{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y63LIZTGZSZG3ZW7XCAEFB7BIL","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":"551a0aef9d5bb6141bc996ce01155accbedd153105e8c7b313370e21ace0e24e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-28T17:48:43Z","title_canon_sha256":"14aaa7896466b1965c077fb96e8967677988ee01450b09f7fe1e86d784cadc48"},"schema_version":"1.0","source":{"id":"2504.20024","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20024","created_at":"2026-07-05T11:19:06Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20024v2","created_at":"2026-07-05T11:19:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20024","created_at":"2026-07-05T11:19:06Z"},{"alias_kind":"pith_short_12","alias_value":"Y63LIZTGZSZG","created_at":"2026-07-05T11:19:06Z"},{"alias_kind":"pith_short_16","alias_value":"Y63LIZTGZSZG3ZW7","created_at":"2026-07-05T11:19:06Z"},{"alias_kind":"pith_short_8","alias_value":"Y63LIZTG","created_at":"2026-07-05T11:19:06Z"}],"graph_snapshots":[{"event_id":"sha256:a44776937bb002b189fda19f4fc4bbcaed20739c1c6da10448a47ee3ff6ab112","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/2504.20024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent advances on multi-modal models, 3D spatial reasoning remains a challenging task for state-of-the-art open-source and proprietary models. Recent studies explore data-driven approaches and achieve enhanced spatial reasoning performance by fine-tuning models on 3D-related visual question-answering data. However, these methods typically perform spatial reasoning in an implicit manner and often fail on questions that are trivial to humans, even with long chain-of-thought reasoning. In this work, we introduce SpatialReasoner, a novel large vision-language model (LVLM) that addresses 3","authors_text":"Alan Yuille, Celso de Melo, Jianwen Xie, Qihao Liu, Wufei Ma, Xingrui Wang, Yu-Cheng Chou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-28T17:48:43Z","title":"SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20024","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:f2ce932e73a068adcf14f0b9be6f47e23157428b9187e4d26352d889573d9405","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":"551a0aef9d5bb6141bc996ce01155accbedd153105e8c7b313370e21ace0e24e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-28T17:48:43Z","title_canon_sha256":"14aaa7896466b1965c077fb96e8967677988ee01450b09f7fe1e86d784cadc48"},"schema_version":"1.0","source":{"id":"2504.20024","kind":"arxiv","version":2}},"canonical_sha256":"c7b6b46666ccb26de6dfb8804287e142c46bc1f682cca4910788d97024fa1ac7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7b6b46666ccb26de6dfb8804287e142c46bc1f682cca4910788d97024fa1ac7","first_computed_at":"2026-07-05T11:19:06.593600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:06.593600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4ckJE3zRb1A5G7KEb5V3Mnu+N2VcyeJeLrZBDVSax38g/Dh6folmzbdE/BclW5yPJJVSP2Dj8YTx7umJRjGnDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:06.594073Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.20024","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2ce932e73a068adcf14f0b9be6f47e23157428b9187e4d26352d889573d9405","sha256:a44776937bb002b189fda19f4fc4bbcaed20739c1c6da10448a47ee3ff6ab112"],"state_sha256":"1c8030be94a1abac534d1f9d717efa6e6d564cfd7bf5ccb50f7f68f34e64d00a"}