{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GCRA6ONMWFPQQTCBEVBCE7VUQ5","short_pith_number":"pith:GCRA6ONM","schema_version":"1.0","canonical_sha256":"30a20f39acb15f084c412542227eb4875d1c3cd3a6df268b6003c0966b3c452c","source":{"kind":"arxiv","id":"2506.14390","version":1},"attestation_state":"computed","paper":{"title":"Enclosing Prototypical Variational Autoencoder for Explainable Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Conrad Orglmeister, Elvira Fleig, Erik Bochinski, Volker Eiselein","submitted_at":"2025-06-17T10:38:29Z","abstract_excerpt":"Understanding the decision-making and trusting the reliability of Deep Machine Learning Models is crucial for adopting such methods to safety-relevant applications. We extend self-explainable Prototypical Variational models with autoencoder-based out-of-distribution (OOD) detection: A Variational Autoencoder is applied to learn a meaningful latent space which can be used for distance-based classification, likelihood estimation for OOD detection, and reconstruction. The In-Distribution (ID) region is defined by a Gaussian mixture distribution with learned prototypes representing the center of e"},"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":"2506.14390","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T10:38:29Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"379c90817e3119de955263dfbc85fd70a8607fa14fb89273d297b8f7d53bb7dd","abstract_canon_sha256":"3b6f91d6688ea2bc0cd47b143c5346af37c6639b2f4948cb314ef0d37684801c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:54.689435Z","signature_b64":"vo2V7sRv5JscOKbsK/IYGTzK2kWmiEfNhJWf+nt1qGM+pAXbaVHvQrUJYXsocbq+9WNMRbDclOtET8YPg/RmAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30a20f39acb15f084c412542227eb4875d1c3cd3a6df268b6003c0966b3c452c","last_reissued_at":"2026-07-05T11:22:54.688954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:54.688954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enclosing Prototypical Variational Autoencoder for Explainable Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Conrad Orglmeister, Elvira Fleig, Erik Bochinski, Volker Eiselein","submitted_at":"2025-06-17T10:38:29Z","abstract_excerpt":"Understanding the decision-making and trusting the reliability of Deep Machine Learning Models is crucial for adopting such methods to safety-relevant applications. We extend self-explainable Prototypical Variational models with autoencoder-based out-of-distribution (OOD) detection: A Variational Autoencoder is applied to learn a meaningful latent space which can be used for distance-based classification, likelihood estimation for OOD detection, and reconstruction. The In-Distribution (ID) region is defined by a Gaussian mixture distribution with learned prototypes representing the center of e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14390","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/2506.14390/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":"2506.14390","created_at":"2026-07-05T11:22:54.689013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14390v1","created_at":"2026-07-05T11:22:54.689013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14390","created_at":"2026-07-05T11:22:54.689013+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCRA6ONMWFPQ","created_at":"2026-07-05T11:22:54.689013+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCRA6ONMWFPQQTCB","created_at":"2026-07-05T11:22:54.689013+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCRA6ONM","created_at":"2026-07-05T11:22:54.689013+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/GCRA6ONMWFPQQTCBEVBCE7VUQ5","json":"https://pith.science/pith/GCRA6ONMWFPQQTCBEVBCE7VUQ5.json","graph_json":"https://pith.science/api/pith-number/GCRA6ONMWFPQQTCBEVBCE7VUQ5/graph.json","events_json":"https://pith.science/api/pith-number/GCRA6ONMWFPQQTCBEVBCE7VUQ5/events.json","paper":"https://pith.science/paper/GCRA6ONM"},"agent_actions":{"view_html":"https://pith.science/pith/GCRA6ONMWFPQQTCBEVBCE7VUQ5","download_json":"https://pith.science/pith/GCRA6ONMWFPQQTCBEVBCE7VUQ5.json","view_paper":"https://pith.science/paper/GCRA6ONM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14390&json=true","fetch_graph":"https://pith.science/api/pith-number/GCRA6ONMWFPQQTCBEVBCE7VUQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/GCRA6ONMWFPQQTCBEVBCE7VUQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCRA6ONMWFPQQTCBEVBCE7VUQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCRA6ONMWFPQQTCBEVBCE7VUQ5/action/storage_attestation","attest_author":"https://pith.science/pith/GCRA6ONMWFPQQTCBEVBCE7VUQ5/action/author_attestation","sign_citation":"https://pith.science/pith/GCRA6ONMWFPQQTCBEVBCE7VUQ5/action/citation_signature","submit_replication":"https://pith.science/pith/GCRA6ONMWFPQQTCBEVBCE7VUQ5/action/replication_record"}},"created_at":"2026-07-05T11:22:54.689013+00:00","updated_at":"2026-07-05T11:22:54.689013+00:00"}