{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:42N4MLP5F227GXNCDX733KEWNZ","short_pith_number":"pith:42N4MLP5","schema_version":"1.0","canonical_sha256":"e69bc62dfd2eb5f35da21dffbda8966e6ffa145e11363cdf3788816951ab4e9c","source":{"kind":"arxiv","id":"2406.02968","version":2},"attestation_state":"computed","paper":{"title":"GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian Splats","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jae-Pil Heo, Sangeek Hyun","submitted_at":"2024-06-05T05:52:20Z","abstract_excerpt":"Most advances in 3D Generative Adversarial Networks (3D GANs) largely depend on ray casting-based volume rendering, which incurs demanding rendering costs. One promising alternative is rasterization-based 3D Gaussian Splatting (3D-GS), providing a much faster rendering speed and explicit 3D representation. In this paper, we exploit Gaussian as a 3D representation for 3D GANs by leveraging its efficient and explicit characteristics. However, in an adversarial framework, we observe that a na\\\"ive generator architecture suffers from training instability and lacks the capability to adjust the scal"},"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":"2406.02968","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T05:52:20Z","cross_cats_sorted":[],"title_canon_sha256":"5617ddf5d3e92f3a2d2f0babd53e5cae155651274d45d9cba5589ae9a6c6eb21","abstract_canon_sha256":"a445763bcba56bfc624bbfedbf6816f7cca16d909f8be8fe05a6de4c4fbe5f41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:49.706783Z","signature_b64":"ds2niIcGC/AtGoisLqYpQB7upZKI7L4HuH02nU3dPIC62vfLA4IDpUY7dXKtU60K9WZlEjAciAninjKFlqYkAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e69bc62dfd2eb5f35da21dffbda8966e6ffa145e11363cdf3788816951ab4e9c","last_reissued_at":"2026-07-05T09:35:49.706282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:49.706282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian Splats","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jae-Pil Heo, Sangeek Hyun","submitted_at":"2024-06-05T05:52:20Z","abstract_excerpt":"Most advances in 3D Generative Adversarial Networks (3D GANs) largely depend on ray casting-based volume rendering, which incurs demanding rendering costs. One promising alternative is rasterization-based 3D Gaussian Splatting (3D-GS), providing a much faster rendering speed and explicit 3D representation. In this paper, we exploit Gaussian as a 3D representation for 3D GANs by leveraging its efficient and explicit characteristics. However, in an adversarial framework, we observe that a na\\\"ive generator architecture suffers from training instability and lacks the capability to adjust the scal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02968","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/2406.02968/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":"2406.02968","created_at":"2026-07-05T09:35:49.706360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02968v2","created_at":"2026-07-05T09:35:49.706360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02968","created_at":"2026-07-05T09:35:49.706360+00:00"},{"alias_kind":"pith_short_12","alias_value":"42N4MLP5F227","created_at":"2026-07-05T09:35:49.706360+00:00"},{"alias_kind":"pith_short_16","alias_value":"42N4MLP5F227GXNC","created_at":"2026-07-05T09:35:49.706360+00:00"},{"alias_kind":"pith_short_8","alias_value":"42N4MLP5","created_at":"2026-07-05T09:35:49.706360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14015","citing_title":"Disentangling 3D from Large Vision-Language Models for Controlled Portrait Generation","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/42N4MLP5F227GXNCDX733KEWNZ","json":"https://pith.science/pith/42N4MLP5F227GXNCDX733KEWNZ.json","graph_json":"https://pith.science/api/pith-number/42N4MLP5F227GXNCDX733KEWNZ/graph.json","events_json":"https://pith.science/api/pith-number/42N4MLP5F227GXNCDX733KEWNZ/events.json","paper":"https://pith.science/paper/42N4MLP5"},"agent_actions":{"view_html":"https://pith.science/pith/42N4MLP5F227GXNCDX733KEWNZ","download_json":"https://pith.science/pith/42N4MLP5F227GXNCDX733KEWNZ.json","view_paper":"https://pith.science/paper/42N4MLP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02968&json=true","fetch_graph":"https://pith.science/api/pith-number/42N4MLP5F227GXNCDX733KEWNZ/graph.json","fetch_events":"https://pith.science/api/pith-number/42N4MLP5F227GXNCDX733KEWNZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42N4MLP5F227GXNCDX733KEWNZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42N4MLP5F227GXNCDX733KEWNZ/action/storage_attestation","attest_author":"https://pith.science/pith/42N4MLP5F227GXNCDX733KEWNZ/action/author_attestation","sign_citation":"https://pith.science/pith/42N4MLP5F227GXNCDX733KEWNZ/action/citation_signature","submit_replication":"https://pith.science/pith/42N4MLP5F227GXNCDX733KEWNZ/action/replication_record"}},"created_at":"2026-07-05T09:35:49.706360+00:00","updated_at":"2026-07-05T09:35:49.706360+00:00"}