{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3GIOPMZUAQWPLWODAN5K32ZAOQ","short_pith_number":"pith:3GIOPMZU","schema_version":"1.0","canonical_sha256":"d990e7b334042cf5d9c3037aadeb2074283e90f4badc0eac9a1d477b7af4edd9","source":{"kind":"arxiv","id":"1811.03205","version":1},"attestation_state":"computed","paper":{"title":"Robustness of Conditional GANs to Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ashish Khetan, Kiran Koshy Thekumparampil, Sewoong Oh, Zinan Lin","submitted_at":"2018-11-08T01:07:17Z","abstract_excerpt":"We study the problem of learning conditional generators from noisy labeled samples, where the labels are corrupted by random noise. A standard training of conditional GANs will not only produce samples with wrong labels, but also generate poor quality samples. We consider two scenarios, depending on whether the noise model is known or not. When the distribution of the noise is known, we introduce a novel architecture which we call Robust Conditional GAN (RCGAN). The main idea is to corrupt the label of the generated sample before feeding to the adversarial discriminator, forcing the generator "},"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":"1811.03205","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-11-08T01:07:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ef83be04a7fa0d3952d78d8076fab2f05298ed16cf5b6601465ff25f2f04d3da","abstract_canon_sha256":"af862584395efeb553b1305ab53534030cfc85d424f1ae7a6bad38d14e33df56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:18.855567Z","signature_b64":"HBr5TVhiDmzMV5KzpM6otX8NNV2QLVoza5pOOBegEzS57auhHUKAQI2ypdelRtyFtXcszkugX5+FeV3/UhBNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d990e7b334042cf5d9c3037aadeb2074283e90f4badc0eac9a1d477b7af4edd9","last_reissued_at":"2026-05-18T00:01:18.855166Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:18.855166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robustness of Conditional GANs to Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ashish Khetan, Kiran Koshy Thekumparampil, Sewoong Oh, Zinan Lin","submitted_at":"2018-11-08T01:07:17Z","abstract_excerpt":"We study the problem of learning conditional generators from noisy labeled samples, where the labels are corrupted by random noise. A standard training of conditional GANs will not only produce samples with wrong labels, but also generate poor quality samples. We consider two scenarios, depending on whether the noise model is known or not. When the distribution of the noise is known, we introduce a novel architecture which we call Robust Conditional GAN (RCGAN). The main idea is to corrupt the label of the generated sample before feeding to the adversarial discriminator, forcing the generator "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03205","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":"1811.03205","created_at":"2026-05-18T00:01:18.855229+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.03205v1","created_at":"2026-05-18T00:01:18.855229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03205","created_at":"2026-05-18T00:01:18.855229+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GIOPMZUAQWP","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GIOPMZUAQWPLWOD","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GIOPMZU","created_at":"2026-05-18T12:32:02.567920+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/3GIOPMZUAQWPLWODAN5K32ZAOQ","json":"https://pith.science/pith/3GIOPMZUAQWPLWODAN5K32ZAOQ.json","graph_json":"https://pith.science/api/pith-number/3GIOPMZUAQWPLWODAN5K32ZAOQ/graph.json","events_json":"https://pith.science/api/pith-number/3GIOPMZUAQWPLWODAN5K32ZAOQ/events.json","paper":"https://pith.science/paper/3GIOPMZU"},"agent_actions":{"view_html":"https://pith.science/pith/3GIOPMZUAQWPLWODAN5K32ZAOQ","download_json":"https://pith.science/pith/3GIOPMZUAQWPLWODAN5K32ZAOQ.json","view_paper":"https://pith.science/paper/3GIOPMZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.03205&json=true","fetch_graph":"https://pith.science/api/pith-number/3GIOPMZUAQWPLWODAN5K32ZAOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/3GIOPMZUAQWPLWODAN5K32ZAOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GIOPMZUAQWPLWODAN5K32ZAOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GIOPMZUAQWPLWODAN5K32ZAOQ/action/storage_attestation","attest_author":"https://pith.science/pith/3GIOPMZUAQWPLWODAN5K32ZAOQ/action/author_attestation","sign_citation":"https://pith.science/pith/3GIOPMZUAQWPLWODAN5K32ZAOQ/action/citation_signature","submit_replication":"https://pith.science/pith/3GIOPMZUAQWPLWODAN5K32ZAOQ/action/replication_record"}},"created_at":"2026-05-18T00:01:18.855229+00:00","updated_at":"2026-05-18T00:01:18.855229+00:00"}