{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PQICLB7LFUXY65NGD2HIQJ4GS4","short_pith_number":"pith:PQICLB7L","schema_version":"1.0","canonical_sha256":"7c102587eb2d2f8f75a61e8e8827869716aae1a64e2cf6345f90122810a3c9fc","source":{"kind":"arxiv","id":"2402.02385","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Robotics with Foundation Models: toward Embodied AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jian Tang, Jinming Li, Junjie Wen, Kun Wu, Ning Liu, Zhengping Che, Zhiyuan Xu","submitted_at":"2024-02-04T07:55:01Z","abstract_excerpt":"While the exploration for embodied AI has spanned multiple decades, it remains a persistent challenge to endow agents with human-level intelligence, including perception, learning, reasoning, decision-making, control, and generalization capabilities, so that they can perform general-purpose tasks in open, unstructured, and dynamic environments. Recent advances in computer vision, natural language processing, and multi-modality learning have shown that the foundation models have superhuman capabilities for specific tasks. They not only provide a solid cornerstone for integrating basic modules 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":"2402.02385","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-04T07:55:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"826ef1d9460dbe64dfd79f6652146e64290a701410cdb937a796e1aec1c34c3f","abstract_canon_sha256":"55787e37ae4f4133efad2994fcb160362913d578af907a0660a7bb4a95802307"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:48.663812Z","signature_b64":"2NKe8l+/kkIRe65lN5+RT7C162/OZR4vzPhiTDapagyzI3aWC12YbeJ1eaiYTQd36aDph3UfqEGFbSrsrX4uCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c102587eb2d2f8f75a61e8e8827869716aae1a64e2cf6345f90122810a3c9fc","last_reissued_at":"2026-07-05T07:41:48.663365Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:48.663365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Robotics with Foundation Models: toward Embodied AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jian Tang, Jinming Li, Junjie Wen, Kun Wu, Ning Liu, Zhengping Che, Zhiyuan Xu","submitted_at":"2024-02-04T07:55:01Z","abstract_excerpt":"While the exploration for embodied AI has spanned multiple decades, it remains a persistent challenge to endow agents with human-level intelligence, including perception, learning, reasoning, decision-making, control, and generalization capabilities, so that they can perform general-purpose tasks in open, unstructured, and dynamic environments. Recent advances in computer vision, natural language processing, and multi-modality learning have shown that the foundation models have superhuman capabilities for specific tasks. They not only provide a solid cornerstone for integrating basic modules i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02385","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/2402.02385/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":"2402.02385","created_at":"2026-07-05T07:41:48.663424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02385v1","created_at":"2026-07-05T07:41:48.663424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02385","created_at":"2026-07-05T07:41:48.663424+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQICLB7LFUXY","created_at":"2026-07-05T07:41:48.663424+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQICLB7LFUXY65NG","created_at":"2026-07-05T07:41:48.663424+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQICLB7L","created_at":"2026-07-05T07:41:48.663424+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12207","citing_title":"Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00053","citing_title":"VLAMotor: Test-Guided Enhancement of Vision-Language-Action Models via Agent-BasedData Synthesis","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":221,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04978","citing_title":"Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2511.15669","citing_title":"DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models","ref_index":44,"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":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02965","citing_title":"Open-Loop Planning, Closed-Loop Verification: Speculative Verification for VLA","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04974","citing_title":"From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Data","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25323","citing_title":"ANCHOR: A Physically Grounded Closed-Loop Framework for Robust Home-Service Mobile Manipulation","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PQICLB7LFUXY65NGD2HIQJ4GS4","json":"https://pith.science/pith/PQICLB7LFUXY65NGD2HIQJ4GS4.json","graph_json":"https://pith.science/api/pith-number/PQICLB7LFUXY65NGD2HIQJ4GS4/graph.json","events_json":"https://pith.science/api/pith-number/PQICLB7LFUXY65NGD2HIQJ4GS4/events.json","paper":"https://pith.science/paper/PQICLB7L"},"agent_actions":{"view_html":"https://pith.science/pith/PQICLB7LFUXY65NGD2HIQJ4GS4","download_json":"https://pith.science/pith/PQICLB7LFUXY65NGD2HIQJ4GS4.json","view_paper":"https://pith.science/paper/PQICLB7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02385&json=true","fetch_graph":"https://pith.science/api/pith-number/PQICLB7LFUXY65NGD2HIQJ4GS4/graph.json","fetch_events":"https://pith.science/api/pith-number/PQICLB7LFUXY65NGD2HIQJ4GS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQICLB7LFUXY65NGD2HIQJ4GS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQICLB7LFUXY65NGD2HIQJ4GS4/action/storage_attestation","attest_author":"https://pith.science/pith/PQICLB7LFUXY65NGD2HIQJ4GS4/action/author_attestation","sign_citation":"https://pith.science/pith/PQICLB7LFUXY65NGD2HIQJ4GS4/action/citation_signature","submit_replication":"https://pith.science/pith/PQICLB7LFUXY65NGD2HIQJ4GS4/action/replication_record"}},"created_at":"2026-07-05T07:41:48.663424+00:00","updated_at":"2026-07-05T07:41:48.663424+00:00"}