{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DPZIGPC45DBOLVKQAEAF4HHFF3","short_pith_number":"pith:DPZIGPC4","schema_version":"1.0","canonical_sha256":"1bf2833c5ce8c2e5d55001005e1ce52efdc52af2c85168cf1e421529483ee2c4","source":{"kind":"arxiv","id":"2310.10702","version":2},"attestation_state":"computed","paper":{"title":"Transparent Anomaly Detection via Concept-based Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Farhood Farahnak, Ivaxi Sheth, Laya Rafiee Sevyeri, Samira Ebrahimi Kahou, Shirin Abbasinejad Enger","submitted_at":"2023-10-16T11:46:26Z","abstract_excerpt":"Advancements in deep learning techniques have given a boost to the performance of anomaly detection. However, real-world and safety-critical applications demand a level of transparency and reasoning beyond accuracy. The task of anomaly detection (AD) focuses on finding whether a given sample follows the learned distribution. Existing methods lack the ability to reason with clear explanations for their outcomes. Hence to overcome this challenge, we propose Transparent {A}nomaly Detection {C}oncept {E}xplanations (ACE). ACE is able to provide human interpretable explanations in the form of conce"},"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":"2310.10702","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T11:46:26Z","cross_cats_sorted":[],"title_canon_sha256":"ec94c5e2244493f3d3162d55146cc02f0e6c34c752a6f175667f0b0d5466d73a","abstract_canon_sha256":"004c93bf9213b45a1309f5193cd32179de6c90bca8191cad5b0f6204a180ea7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:13.207018Z","signature_b64":"HUIsms+Dnx+imLLQJzrliGiKaLNb+Fc3LUL5uBHGizlvvBaSJ/NTGfk0TyMUeZ3M9yL19C5Yrc6Me/Gynz5SCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bf2833c5ce8c2e5d55001005e1ce52efdc52af2c85168cf1e421529483ee2c4","last_reissued_at":"2026-07-05T07:08:13.206513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:13.206513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transparent Anomaly Detection via Concept-based Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Farhood Farahnak, Ivaxi Sheth, Laya Rafiee Sevyeri, Samira Ebrahimi Kahou, Shirin Abbasinejad Enger","submitted_at":"2023-10-16T11:46:26Z","abstract_excerpt":"Advancements in deep learning techniques have given a boost to the performance of anomaly detection. However, real-world and safety-critical applications demand a level of transparency and reasoning beyond accuracy. The task of anomaly detection (AD) focuses on finding whether a given sample follows the learned distribution. Existing methods lack the ability to reason with clear explanations for their outcomes. Hence to overcome this challenge, we propose Transparent {A}nomaly Detection {C}oncept {E}xplanations (ACE). ACE is able to provide human interpretable explanations in the form of conce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10702","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/2310.10702/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":"2310.10702","created_at":"2026-07-05T07:08:13.206587+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10702v2","created_at":"2026-07-05T07:08:13.206587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10702","created_at":"2026-07-05T07:08:13.206587+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPZIGPC45DBO","created_at":"2026-07-05T07:08:13.206587+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPZIGPC45DBOLVKQ","created_at":"2026-07-05T07:08:13.206587+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPZIGPC4","created_at":"2026-07-05T07:08:13.206587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10669","citing_title":"In Defense of Information Leakage in Concept-based Models","ref_index":235,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DPZIGPC45DBOLVKQAEAF4HHFF3","json":"https://pith.science/pith/DPZIGPC45DBOLVKQAEAF4HHFF3.json","graph_json":"https://pith.science/api/pith-number/DPZIGPC45DBOLVKQAEAF4HHFF3/graph.json","events_json":"https://pith.science/api/pith-number/DPZIGPC45DBOLVKQAEAF4HHFF3/events.json","paper":"https://pith.science/paper/DPZIGPC4"},"agent_actions":{"view_html":"https://pith.science/pith/DPZIGPC45DBOLVKQAEAF4HHFF3","download_json":"https://pith.science/pith/DPZIGPC45DBOLVKQAEAF4HHFF3.json","view_paper":"https://pith.science/paper/DPZIGPC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10702&json=true","fetch_graph":"https://pith.science/api/pith-number/DPZIGPC45DBOLVKQAEAF4HHFF3/graph.json","fetch_events":"https://pith.science/api/pith-number/DPZIGPC45DBOLVKQAEAF4HHFF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPZIGPC45DBOLVKQAEAF4HHFF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPZIGPC45DBOLVKQAEAF4HHFF3/action/storage_attestation","attest_author":"https://pith.science/pith/DPZIGPC45DBOLVKQAEAF4HHFF3/action/author_attestation","sign_citation":"https://pith.science/pith/DPZIGPC45DBOLVKQAEAF4HHFF3/action/citation_signature","submit_replication":"https://pith.science/pith/DPZIGPC45DBOLVKQAEAF4HHFF3/action/replication_record"}},"created_at":"2026-07-05T07:08:13.206587+00:00","updated_at":"2026-07-05T07:08:13.206587+00:00"}