{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZFKR5QADZMDOJ37IPLAF3BWS6E","short_pith_number":"pith:ZFKR5QAD","schema_version":"1.0","canonical_sha256":"c9551ec003cb06e4efe87ac05d86d2f13ee90f6b167367331e0a5bccb13ba858","source":{"kind":"arxiv","id":"1705.02894","version":2},"attestation_state":"computed","paper":{"title":"Geometric GAN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.AI","cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Jae Hyun Lim, Jong Chul Ye","submitted_at":"2017-05-08T14:32:33Z","abstract_excerpt":"Generative Adversarial Nets (GANs) represent an important milestone for effective generative models, which has inspired numerous variants seemingly different from each other. One of the main contributions of this paper is to reveal a unified geometric structure in GAN and its variants. Specifically, we show that the adversarial generative model training can be decomposed into three geometric steps: separating hyperplane search, discriminator parameter update away from the separating hyperplane, and the generator update along the normal vector direction of the separating hyperplane. This geomet"},"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":"1705.02894","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-08T14:32:33Z","cross_cats_sorted":["cond-mat.dis-nn","cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"bc7c17b1a3b4d8ef03a6a76b98c80f8801e68f67b623c74c0909630fdc0ff6df","abstract_canon_sha256":"13c38e0d5f1b0921cb3c5e1babf483c402426ac1f2039aa3e89351b036ea4848"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:50.928570Z","signature_b64":"bfSGjMh+tK9O22uXL2im0LJjz6/lSnekvizjqqw8yBuOsQ2PBCacE3W+wHplSTq/6BHHAPDeXDnJa/Xe4yjJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9551ec003cb06e4efe87ac05d86d2f13ee90f6b167367331e0a5bccb13ba858","last_reissued_at":"2026-05-18T00:44:50.927905Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:50.927905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometric GAN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.AI","cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Jae Hyun Lim, Jong Chul Ye","submitted_at":"2017-05-08T14:32:33Z","abstract_excerpt":"Generative Adversarial Nets (GANs) represent an important milestone for effective generative models, which has inspired numerous variants seemingly different from each other. One of the main contributions of this paper is to reveal a unified geometric structure in GAN and its variants. Specifically, we show that the adversarial generative model training can be decomposed into three geometric steps: separating hyperplane search, discriminator parameter update away from the separating hyperplane, and the generator update along the normal vector direction of the separating hyperplane. This geomet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.02894","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":""},"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":"1705.02894","created_at":"2026-05-18T00:44:50.928008+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.02894v2","created_at":"2026-05-18T00:44:50.928008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.02894","created_at":"2026-05-18T00:44:50.928008+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFKR5QADZMDO","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFKR5QADZMDOJ37I","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFKR5QAD","created_at":"2026-05-18T12:31:59.375834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"1906.11080","citing_title":"AGAN: Towards Automated Design of Generative Adversarial Networks","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06143","citing_title":"Neural Embedding for Physical Manipulations","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01273","citing_title":"Learning Stratigraphically Consistent Relative Geologic Time from 3D Seismic Data via Sinusoidal Mapping","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17605","citing_title":"Venom: A PyTorch Generative Modeling Toolkit","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15284","citing_title":"Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.01929","citing_title":"Woosh: A Sound Effects Foundation Model","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"1809.11096","citing_title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04904","citing_title":"Exploring Clustering Capability of Inpainting Model Embeddings for Pattern-based Individual Identification","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01273","citing_title":"Learning Stratigraphically Consistent Relative Geologic Time from 3D Seismic Data via Sinusoidal Mapping","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11521","citing_title":"Continuous Adversarial Flow Models","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07495","citing_title":"Lightweight Unpaired Smartphone ISP Transfer with Semantic Pseudo-Pairing","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFKR5QADZMDOJ37IPLAF3BWS6E","json":"https://pith.science/pith/ZFKR5QADZMDOJ37IPLAF3BWS6E.json","graph_json":"https://pith.science/api/pith-number/ZFKR5QADZMDOJ37IPLAF3BWS6E/graph.json","events_json":"https://pith.science/api/pith-number/ZFKR5QADZMDOJ37IPLAF3BWS6E/events.json","paper":"https://pith.science/paper/ZFKR5QAD"},"agent_actions":{"view_html":"https://pith.science/pith/ZFKR5QADZMDOJ37IPLAF3BWS6E","download_json":"https://pith.science/pith/ZFKR5QADZMDOJ37IPLAF3BWS6E.json","view_paper":"https://pith.science/paper/ZFKR5QAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.02894&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFKR5QADZMDOJ37IPLAF3BWS6E/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFKR5QADZMDOJ37IPLAF3BWS6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFKR5QADZMDOJ37IPLAF3BWS6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFKR5QADZMDOJ37IPLAF3BWS6E/action/storage_attestation","attest_author":"https://pith.science/pith/ZFKR5QADZMDOJ37IPLAF3BWS6E/action/author_attestation","sign_citation":"https://pith.science/pith/ZFKR5QADZMDOJ37IPLAF3BWS6E/action/citation_signature","submit_replication":"https://pith.science/pith/ZFKR5QADZMDOJ37IPLAF3BWS6E/action/replication_record"}},"created_at":"2026-05-18T00:44:50.928008+00:00","updated_at":"2026-05-18T00:44:50.928008+00:00"}