{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CLCFFGOWFOLACEM5NZONFLVBSI","short_pith_number":"pith:CLCFFGOW","schema_version":"1.0","canonical_sha256":"12c45299d62b9601119d6e5cd2aea1922f72a410cbc3bd24665d6349fa380291","source":{"kind":"arxiv","id":"2201.02692","version":3},"attestation_state":"computed","paper":{"title":"Improved Input Reprogramming for GAN Conditioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daewon Seo, Kangwook Lee, Liang Shang, Tuan Dinh, Zhixu Du","submitted_at":"2022-01-07T22:06:47Z","abstract_excerpt":"We study the GAN conditioning problem, whose goal is to convert a pretrained unconditional GAN into a conditional GAN using labeled data. We first identify and analyze three approaches to this problem -- conditional GAN training from scratch, fine-tuning, and input reprogramming. Our analysis reveals that when the amount of labeled data is small, input reprogramming performs the best. Motivated by real-world scenarios with scarce labeled data, we focus on the input reprogramming approach and carefully analyze the existing algorithm. After identifying a few critical issues of the previous input"},"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":"2201.02692","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-07T22:06:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1bec2700f98a0aeecc1d6f2b1cbe34ca25b0feaa030140dccba39a671ecbeca5","abstract_canon_sha256":"980ddec5cc56c284e78af854589633acdcc04dc6b735f3fd64584d510eb327c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:26.743066Z","signature_b64":"g84PK0gL/0nXvcnvcTb9D/Fy0t0etPVP7ArknEklkU5HBECKRmSXpbMJZjs4H/V/kMZWfTPRfLZKKnDFFOioCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12c45299d62b9601119d6e5cd2aea1922f72a410cbc3bd24665d6349fa380291","last_reissued_at":"2026-07-05T03:54:26.742659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:26.742659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Input Reprogramming for GAN Conditioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daewon Seo, Kangwook Lee, Liang Shang, Tuan Dinh, Zhixu Du","submitted_at":"2022-01-07T22:06:47Z","abstract_excerpt":"We study the GAN conditioning problem, whose goal is to convert a pretrained unconditional GAN into a conditional GAN using labeled data. We first identify and analyze three approaches to this problem -- conditional GAN training from scratch, fine-tuning, and input reprogramming. Our analysis reveals that when the amount of labeled data is small, input reprogramming performs the best. Motivated by real-world scenarios with scarce labeled data, we focus on the input reprogramming approach and carefully analyze the existing algorithm. After identifying a few critical issues of the previous input"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02692","kind":"arxiv","version":3},"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/2201.02692/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":"2201.02692","created_at":"2026-07-05T03:54:26.742712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.02692v3","created_at":"2026-07-05T03:54:26.742712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02692","created_at":"2026-07-05T03:54:26.742712+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLCFFGOWFOLA","created_at":"2026-07-05T03:54:26.742712+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLCFFGOWFOLACEM5","created_at":"2026-07-05T03:54:26.742712+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLCFFGOW","created_at":"2026-07-05T03:54:26.742712+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/CLCFFGOWFOLACEM5NZONFLVBSI","json":"https://pith.science/pith/CLCFFGOWFOLACEM5NZONFLVBSI.json","graph_json":"https://pith.science/api/pith-number/CLCFFGOWFOLACEM5NZONFLVBSI/graph.json","events_json":"https://pith.science/api/pith-number/CLCFFGOWFOLACEM5NZONFLVBSI/events.json","paper":"https://pith.science/paper/CLCFFGOW"},"agent_actions":{"view_html":"https://pith.science/pith/CLCFFGOWFOLACEM5NZONFLVBSI","download_json":"https://pith.science/pith/CLCFFGOWFOLACEM5NZONFLVBSI.json","view_paper":"https://pith.science/paper/CLCFFGOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.02692&json=true","fetch_graph":"https://pith.science/api/pith-number/CLCFFGOWFOLACEM5NZONFLVBSI/graph.json","fetch_events":"https://pith.science/api/pith-number/CLCFFGOWFOLACEM5NZONFLVBSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLCFFGOWFOLACEM5NZONFLVBSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLCFFGOWFOLACEM5NZONFLVBSI/action/storage_attestation","attest_author":"https://pith.science/pith/CLCFFGOWFOLACEM5NZONFLVBSI/action/author_attestation","sign_citation":"https://pith.science/pith/CLCFFGOWFOLACEM5NZONFLVBSI/action/citation_signature","submit_replication":"https://pith.science/pith/CLCFFGOWFOLACEM5NZONFLVBSI/action/replication_record"}},"created_at":"2026-07-05T03:54:26.742712+00:00","updated_at":"2026-07-05T03:54:26.742712+00:00"}