{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N3OZ5MRLRRZRG2VNJH37QQ6AOY","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":"0d20e85e545769fd71b4096cc8f13b4974663ce1b4b58751bba61a910f8e08ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-01T18:36:17Z","title_canon_sha256":"64e5dbe797962c0a5899fd25f80df6a6b3abb95cee7554db661ac13a781d35d6"},"schema_version":"1.0","source":{"id":"2505.00788","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00788","created_at":"2026-07-05T11:19:06Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00788v3","created_at":"2026-07-05T11:19:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00788","created_at":"2026-07-05T11:19:06Z"},{"alias_kind":"pith_short_12","alias_value":"N3OZ5MRLRRZR","created_at":"2026-07-05T11:19:06Z"},{"alias_kind":"pith_short_16","alias_value":"N3OZ5MRLRRZRG2VN","created_at":"2026-07-05T11:19:06Z"},{"alias_kind":"pith_short_8","alias_value":"N3OZ5MRL","created_at":"2026-07-05T11:19:06Z"}],"graph_snapshots":[{"event_id":"sha256:1a0465db705aef7de0822b7fd8a8a073cf4ddf4daffc2dfea7f6e7b3b0548162","target":"graph","created_at":"2026-07-05T11:19:06Z","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/2505.00788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans naturally understand 3D spatial relationships, enabling complex reasoning like predicting collisions of vehicles from different directions. Current large multimodal models (LMMs), however, lack of this capability of 3D spatial reasoning. This limitation stems from the scarcity of 3D training data and the bias in current model designs toward 2D data. In this paper, we systematically study the impact of 3D-informed data, architecture, and training setups, introducing SpatialLLM, a large multi-modal model with advanced 3D spatial reasoning abilities. To address data limitations, we develop","authors_text":"Alan Yuille, Celso M de Melo, Jieneng Chen, Luoxin Ye, Wufei Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-01T18:36:17Z","title":"SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00788","kind":"arxiv","version":3},"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":"sha256:15e260004af5ec37eff1d22743302824cc36988b2213a47253d4a58987d379da","target":"record","created_at":"2026-07-05T11:19:06Z","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":"0d20e85e545769fd71b4096cc8f13b4974663ce1b4b58751bba61a910f8e08ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-01T18:36:17Z","title_canon_sha256":"64e5dbe797962c0a5899fd25f80df6a6b3abb95cee7554db661ac13a781d35d6"},"schema_version":"1.0","source":{"id":"2505.00788","kind":"arxiv","version":3}},"canonical_sha256":"6edd9eb22b8c73136aad49f7f843c07600ea7842aeb60c7b4d2d8395a7d2ed30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6edd9eb22b8c73136aad49f7f843c07600ea7842aeb60c7b4d2d8395a7d2ed30","first_computed_at":"2026-07-05T11:19:06.874106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:06.874106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EDW1kwNWASvG+pgE/wbQmaBnfLL8b53eJelN7prZyWlNeiBcD3tyI5Dm+LLRzNSimyz/8zwCN6JyyB/T4q42AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:06.874549Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.00788","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15e260004af5ec37eff1d22743302824cc36988b2213a47253d4a58987d379da","sha256:1a0465db705aef7de0822b7fd8a8a073cf4ddf4daffc2dfea7f6e7b3b0548162"],"state_sha256":"19f2173ab35361690a41e1320fb7d3794cc894c9b17d2b16bc0d2bc957f28c4a"}