{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3M5TYOBG2BA6BDWXJ5NQIYVPDH","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":"437d12d10d74f41a6f126872e2c00bbdf7dd9256859eae824199ce0268b501de","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T15:52:59Z","title_canon_sha256":"5f4ee2c013f0120ac26a7a7e04b6621fc588a850759f2ebfc8838bb1f7af6536"},"schema_version":"1.0","source":{"id":"2507.00886","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00886","created_at":"2026-07-05T11:30:16Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00886v1","created_at":"2026-07-05T11:30:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00886","created_at":"2026-07-05T11:30:16Z"},{"alias_kind":"pith_short_12","alias_value":"3M5TYOBG2BA6","created_at":"2026-07-05T11:30:16Z"},{"alias_kind":"pith_short_16","alias_value":"3M5TYOBG2BA6BDWX","created_at":"2026-07-05T11:30:16Z"},{"alias_kind":"pith_short_8","alias_value":"3M5TYOBG","created_at":"2026-07-05T11:30:16Z"}],"graph_snapshots":[{"event_id":"sha256:be788c4f2be33db0e3c7ed8b87531bbdb08502995d5c1593f542b0381ce69570","target":"graph","created_at":"2026-07-05T11:30:16Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.00886/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anna-Maria Halacheva, Danda Pani Paudel, Jan-Nico Zaech, Luc Van Gool, Xi Wang","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T15:52:59Z","title":"GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00886","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:39eae10b9c219b4cdba13e04a0d79df0540c858ace1d326f76f2e9cd01e4fa22","target":"record","created_at":"2026-07-05T11:30:16Z","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":"437d12d10d74f41a6f126872e2c00bbdf7dd9256859eae824199ce0268b501de","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T15:52:59Z","title_canon_sha256":"5f4ee2c013f0120ac26a7a7e04b6621fc588a850759f2ebfc8838bb1f7af6536"},"schema_version":"1.0","source":{"id":"2507.00886","kind":"arxiv","version":1}},"canonical_sha256":"db3b3c3826d041e08ed74f5b0462af19c31bb8bb7a222f436bb1b2c33872d8d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db3b3c3826d041e08ed74f5b0462af19c31bb8bb7a222f436bb1b2c33872d8d4","first_computed_at":"2026-07-05T11:30:16.686553Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:16.686553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x0FE7vaiPN0FHswW1wbXQqPdEVLdFBdcAJeF4g/YStK5dUSa3KX5P1ajm6eVhvLVYG8xX2o5FExMFuKpWTVJDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:16.687051Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00886","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39eae10b9c219b4cdba13e04a0d79df0540c858ace1d326f76f2e9cd01e4fa22","sha256:be788c4f2be33db0e3c7ed8b87531bbdb08502995d5c1593f542b0381ce69570"],"state_sha256":"0f7f623482793d17851f860348658aa8c7b231e0fb8799495ef43255ccf4579a"}