{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:N776RGDXEQMJ3NURE4DRNIS7C6","short_pith_number":"pith:N776RGDX","schema_version":"1.0","canonical_sha256":"6fffe8987724189db691270716a25f179f221bf13f6db6b41f6e9c1138db5685","source":{"kind":"arxiv","id":"2003.10713","version":3},"attestation_state":"computed","paper":{"title":"Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bhanukiran Vinzamuri, Gowthami Somepalli, Soheil Feizi, Yexin Wu, Yogesh Balaji","submitted_at":"2020-03-24T08:26:58Z","abstract_excerpt":"Detecting out of distribution (OOD) samples is of paramount importance in all Machine Learning applications. Deep generative modeling has emerged as a dominant paradigm to model complex data distributions without labels. However, prior work has shown that generative models tend to assign higher likelihoods to OOD samples compared to the data distribution on which they were trained. First, we propose Adversarial Mirrored Autoencoder (AMA), a variant of Adversarial Autoencoder, which uses a mirrored Wasserstein loss in the discriminator to enforce better semantic-level reconstruction. We also pr"},"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":"2003.10713","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-24T08:26:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ad1bdaee3b1ff90ecf156eb2bd0c094bb9e47fe435604acfc8cdb94029dc50e8","abstract_canon_sha256":"a4b1e1bb2e17f0fa1b7834ce11cb6ec50f3d1de7e9648bc91357a0220c24ecaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:04:05.918854Z","signature_b64":"q+sgooLiok7zzFV2l71Y6gL2+o4vfBozRhSATFaIvsrNTlJKUiFaSxTIT8beNbDTp0v+Uf/4R+kPWEj+TZX4Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fffe8987724189db691270716a25f179f221bf13f6db6b41f6e9c1138db5685","last_reissued_at":"2026-07-05T02:04:05.918469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:04:05.918469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bhanukiran Vinzamuri, Gowthami Somepalli, Soheil Feizi, Yexin Wu, Yogesh Balaji","submitted_at":"2020-03-24T08:26:58Z","abstract_excerpt":"Detecting out of distribution (OOD) samples is of paramount importance in all Machine Learning applications. Deep generative modeling has emerged as a dominant paradigm to model complex data distributions without labels. However, prior work has shown that generative models tend to assign higher likelihoods to OOD samples compared to the data distribution on which they were trained. First, we propose Adversarial Mirrored Autoencoder (AMA), a variant of Adversarial Autoencoder, which uses a mirrored Wasserstein loss in the discriminator to enforce better semantic-level reconstruction. We also pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.10713","kind":"arxiv","version":3},"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/2003.10713/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":"2003.10713","created_at":"2026-07-05T02:04:05.918523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.10713v3","created_at":"2026-07-05T02:04:05.918523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.10713","created_at":"2026-07-05T02:04:05.918523+00:00"},{"alias_kind":"pith_short_12","alias_value":"N776RGDXEQMJ","created_at":"2026-07-05T02:04:05.918523+00:00"},{"alias_kind":"pith_short_16","alias_value":"N776RGDXEQMJ3NUR","created_at":"2026-07-05T02:04:05.918523+00:00"},{"alias_kind":"pith_short_8","alias_value":"N776RGDX","created_at":"2026-07-05T02:04:05.918523+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/N776RGDXEQMJ3NURE4DRNIS7C6","json":"https://pith.science/pith/N776RGDXEQMJ3NURE4DRNIS7C6.json","graph_json":"https://pith.science/api/pith-number/N776RGDXEQMJ3NURE4DRNIS7C6/graph.json","events_json":"https://pith.science/api/pith-number/N776RGDXEQMJ3NURE4DRNIS7C6/events.json","paper":"https://pith.science/paper/N776RGDX"},"agent_actions":{"view_html":"https://pith.science/pith/N776RGDXEQMJ3NURE4DRNIS7C6","download_json":"https://pith.science/pith/N776RGDXEQMJ3NURE4DRNIS7C6.json","view_paper":"https://pith.science/paper/N776RGDX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.10713&json=true","fetch_graph":"https://pith.science/api/pith-number/N776RGDXEQMJ3NURE4DRNIS7C6/graph.json","fetch_events":"https://pith.science/api/pith-number/N776RGDXEQMJ3NURE4DRNIS7C6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N776RGDXEQMJ3NURE4DRNIS7C6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N776RGDXEQMJ3NURE4DRNIS7C6/action/storage_attestation","attest_author":"https://pith.science/pith/N776RGDXEQMJ3NURE4DRNIS7C6/action/author_attestation","sign_citation":"https://pith.science/pith/N776RGDXEQMJ3NURE4DRNIS7C6/action/citation_signature","submit_replication":"https://pith.science/pith/N776RGDXEQMJ3NURE4DRNIS7C6/action/replication_record"}},"created_at":"2026-07-05T02:04:05.918523+00:00","updated_at":"2026-07-05T02:04:05.918523+00:00"}