{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FXW3JPZUNYHDJLKYVHSKVJ2N3X","short_pith_number":"pith:FXW3JPZU","schema_version":"1.0","canonical_sha256":"2dedb4bf346e0e34ad58a9e4aaa74dddd57ce6f186009501d278d8768a6f10d1","source":{"kind":"arxiv","id":"2505.21906","version":2},"attestation_state":"computed","paper":{"title":"ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Chaomin Shen, Junjie Wen, Yichen Zhu, Yi Xu, Zhongyi Zhou","submitted_at":"2025-05-28T02:48:42Z","abstract_excerpt":"Vision-language-action (VLA) models have emerged as the next generation of models in robotics. However, despite leveraging powerful pre-trained Vision-Language Models (VLMs), existing end-to-end VLA systems often lose key capabilities during fine-tuning as the model adapts to specific robotic tasks. We argue that a generalizable VLA model should retain and expand upon the VLM's core competencies: 1) Open-world embodied reasoning - the VLA should inherit the knowledge from VLM, i.e., recognize anything that the VLM can recognize, be capable of solving math problems, and possess visual-spatial i"},"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":"2505.21906","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-28T02:48:42Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"bed0de23e7232c239cddfde13ce7dc91c34868dba8333b595629af6e40479a2d","abstract_canon_sha256":"d7e5bd94a2e8a6dbf795b7c3370d753b1f7d7dc6be6b0d0b3ded72dcfd7b1fe7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:33.898795Z","signature_b64":"A212Ou7puitU6SzkerVejKcV+J2qoXdr4VLq2JCvxWYg+LxcyXFVb8DBaXZ5mUHsWvScvWKlT9ww2LipdSQOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2dedb4bf346e0e34ad58a9e4aaa74dddd57ce6f186009501d278d8768a6f10d1","last_reissued_at":"2026-07-05T11:12:33.898239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:33.898239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Chaomin Shen, Junjie Wen, Yichen Zhu, Yi Xu, Zhongyi Zhou","submitted_at":"2025-05-28T02:48:42Z","abstract_excerpt":"Vision-language-action (VLA) models have emerged as the next generation of models in robotics. However, despite leveraging powerful pre-trained Vision-Language Models (VLMs), existing end-to-end VLA systems often lose key capabilities during fine-tuning as the model adapts to specific robotic tasks. We argue that a generalizable VLA model should retain and expand upon the VLM's core competencies: 1) Open-world embodied reasoning - the VLA should inherit the knowledge from VLM, i.e., recognize anything that the VLM can recognize, be capable of solving math problems, and possess visual-spatial i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21906","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/2505.21906/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":"2505.21906","created_at":"2026-07-05T11:12:33.898302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21906v2","created_at":"2026-07-05T11:12:33.898302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21906","created_at":"2026-07-05T11:12:33.898302+00:00"},{"alias_kind":"pith_short_12","alias_value":"FXW3JPZUNYHD","created_at":"2026-07-05T11:12:33.898302+00:00"},{"alias_kind":"pith_short_16","alias_value":"FXW3JPZUNYHDJLKY","created_at":"2026-07-05T11:12:33.898302+00:00"},{"alias_kind":"pith_short_8","alias_value":"FXW3JPZU","created_at":"2026-07-05T11:12:33.898302+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23157","citing_title":"Bridging Semantics and Kinematics: A Modular Framework for Zero-Shot Robotic Manipulation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03392","citing_title":"OpenEAI-Platform: An Open-source Embodied Artificial Intelligence Hardware-Software Unified Platform","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02565","citing_title":"Policy-based Foveated Imaging and Perception","ref_index":128,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00229","citing_title":"Continuous Reasoning for Vision-Language-Action","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01191","citing_title":"Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2503.03480","citing_title":"SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17486","citing_title":"DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15298","citing_title":"PhysBrain 1.0 Technical Report","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14058","citing_title":"What Matters in Building Vision-Language-Action Models for Generalist Robots","ref_index":54,"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":131,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20231","citing_title":"UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Models","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25459","citing_title":"GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01194","citing_title":"VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01191","citing_title":"Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00321","citing_title":"Embodied Interpretability: Linking Causal Understanding to Generalization in Vision-Language-Action Models","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FXW3JPZUNYHDJLKYVHSKVJ2N3X","json":"https://pith.science/pith/FXW3JPZUNYHDJLKYVHSKVJ2N3X.json","graph_json":"https://pith.science/api/pith-number/FXW3JPZUNYHDJLKYVHSKVJ2N3X/graph.json","events_json":"https://pith.science/api/pith-number/FXW3JPZUNYHDJLKYVHSKVJ2N3X/events.json","paper":"https://pith.science/paper/FXW3JPZU"},"agent_actions":{"view_html":"https://pith.science/pith/FXW3JPZUNYHDJLKYVHSKVJ2N3X","download_json":"https://pith.science/pith/FXW3JPZUNYHDJLKYVHSKVJ2N3X.json","view_paper":"https://pith.science/paper/FXW3JPZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21906&json=true","fetch_graph":"https://pith.science/api/pith-number/FXW3JPZUNYHDJLKYVHSKVJ2N3X/graph.json","fetch_events":"https://pith.science/api/pith-number/FXW3JPZUNYHDJLKYVHSKVJ2N3X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FXW3JPZUNYHDJLKYVHSKVJ2N3X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FXW3JPZUNYHDJLKYVHSKVJ2N3X/action/storage_attestation","attest_author":"https://pith.science/pith/FXW3JPZUNYHDJLKYVHSKVJ2N3X/action/author_attestation","sign_citation":"https://pith.science/pith/FXW3JPZUNYHDJLKYVHSKVJ2N3X/action/citation_signature","submit_replication":"https://pith.science/pith/FXW3JPZUNYHDJLKYVHSKVJ2N3X/action/replication_record"}},"created_at":"2026-07-05T11:12:33.898302+00:00","updated_at":"2026-07-05T11:12:33.898302+00:00"}