{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KU6MWGZKJUMXHZNUFJJSQA65YV","short_pith_number":"pith:KU6MWGZK","schema_version":"1.0","canonical_sha256":"553ccb1b2a4d1973e5b42a532803ddc57cf4b5a8f53f22274ed98900d2af02e0","source":{"kind":"arxiv","id":"2501.16764","version":1},"attestation_state":"computed","paper":{"title":"DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bangbang Yang, Chenguo Lin, Panwang Pan, Yadong Mu, Zeming Li","submitted_at":"2025-01-28T07:38:59Z","abstract_excerpt":"Recent advancements in 3D content generation from text or a single image struggle with limited high-quality 3D datasets and inconsistency from 2D multi-view generation. We introduce DiffSplat, a novel 3D generative framework that natively generates 3D Gaussian splats by taming large-scale text-to-image diffusion models. It differs from previous 3D generative models by effectively utilizing web-scale 2D priors while maintaining 3D consistency in a unified model. To bootstrap the training, a lightweight reconstruction model is proposed to instantly produce multi-view Gaussian splat grids for sca"},"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":"2501.16764","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-28T07:38:59Z","cross_cats_sorted":[],"title_canon_sha256":"5feb1e2edf926de353325cc30a3219b3c6945b943762f8f7e1cc0a500e279592","abstract_canon_sha256":"a4bdd600689626b5e8b8a4ac87c89ff2e6813a8ddf73846acc7c7830f08963c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:18.208267Z","signature_b64":"tAI2nSnjCxssoRUlGfzXT2zLe4FgvmLfwrvf7oCgP0A3njfyMoIwWOW9beHodjH1Gc+lExtBUhJh9xD3u4xEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"553ccb1b2a4d1973e5b42a532803ddc57cf4b5a8f53f22274ed98900d2af02e0","last_reissued_at":"2026-07-05T10:06:18.207866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:18.207866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bangbang Yang, Chenguo Lin, Panwang Pan, Yadong Mu, Zeming Li","submitted_at":"2025-01-28T07:38:59Z","abstract_excerpt":"Recent advancements in 3D content generation from text or a single image struggle with limited high-quality 3D datasets and inconsistency from 2D multi-view generation. We introduce DiffSplat, a novel 3D generative framework that natively generates 3D Gaussian splats by taming large-scale text-to-image diffusion models. It differs from previous 3D generative models by effectively utilizing web-scale 2D priors while maintaining 3D consistency in a unified model. To bootstrap the training, a lightweight reconstruction model is proposed to instantly produce multi-view Gaussian splat grids for sca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16764","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/2501.16764/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":"2501.16764","created_at":"2026-07-05T10:06:18.207921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16764v1","created_at":"2026-07-05T10:06:18.207921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16764","created_at":"2026-07-05T10:06:18.207921+00:00"},{"alias_kind":"pith_short_12","alias_value":"KU6MWGZKJUMX","created_at":"2026-07-05T10:06:18.207921+00:00"},{"alias_kind":"pith_short_16","alias_value":"KU6MWGZKJUMXHZNU","created_at":"2026-07-05T10:06:18.207921+00:00"},{"alias_kind":"pith_short_8","alias_value":"KU6MWGZK","created_at":"2026-07-05T10:06:18.207921+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01803","citing_title":"PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2509.07435","citing_title":"DreamLifting: A Plug-in Module Lifting MV Diffusion Models for 3D Asset Generation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00503","citing_title":"Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25459","citing_title":"GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KU6MWGZKJUMXHZNUFJJSQA65YV","json":"https://pith.science/pith/KU6MWGZKJUMXHZNUFJJSQA65YV.json","graph_json":"https://pith.science/api/pith-number/KU6MWGZKJUMXHZNUFJJSQA65YV/graph.json","events_json":"https://pith.science/api/pith-number/KU6MWGZKJUMXHZNUFJJSQA65YV/events.json","paper":"https://pith.science/paper/KU6MWGZK"},"agent_actions":{"view_html":"https://pith.science/pith/KU6MWGZKJUMXHZNUFJJSQA65YV","download_json":"https://pith.science/pith/KU6MWGZKJUMXHZNUFJJSQA65YV.json","view_paper":"https://pith.science/paper/KU6MWGZK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16764&json=true","fetch_graph":"https://pith.science/api/pith-number/KU6MWGZKJUMXHZNUFJJSQA65YV/graph.json","fetch_events":"https://pith.science/api/pith-number/KU6MWGZKJUMXHZNUFJJSQA65YV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KU6MWGZKJUMXHZNUFJJSQA65YV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KU6MWGZKJUMXHZNUFJJSQA65YV/action/storage_attestation","attest_author":"https://pith.science/pith/KU6MWGZKJUMXHZNUFJJSQA65YV/action/author_attestation","sign_citation":"https://pith.science/pith/KU6MWGZKJUMXHZNUFJJSQA65YV/action/citation_signature","submit_replication":"https://pith.science/pith/KU6MWGZKJUMXHZNUFJJSQA65YV/action/replication_record"}},"created_at":"2026-07-05T10:06:18.207921+00:00","updated_at":"2026-07-05T10:06:18.207921+00:00"}