{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B4TRNBLFLBMX2T5S3L5FSFC4QO","short_pith_number":"pith:B4TRNBLF","schema_version":"1.0","canonical_sha256":"0f2716856558597d4fb2dafa59145c838a81e76b712c57a051387f47a5d558cf","source":{"kind":"arxiv","id":"2110.08718","version":1},"attestation_state":"computed","paper":{"title":"AE-StyleGAN: Improved Training of Style-Based Auto-Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Dimitris Metaxas, Ligong Han, Martin Renqiang Min, Ruijiang Gao, Sri Harsha Musunuri, Yu Tian","submitted_at":"2021-10-17T04:25:51Z","abstract_excerpt":"StyleGANs have shown impressive results on data generation and manipulation in recent years, thanks to its disentangled style latent space. A lot of efforts have been made in inverting a pretrained generator, where an encoder is trained ad hoc after the generator is trained in a two-stage fashion. In this paper, we focus on style-based generators asking a scientific question: Does forcing such a generator to reconstruct real data lead to more disentangled latent space and make the inversion process from image to latent space easy? We describe a new methodology to train a style-based autoencode"},"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":"2110.08718","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-17T04:25:51Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"64dc3141678be36bd37617c7f4d584f1be942fc870ffc82d36716479d0d9987d","abstract_canon_sha256":"6065df0c5c06614b6d680a8335312ab325d7aa8b33182a2334250881561ebf64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:19.766231Z","signature_b64":"Oeyf4bESkco4QnANsdT8NcHa4W8trzSlN8HBxWZ5KM8jb949qFKQIp+NqC2EFpVLh0CbKZYDGsGkqJhlA3ADBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f2716856558597d4fb2dafa59145c838a81e76b712c57a051387f47a5d558cf","last_reissued_at":"2026-07-05T03:23:19.765841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:19.765841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AE-StyleGAN: Improved Training of Style-Based Auto-Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Dimitris Metaxas, Ligong Han, Martin Renqiang Min, Ruijiang Gao, Sri Harsha Musunuri, Yu Tian","submitted_at":"2021-10-17T04:25:51Z","abstract_excerpt":"StyleGANs have shown impressive results on data generation and manipulation in recent years, thanks to its disentangled style latent space. A lot of efforts have been made in inverting a pretrained generator, where an encoder is trained ad hoc after the generator is trained in a two-stage fashion. In this paper, we focus on style-based generators asking a scientific question: Does forcing such a generator to reconstruct real data lead to more disentangled latent space and make the inversion process from image to latent space easy? We describe a new methodology to train a style-based autoencode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08718","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/2110.08718/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":"2110.08718","created_at":"2026-07-05T03:23:19.765897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.08718v1","created_at":"2026-07-05T03:23:19.765897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08718","created_at":"2026-07-05T03:23:19.765897+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4TRNBLFLBMX","created_at":"2026-07-05T03:23:19.765897+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4TRNBLFLBMX2T5S","created_at":"2026-07-05T03:23:19.765897+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4TRNBLF","created_at":"2026-07-05T03:23:19.765897+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/B4TRNBLFLBMX2T5S3L5FSFC4QO","json":"https://pith.science/pith/B4TRNBLFLBMX2T5S3L5FSFC4QO.json","graph_json":"https://pith.science/api/pith-number/B4TRNBLFLBMX2T5S3L5FSFC4QO/graph.json","events_json":"https://pith.science/api/pith-number/B4TRNBLFLBMX2T5S3L5FSFC4QO/events.json","paper":"https://pith.science/paper/B4TRNBLF"},"agent_actions":{"view_html":"https://pith.science/pith/B4TRNBLFLBMX2T5S3L5FSFC4QO","download_json":"https://pith.science/pith/B4TRNBLFLBMX2T5S3L5FSFC4QO.json","view_paper":"https://pith.science/paper/B4TRNBLF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.08718&json=true","fetch_graph":"https://pith.science/api/pith-number/B4TRNBLFLBMX2T5S3L5FSFC4QO/graph.json","fetch_events":"https://pith.science/api/pith-number/B4TRNBLFLBMX2T5S3L5FSFC4QO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4TRNBLFLBMX2T5S3L5FSFC4QO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4TRNBLFLBMX2T5S3L5FSFC4QO/action/storage_attestation","attest_author":"https://pith.science/pith/B4TRNBLFLBMX2T5S3L5FSFC4QO/action/author_attestation","sign_citation":"https://pith.science/pith/B4TRNBLFLBMX2T5S3L5FSFC4QO/action/citation_signature","submit_replication":"https://pith.science/pith/B4TRNBLFLBMX2T5S3L5FSFC4QO/action/replication_record"}},"created_at":"2026-07-05T03:23:19.765897+00:00","updated_at":"2026-07-05T03:23:19.765897+00:00"}