{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3VYOQGYKYZBWXCBQFAE2ITZISQ","short_pith_number":"pith:3VYOQGYK","schema_version":"1.0","canonical_sha256":"dd70e81b0ac6436b88302809a44f2894261ea32115930f3112e3bce3e8578621","source":{"kind":"arxiv","id":"2405.13031","version":2},"attestation_state":"computed","paper":{"title":"A Robust Autoencoder Ensemble-Based Approach for Anomaly Detection in Text","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Christophe Marsala, Jeremie Pantin","submitted_at":"2024-05-16T10:45:43Z","abstract_excerpt":"Anomaly detection (AD) is a fast growing and popular domain among established applications like vision and time series. We observe a rich literature for these applications, but anomaly detection in text is only starting to blossom. Recently, self-supervised methods with self-attention mechanism have been the most popular choice. While recent works have proposed a working ground for building and benchmarking state of the art approaches, we propose two principal contributions in this paper: contextual anomaly contamination and a novel ensemble-based approach. Our method, Textual Anomaly Contamin"},"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":"2405.13031","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-16T10:45:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8923b79854b6ab277207a1c99cbad8311ac2f22d54e85c2d00db7e6330e986c0","abstract_canon_sha256":"826df986fa4ec8942d5ae73caf1e98baa9999ffc537b57c63ff05ff6441fc107"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:25.989069Z","signature_b64":"7yjUtUZBMFH5c4CVh0Y2HxYQImC5zMdDzaYiD4P+wLVRsu7aT9yWjX0/96ZXCo9jZdRjhX0Auf5Iq3cTEXK3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd70e81b0ac6436b88302809a44f2894261ea32115930f3112e3bce3e8578621","last_reissued_at":"2026-07-05T09:08:25.988558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:25.988558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Robust Autoencoder Ensemble-Based Approach for Anomaly Detection in Text","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Christophe Marsala, Jeremie Pantin","submitted_at":"2024-05-16T10:45:43Z","abstract_excerpt":"Anomaly detection (AD) is a fast growing and popular domain among established applications like vision and time series. We observe a rich literature for these applications, but anomaly detection in text is only starting to blossom. Recently, self-supervised methods with self-attention mechanism have been the most popular choice. While recent works have proposed a working ground for building and benchmarking state of the art approaches, we propose two principal contributions in this paper: contextual anomaly contamination and a novel ensemble-based approach. Our method, Textual Anomaly Contamin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13031","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/2405.13031/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":"2405.13031","created_at":"2026-07-05T09:08:25.988619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13031v2","created_at":"2026-07-05T09:08:25.988619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13031","created_at":"2026-07-05T09:08:25.988619+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VYOQGYKYZBW","created_at":"2026-07-05T09:08:25.988619+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VYOQGYKYZBWXCBQ","created_at":"2026-07-05T09:08:25.988619+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VYOQGYK","created_at":"2026-07-05T09:08:25.988619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12295","citing_title":"Text-ADBench: Text Anomaly Detection Benchmark based on LLMs Embedding","ref_index":73,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VYOQGYKYZBWXCBQFAE2ITZISQ","json":"https://pith.science/pith/3VYOQGYKYZBWXCBQFAE2ITZISQ.json","graph_json":"https://pith.science/api/pith-number/3VYOQGYKYZBWXCBQFAE2ITZISQ/graph.json","events_json":"https://pith.science/api/pith-number/3VYOQGYKYZBWXCBQFAE2ITZISQ/events.json","paper":"https://pith.science/paper/3VYOQGYK"},"agent_actions":{"view_html":"https://pith.science/pith/3VYOQGYKYZBWXCBQFAE2ITZISQ","download_json":"https://pith.science/pith/3VYOQGYKYZBWXCBQFAE2ITZISQ.json","view_paper":"https://pith.science/paper/3VYOQGYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13031&json=true","fetch_graph":"https://pith.science/api/pith-number/3VYOQGYKYZBWXCBQFAE2ITZISQ/graph.json","fetch_events":"https://pith.science/api/pith-number/3VYOQGYKYZBWXCBQFAE2ITZISQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VYOQGYKYZBWXCBQFAE2ITZISQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VYOQGYKYZBWXCBQFAE2ITZISQ/action/storage_attestation","attest_author":"https://pith.science/pith/3VYOQGYKYZBWXCBQFAE2ITZISQ/action/author_attestation","sign_citation":"https://pith.science/pith/3VYOQGYKYZBWXCBQFAE2ITZISQ/action/citation_signature","submit_replication":"https://pith.science/pith/3VYOQGYKYZBWXCBQFAE2ITZISQ/action/replication_record"}},"created_at":"2026-07-05T09:08:25.988619+00:00","updated_at":"2026-07-05T09:08:25.988619+00:00"}