{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EXGSZZT5YV6ARBXISXMXJHQ7KA","short_pith_number":"pith:EXGSZZT5","schema_version":"1.0","canonical_sha256":"25cd2ce67dc57c0886e895d9749e1f502b435c0d0ed010e9c5a74c7f872816f7","source":{"kind":"arxiv","id":"2002.03754","version":3},"attestation_state":"computed","paper":{"title":"Unsupervised Discovery of Interpretable Directions in the GAN Latent Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrey Voynov, Artem Babenko","submitted_at":"2020-02-10T13:57:14Z","abstract_excerpt":"The latent spaces of GAN models often have semantically meaningful directions. Moving in these directions corresponds to human-interpretable image transformations, such as zooming or recoloring, enabling a more controllable generation process. However, the discovery of such directions is currently performed in a supervised manner, requiring human labels, pretrained models, or some form of self-supervision. These requirements severely restrict a range of directions existing approaches can discover. In this paper, we introduce an unsupervised method to identify interpretable directions in the la"},"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":"2002.03754","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-10T13:57:14Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"748f476529d2c1f0d8bd6a48849a701a4bfa6ea82a3f02d80dc12b75867232e9","abstract_canon_sha256":"2c00242f531ad556278aa48ec466bac01059020181e2d2a2adc1ea0b929b0144"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:09.210698Z","signature_b64":"AQ+HSdqVHq0GwU4QlL093VY2IeDXFtPTI3rs5a5TWFKS8SZXHSyLtMBjCpvl0HVsNJ6lPqXeYVWhL8dEDs84BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25cd2ce67dc57c0886e895d9749e1f502b435c0d0ed010e9c5a74c7f872816f7","last_reissued_at":"2026-07-05T01:13:09.210282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:09.210282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Discovery of Interpretable Directions in the GAN Latent Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrey Voynov, Artem Babenko","submitted_at":"2020-02-10T13:57:14Z","abstract_excerpt":"The latent spaces of GAN models often have semantically meaningful directions. Moving in these directions corresponds to human-interpretable image transformations, such as zooming or recoloring, enabling a more controllable generation process. However, the discovery of such directions is currently performed in a supervised manner, requiring human labels, pretrained models, or some form of self-supervision. These requirements severely restrict a range of directions existing approaches can discover. In this paper, we introduce an unsupervised method to identify interpretable directions in the la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03754","kind":"arxiv","version":3},"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/2002.03754/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":"2002.03754","created_at":"2026-07-05T01:13:09.210335+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.03754v3","created_at":"2026-07-05T01:13:09.210335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03754","created_at":"2026-07-05T01:13:09.210335+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXGSZZT5YV6A","created_at":"2026-07-05T01:13:09.210335+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXGSZZT5YV6ARBXI","created_at":"2026-07-05T01:13:09.210335+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXGSZZT5","created_at":"2026-07-05T01:13:09.210335+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23679","citing_title":"Semantic Browsing: Controllable Diversity for Image Generation","ref_index":125,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EXGSZZT5YV6ARBXISXMXJHQ7KA","json":"https://pith.science/pith/EXGSZZT5YV6ARBXISXMXJHQ7KA.json","graph_json":"https://pith.science/api/pith-number/EXGSZZT5YV6ARBXISXMXJHQ7KA/graph.json","events_json":"https://pith.science/api/pith-number/EXGSZZT5YV6ARBXISXMXJHQ7KA/events.json","paper":"https://pith.science/paper/EXGSZZT5"},"agent_actions":{"view_html":"https://pith.science/pith/EXGSZZT5YV6ARBXISXMXJHQ7KA","download_json":"https://pith.science/pith/EXGSZZT5YV6ARBXISXMXJHQ7KA.json","view_paper":"https://pith.science/paper/EXGSZZT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.03754&json=true","fetch_graph":"https://pith.science/api/pith-number/EXGSZZT5YV6ARBXISXMXJHQ7KA/graph.json","fetch_events":"https://pith.science/api/pith-number/EXGSZZT5YV6ARBXISXMXJHQ7KA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXGSZZT5YV6ARBXISXMXJHQ7KA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXGSZZT5YV6ARBXISXMXJHQ7KA/action/storage_attestation","attest_author":"https://pith.science/pith/EXGSZZT5YV6ARBXISXMXJHQ7KA/action/author_attestation","sign_citation":"https://pith.science/pith/EXGSZZT5YV6ARBXISXMXJHQ7KA/action/citation_signature","submit_replication":"https://pith.science/pith/EXGSZZT5YV6ARBXISXMXJHQ7KA/action/replication_record"}},"created_at":"2026-07-05T01:13:09.210335+00:00","updated_at":"2026-07-05T01:13:09.210335+00:00"}