{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JULNET4BKR2CMIOYAMTYKDJKSR","short_pith_number":"pith:JULNET4B","canonical_record":{"source":{"id":"2605.13600","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:35:31Z","cross_cats_sorted":[],"title_canon_sha256":"56ec71ba0809b46f7455cae7774de84fa51c0fa451e7e1cb1ca712a53841b1ed","abstract_canon_sha256":"53369c60f99a84e2d7edfb95564554667a3fbe94f3656a8dcd1a53b0888d7f2d"},"schema_version":"1.0"},"canonical_sha256":"4d16d24f8154742621d80327850d2a9445da6c13d8c16542979e51a885de64b8","source":{"kind":"arxiv","id":"2605.13600","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13600","created_at":"2026-05-18T02:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13600v1","created_at":"2026-05-18T02:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13600","created_at":"2026-05-18T02:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"JULNET4BKR2C","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"JULNET4BKR2CMIOY","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"JULNET4B","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JULNET4BKR2CMIOYAMTYKDJKSR","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13600","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:35:31Z","cross_cats_sorted":[],"title_canon_sha256":"56ec71ba0809b46f7455cae7774de84fa51c0fa451e7e1cb1ca712a53841b1ed","abstract_canon_sha256":"53369c60f99a84e2d7edfb95564554667a3fbe94f3656a8dcd1a53b0888d7f2d"},"schema_version":"1.0"},"canonical_sha256":"4d16d24f8154742621d80327850d2a9445da6c13d8c16542979e51a885de64b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:22.942783Z","signature_b64":"jBQWUn1J7hbxY8RcTDVKG9yaWqcIvP2A9YUn6atqtdYF5li1E+070Nx8Ib0lIthwSpgvhlClGNSN4CvcmMnLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d16d24f8154742621d80327850d2a9445da6c13d8c16542979e51a885de64b8","last_reissued_at":"2026-05-18T02:44:22.942376Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:22.942376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13600","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6A0oZ8EFkC0e5eQHxYMZZFC2m/8zyDaHm+opL8bjAs6rVkWZIAh7vsSNidxIP2FJ5P54B+EuSEPAw9/fb7JtAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T02:53:43.043975Z"},"content_sha256":"49eae86d6ed5718218971d1c565aed96ee011e6948a06be8e75d927d777c1641","schema_version":"1.0","event_id":"sha256:49eae86d6ed5718218971d1c565aed96ee011e6948a06be8e75d927d777c1641"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JULNET4BKR2CMIOYAMTYKDJKSR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparse Code Uplifting for Efficient 3D Language Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Sparse code uplifting from 2D images to 3D Gaussians delivers up to 400 times faster training for open-vocabulary scene understanding.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lovre Antonio Budimir, Nandita Vijaykumar, Steve Ryhner, Sven Lon\\v{c}ari\\'c, Yushi Guan","submitted_at":"2026-05-13T14:35:31Z","abstract_excerpt":"3D Language Gaussian Splatting (3DLGS) augments 3D Gaussian Splatting with language-aligned visual features for open-vocabulary 3D scene understanding. A core challenge is efficiently associating high-dimensional vision-language embeddings with millions of 3D Gaussians while preserving efficient feature rendering for text-based querying. Existing methods either store dense features directly on Gaussians, causing high storage costs and slow rendering, or learn compact representations through expensive per-scene optimization with repeated feature rasterization. No existing method simultaneously "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our method achieves up to 400× training speedup while being 3× more memory efficient during training compared to the state-of-the-art in rendering speed. Across multiple benchmarks, SCOUP matches or outperforms existing methods in open-vocabulary querying accuracy.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That sparse codebook coefficients learned entirely from 2D image regions can be uplifted to 3D Gaussians via weighted multi-view aggregation and Top-K filtering without substantial loss of semantic accuracy or the need for per-scene language optimization.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SCOUP decouples 2D sparse code learning from 3D Gaussian optimization to deliver up to 400x training speedup and 3x better memory efficiency while matching accuracy on open-vocabulary 3D queries.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Sparse code uplifting from 2D images to 3D Gaussians delivers up to 400 times faster training for open-vocabulary scene understanding.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"454fefc7b7b2f4d3960379d71122ce926740c8aff21402d0c9655603f5a68839"},"source":{"id":"2605.13600","kind":"arxiv","version":1},"verdict":{"id":"9b550f01-b106-4a13-bbe0-6dbff00084df","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:22:41.364916Z","strongest_claim":"Our method achieves up to 400× training speedup while being 3× more memory efficient during training compared to the state-of-the-art in rendering speed. Across multiple benchmarks, SCOUP matches or outperforms existing methods in open-vocabulary querying accuracy.","one_line_summary":"SCOUP decouples 2D sparse code learning from 3D Gaussian optimization to deliver up to 400x training speedup and 3x better memory efficiency while matching accuracy on open-vocabulary 3D queries.