{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:P2LDMZCIHAF3TZWQHHNRCIKR4R","short_pith_number":"pith:P2LDMZCI","schema_version":"1.0","canonical_sha256":"7e96366448380bb9e6d039db112151e441f121f8c7cbc21154dd520e3e97266e","source":{"kind":"arxiv","id":"2203.17272","version":2},"attestation_state":"computed","paper":{"title":"MyStyle: A Personalized Generative Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Daniel Cohen-Or, Inbar Mosseri, Kfir Aberman, Michal Yarom, Orly Liba, Qiurui He, Yael Pritch, Yossi Gandelsman, Yotam Nitzan","submitted_at":"2022-03-31T17:59:19Z","abstract_excerpt":"We introduce MyStyle, a personalized deep generative prior trained with a few shots of an individual. MyStyle allows to reconstruct, enhance and edit images of a specific person, such that the output is faithful to the person's key facial characteristics. Given a small reference set of portrait images of a person (~100), we tune the weights of a pretrained StyleGAN face generator to form a local, low-dimensional, personalized manifold in the latent space. We show that this manifold constitutes a personalized region that spans latent codes associated with diverse portrait images of the individu"},"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":"2203.17272","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-31T17:59:19Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"96e9ad11f6daf65595c69f20962a26958724d5ae331c8dca16ed9d85a95efc02","abstract_canon_sha256":"1dbd961fcfec5ddf62323e7eb169dd2ad740fef8e878d9e87f994ca76e907bb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:03.066954Z","signature_b64":"K7JVUemlaHs01g9pCIUOKEKNCBsTRGAUZjF7MKH9ltDtUxCUO4eQtQgextR15p1BFFrtl2GcOrFKxYZI/mF0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e96366448380bb9e6d039db112151e441f121f8c7cbc21154dd520e3e97266e","last_reissued_at":"2026-07-05T05:04:03.066469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:03.066469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MyStyle: A Personalized Generative Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Daniel Cohen-Or, Inbar Mosseri, Kfir Aberman, Michal Yarom, Orly Liba, Qiurui He, Yael Pritch, Yossi Gandelsman, Yotam Nitzan","submitted_at":"2022-03-31T17:59:19Z","abstract_excerpt":"We introduce MyStyle, a personalized deep generative prior trained with a few shots of an individual. MyStyle allows to reconstruct, enhance and edit images of a specific person, such that the output is faithful to the person's key facial characteristics. Given a small reference set of portrait images of a person (~100), we tune the weights of a pretrained StyleGAN face generator to form a local, low-dimensional, personalized manifold in the latent space. We show that this manifold constitutes a personalized region that spans latent codes associated with diverse portrait images of the individu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.17272","kind":"arxiv","version":2},"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/2203.17272/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":"2203.17272","created_at":"2026-07-05T05:04:03.066526+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.17272v2","created_at":"2026-07-05T05:04:03.066526+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.17272","created_at":"2026-07-05T05:04:03.066526+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2LDMZCIHAF3","created_at":"2026-07-05T05:04:03.066526+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2LDMZCIHAF3TZWQ","created_at":"2026-07-05T05:04:03.066526+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2LDMZCI","created_at":"2026-07-05T05:04:03.066526+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26515","citing_title":"Forget, Anticipate and Adapt: Test Time Training for Long Videos","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26515","citing_title":"Forget, Anticipate and Adapt: Test Time Training for Long Videos","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2302.05543","citing_title":"Adding Conditional Control to Text-to-Image Diffusion Models","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2208.01618","citing_title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2LDMZCIHAF3TZWQHHNRCIKR4R","json":"https://pith.science/pith/P2LDMZCIHAF3TZWQHHNRCIKR4R.json","graph_json":"https://pith.science/api/pith-number/P2LDMZCIHAF3TZWQHHNRCIKR4R/graph.json","events_json":"https://pith.science/api/pith-number/P2LDMZCIHAF3TZWQHHNRCIKR4R/events.json","paper":"https://pith.science/paper/P2LDMZCI"},"agent_actions":{"view_html":"https://pith.science/pith/P2LDMZCIHAF3TZWQHHNRCIKR4R","download_json":"https://pith.science/pith/P2LDMZCIHAF3TZWQHHNRCIKR4R.json","view_paper":"https://pith.science/paper/P2LDMZCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.17272&json=true","fetch_graph":"https://pith.science/api/pith-number/P2LDMZCIHAF3TZWQHHNRCIKR4R/graph.json","fetch_events":"https://pith.science/api/pith-number/P2LDMZCIHAF3TZWQHHNRCIKR4R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2LDMZCIHAF3TZWQHHNRCIKR4R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2LDMZCIHAF3TZWQHHNRCIKR4R/action/storage_attestation","attest_author":"https://pith.science/pith/P2LDMZCIHAF3TZWQHHNRCIKR4R/action/author_attestation","sign_citation":"https://pith.science/pith/P2LDMZCIHAF3TZWQHHNRCIKR4R/action/citation_signature","submit_replication":"https://pith.science/pith/P2LDMZCIHAF3TZWQHHNRCIKR4R/action/replication_record"}},"created_at":"2026-07-05T05:04:03.066526+00:00","updated_at":"2026-07-05T05:04:03.066526+00:00"}