{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PGOMFKOHOY2IIS6QLUIANIIHKG","short_pith_number":"pith:PGOMFKOH","schema_version":"1.0","canonical_sha256":"799cc2a9c77634844bd05d1006a10751be9b18ce8aad4fa34e4ad10e4e25753d","source":{"kind":"arxiv","id":"2505.16517","version":2},"attestation_state":"computed","paper":{"title":"ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chenxi Wang, Guangxian Ouyang, Mingzhe Li, Qian Jiang, Rui Yan, Xiaoqing Zhang, Xiuying Chen, Yuheng Ji, Zeyu Zhang, Zhenhao Chen, Zhongzhi Li, Zirui Song, Zixiang Xu","submitted_at":"2025-05-22T10:57:07Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have recently advanced robotic manipulation by leveraging vision for scene perception and language for instruction following. However, existing methods rely heavily on costly human-annotated training datasets, which limits their generalization and causes them to struggle in out-of-domain (OOD) scenarios, reducing real-world adaptability. To address these challenges, we propose ManipLVM-R1, a novel reinforcement learning framework that replaces traditional supervision with Reinforcement Learning using Verifiable Rewards (RLVR). By directly optimizing for tas"},"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":"2505.16517","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-22T10:57:07Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"017f9c604f5aec42e1c58b3204f280b3baac7e938c2b8b5e0f763e72ba7cadae","abstract_canon_sha256":"5c3343ffa4197de45f784258cf43ad557b2df0e731cd8ec885e921f599345ff1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:15.300023Z","signature_b64":"yzuegnscaTbB3tvt5P6GZ+/CXUP3mjD8fmn87HOYaMo/BGR8Z4wsHw60yJHeAe+CEltQWgUp0oxiAgzPd9TkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"799cc2a9c77634844bd05d1006a10751be9b18ce8aad4fa34e4ad10e4e25753d","last_reissued_at":"2026-07-05T11:09:15.299519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:15.299519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chenxi Wang, Guangxian Ouyang, Mingzhe Li, Qian Jiang, Rui Yan, Xiaoqing Zhang, Xiuying Chen, Yuheng Ji, Zeyu Zhang, Zhenhao Chen, Zhongzhi Li, Zirui Song, Zixiang Xu","submitted_at":"2025-05-22T10:57:07Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have recently advanced robotic manipulation by leveraging vision for scene perception and language for instruction following. However, existing methods rely heavily on costly human-annotated training datasets, which limits their generalization and causes them to struggle in out-of-domain (OOD) scenarios, reducing real-world adaptability. To address these challenges, we propose ManipLVM-R1, a novel reinforcement learning framework that replaces traditional supervision with Reinforcement Learning using Verifiable Rewards (RLVR). By directly optimizing for tas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16517","kind":"arxiv","version":2},"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/2505.16517/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":"2505.16517","created_at":"2026-07-05T11:09:15.299581+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16517v2","created_at":"2026-07-05T11:09:15.299581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16517","created_at":"2026-07-05T11:09:15.299581+00:00"},{"alias_kind":"pith_short_12","alias_value":"PGOMFKOHOY2I","created_at":"2026-07-05T11:09:15.299581+00:00"},{"alias_kind":"pith_short_16","alias_value":"PGOMFKOHOY2IIS6Q","created_at":"2026-07-05T11:09:15.299581+00:00"},{"alias_kind":"pith_short_8","alias_value":"PGOMFKOH","created_at":"2026-07-05T11:09:15.299581+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.23058","citing_title":"GeoWorld: Geometric World Models","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":80,"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":46,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12982","citing_title":"Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00663","citing_title":"Affordance Agent Harness: Verification-Gated Skill Orchestration","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00663","citing_title":"Affordance Agent Harness: Verification-Gated Skill Orchestration","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PGOMFKOHOY2IIS6QLUIANIIHKG","json":"https://pith.science/pith/PGOMFKOHOY2IIS6QLUIANIIHKG.json","graph_json":"https://pith.science/api/pith-number/PGOMFKOHOY2IIS6QLUIANIIHKG/graph.json","events_json":"https://pith.science/api/pith-number/PGOMFKOHOY2IIS6QLUIANIIHKG/events.json","paper":"https://pith.science/paper/PGOMFKOH"},"agent_actions":{"view_html":"https://pith.science/pith/PGOMFKOHOY2IIS6QLUIANIIHKG","download_json":"https://pith.science/pith/PGOMFKOHOY2IIS6QLUIANIIHKG.json","view_paper":"https://pith.science/paper/PGOMFKOH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16517&json=true","fetch_graph":"https://pith.science/api/pith-number/PGOMFKOHOY2IIS6QLUIANIIHKG/graph.json","fetch_events":"https://pith.science/api/pith-number/PGOMFKOHOY2IIS6QLUIANIIHKG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PGOMFKOHOY2IIS6QLUIANIIHKG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PGOMFKOHOY2IIS6QLUIANIIHKG/action/storage_attestation","attest_author":"https://pith.science/pith/PGOMFKOHOY2IIS6QLUIANIIHKG/action/author_attestation","sign_citation":"https://pith.science/pith/PGOMFKOHOY2IIS6QLUIANIIHKG/action/citation_signature","submit_replication":"https://pith.science/pith/PGOMFKOHOY2IIS6QLUIANIIHKG/action/replication_record"}},"created_at":"2026-07-05T11:09:15.299581+00:00","updated_at":"2026-07-05T11:09:15.299581+00:00"}