{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BMDKUVF2EDAOS4E53FCUWJ5IB6","short_pith_number":"pith:BMDKUVF2","schema_version":"1.0","canonical_sha256":"0b06aa54ba20c0e9709dd9454b27a80f803ebae58a2b84bb339829e469a0fad5","source":{"kind":"arxiv","id":"2504.12680","version":1},"attestation_state":"computed","paper":{"title":"Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Baining Zhao, Chen Gao, Fanhang Man, Jianjie Fang, Jinqiang Cui, Wenwu Zhu, Xinlei Chen, Xin Wang, Yong Li, Ziyou Wang","submitted_at":"2025-04-17T06:16:11Z","abstract_excerpt":"Humans can perceive and reason about spatial relationships from sequential visual observations, such as egocentric video streams. However, how pretrained models acquire such abilities, especially high-level reasoning, remains unclear. This paper introduces Embodied-R, a collaborative framework combining large-scale Vision-Language Models (VLMs) for perception and small-scale Language Models (LMs) for reasoning. Using Reinforcement Learning (RL) with a novel reward system considering think-answer logical consistency, the model achieves slow-thinking capabilities with limited computational resou"},"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":"2504.12680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-17T06:16:11Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ae582487fd8885f25b9b82c53e1b56aaf3e8b70ee4ff6be949dfe3bec04af7a0","abstract_canon_sha256":"c6599e5ff69a42c04c7afc5c3efaa4187b8f108f8996dd9b1d48444397c1a45f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:20.507521Z","signature_b64":"pm6wWyLZHi6PgTshda/BqnjUXW4JtKiakvDcMNR0umdqb5zoh3SZh99lK3t6wzS/rQEhW4UIAX/JzFskBEHnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b06aa54ba20c0e9709dd9454b27a80f803ebae58a2b84bb339829e469a0fad5","last_reissued_at":"2026-07-05T10:50:20.507013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:20.507013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Baining Zhao, Chen Gao, Fanhang Man, Jianjie Fang, Jinqiang Cui, Wenwu Zhu, Xinlei Chen, Xin Wang, Yong Li, Ziyou Wang","submitted_at":"2025-04-17T06:16:11Z","abstract_excerpt":"Humans can perceive and reason about spatial relationships from sequential visual observations, such as egocentric video streams. However, how pretrained models acquire such abilities, especially high-level reasoning, remains unclear. This paper introduces Embodied-R, a collaborative framework combining large-scale Vision-Language Models (VLMs) for perception and small-scale Language Models (LMs) for reasoning. Using Reinforcement Learning (RL) with a novel reward system considering think-answer logical consistency, the model achieves slow-thinking capabilities with limited computational resou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12680","kind":"arxiv","version":1},"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/2504.12680/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":"2504.12680","created_at":"2026-07-05T10:50:20.507078+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.12680v1","created_at":"2026-07-05T10:50:20.507078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12680","created_at":"2026-07-05T10:50:20.507078+00:00"},{"alias_kind":"pith_short_12","alias_value":"BMDKUVF2EDAO","created_at":"2026-07-05T10:50:20.507078+00:00"},{"alias_kind":"pith_short_16","alias_value":"BMDKUVF2EDAOS4E5","created_at":"2026-07-05T10:50:20.507078+00:00"},{"alias_kind":"pith_short_8","alias_value":"BMDKUVF2","created_at":"2026-07-05T10:50:20.507078+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23176","citing_title":"DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23176","citing_title":"DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2505.23678","citing_title":"Grounded Reinforcement Learning for Visual Reasoning","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2511.15669","citing_title":"DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13073","citing_title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","ref_index":174,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":125,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BMDKUVF2EDAOS4E53FCUWJ5IB6","json":"https://pith.science/pith/BMDKUVF2EDAOS4E53FCUWJ5IB6.json","graph_json":"https://pith.science/api/pith-number/BMDKUVF2EDAOS4E53FCUWJ5IB6/graph.json","events_json":"https://pith.science/api/pith-number/BMDKUVF2EDAOS4E53FCUWJ5IB6/events.json","paper":"https://pith.science/paper/BMDKUVF2"},"agent_actions":{"view_html":"https://pith.science/pith/BMDKUVF2EDAOS4E53FCUWJ5IB6","download_json":"https://pith.science/pith/BMDKUVF2EDAOS4E53FCUWJ5IB6.json","view_paper":"https://pith.science/paper/BMDKUVF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.12680&json=true","fetch_graph":"https://pith.science/api/pith-number/BMDKUVF2EDAOS4E53FCUWJ5IB6/graph.json","fetch_events":"https://pith.science/api/pith-number/BMDKUVF2EDAOS4E53FCUWJ5IB6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BMDKUVF2EDAOS4E53FCUWJ5IB6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BMDKUVF2EDAOS4E53FCUWJ5IB6/action/storage_attestation","attest_author":"https://pith.science/pith/BMDKUVF2EDAOS4E53FCUWJ5IB6/action/author_attestation","sign_citation":"https://pith.science/pith/BMDKUVF2EDAOS4E53FCUWJ5IB6/action/citation_signature","submit_replication":"https://pith.science/pith/BMDKUVF2EDAOS4E53FCUWJ5IB6/action/replication_record"}},"created_at":"2026-07-05T10:50:20.507078+00:00","updated_at":"2026-07-05T10:50:20.507078+00:00"}