{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:J76XVN2WWC6RUHWQ7GRVAEJJET","short_pith_number":"pith:J76XVN2W","schema_version":"1.0","canonical_sha256":"4ffd7ab756b0bd1a1ed0f9a350112924ccf5c41d06b78ef66074df75c0c9b978","source":{"kind":"arxiv","id":"2102.02766","version":1},"attestation_state":"computed","paper":{"title":"Designing an Encoder for StyleGAN Image Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Cohen-Or, Omer Tov, Or Patashnik, Yotam Nitzan, Yuval Alaluf","submitted_at":"2021-02-04T17:52:38Z","abstract_excerpt":"Recently, there has been a surge of diverse methods for performing image editing by employing pre-trained unconditional generators. Applying these methods on real images, however, remains a challenge, as it necessarily requires the inversion of the images into their latent space. To successfully invert a real image, one needs to find a latent code that reconstructs the input image accurately, and more importantly, allows for its meaningful manipulation. In this paper, we carefully study the latent space of StyleGAN, the state-of-the-art unconditional generator. We identify and analyze the exis"},"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":"2102.02766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-04T17:52:38Z","cross_cats_sorted":[],"title_canon_sha256":"3bf1f88284858d3596d46cd5ab16ad2a1e6bd2eb92cde426e1cf51261abe9868","abstract_canon_sha256":"d4de695b4e765bc2ef8497ff86a506ccb41867bae4296d5d361fcdadf2e22dff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:12:51.344308Z","signature_b64":"AdQ+5qYFLW7greB8os2/N/KrAWQLyrHypuIqLd6HFBqQotV17w2lClxDJsrMYVY6Ba4f01sB8WjQOG/Z3moUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ffd7ab756b0bd1a1ed0f9a350112924ccf5c41d06b78ef66074df75c0c9b978","last_reissued_at":"2026-07-05T02:12:51.343936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:12:51.343936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Designing an Encoder for StyleGAN Image Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Cohen-Or, Omer Tov, Or Patashnik, Yotam Nitzan, Yuval Alaluf","submitted_at":"2021-02-04T17:52:38Z","abstract_excerpt":"Recently, there has been a surge of diverse methods for performing image editing by employing pre-trained unconditional generators. Applying these methods on real images, however, remains a challenge, as it necessarily requires the inversion of the images into their latent space. To successfully invert a real image, one needs to find a latent code that reconstructs the input image accurately, and more importantly, allows for its meaningful manipulation. In this paper, we carefully study the latent space of StyleGAN, the state-of-the-art unconditional generator. We identify and analyze the exis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02766","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/2102.02766/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":"2102.02766","created_at":"2026-07-05T02:12:51.343987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.02766v1","created_at":"2026-07-05T02:12:51.343987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02766","created_at":"2026-07-05T02:12:51.343987+00:00"},{"alias_kind":"pith_short_12","alias_value":"J76XVN2WWC6R","created_at":"2026-07-05T02:12:51.343987+00:00"},{"alias_kind":"pith_short_16","alias_value":"J76XVN2WWC6RUHWQ","created_at":"2026-07-05T02:12:51.343987+00:00"},{"alias_kind":"pith_short_8","alias_value":"J76XVN2W","created_at":"2026-07-05T02:12:51.343987+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23679","citing_title":"Semantic Browsing: Controllable Diversity for Image Generation","ref_index":132,"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":31,"is_internal_anchor":false},{"citing_arxiv_id":"2208.01626","citing_title":"Prompt-to-Prompt Image Editing with Cross Attention Control","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J76XVN2WWC6RUHWQ7GRVAEJJET","json":"https://pith.science/pith/J76XVN2WWC6RUHWQ7GRVAEJJET.json","graph_json":"https://pith.science/api/pith-number/J76XVN2WWC6RUHWQ7GRVAEJJET/graph.json","events_json":"https://pith.science/api/pith-number/J76XVN2WWC6RUHWQ7GRVAEJJET/events.json","paper":"https://pith.science/paper/J76XVN2W"},"agent_actions":{"view_html":"https://pith.science/pith/J76XVN2WWC6RUHWQ7GRVAEJJET","download_json":"https://pith.science/pith/J76XVN2WWC6RUHWQ7GRVAEJJET.json","view_paper":"https://pith.science/paper/J76XVN2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.02766&json=true","fetch_graph":"https://pith.science/api/pith-number/J76XVN2WWC6RUHWQ7GRVAEJJET/graph.json","fetch_events":"https://pith.science/api/pith-number/J76XVN2WWC6RUHWQ7GRVAEJJET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J76XVN2WWC6RUHWQ7GRVAEJJET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J76XVN2WWC6RUHWQ7GRVAEJJET/action/storage_attestation","attest_author":"https://pith.science/pith/J76XVN2WWC6RUHWQ7GRVAEJJET/action/author_attestation","sign_citation":"https://pith.science/pith/J76XVN2WWC6RUHWQ7GRVAEJJET/action/citation_signature","submit_replication":"https://pith.science/pith/J76XVN2WWC6RUHWQ7GRVAEJJET/action/replication_record"}},"created_at":"2026-07-05T02:12:51.343987+00:00","updated_at":"2026-07-05T02:12:51.343987+00:00"}