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That sparse codebook coefficients learned entirely from 2D image regions can be uplifted to 3D Gaussians via weighted multi-view aggregation and Top-K filtering without substantial loss of semantic accuracy or the need for per-scene language optimization.","pith_extraction_headline":"Sparse code uplifting from 2D images to 3D Gaussians delivers up to 400 times faster training for open-vocabulary scene understanding."},"references":{"count":43,"sample":[{"doi":"","year":2026,"title":"GALA: Guided attention with language alignment for open vocabulary gaussian splatting","work_id":"e8b07e34-4e73-4283-8b36-e419ae34b2b2","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Barron, Ben Mildenhall, Dor Verbin, Pratul P","work_id":"0aedd240-1463-4d03-bd4e-c8aff93e2414","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Gaussianeditor: Swift and controllable 3d editing with gaussian splatting.2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 21476–21485, 2023","work_id":"05058a69-c172-4cf0-bec7-c096214c88c7","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/cvpr52733.2024.02022","year":2024,"title":"URL https://doi.org/10.1109/CVPR52733","work_id":"7efbc2dd-b0f2-4f71-bb1c-d2fcf110d805","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Occam’s lgs: An efficient approach for language gaussian splatting","work_id":"9baf9d6e-f4e6-46a2-abfe-cd7588f4a792","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":43,"snapshot_sha256":"a1f80dc2a830356b712bebeaed8e5861d118bcec65f35261555cbad8f6049d82","internal_anchors":2},"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"},"verdict_id":"9b550f01-b106-4a13-bbe0-6dbff00084df"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FoadPmUZJoRHy83nD9C0fiai+MtUnd0W6TDHBTOsZQcueNUiyDA3nA+Xm6acFrnRhot8jw7ZjKmHVpWW96WXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T02:53:43.044675Z"},"content_sha256":"faca41055918d57a73ada5aa82a2bfed88be91bbc36489066888f67a6f733b23","schema_version":"1.0","event_id":"sha256:faca41055918d57a73ada5aa82a2bfed88be91bbc36489066888f67a6f733b23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JULNET4BKR2CMIOYAMTYKDJKSR/bundle.json","state_url":"https://pith.science/pith/JULNET4BKR2CMIOYAMTYKDJKSR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JULNET4BKR2CMIOYAMTYKDJKSR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T02:53:43Z","links":{"resolver":"https://pith.science/pith/JULNET4BKR2CMIOYAMTYKDJKSR","bundle":"https://pith.science/pith/JULNET4BKR2CMIOYAMTYKDJKSR/bundle.json","state":"https://pith.science/pith/JULNET4BKR2CMIOYAMTYKDJKSR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JULNET4BKR2CMIOYAMTYKDJKSR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JULNET4BKR2CMIOYAMTYKDJKSR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"53369c60f99a84e2d7edfb95564554667a3fbe94f3656a8dcd1a53b0888d7f2d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:35:31Z","title_canon_sha256":"56ec71ba0809b46f7455cae7774de84fa51c0fa451e7e1cb1ca712a53841b1ed"},"schema_version":"1.0","source":{"id":"2605.13600","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13600","created_at":"2026-05-18T02:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13600v1","created_at":"2026-05-18T02:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13600","created_at":"2026-05-18T02:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"JULNET4BKR2C","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"JULNET4BKR2CMIOY","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"JULNET4B","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:faca41055918d57a73ada5aa82a2bfed88be91bbc36489066888f67a6f733b23","target":"graph","created_at":"2026-05-18T02:44:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our method achieves up to 400× training speedup while being 3× more memory efficient during training compared to the state-of-the-art in rendering speed. Across multiple benchmarks, SCOUP matches or outperforms existing methods in open-vocabulary querying accuracy."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That sparse codebook coefficients learned entirely from 2D image regions can be uplifted to 3D Gaussians via weighted multi-view aggregation and Top-K filtering without substantial loss of semantic accuracy or the need for per-scene language optimization."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SCOUP decouples 2D sparse code learning from 3D Gaussian optimization to deliver up to 400x training speedup and 3x better memory efficiency while matching accuracy on open-vocabulary 3D queries."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Sparse code uplifting from 2D images to 3D Gaussians delivers up to 400 times faster training for open-vocabulary scene understanding."