{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IDC3K2XENZD5TP7DK7CGDHKNII","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":"3bd15c244d80a6a7e41ce2c585cf43d245cd8906261613ff52a1b559c1dffee8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-06T16:38:48Z","title_canon_sha256":"c6763f280ab262e1b4861ba5aa45d786e3f6da1713499895742470ae9a02d6f7"},"schema_version":"1.0","source":{"id":"2504.04540","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04540","created_at":"2026-05-28T02:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04540v2","created_at":"2026-05-28T02:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04540","created_at":"2026-05-28T02:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"IDC3K2XENZD5","created_at":"2026-05-28T02:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"IDC3K2XENZD5TP7D","created_at":"2026-05-28T02:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"IDC3K2XE","created_at":"2026-05-28T02:04:40Z"}],"graph_snapshots":[{"event_id":"sha256:8d71a2c33da15e6a1946761e7e5c4ad5ce0923c22191566d1a72f9bc0cadfde6","target":"graph","created_at":"2026-05-28T02:04:40Z","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/2504.04540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D Large Language Models (LLMs) leveraging spatial information in point clouds for 3D spatial reasoning attract great attention. Despite some promising results, the advantages of point clouds over other modalities remain unclear. Moreover, existing 3D benchmarks are insufficient for fairly evaluating the ability of multimodal LLMs to comprehend spatial concepts. To address these challenges, we introduce ScanReQA, a 3D spatial reasoning benchmark encompassing text, vision, and point cloud modalities. We then evaluate the performance of text, 2D, and 3D LLMs on the benchmark to compare the effec","authors_text":"Chen Gao, Heng Dong, Jianjie Fang, Kaiyuan Li, Ruiying Peng, Weichen Zhang, Wei Li, Xinlei Chen, Xin Wang, Xin Zeng, Yong Li, Ziyou Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-06T16:38:48Z","title":"The Point, the Vision and the Text: Does Point Cloud Boost Spatial Reasoning of Large Language Models? A Bias-Controlled Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04540","kind":"arxiv","version":2},"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":"sha256:2f86333a7bfb1e0b736a53c313a7a183080c797857260d82934bafbdf6bab40d","target":"record","created_at":"2026-05-28T02:04:40Z","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":"3bd15c244d80a6a7e41ce2c585cf43d245cd8906261613ff52a1b559c1dffee8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-06T16:38:48Z","title_canon_sha256":"c6763f280ab262e1b4861ba5aa45d786e3f6da1713499895742470ae9a02d6f7"},"schema_version":"1.0","source":{"id":"2504.04540","kind":"arxiv","version":2}},"canonical_sha256":"40c5b56ae46e47d9bfe357c4619d4d422ccd48992c16893d1fe6e3172e1b6450","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40c5b56ae46e47d9bfe357c4619d4d422ccd48992c16893d1fe6e3172e1b6450","first_computed_at":"2026-05-28T02:04:40.340127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:04:40.340127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i3puqH0Wl0jnCWUfVxkuEdy+x4xM2cPny8e4ZfZSw619JatT9UUxpJ6jvT7I9MpwFZhrJCX/kiE/IzpWkATMAw==","signature_status":"signed_v1","signed_at":"2026-05-28T02:04:40.340775Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.04540","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f86333a7bfb1e0b736a53c313a7a183080c797857260d82934bafbdf6bab40d","sha256:8d71a2c33da15e6a1946761e7e5c4ad5ce0923c22191566d1a72f9bc0cadfde6"],"state_sha256":"077bbaab100b5c9c57b607d83d86132d6e785334f149566faea42629d92177ca"}