{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UL4PFD76L7PEP7IG56WLOUM6KG","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":"0dc9186b445367ad0caa5270f5b73d07b2ad735dba98b9bb858c24df3952001c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T17:57:38Z","title_canon_sha256":"8280ea738705021f0fc4c0344508cc8d6a496045575b2ffd2196bec4efbd5347"},"schema_version":"1.0","source":{"id":"2505.15804","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15804","created_at":"2026-07-05T11:34:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15804v3","created_at":"2026-07-05T11:34:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15804","created_at":"2026-07-05T11:34:51Z"},{"alias_kind":"pith_short_12","alias_value":"UL4PFD76L7PE","created_at":"2026-07-05T11:34:51Z"},{"alias_kind":"pith_short_16","alias_value":"UL4PFD76L7PEP7IG","created_at":"2026-07-05T11:34:51Z"},{"alias_kind":"pith_short_8","alias_value":"UL4PFD76","created_at":"2026-07-05T11:34:51Z"}],"graph_snapshots":[{"event_id":"sha256:090b0e6c747ad06e23b3f663da52762c25b8c58454ee2314f165056e5c28f164","target":"graph","created_at":"2026-07-05T11:34:51Z","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/2505.15804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, yet they lag significantly behind humans in spatial reasoning. We investigate this gap through Transformation-Driven Visual Reasoning (TVR), a challenging task requiring identification of object transformations across images under varying viewpoints. While traditional Supervised Fine-Tuning (SFT) fails to generate coherent reasoning paths in cross-view settings, sparse-reward Reinforcement Learning (RL) suffers from inefficient exploration and slow convergence. To address these limitations,","authors_text":"Deli Zhao, Mingze Li, Songyou Li, Tingyang Xu, Wenbing Huang, Yu Rong, Ziqi Zhang, Zongyang Ma, Zongzhao Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T17:57:38Z","title":"STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15804","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:fab2b0f871e7f861b1e672b6ff78b8ae8604246d688fdc151adcecf3c0f056e9","target":"record","created_at":"2026-07-05T11:34:51Z","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":"0dc9186b445367ad0caa5270f5b73d07b2ad735dba98b9bb858c24df3952001c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T17:57:38Z","title_canon_sha256":"8280ea738705021f0fc4c0344508cc8d6a496045575b2ffd2196bec4efbd5347"},"schema_version":"1.0","source":{"id":"2505.15804","kind":"arxiv","version":3}},"canonical_sha256":"a2f8f28ffe5fde47fd06efacb7519e518710f752b0f73d41307c48e362715825","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2f8f28ffe5fde47fd06efacb7519e518710f752b0f73d41307c48e362715825","first_computed_at":"2026-07-05T11:34:51.423970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:51.423970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VaecQt7TyYwlsj6Zrg7dzsYPnZ/ajN1akdFQ9SY+Bo0Ahwu0JyLrftVE5UOHQIgt9BkKkFjkVRD0wTWKZDlyAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:51.424521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15804","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fab2b0f871e7f861b1e672b6ff78b8ae8604246d688fdc151adcecf3c0f056e9","sha256:090b0e6c747ad06e23b3f663da52762c25b8c58454ee2314f165056e5c28f164"],"state_sha256":"f4e0dd35dd65e2ee59de0506cff2b5e2b933745b461fd603c8e9ab792b752ea8"}