{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XAVSZ7HVEIW3EKI73SX6RRVODB","short_pith_number":"pith:XAVSZ7HV","schema_version":"1.0","canonical_sha256":"b82b2cfcf5222db2291fdcafe8c6ae187f3cf161109e6eaf3c1bb59aa27e5426","source":{"kind":"arxiv","id":"2502.01920","version":2},"attestation_state":"computed","paper":{"title":"Anomaly Detection via Autoencoder Composite Features and NCE","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Austin J. Brockmeier, Yalin Liao","submitted_at":"2025-02-04T01:29:22Z","abstract_excerpt":"Unsupervised anomaly detection is a challenging task. Autoencoders (AEs) or generative models are often employed to model the data distribution of normal inputs and subsequently identify anomalous, out-of-distribution inputs by high reconstruction error or low likelihood, respectively. However, AEs may generalize and achieve small reconstruction errors on abnormal inputs. We propose a decoupled training approach for anomaly detection that both an AE and a likelihood model trained with noise contrastive estimation (NCE). After training the AE, NCE estimates a probability density function, to se"},"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":"2502.01920","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T01:29:22Z","cross_cats_sorted":[],"title_canon_sha256":"9afacf53c1a89fd97927d934faabca8f1aa76206b5f6e198c50abff7ca99cb52","abstract_canon_sha256":"b86c6e69d53edca40cc0e4b83cbe251a7f8f2c59beba80d8b68a911b0e26f5f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:51.109433Z","signature_b64":"leMAOUGL17jlVrix28EaR5togHovgcLEN5dr8GnU6RG+HF5dCgat9sEcxVuTAbBgRwvzuCst3Ms+/rsn5mOJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b82b2cfcf5222db2291fdcafe8c6ae187f3cf161109e6eaf3c1bb59aa27e5426","last_reissued_at":"2026-07-05T11:19:51.109020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:51.109020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Anomaly Detection via Autoencoder Composite Features and NCE","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Austin J. Brockmeier, Yalin Liao","submitted_at":"2025-02-04T01:29:22Z","abstract_excerpt":"Unsupervised anomaly detection is a challenging task. Autoencoders (AEs) or generative models are often employed to model the data distribution of normal inputs and subsequently identify anomalous, out-of-distribution inputs by high reconstruction error or low likelihood, respectively. However, AEs may generalize and achieve small reconstruction errors on abnormal inputs. We propose a decoupled training approach for anomaly detection that both an AE and a likelihood model trained with noise contrastive estimation (NCE). After training the AE, NCE estimates a probability density function, to se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01920","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/2502.01920/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":"2502.01920","created_at":"2026-07-05T11:19:51.109074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01920v2","created_at":"2026-07-05T11:19:51.109074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01920","created_at":"2026-07-05T11:19:51.109074+00:00"},{"alias_kind":"pith_short_12","alias_value":"XAVSZ7HVEIW3","created_at":"2026-07-05T11:19:51.109074+00:00"},{"alias_kind":"pith_short_16","alias_value":"XAVSZ7HVEIW3EKI7","created_at":"2026-07-05T11:19:51.109074+00:00"},{"alias_kind":"pith_short_8","alias_value":"XAVSZ7HV","created_at":"2026-07-05T11:19:51.109074+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/XAVSZ7HVEIW3EKI73SX6RRVODB","json":"https://pith.science/pith/XAVSZ7HVEIW3EKI73SX6RRVODB.json","graph_json":"https://pith.science/api/pith-number/XAVSZ7HVEIW3EKI73SX6RRVODB/graph.json","events_json":"https://pith.science/api/pith-number/XAVSZ7HVEIW3EKI73SX6RRVODB/events.json","paper":"https://pith.science/paper/XAVSZ7HV"},"agent_actions":{"view_html":"https://pith.science/pith/XAVSZ7HVEIW3EKI73SX6RRVODB","download_json":"https://pith.science/pith/XAVSZ7HVEIW3EKI73SX6RRVODB.json","view_paper":"https://pith.science/paper/XAVSZ7HV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01920&json=true","fetch_graph":"https://pith.science/api/pith-number/XAVSZ7HVEIW3EKI73SX6RRVODB/graph.json","fetch_events":"https://pith.science/api/pith-number/XAVSZ7HVEIW3EKI73SX6RRVODB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XAVSZ7HVEIW3EKI73SX6RRVODB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XAVSZ7HVEIW3EKI73SX6RRVODB/action/storage_attestation","attest_author":"https://pith.science/pith/XAVSZ7HVEIW3EKI73SX6RRVODB/action/author_attestation","sign_citation":"https://pith.science/pith/XAVSZ7HVEIW3EKI73SX6RRVODB/action/citation_signature","submit_replication":"https://pith.science/pith/XAVSZ7HVEIW3EKI73SX6RRVODB/action/replication_record"}},"created_at":"2026-07-05T11:19:51.109074+00:00","updated_at":"2026-07-05T11:19:51.109074+00:00"}