{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5GWNH7XD46PZSC7MS25OZUNNPU","short_pith_number":"pith:5GWNH7XD","schema_version":"1.0","canonical_sha256":"e9acd3fee3e79f990bec96baecd1ad7d32f9bde25f27b3de5133750969027b31","source":{"kind":"arxiv","id":"2307.08319","version":1},"attestation_state":"computed","paper":{"title":"Soft Curriculum for Learning Conditional GANs with Noisy-Labeled and Uncurated Unlabeled Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Duc Minh Vo, Hideki Nakayama, Kai Katsumata, Tatsuya Harada","submitted_at":"2023-07-17T08:31:59Z","abstract_excerpt":"Label-noise or curated unlabeled data is used to compensate for the assumption of clean labeled data in training the conditional generative adversarial network; however, satisfying such an extended assumption is occasionally laborious or impractical. As a step towards generative modeling accessible to everyone, we introduce a novel conditional image generation framework that accepts noisy-labeled and uncurated unlabeled data during training: (i) closed-set and open-set label noise in labeled data and (ii) closed-set and open-set unlabeled data. To combat it, we propose soft curriculum learning"},"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":"2307.08319","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-17T08:31:59Z","cross_cats_sorted":[],"title_canon_sha256":"3347fae1c07628c254c4805a5863ec7aa8914862625cc3f13b77394b2af1893d","abstract_canon_sha256":"8757c0cc7ae6c561634f67f9cf7e0483d96f1eb47750b13525fbd2bbb6324d37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:23.087653Z","signature_b64":"aTLTnkqxBgEUKTMh+ujcsZoCajLGdXuut264bs0xp1w7cla0DggFTtp8mFPWIvQ58P9wAEi/ED/EObor2ZN3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9acd3fee3e79f990bec96baecd1ad7d32f9bde25f27b3de5133750969027b31","last_reissued_at":"2026-07-05T06:31:23.087231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:23.087231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Soft Curriculum for Learning Conditional GANs with Noisy-Labeled and Uncurated Unlabeled Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Duc Minh Vo, Hideki Nakayama, Kai Katsumata, Tatsuya Harada","submitted_at":"2023-07-17T08:31:59Z","abstract_excerpt":"Label-noise or curated unlabeled data is used to compensate for the assumption of clean labeled data in training the conditional generative adversarial network; however, satisfying such an extended assumption is occasionally laborious or impractical. As a step towards generative modeling accessible to everyone, we introduce a novel conditional image generation framework that accepts noisy-labeled and uncurated unlabeled data during training: (i) closed-set and open-set label noise in labeled data and (ii) closed-set and open-set unlabeled data. To combat it, we propose soft curriculum learning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08319","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.08319/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":"2307.08319","created_at":"2026-07-05T06:31:23.087286+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.08319v1","created_at":"2026-07-05T06:31:23.087286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08319","created_at":"2026-07-05T06:31:23.087286+00:00"},{"alias_kind":"pith_short_12","alias_value":"5GWNH7XD46PZ","created_at":"2026-07-05T06:31:23.087286+00:00"},{"alias_kind":"pith_short_16","alias_value":"5GWNH7XD46PZSC7M","created_at":"2026-07-05T06:31:23.087286+00:00"},{"alias_kind":"pith_short_8","alias_value":"5GWNH7XD","created_at":"2026-07-05T06:31:23.087286+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/5GWNH7XD46PZSC7MS25OZUNNPU","json":"https://pith.science/pith/5GWNH7XD46PZSC7MS25OZUNNPU.json","graph_json":"https://pith.science/api/pith-number/5GWNH7XD46PZSC7MS25OZUNNPU/graph.json","events_json":"https://pith.science/api/pith-number/5GWNH7XD46PZSC7MS25OZUNNPU/events.json","paper":"https://pith.science/paper/5GWNH7XD"},"agent_actions":{"view_html":"https://pith.science/pith/5GWNH7XD46PZSC7MS25OZUNNPU","download_json":"https://pith.science/pith/5GWNH7XD46PZSC7MS25OZUNNPU.json","view_paper":"https://pith.science/paper/5GWNH7XD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.08319&json=true","fetch_graph":"https://pith.science/api/pith-number/5GWNH7XD46PZSC7MS25OZUNNPU/graph.json","fetch_events":"https://pith.science/api/pith-number/5GWNH7XD46PZSC7MS25OZUNNPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5GWNH7XD46PZSC7MS25OZUNNPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5GWNH7XD46PZSC7MS25OZUNNPU/action/storage_attestation","attest_author":"https://pith.science/pith/5GWNH7XD46PZSC7MS25OZUNNPU/action/author_attestation","sign_citation":"https://pith.science/pith/5GWNH7XD46PZSC7MS25OZUNNPU/action/citation_signature","submit_replication":"https://pith.science/pith/5GWNH7XD46PZSC7MS25OZUNNPU/action/replication_record"}},"created_at":"2026-07-05T06:31:23.087286+00:00","updated_at":"2026-07-05T06:31:23.087286+00:00"}