{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3M5TYOBG2BA6BDWXJ5NQIYVPDH","short_pith_number":"pith:3M5TYOBG","schema_version":"1.0","canonical_sha256":"db3b3c3826d041e08ed74f5b0462af19c31bb8bb7a222f436bb1b2c33872d8d4","source":{"kind":"arxiv","id":"2507.00886","version":1},"attestation_state":"computed","paper":{"title":"GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Anna-Maria Halacheva, Danda Pani Paudel, Jan-Nico Zaech, Luc Van Gool, Xi Wang","submitted_at":"2025-07-01T15:52:59Z","abstract_excerpt":"As multimodal language models advance, their application to 3D scene understanding is a fast-growing frontier, driving the development of 3D Vision-Language Models (VLMs). Current methods show strong dependence on object detectors, introducing processing bottlenecks and limitations in taxonomic flexibility. To address these limitations, we propose a scene-centric 3D VLM for 3D Gaussian splat scenes that employs language- and task-aware scene representations. Our approach directly embeds rich linguistic features into the 3D scene representation by associating language with each Gaussian primiti"},"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":"2507.00886","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T15:52:59Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"5f4ee2c013f0120ac26a7a7e04b6621fc588a850759f2ebfc8838bb1f7af6536","abstract_canon_sha256":"437d12d10d74f41a6f126872e2c00bbdf7dd9256859eae824199ce0268b501de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:16.687051Z","signature_b64":"x0FE7vaiPN0FHswW1wbXQqPdEVLdFBdcAJeF4g/YStK5dUSa3KX5P1ajm6eVhvLVYG8xX2o5FExMFuKpWTVJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db3b3c3826d041e08ed74f5b0462af19c31bb8bb7a222f436bb1b2c33872d8d4","last_reissued_at":"2026-07-05T11:30:16.686553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:16.686553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Anna-Maria Halacheva, Danda Pani Paudel, Jan-Nico Zaech, Luc Van Gool, Xi Wang","submitted_at":"2025-07-01T15:52:59Z","abstract_excerpt":"As multimodal language models advance, their application to 3D scene understanding is a fast-growing frontier, driving the development of 3D Vision-Language Models (VLMs). Current methods show strong dependence on object detectors, introducing processing bottlenecks and limitations in taxonomic flexibility. To address these limitations, we propose a scene-centric 3D VLM for 3D Gaussian splat scenes that employs language- and task-aware scene representations. Our approach directly embeds rich linguistic features into the 3D scene representation by associating language with each Gaussian primiti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00886","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/2507.00886/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":"2507.00886","created_at":"2026-07-05T11:30:16.686615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00886v1","created_at":"2026-07-05T11:30:16.686615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00886","created_at":"2026-07-05T11:30:16.686615+00:00"},{"alias_kind":"pith_short_12","alias_value":"3M5TYOBG2BA6","created_at":"2026-07-05T11:30:16.686615+00:00"},{"alias_kind":"pith_short_16","alias_value":"3M5TYOBG2BA6BDWX","created_at":"2026-07-05T11:30:16.686615+00:00"},{"alias_kind":"pith_short_8","alias_value":"3M5TYOBG","created_at":"2026-07-05T11:30:16.686615+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.23180","citing_title":"GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18210","citing_title":"Motion-Enabled Tomography via Gaussian Mixture Models","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2512.17817","citing_title":"Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3M5TYOBG2BA6BDWXJ5NQIYVPDH","json":"https://pith.science/pith/3M5TYOBG2BA6BDWXJ5NQIYVPDH.json","graph_json":"https://pith.science/api/pith-number/3M5TYOBG2BA6BDWXJ5NQIYVPDH/graph.json","events_json":"https://pith.science/api/pith-number/3M5TYOBG2BA6BDWXJ5NQIYVPDH/events.json","paper":"https://pith.science/paper/3M5TYOBG"},"agent_actions":{"view_html":"https://pith.science/pith/3M5TYOBG2BA6BDWXJ5NQIYVPDH","download_json":"https://pith.science/pith/3M5TYOBG2BA6BDWXJ5NQIYVPDH.json","view_paper":"https://pith.science/paper/3M5TYOBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00886&json=true","fetch_graph":"https://pith.science/api/pith-number/3M5TYOBG2BA6BDWXJ5NQIYVPDH/graph.json","fetch_events":"https://pith.science/api/pith-number/3M5TYOBG2BA6BDWXJ5NQIYVPDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3M5TYOBG2BA6BDWXJ5NQIYVPDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3M5TYOBG2BA6BDWXJ5NQIYVPDH/action/storage_attestation","attest_author":"https://pith.science/pith/3M5TYOBG2BA6BDWXJ5NQIYVPDH/action/author_attestation","sign_citation":"https://pith.science/pith/3M5TYOBG2BA6BDWXJ5NQIYVPDH/action/citation_signature","submit_replication":"https://pith.science/pith/3M5TYOBG2BA6BDWXJ5NQIYVPDH/action/replication_record"}},"created_at":"2026-07-05T11:30:16.686615+00:00","updated_at":"2026-07-05T11:30:16.686615+00:00"}