{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NATUNNLE5VDV3PSBTWPRSPUP62","short_pith_number":"pith:NATUNNLE","schema_version":"1.0","canonical_sha256":"682746b564ed475dbe419d9f193e8ff6bb16f7ec7db2921ab12f6a2a436e9b23","source":{"kind":"arxiv","id":"2403.08294","version":1},"attestation_state":"computed","paper":{"title":"Attack Deterministic Conditional Image Generative Models for Diverse and Controllable Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haibo Chen, Huaizhong Lin, Jiafu Chen, Jiakai Sun, Lei Zhao, Tianyi Chu, Wei Xing, Zhizhong Wang","submitted_at":"2024-03-13T06:57:23Z","abstract_excerpt":"Existing generative adversarial network (GAN) based conditional image generative models typically produce fixed output for the same conditional input, which is unreasonable for highly subjective tasks, such as large-mask image inpainting or style transfer. On the other hand, GAN-based diverse image generative methods require retraining/fine-tuning the network or designing complex noise injection functions, which is computationally expensive, task-specific, or struggle to generate high-quality results. Given that many deterministic conditional image generative models have been able to produce h"},"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":"2403.08294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-13T06:57:23Z","cross_cats_sorted":[],"title_canon_sha256":"68dc187df382913143b3767ca99ed381bb78c9cdd047a5bb3134e4bc02f3da2a","abstract_canon_sha256":"1f7b0a0d5d50ea966d507509e61b1fc8c56b94c4eadf0b96f12502d4c9b59bd2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:36.851864Z","signature_b64":"miKnxmyX0VAnOQQf/9UOfv4pFukblHPR+UjolaD6kbatYbX3FV68CpAm3ysCtt3BW7bpCBo+PkLVqvN7DwW0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"682746b564ed475dbe419d9f193e8ff6bb16f7ec7db2921ab12f6a2a436e9b23","last_reissued_at":"2026-07-05T07:55:36.851367Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:36.851367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attack Deterministic Conditional Image Generative Models for Diverse and Controllable Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haibo Chen, Huaizhong Lin, Jiafu Chen, Jiakai Sun, Lei Zhao, Tianyi Chu, Wei Xing, Zhizhong Wang","submitted_at":"2024-03-13T06:57:23Z","abstract_excerpt":"Existing generative adversarial network (GAN) based conditional image generative models typically produce fixed output for the same conditional input, which is unreasonable for highly subjective tasks, such as large-mask image inpainting or style transfer. On the other hand, GAN-based diverse image generative methods require retraining/fine-tuning the network or designing complex noise injection functions, which is computationally expensive, task-specific, or struggle to generate high-quality results. Given that many deterministic conditional image generative models have been able to produce h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08294","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/2403.08294/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":"2403.08294","created_at":"2026-07-05T07:55:36.851430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.08294v1","created_at":"2026-07-05T07:55:36.851430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08294","created_at":"2026-07-05T07:55:36.851430+00:00"},{"alias_kind":"pith_short_12","alias_value":"NATUNNLE5VDV","created_at":"2026-07-05T07:55:36.851430+00:00"},{"alias_kind":"pith_short_16","alias_value":"NATUNNLE5VDV3PSB","created_at":"2026-07-05T07:55:36.851430+00:00"},{"alias_kind":"pith_short_8","alias_value":"NATUNNLE","created_at":"2026-07-05T07:55:36.851430+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/NATUNNLE5VDV3PSBTWPRSPUP62","json":"https://pith.science/pith/NATUNNLE5VDV3PSBTWPRSPUP62.json","graph_json":"https://pith.science/api/pith-number/NATUNNLE5VDV3PSBTWPRSPUP62/graph.json","events_json":"https://pith.science/api/pith-number/NATUNNLE5VDV3PSBTWPRSPUP62/events.json","paper":"https://pith.science/paper/NATUNNLE"},"agent_actions":{"view_html":"https://pith.science/pith/NATUNNLE5VDV3PSBTWPRSPUP62","download_json":"https://pith.science/pith/NATUNNLE5VDV3PSBTWPRSPUP62.json","view_paper":"https://pith.science/paper/NATUNNLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.08294&json=true","fetch_graph":"https://pith.science/api/pith-number/NATUNNLE5VDV3PSBTWPRSPUP62/graph.json","fetch_events":"https://pith.science/api/pith-number/NATUNNLE5VDV3PSBTWPRSPUP62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NATUNNLE5VDV3PSBTWPRSPUP62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NATUNNLE5VDV3PSBTWPRSPUP62/action/storage_attestation","attest_author":"https://pith.science/pith/NATUNNLE5VDV3PSBTWPRSPUP62/action/author_attestation","sign_citation":"https://pith.science/pith/NATUNNLE5VDV3PSBTWPRSPUP62/action/citation_signature","submit_replication":"https://pith.science/pith/NATUNNLE5VDV3PSBTWPRSPUP62/action/replication_record"}},"created_at":"2026-07-05T07:55:36.851430+00:00","updated_at":"2026-07-05T07:55:36.851430+00:00"}