{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:56LUWHQ6HLOF75TU2CYMJWPFCQ","short_pith_number":"pith:56LUWHQ6","schema_version":"1.0","canonical_sha256":"ef974b1e1e3adc5ff674d0b0c4d9e51400a1f95012ab9629f14340a18311ccc8","source":{"kind":"arxiv","id":"2603.26661","version":2},"attestation_state":"computed","paper":{"title":"GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Barbara R\\\"ossle, Katharina Schmid, Matthias Nie{\\ss}ner, Nicolas von L\\\"utzow","submitted_at":"2026-03-27T17:58:05Z","abstract_excerpt":"Most recent advances in 3D generative modeling rely on diffusion or flow-matching formulations. We instead explore a fully autoregressive alternative and introduce GaussianGPT, a transformer-based model that directly generates 3D Gaussians via next-token prediction, thus facilitating full 3D scene generation. We first compress Gaussian primitives into a discrete latent grid using a sparse 3D convolutional autoencoder with vector quantization. The resulting tokens are serialized and modeled using a causal transformer with 3D rotary positional embedding, enabling sequential generation of spatial"},"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":"2603.26661","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-27T17:58:05Z","cross_cats_sorted":[],"title_canon_sha256":"f3e979c7804b87c04ccafe9c285434c95346653ca0dae11f8393695734048caf","abstract_canon_sha256":"5b9c96c44adf6ae3db3131cfa1ddda179fcd25a9b7b5cc3b1712f58c36de1fe3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:07.702798Z","signature_b64":"HzGFOg4nmuMoVjwCU6n8TTKRETGURf/B1sRLfgoSuYp8PWOTzKqrOyG9j23zkHmR4QEbQ4VqoCrXSWDsUnrpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef974b1e1e3adc5ff674d0b0c4d9e51400a1f95012ab9629f14340a18311ccc8","last_reissued_at":"2026-07-02T01:18:07.702283Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:07.702283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Barbara R\\\"ossle, Katharina Schmid, Matthias Nie{\\ss}ner, Nicolas von L\\\"utzow","submitted_at":"2026-03-27T17:58:05Z","abstract_excerpt":"Most recent advances in 3D generative modeling rely on diffusion or flow-matching formulations. We instead explore a fully autoregressive alternative and introduce GaussianGPT, a transformer-based model that directly generates 3D Gaussians via next-token prediction, thus facilitating full 3D scene generation. We first compress Gaussian primitives into a discrete latent grid using a sparse 3D convolutional autoencoder with vector quantization. The resulting tokens are serialized and modeled using a causal transformer with 3D rotary positional embedding, enabling sequential generation of spatial"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.26661","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/2603.26661/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":"2603.26661","created_at":"2026-07-02T01:18:07.702378+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.26661v2","created_at":"2026-07-02T01:18:07.702378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.26661","created_at":"2026-07-02T01:18:07.702378+00:00"},{"alias_kind":"pith_short_12","alias_value":"56LUWHQ6HLOF","created_at":"2026-07-02T01:18:07.702378+00:00"},{"alias_kind":"pith_short_16","alias_value":"56LUWHQ6HLOF75TU","created_at":"2026-07-02T01:18:07.702378+00:00"},{"alias_kind":"pith_short_8","alias_value":"56LUWHQ6","created_at":"2026-07-02T01:18:07.702378+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.26182","citing_title":"BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenization","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/56LUWHQ6HLOF75TU2CYMJWPFCQ","json":"https://pith.science/pith/56LUWHQ6HLOF75TU2CYMJWPFCQ.json","graph_json":"https://pith.science/api/pith-number/56LUWHQ6HLOF75TU2CYMJWPFCQ/graph.json","events_json":"https://pith.science/api/pith-number/56LUWHQ6HLOF75TU2CYMJWPFCQ/events.json","paper":"https://pith.science/paper/56LUWHQ6"},"agent_actions":{"view_html":"https://pith.science/pith/56LUWHQ6HLOF75TU2CYMJWPFCQ","download_json":"https://pith.science/pith/56LUWHQ6HLOF75TU2CYMJWPFCQ.json","view_paper":"https://pith.science/paper/56LUWHQ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.26661&json=true","fetch_graph":"https://pith.science/api/pith-number/56LUWHQ6HLOF75TU2CYMJWPFCQ/graph.json","fetch_events":"https://pith.science/api/pith-number/56LUWHQ6HLOF75TU2CYMJWPFCQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/56LUWHQ6HLOF75TU2CYMJWPFCQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/56LUWHQ6HLOF75TU2CYMJWPFCQ/action/storage_attestation","attest_author":"https://pith.science/pith/56LUWHQ6HLOF75TU2CYMJWPFCQ/action/author_attestation","sign_citation":"https://pith.science/pith/56LUWHQ6HLOF75TU2CYMJWPFCQ/action/citation_signature","submit_replication":"https://pith.science/pith/56LUWHQ6HLOF75TU2CYMJWPFCQ/action/replication_record"}},"created_at":"2026-07-02T01:18:07.702378+00:00","updated_at":"2026-07-02T01:18:07.702378+00:00"}