{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4CHOCVZ5ASCRSBEXX3OJZWAK5R","short_pith_number":"pith:4CHOCVZ5","schema_version":"1.0","canonical_sha256":"e08ee1573d0485190497bedc9cd80aec6f5280096348c7917cd05d2c2c3e0c1f","source":{"kind":"arxiv","id":"1905.11890","version":1},"attestation_state":"computed","paper":{"title":"Anomaly scores for generative models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jan B\\'im, Tom\\'a\\v{s} Pevn\\'y, V\\'aclav \\v{S}m\\'idl","submitted_at":"2019-05-28T15:35:39Z","abstract_excerpt":"Reconstruction error is a prevalent score used to identify anomalous samples when data are modeled by generative models, such as (variational) auto-encoders or generative adversarial networks. This score relies on the assumption that normal samples are located on a manifold and all anomalous samples are located outside. Since the manifold can be learned only where the training data lie, there are no guarantees how the reconstruction error behaves elsewhere and the score, therefore, seems to be ill-defined. This work defines an anomaly score that is theoretically compatible with generative mode"},"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":"1905.11890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-28T15:35:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f85e5ee1dee632936fcfa4bb844918d84cec34da71c72821802d980abe8e8d8c","abstract_canon_sha256":"953fd6dac96bf639a7e698aea08582efcdae05e4b7096d20d13b6b84608526a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:50.012292Z","signature_b64":"aNEps8PywzkYf8mlzNCHaopIceNw1ohtX9nslCnmXHNxKwL8A67ovA7Dt+RnGLQWFiBc1psqnLcH7LZkxOx0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e08ee1573d0485190497bedc9cd80aec6f5280096348c7917cd05d2c2c3e0c1f","last_reissued_at":"2026-05-17T23:44:50.011631Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:50.011631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Anomaly scores for generative models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jan B\\'im, Tom\\'a\\v{s} Pevn\\'y, V\\'aclav \\v{S}m\\'idl","submitted_at":"2019-05-28T15:35:39Z","abstract_excerpt":"Reconstruction error is a prevalent score used to identify anomalous samples when data are modeled by generative models, such as (variational) auto-encoders or generative adversarial networks. This score relies on the assumption that normal samples are located on a manifold and all anomalous samples are located outside. Since the manifold can be learned only where the training data lie, there are no guarantees how the reconstruction error behaves elsewhere and the score, therefore, seems to be ill-defined. This work defines an anomaly score that is theoretically compatible with generative mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11890","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":""},"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":"1905.11890","created_at":"2026-05-17T23:44:50.011732+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11890v1","created_at":"2026-05-17T23:44:50.011732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11890","created_at":"2026-05-17T23:44:50.011732+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CHOCVZ5ASCR","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CHOCVZ5ASCRSBEX","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CHOCVZ5","created_at":"2026-05-18T12:33:10.108867+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/4CHOCVZ5ASCRSBEXX3OJZWAK5R","json":"https://pith.science/pith/4CHOCVZ5ASCRSBEXX3OJZWAK5R.json","graph_json":"https://pith.science/api/pith-number/4CHOCVZ5ASCRSBEXX3OJZWAK5R/graph.json","events_json":"https://pith.science/api/pith-number/4CHOCVZ5ASCRSBEXX3OJZWAK5R/events.json","paper":"https://pith.science/paper/4CHOCVZ5"},"agent_actions":{"view_html":"https://pith.science/pith/4CHOCVZ5ASCRSBEXX3OJZWAK5R","download_json":"https://pith.science/pith/4CHOCVZ5ASCRSBEXX3OJZWAK5R.json","view_paper":"https://pith.science/paper/4CHOCVZ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11890&json=true","fetch_graph":"https://pith.science/api/pith-number/4CHOCVZ5ASCRSBEXX3OJZWAK5R/graph.json","fetch_events":"https://pith.science/api/pith-number/4CHOCVZ5ASCRSBEXX3OJZWAK5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CHOCVZ5ASCRSBEXX3OJZWAK5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CHOCVZ5ASCRSBEXX3OJZWAK5R/action/storage_attestation","attest_author":"https://pith.science/pith/4CHOCVZ5ASCRSBEXX3OJZWAK5R/action/author_attestation","sign_citation":"https://pith.science/pith/4CHOCVZ5ASCRSBEXX3OJZWAK5R/action/citation_signature","submit_replication":"https://pith.science/pith/4CHOCVZ5ASCRSBEXX3OJZWAK5R/action/replication_record"}},"created_at":"2026-05-17T23:44:50.011732+00:00","updated_at":"2026-05-17T23:44:50.011732+00:00"}