{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OFYJAR3ZRGE4YIMCJ5VW7MQY7I","short_pith_number":"pith:OFYJAR3Z","schema_version":"1.0","canonical_sha256":"71709047798989cc21824f6b6fb218fa2019ce401213f1af36db8b9c5e36e29f","source":{"kind":"arxiv","id":"2408.10906","version":2},"attestation_state":"computed","paper":{"title":"ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Ren, Danda Pani Paudel, Ender Konukoglu, Luc Van Gool, Nicu Sebe, Qi Ma, Theo Gevers, Yue Li","submitted_at":"2024-08-20T14:49:14Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has become the de facto method of 3D representation in many vision tasks. This calls for the 3D understanding directly in this representation space. To facilitate the research in this direction, we first build ShapeSplat, a large-scale dataset of 3DGS using the commonly used ShapeNet, ModelNet and Objaverse datasets. Our dataset ShapeSplat consists of 206K objects spanning over 87 unique categories, whose labels are in accordance with the respective datasets. The creation of this dataset utilized the compute equivalent of 3.8 GPU years on a TITAN XP GPU.\n  We utili"},"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":"2408.10906","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-20T14:49:14Z","cross_cats_sorted":[],"title_canon_sha256":"df6a7dbef56f41924a7439ff8417e79654d5ba6f0ef220cab077c9437f09e32b","abstract_canon_sha256":"c9550dda956910b117a00af2e425c58f5b8efdc7a51c655fe4fe758e3f3951c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:01.136808Z","signature_b64":"pK68mmaWyBgkc8ZS3GWFQ1sfWgvwDtmYjIt2B2pMW53PjTjJ/mByIsiqTsd/WRKx+MhOLj9SuCFP5wU7zO8NCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71709047798989cc21824f6b6fb218fa2019ce401213f1af36db8b9c5e36e29f","last_reissued_at":"2026-07-05T12:06:01.136349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:01.136349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Ren, Danda Pani Paudel, Ender Konukoglu, Luc Van Gool, Nicu Sebe, Qi Ma, Theo Gevers, Yue Li","submitted_at":"2024-08-20T14:49:14Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has become the de facto method of 3D representation in many vision tasks. This calls for the 3D understanding directly in this representation space. To facilitate the research in this direction, we first build ShapeSplat, a large-scale dataset of 3DGS using the commonly used ShapeNet, ModelNet and Objaverse datasets. Our dataset ShapeSplat consists of 206K objects spanning over 87 unique categories, whose labels are in accordance with the respective datasets. The creation of this dataset utilized the compute equivalent of 3.8 GPU years on a TITAN XP GPU.\n  We utili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10906","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/2408.10906/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":"2408.10906","created_at":"2026-07-05T12:06:01.136410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10906v2","created_at":"2026-07-05T12:06:01.136410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10906","created_at":"2026-07-05T12:06:01.136410+00:00"},{"alias_kind":"pith_short_12","alias_value":"OFYJAR3ZRGE4","created_at":"2026-07-05T12:06:01.136410+00:00"},{"alias_kind":"pith_short_16","alias_value":"OFYJAR3ZRGE4YIMC","created_at":"2026-07-05T12:06:01.136410+00:00"},{"alias_kind":"pith_short_8","alias_value":"OFYJAR3Z","created_at":"2026-07-05T12:06:01.136410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29549","citing_title":"Learning Representations from 3D Gaussian Splats","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28185","citing_title":"Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OFYJAR3ZRGE4YIMCJ5VW7MQY7I","json":"https://pith.science/pith/OFYJAR3ZRGE4YIMCJ5VW7MQY7I.json","graph_json":"https://pith.science/api/pith-number/OFYJAR3ZRGE4YIMCJ5VW7MQY7I/graph.json","events_json":"https://pith.science/api/pith-number/OFYJAR3ZRGE4YIMCJ5VW7MQY7I/events.json","paper":"https://pith.science/paper/OFYJAR3Z"},"agent_actions":{"view_html":"https://pith.science/pith/OFYJAR3ZRGE4YIMCJ5VW7MQY7I","download_json":"https://pith.science/pith/OFYJAR3ZRGE4YIMCJ5VW7MQY7I.json","view_paper":"https://pith.science/paper/OFYJAR3Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10906&json=true","fetch_graph":"https://pith.science/api/pith-number/OFYJAR3ZRGE4YIMCJ5VW7MQY7I/graph.json","fetch_events":"https://pith.science/api/pith-number/OFYJAR3ZRGE4YIMCJ5VW7MQY7I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OFYJAR3ZRGE4YIMCJ5VW7MQY7I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OFYJAR3ZRGE4YIMCJ5VW7MQY7I/action/storage_attestation","attest_author":"https://pith.science/pith/OFYJAR3ZRGE4YIMCJ5VW7MQY7I/action/author_attestation","sign_citation":"https://pith.science/pith/OFYJAR3ZRGE4YIMCJ5VW7MQY7I/action/citation_signature","submit_replication":"https://pith.science/pith/OFYJAR3ZRGE4YIMCJ5VW7MQY7I/action/replication_record"}},"created_at":"2026-07-05T12:06:01.136410+00:00","updated_at":"2026-07-05T12:06:01.136410+00:00"}