{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MWDNFZPWLD2OICFD3JJ4S4FJAQ","short_pith_number":"pith:MWDNFZPW","schema_version":"1.0","canonical_sha256":"6586d2e5f658f4e408a3da53c970a90407ae3194c12893260db4de1bb8d3f277","source":{"kind":"arxiv","id":"2302.12464","version":1},"attestation_state":"computed","paper":{"title":"RGI: robust GAN-inversion for mask-free image inpainting and unsupervised pixel-wise anomaly detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Haoping Bai, Jianjun Shi, Jiulong Shan, Meng Cao, Ping Huang, Shancong Mou, Xiaoyi Gu","submitted_at":"2023-02-24T05:43:03Z","abstract_excerpt":"Generative adversarial networks (GANs), trained on a large-scale image dataset, can be a good approximator of the natural image manifold. GAN-inversion, using a pre-trained generator as a deep generative prior, is a promising tool for image restoration under corruptions. However, the performance of GAN-inversion can be limited by a lack of robustness to unknown gross corruptions, i.e., the restored image might easily deviate from the ground truth. In this paper, we propose a Robust GAN-inversion (RGI) method with a provable robustness guarantee to achieve image restoration under unknown \\texti"},"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":"2302.12464","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-24T05:43:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5c6c56e1acadc1d8870a184534043c69f5a528f6721491ee32270984f834e8ee","abstract_canon_sha256":"2c2d2f5e145fda6dbfa24424162761d8b411b61d8f0bf412caf15dcd063aa653"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:10.184659Z","signature_b64":"PJsAAWjP27GeT+4QkffaYzi+kKqWh1Lp/OVjB0vezwO2yhqFvhE+In3tBKhhjSDgimcHiCK8AsjY9074VPLtBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6586d2e5f658f4e408a3da53c970a90407ae3194c12893260db4de1bb8d3f277","last_reissued_at":"2026-07-05T05:45:10.184071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:10.184071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RGI: robust GAN-inversion for mask-free image inpainting and unsupervised pixel-wise anomaly detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Haoping Bai, Jianjun Shi, Jiulong Shan, Meng Cao, Ping Huang, Shancong Mou, Xiaoyi Gu","submitted_at":"2023-02-24T05:43:03Z","abstract_excerpt":"Generative adversarial networks (GANs), trained on a large-scale image dataset, can be a good approximator of the natural image manifold. GAN-inversion, using a pre-trained generator as a deep generative prior, is a promising tool for image restoration under corruptions. However, the performance of GAN-inversion can be limited by a lack of robustness to unknown gross corruptions, i.e., the restored image might easily deviate from the ground truth. In this paper, we propose a Robust GAN-inversion (RGI) method with a provable robustness guarantee to achieve image restoration under unknown \\texti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12464","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/2302.12464/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":"2302.12464","created_at":"2026-07-05T05:45:10.184135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.12464v1","created_at":"2026-07-05T05:45:10.184135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12464","created_at":"2026-07-05T05:45:10.184135+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWDNFZPWLD2O","created_at":"2026-07-05T05:45:10.184135+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWDNFZPWLD2OICFD","created_at":"2026-07-05T05:45:10.184135+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWDNFZPW","created_at":"2026-07-05T05:45:10.184135+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/MWDNFZPWLD2OICFD3JJ4S4FJAQ","json":"https://pith.science/pith/MWDNFZPWLD2OICFD3JJ4S4FJAQ.json","graph_json":"https://pith.science/api/pith-number/MWDNFZPWLD2OICFD3JJ4S4FJAQ/graph.json","events_json":"https://pith.science/api/pith-number/MWDNFZPWLD2OICFD3JJ4S4FJAQ/events.json","paper":"https://pith.science/paper/MWDNFZPW"},"agent_actions":{"view_html":"https://pith.science/pith/MWDNFZPWLD2OICFD3JJ4S4FJAQ","download_json":"https://pith.science/pith/MWDNFZPWLD2OICFD3JJ4S4FJAQ.json","view_paper":"https://pith.science/paper/MWDNFZPW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.12464&json=true","fetch_graph":"https://pith.science/api/pith-number/MWDNFZPWLD2OICFD3JJ4S4FJAQ/graph.json","fetch_events":"https://pith.science/api/pith-number/MWDNFZPWLD2OICFD3JJ4S4FJAQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWDNFZPWLD2OICFD3JJ4S4FJAQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWDNFZPWLD2OICFD3JJ4S4FJAQ/action/storage_attestation","attest_author":"https://pith.science/pith/MWDNFZPWLD2OICFD3JJ4S4FJAQ/action/author_attestation","sign_citation":"https://pith.science/pith/MWDNFZPWLD2OICFD3JJ4S4FJAQ/action/citation_signature","submit_replication":"https://pith.science/pith/MWDNFZPWLD2OICFD3JJ4S4FJAQ/action/replication_record"}},"created_at":"2026-07-05T05:45:10.184135+00:00","updated_at":"2026-07-05T05:45:10.184135+00:00"}