":"2310.06047","created_at":"2026-07-05T06:59:03.480048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.06047v1","created_at":"2026-07-05T06:59:03.480048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06047","created_at":"2026-07-05T06:59:03.480048+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCOWMEXECGOA","created_at":"2026-07-05T06:59:03.480048+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCOWMEXECGOA72EO","created_at":"2026-07-05T06:59:03.480048+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCOWMEXE","created_at":"2026-07-05T06:59:03.480048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XCOWMEXECGOA72EOAXIVWBC3XT","json":"https://pith.science/pith/XCOWMEXECGOA72EOAXIVWBC3XT.json","graph_json":"https://pith.science/api/pith-number/XCOWMEXECGOA72EOAXIVWBC3XT/graph.json","events_json":"https://pith.science/api/pith-number/XCOWMEXECGOA72EOAXIVWBC3XT/events.json","paper":"https://pith.science/paper/XCOWMEXE"},"agent_actions":{"view_html":"https://pith.science/pith/XCOWMEXECGOA72EOAXIVWBC3XT","download_json":"https://pith.science/pith/XCOWMEXECGOA72EOAXIVWBC3XT.json","view_paper":"https://pith.science/paper/XCOWMEXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.06047&json=true","fetch_graph":"https://pith.science/api/pith-number/XCOWMEXECGOA72EOAXIVWBC3XT/graph.json","fetch_events":"https://pith.science/api/pith-number/XCOWMEXECGOA72EOAXIVWBC3XT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCOWMEXECGOA72EOAXIVWBC3XT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCOWMEXECGOA72EOAXIVWBC3XT/action/storage_attestation","attest_author":"https://pith.science/pith/XCOWMEXECGOA72EOAXIVWBC3XT/action/author_attestation","sign_citation":"https://pith.science/pith/XCOWMEXECGOA72EOAXIVWBC3XT/action/citation_signature","submit_replication":"https://pith.science/pith/XCOWMEXECGOA72EOAXIVWBC3XT/action/replication_record"}},"created_at":"2026-07-05T06:59:03.480048+00:00","updated_at":"2026-07-05T06:59:03.480048+00:00"}