{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GOIMTCY3BQPJBMZ6DIQRSVPAA5","short_pith_number":"pith:GOIMTCY3","schema_version":"1.0","canonical_sha256":"3390c98b1b0c1e90b33e1a211955e0074e4300cdb163aee2db4493237c698972","source":{"kind":"arxiv","id":"1711.08534","version":2},"attestation_state":"computed","paper":{"title":"Safer Classification by Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Angelina Wang, Aviv Tamar, Pieter Abbeel, William Wang, Xi Chen","submitted_at":"2017-11-22T23:32:20Z","abstract_excerpt":"The discriminative approach to classification using deep neural networks has become the de-facto standard in various fields. Complementing recent reservations about safety against adversarial examples, we show that conventional discriminative methods can easily be fooled to provide incorrect labels with very high confidence to out of distribution examples. We posit that a generative approach is the natural remedy for this problem, and propose a method for classification using generative models. At training time, we learn a generative model for each class, while at test time, given an example t"},"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":"1711.08534","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-22T23:32:20Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"787351f97e5300703e544b50cb5ae503fe5230394bca11dd074c9710087745a9","abstract_canon_sha256":"70b5818a000cbefe538c06f9f623b4c0509cc706079d2d523846e443ff48b828"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:03.603446Z","signature_b64":"mOD3BJYB4MulUuHYWDS0qWob6oYZOrC2rf0Yo93HO4buoRrT1zuaAC+MjzYFk4ODiBrpiZYfO23dVhupCMl+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3390c98b1b0c1e90b33e1a211955e0074e4300cdb163aee2db4493237c698972","last_reissued_at":"2026-05-18T00:10:03.602689Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:03.602689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safer Classification by Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Angelina Wang, Aviv Tamar, Pieter Abbeel, William Wang, Xi Chen","submitted_at":"2017-11-22T23:32:20Z","abstract_excerpt":"The discriminative approach to classification using deep neural networks has become the de-facto standard in various fields. Complementing recent reservations about safety against adversarial examples, we show that conventional discriminative methods can easily be fooled to provide incorrect labels with very high confidence to out of distribution examples. We posit that a generative approach is the natural remedy for this problem, and propose a method for classification using generative models. At training time, we learn a generative model for each class, while at test time, given an example t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08534","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":""},"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":"1711.08534","created_at":"2026-05-18T00:10:03.602811+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.08534v2","created_at":"2026-05-18T00:10:03.602811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08534","created_at":"2026-05-18T00:10:03.602811+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOIMTCY3BQPJ","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOIMTCY3BQPJBMZ6","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOIMTCY3","created_at":"2026-05-18T12:31:18.294218+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/GOIMTCY3BQPJBMZ6DIQRSVPAA5","json":"https://pith.science/pith/GOIMTCY3BQPJBMZ6DIQRSVPAA5.json","graph_json":"https://pith.science/api/pith-number/GOIMTCY3BQPJBMZ6DIQRSVPAA5/graph.json","events_json":"https://pith.science/api/pith-number/GOIMTCY3BQPJBMZ6DIQRSVPAA5/events.json","paper":"https://pith.science/paper/GOIMTCY3"},"agent_actions":{"view_html":"https://pith.science/pith/GOIMTCY3BQPJBMZ6DIQRSVPAA5","download_json":"https://pith.science/pith/GOIMTCY3BQPJBMZ6DIQRSVPAA5.json","view_paper":"https://pith.science/paper/GOIMTCY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.08534&json=true","fetch_graph":"https://pith.science/api/pith-number/GOIMTCY3BQPJBMZ6DIQRSVPAA5/graph.json","fetch_events":"https://pith.science/api/pith-number/GOIMTCY3BQPJBMZ6DIQRSVPAA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOIMTCY3BQPJBMZ6DIQRSVPAA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOIMTCY3BQPJBMZ6DIQRSVPAA5/action/storage_attestation","attest_author":"https://pith.science/pith/GOIMTCY3BQPJBMZ6DIQRSVPAA5/action/author_attestation","sign_citation":"https://pith.science/pith/GOIMTCY3BQPJBMZ6DIQRSVPAA5/action/citation_signature","submit_replication":"https://pith.science/pith/GOIMTCY3BQPJBMZ6DIQRSVPAA5/action/replication_record"}},"created_at":"2026-05-18T00:10:03.602811+00:00","updated_at":"2026-05-18T00:10:03.602811+00:00"}