{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XCCCSQSFV3UHFSG2R2E4PEPICI","short_pith_number":"pith:XCCCSQSF","schema_version":"1.0","canonical_sha256":"b884294245aee872c8da8e89c791e812031cf97bef97ee4b0b962b49c7d0d484","source":{"kind":"arxiv","id":"1904.00152","version":2},"attestation_state":"computed","paper":{"title":"Robust Subspace Recovery Layer for Unsupervised Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chieh-Hsin Lai, Dongmian Zou, Gilad Lerman","submitted_at":"2019-03-30T05:30:54Z","abstract_excerpt":"We propose a neural network for unsupervised anomaly detection with a novel robust subspace recovery layer (RSR layer). This layer seeks to extract the underlying subspace from a latent representation of the given data and removes outliers that lie away from this subspace. It is used within an autoencoder. The encoder maps the data into a latent space, from which the RSR layer extracts the subspace. The decoder then smoothly maps back the underlying subspace to a \"manifold\" close to the original inliers. Inliers and outliers are distinguished according to the distances between the original and"},"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":"1904.00152","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-30T05:30:54Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"74db9b4b8712c1721c05c946df65a40de2958e04aface289b09993c1c133bc59","abstract_canon_sha256":"018fdcb3432b77f630a3fa776d02d90d224c904fb7fb79b812dbc4c6ff19223e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:34.983103Z","signature_b64":"2bLB5rgZs3tXvsau2toS2iKyfFYWpRupSTqUpgGpyOXxsEymhnWBADf/K6sD5i6TtAZ8SMYY/ZVKd72aROyFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b884294245aee872c8da8e89c791e812031cf97bef97ee4b0b962b49c7d0d484","last_reissued_at":"2026-07-05T03:48:34.982600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:34.982600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Subspace Recovery Layer for Unsupervised Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chieh-Hsin Lai, Dongmian Zou, Gilad Lerman","submitted_at":"2019-03-30T05:30:54Z","abstract_excerpt":"We propose a neural network for unsupervised anomaly detection with a novel robust subspace recovery layer (RSR layer). This layer seeks to extract the underlying subspace from a latent representation of the given data and removes outliers that lie away from this subspace. It is used within an autoencoder. The encoder maps the data into a latent space, from which the RSR layer extracts the subspace. The decoder then smoothly maps back the underlying subspace to a \"manifold\" close to the original inliers. Inliers and outliers are distinguished according to the distances between the original and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.00152","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/1904.00152/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":"1904.00152","created_at":"2026-07-05T03:48:34.982683+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.00152v2","created_at":"2026-07-05T03:48:34.982683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.00152","created_at":"2026-07-05T03:48:34.982683+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCCCSQSFV3UH","created_at":"2026-07-05T03:48:34.982683+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCCCSQSFV3UHFSG2","created_at":"2026-07-05T03:48:34.982683+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCCCSQSF","created_at":"2026-07-05T03:48:34.982683+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27148","citing_title":"Landseer: Exploring the Machine Learning Defense Landscape","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14726","citing_title":"Catching Every Ripple: Enhanced Anomaly Awareness via Dynamic Concept Adaptation","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XCCCSQSFV3UHFSG2R2E4PEPICI","json":"https://pith.science/pith/XCCCSQSFV3UHFSG2R2E4PEPICI.json","graph_json":"https://pith.science/api/pith-number/XCCCSQSFV3UHFSG2R2E4PEPICI/graph.json","events_json":"https://pith.science/api/pith-number/XCCCSQSFV3UHFSG2R2E4PEPICI/events.json","paper":"https://pith.science/paper/XCCCSQSF"},"agent_actions":{"view_html":"https://pith.science/pith/XCCCSQSFV3UHFSG2R2E4PEPICI","download_json":"https://pith.science/pith/XCCCSQSFV3UHFSG2R2E4PEPICI.json","view_paper":"https://pith.science/paper/XCCCSQSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.00152&json=true","fetch_graph":"https://pith.science/api/pith-number/XCCCSQSFV3UHFSG2R2E4PEPICI/graph.json","fetch_events":"https://pith.science/api/pith-number/XCCCSQSFV3UHFSG2R2E4PEPICI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCCCSQSFV3UHFSG2R2E4PEPICI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCCCSQSFV3UHFSG2R2E4PEPICI/action/storage_attestation","attest_author":"https://pith.science/pith/XCCCSQSFV3UHFSG2R2E4PEPICI/action/author_attestation","sign_citation":"https://pith.science/pith/XCCCSQSFV3UHFSG2R2E4PEPICI/action/citation_signature","submit_replication":"https://pith.science/pith/XCCCSQSFV3UHFSG2R2E4PEPICI/action/replication_record"}},"created_at":"2026-07-05T03:48:34.982683+00:00","updated_at":"2026-07-05T03:48:34.982683+00:00"}