{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TXXPAB56ELIAICN5RTYRYNDIVQ","short_pith_number":"pith:TXXPAB56","schema_version":"1.0","canonical_sha256":"9deef007be22d00409bd8cf11c3468ac1758d8acfb6b77e2158151b8101fbd1f","source":{"kind":"arxiv","id":"2412.01292","version":2},"attestation_state":"computed","paper":{"title":"LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuang Gan, Hongyan Zhi, Junyan Li, Mingkui Tan, Peihao Chen, Shuailei Ma, Tianhang Xiang, Xinyu Sun, Yinjie Lei","submitted_at":"2024-12-02T09:07:57Z","abstract_excerpt":"Research on 3D Vision-Language Models (3D-VLMs) is gaining increasing attention, which is crucial for developing embodied AI within 3D scenes, such as visual navigation and embodied question answering. Due to the high density of visual features, especially in large 3D scenes, accurately locating task-relevant visual information is challenging. Existing works attempt to segment all objects and consider their features as scene representations. However, these task-agnostic object features include much redundant information and missing details for the task-relevant area. To tackle these problems, "},"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":"2412.01292","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T09:07:57Z","cross_cats_sorted":[],"title_canon_sha256":"0dfcc4ef406e94a55d80164e052c87f3316061f6be27c3117c2b41a3505db315","abstract_canon_sha256":"a90b26164bfc607d29ca687109463896dd1aa548fb3f058646b16bffdaebc170"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:25.618235Z","signature_b64":"tJGz7jCnNFOsy5CN6d4XaTo6kgCe6v3hHKf4vDDT79F0iZ942ijf4VeBWeVkDxIkCQu6Bz/boFyG+mhfF8oZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9deef007be22d00409bd8cf11c3468ac1758d8acfb6b77e2158151b8101fbd1f","last_reissued_at":"2026-07-05T10:08:25.617755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:25.617755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuang Gan, Hongyan Zhi, Junyan Li, Mingkui Tan, Peihao Chen, Shuailei Ma, Tianhang Xiang, Xinyu Sun, Yinjie Lei","submitted_at":"2024-12-02T09:07:57Z","abstract_excerpt":"Research on 3D Vision-Language Models (3D-VLMs) is gaining increasing attention, which is crucial for developing embodied AI within 3D scenes, such as visual navigation and embodied question answering. Due to the high density of visual features, especially in large 3D scenes, accurately locating task-relevant visual information is challenging. Existing works attempt to segment all objects and consider their features as scene representations. However, these task-agnostic object features include much redundant information and missing details for the task-relevant area. To tackle these problems, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01292","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/2412.01292/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":"2412.01292","created_at":"2026-07-05T10:08:25.617821+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01292v2","created_at":"2026-07-05T10:08:25.617821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01292","created_at":"2026-07-05T10:08:25.617821+00:00"},{"alias_kind":"pith_short_12","alias_value":"TXXPAB56ELIA","created_at":"2026-07-05T10:08:25.617821+00:00"},{"alias_kind":"pith_short_16","alias_value":"TXXPAB56ELIAICN5","created_at":"2026-07-05T10:08:25.617821+00:00"},{"alias_kind":"pith_short_8","alias_value":"TXXPAB56","created_at":"2026-07-05T10:08:25.617821+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TXXPAB56ELIAICN5RTYRYNDIVQ","json":"https://pith.science/pith/TXXPAB56ELIAICN5RTYRYNDIVQ.json","graph_json":"https://pith.science/api/pith-number/TXXPAB56ELIAICN5RTYRYNDIVQ/graph.json","events_json":"https://pith.science/api/pith-number/TXXPAB56ELIAICN5RTYRYNDIVQ/events.json","paper":"https://pith.science/paper/TXXPAB56"},"agent_actions":{"view_html":"https://pith.science/pith/TXXPAB56ELIAICN5RTYRYNDIVQ","download_json":"https://pith.science/pith/TXXPAB56ELIAICN5RTYRYNDIVQ.json","view_paper":"https://pith.science/paper/TXXPAB56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01292&json=true","fetch_graph":"https://pith.science/api/pith-number/TXXPAB56ELIAICN5RTYRYNDIVQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TXXPAB56ELIAICN5RTYRYNDIVQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TXXPAB56ELIAICN5RTYRYNDIVQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TXXPAB56ELIAICN5RTYRYNDIVQ/action/storage_attestation","attest_author":"https://pith.science/pith/TXXPAB56ELIAICN5RTYRYNDIVQ/action/author_attestation","sign_citation":"https://pith.science/pith/TXXPAB56ELIAICN5RTYRYNDIVQ/action/citation_signature","submit_replication":"https://pith.science/pith/TXXPAB56ELIAICN5RTYRYNDIVQ/action/replication_record"}},"created_at":"2026-07-05T10:08:25.617821+00:00","updated_at":"2026-07-05T10:08:25.617821+00:00"}