{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RGDMH4OTO6QYEKMF3623CXLUUX","short_pith_number":"pith:RGDMH4OT","schema_version":"1.0","canonical_sha256":"8986c3f1d377a1822985dfb5b15d74a5dc97a53a5cf6d87f29468c43d7ea8386","source":{"kind":"arxiv","id":"1810.01392","version":4},"attestation_state":"computed","paper":{"title":"WAIC, but Why? Generative Ensembles for Robust Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander A. Alemi, Eric Jang, Hyunsun Choi","submitted_at":"2018-10-02T17:32:07Z","abstract_excerpt":"Machine learning models encounter Out-of-Distribution (OoD) errors when the data seen at test time are generated from a different stochastic generator than the one used to generate the training data. One proposal to scale OoD detection to high-dimensional data is to learn a tractable likelihood approximation of the training distribution, and use it to reject unlikely inputs. However, likelihood models on natural data are themselves susceptible to OoD errors, and even assign large likelihoods to samples from other datasets. To mitigate this problem, we propose Generative Ensembles, which robust"},"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":"1810.01392","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-02T17:32:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1588f5c266a89f72ae72aa08a0582923e528fcc9ef212bf9f61a2e03bc26ed88","abstract_canon_sha256":"ce8dadda746a651dead5308ac5b3cd8d902ef671f51eb3eb9120004de2d1c53b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:15.319649Z","signature_b64":"XQ+wqWC1UwhhqlEDOidDtpusNUq2j41v+h8lrenYOU2fywbVafeU6eurcb6TWoIrL8fiLNXf+KXt1GSGIE2sDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8986c3f1d377a1822985dfb5b15d74a5dc97a53a5cf6d87f29468c43d7ea8386","last_reissued_at":"2026-05-17T23:45:15.319002Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:15.319002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WAIC, but Why? Generative Ensembles for Robust Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander A. Alemi, Eric Jang, Hyunsun Choi","submitted_at":"2018-10-02T17:32:07Z","abstract_excerpt":"Machine learning models encounter Out-of-Distribution (OoD) errors when the data seen at test time are generated from a different stochastic generator than the one used to generate the training data. One proposal to scale OoD detection to high-dimensional data is to learn a tractable likelihood approximation of the training distribution, and use it to reject unlikely inputs. However, likelihood models on natural data are themselves susceptible to OoD errors, and even assign large likelihoods to samples from other datasets. To mitigate this problem, we propose Generative Ensembles, which robust"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01392","kind":"arxiv","version":4},"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":"1810.01392","created_at":"2026-05-17T23:45:15.319109+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.01392v4","created_at":"2026-05-17T23:45:15.319109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01392","created_at":"2026-05-17T23:45:15.319109+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGDMH4OTO6QY","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGDMH4OTO6QYEKMF","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGDMH4OT","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.04572","citing_title":"Out-of-Distribution Detection Using Neural Rendering Generative Models","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22496","citing_title":"The Signal in the Noise: OOD Detection Through Goodness-of-Fit Testing in Factorised Latent Spaces","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11014","citing_title":"Backbone-Equated Diffusion OOD via Sparse Internal Snapshots","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05638","citing_title":"Scaling Pretrained Representations Enables Label-Free Out-of-Distribution Detection Without Fine-Tuning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18804","citing_title":"Geometric Decoupling: Diagnosing the Structural Instability of Latent","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RGDMH4OTO6QYEKMF3623CXLUUX","json":"https://pith.science/pith/RGDMH4OTO6QYEKMF3623CXLUUX.json","graph_json":"https://pith.science/api/pith-number/RGDMH4OTO6QYEKMF3623CXLUUX/graph.json","events_json":"https://pith.science/api/pith-number/RGDMH4OTO6QYEKMF3623CXLUUX/events.json","paper":"https://pith.science/paper/RGDMH4OT"},"agent_actions":{"view_html":"https://pith.science/pith/RGDMH4OTO6QYEKMF3623CXLUUX","download_json":"https://pith.science/pith/RGDMH4OTO6QYEKMF3623CXLUUX.json","view_paper":"https://pith.science/paper/RGDMH4OT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.01392&json=true","fetch_graph":"https://pith.science/api/pith-number/RGDMH4OTO6QYEKMF3623CXLUUX/graph.json","fetch_events":"https://pith.science/api/pith-number/RGDMH4OTO6QYEKMF3623CXLUUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGDMH4OTO6QYEKMF3623CXLUUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGDMH4OTO6QYEKMF3623CXLUUX/action/storage_attestation","attest_author":"https://pith.science/pith/RGDMH4OTO6QYEKMF3623CXLUUX/action/author_attestation","sign_citation":"https://pith.science/pith/RGDMH4OTO6QYEKMF3623CXLUUX/action/citation_signature","submit_replication":"https://pith.science/pith/RGDMH4OTO6QYEKMF3623CXLUUX/action/replication_record"}},"created_at":"2026-05-17T23:45:15.319109+00:00","updated_at":"2026-05-17T23:45:15.319109+00:00"}