}],"snapshot_sha256":"454fefc7b7b2f4d3960379d71122ce926740c8aff21402d0c9655603f5a68839"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"3D Language Gaussian Splatting (3DLGS) augments 3D Gaussian Splatting with language-aligned visual features for open-vocabulary 3D scene understanding. A core challenge is efficiently associating high-dimensional vision-language embeddings with millions of 3D Gaussians while preserving efficient feature rendering for text-based querying. Existing methods either store dense features directly on Gaussians, causing high storage costs and slow rendering, or learn compact representations through expensive per-scene optimization with repeated feature rasterization. No existing method simultaneously ","authors_text":"Lovre Antonio Budimir, Nandita Vijaykumar, Steve Ryhner, Sven Lon\\v{c}ari\\'c, Yushi Guan","cross_cats":[],"headline":"Sparse code uplifting from 2D images to 3D Gaussians delivers up to 400 times faster training for open-vocabulary scene understanding.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:35:31Z","title":"Sparse Code Uplifting for Efficient 3D Language Gaussian Splatting"},"references":{"count":43,"internal_anchors":2,"resolved_work":43,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"GALA: Guided attention with language alignment for open vocabulary gaussian splatting","work_id":"e8b07e34-4e73-4283-8b36-e419ae34b2b2","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Barron, Ben Mildenhall, Dor Verbin, Pratul P","work_id":"0aedd240-1463-4d03-bd4e-c8aff93e2414","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Gaussianeditor: Swift and controllable 3d editing with gaussian splatting.2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 21476–21485, 2023","work_id":"05058a69-c172-4cf0-bec7-c096214c88c7","year":2024},{"cited_arxiv_id":"","doi":"10.1109/cvpr52733.2024.02022","is_internal_anchor":false,"ref_index":4,"title":"URL https://doi.org/10.1109/CVPR52733","work_id":"7efbc2dd-b0f2-4f71-bb1c-d2fcf110d805","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Occam’s lgs: An efficient approach for language gaussian splatting","work_id":"9baf9d6e-f4e6-46a2-abfe-cd7588f4a792","year":2025}],"snapshot_sha256":"a1f80dc2a830356b712bebeaed8e5861d118bcec65f35261555cbad8f6049d82"},"source":{"id":"2605.13600","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:22:41.364916Z","id":"9b550f01-b106-4a13-bbe0-6dbff00084df","model_set":{"reader":"grok-4.3"},"one_line_summary":"SCOUP decouples 2D sparse code learning from 3D Gaussian optimization to deliver up to 400x training speedup and 3x better memory efficiency while matching accuracy on open-vocabulary 3D queries.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Sparse code uplifting from 2D images to 3D Gaussians delivers up to 400 times faster training for open-vocabulary scene understanding.","strongest_claim":"Our method achieves up to 400× training speedup while being 3× more memory efficient during training compared to the state-of-the-art in rendering speed. Across multiple benchmarks, SCOUP matches or outperforms existing methods in open-vocabulary querying accuracy.","weakest_assumption":"That sparse codebook coefficients learned entirely from 2D image regions can be uplifted to 3D Gaussians via weighted multi-view aggregation and Top-K filtering without substantial loss of semantic accuracy or the need for per-scene language optimization."}},"verdict_id":"9b550f01-b106-4a13-bbe0-6dbff00084df"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:49eae86d6ed5718218971d1c565aed96ee011e6948a06be8e75d927d777c1641","target":"record","created_at":"2026-05-18T02:44:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"53369c60f99a84e2d7edfb95564554667a3fbe94f3656a8dcd1a53b0888d7f2d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T14:35:31Z","title_canon_sha256":"56ec71ba0809b46f7455cae7774de84fa51c0fa451e7e1cb1ca712a53841b1ed"},"schema_version":"1.0","source":{"id":"2605.13600","kind":"arxiv","version":1}},"canonical_sha256":"4d16d24f8154742621d80327850d2a9445da6c13d8c16542979e51a885de64b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d16d24f8154742621d80327850d2a9445da6c13d8c16542979e51a885de64b8","first_computed_at":"2026-05-18T02:44:22.942376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:22.942376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jBQWUn1J7hbxY8RcTDVKG9yaWqcIvP2A9YUn6atqtdYF5li1E+070Nx8Ib0lIthwSpgvhlClGNSN4CvcmMnLDA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:22.942783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13600","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49eae86d6ed5718218971d1c565aed96ee011e6948a06be8e75d927d777c1641","sha256:faca41055918d57a73ada5aa82a2bfed88be91bbc36489066888f67a6f733b23"],"state_sha256":"89d921e3e260319fb12b97c6323644b44e1d522271c1b12a0953e7ddf0f25848"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e5Hn73MMFLwhJoR+DdpCrOe560ayfxVCU4sCghK/ucmPyReW7Fh9GQ1SlB/Cf/FcBlKIHmM4Qb2adoSGEmhrAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T02:53:43.047427Z","bundle_sha256":"0f9d17ff86811ecd850dd9a85bc9c48a0df72a1bebcf078d8fb006f3ac4a5065"}}