{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UL4PFD76L7PEP7IG56WLOUM6KG","short_pith_number":"pith:UL4PFD76","schema_version":"1.0","canonical_sha256":"a2f8f28ffe5fde47fd06efacb7519e518710f752b0f73d41307c48e362715825","source":{"kind":"arxiv","id":"2505.15804","version":3},"attestation_state":"computed","paper":{"title":"STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deli Zhao, Mingze Li, Songyou Li, Tingyang Xu, Wenbing Huang, Yu Rong, Ziqi Zhang, Zongyang Ma, Zongzhao Li","submitted_at":"2025-05-21T17:57:38Z","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,"},"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":"2505.15804","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T17:57:38Z","cross_cats_sorted":[],"title_canon_sha256":"8280ea738705021f0fc4c0344508cc8d6a496045575b2ffd2196bec4efbd5347","abstract_canon_sha256":"0dc9186b445367ad0caa5270f5b73d07b2ad735dba98b9bb858c24df3952001c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:51.424521Z","signature_b64":"VaecQt7TyYwlsj6Zrg7dzsYPnZ/ajN1akdFQ9SY+Bo0Ahwu0JyLrftVE5UOHQIgt9BkKkFjkVRD0wTWKZDlyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2f8f28ffe5fde47fd06efacb7519e518710f752b0f73d41307c48e362715825","last_reissued_at":"2026-07-05T11:34:51.423970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:51.423970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deli Zhao, Mingze Li, Songyou Li, Tingyang Xu, Wenbing Huang, Yu Rong, Ziqi Zhang, Zongyang Ma, Zongzhao Li","submitted_at":"2025-05-21T17:57:38Z","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,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15804","kind":"arxiv","version":3},"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/2505.15804/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":"2505.15804","created_at":"2026-07-05T11:34:51.424031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15804v3","created_at":"2026-07-05T11:34:51.424031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15804","created_at":"2026-07-05T11:34:51.424031+00:00"},{"alias_kind":"pith_short_12","alias_value":"UL4PFD76L7PE","created_at":"2026-07-05T11:34:51.424031+00:00"},{"alias_kind":"pith_short_16","alias_value":"UL4PFD76L7PEP7IG","created_at":"2026-07-05T11:34:51.424031+00:00"},{"alias_kind":"pith_short_8","alias_value":"UL4PFD76","created_at":"2026-07-05T11:34:51.424031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":192,"is_internal_anchor":false},{"citing_arxiv_id":"2509.02547","citing_title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","ref_index":233,"is_internal_anchor":false},{"citing_arxiv_id":"2511.11113","citing_title":"VIDEOP2R: Video Understanding from Perception to Reasoning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03043","citing_title":"OneThinker: All-in-one Reasoning Model for Image and Video","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00181","citing_title":"CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27494","citing_title":"Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":297,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21776","citing_title":"Video-R1: Reinforcing Video Reasoning in MLLMs","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04379","citing_title":"Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05393","citing_title":"Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04372","citing_title":"Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UL4PFD76L7PEP7IG56WLOUM6KG","json":"https://pith.science/pith/UL4PFD76L7PEP7IG56WLOUM6KG.json","graph_json":"https://pith.science/api/pith-number/UL4PFD76L7PEP7IG56WLOUM6KG/graph.json","events_json":"https://pith.science/api/pith-number/UL4PFD76L7PEP7IG56WLOUM6KG/events.json","paper":"https://pith.science/paper/UL4PFD76"},"agent_actions":{"view_html":"https://pith.science/pith/UL4PFD76L7PEP7IG56WLOUM6KG","download_json":"https://pith.science/pith/UL4PFD76L7PEP7IG56WLOUM6KG.json","view_paper":"https://pith.science/paper/UL4PFD76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15804&json=true","fetch_graph":"https://pith.science/api/pith-number/UL4PFD76L7PEP7IG56WLOUM6KG/graph.json","fetch_events":"https://pith.science/api/pith-number/UL4PFD76L7PEP7IG56WLOUM6KG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UL4PFD76L7PEP7IG56WLOUM6KG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UL4PFD76L7PEP7IG56WLOUM6KG/action/storage_attestation","attest_author":"https://pith.science/pith/UL4PFD76L7PEP7IG56WLOUM6KG/action/author_attestation","sign_citation":"https://pith.science/pith/UL4PFD76L7PEP7IG56WLOUM6KG/action/citation_signature","submit_replication":"https://pith.science/pith/UL4PFD76L7PEP7IG56WLOUM6KG/action/replication_record"}},"created_at":"2026-07-05T11:34:51.424031+00:00","updated_at":"2026-07-05T11:34:51.424031+00:00"}