{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FC4EXAXJO3PA5ABKONE6N2DGM6","short_pith_number":"pith:FC4EXAXJ","schema_version":"1.0","canonical_sha256":"28b84b82e976de0e802a7349e6e866679d8c1a3489e7ff2f0a0b4e8853d97d57","source":{"kind":"arxiv","id":"2402.16117","version":1},"attestation_state":"computed","paper":{"title":"RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Chaofan Tao, Chao Yang, Chongjian Ge, Haibao Yu, Jifeng Dai, Junting Chen, Mengkang Hu, Mingyu Ding, Peize Sun, Ping Luo, Qiaojun Yu, Qinglong Zhang, Runjian Chen, Shoufa Chen, Wenhai Wang, Wenqi Shao, Yao Mu, Yu Qiao, Zhixuan Liang","submitted_at":"2024-02-25T15:31:43Z","abstract_excerpt":"Robotic behavior synthesis, the problem of understanding multimodal inputs and generating precise physical control for robots, is an important part of Embodied AI. Despite successes in applying multimodal large language models for high-level understanding, it remains challenging to translate these conceptual understandings into detailed robotic actions while achieving generalization across various scenarios. In this paper, we propose a tree-structured multimodal code generation framework for generalized robotic behavior synthesis, termed RoboCodeX. RoboCodeX decomposes high-level human instruc"},"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":"2402.16117","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-25T15:31:43Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"ffd4196482de0c2d905c95709935b45af4b7b578d497f470a3de191d323cac63","abstract_canon_sha256":"9dfa6a42483d1180864d1e6dac11c09509a160f420fcbea6146e1032f9bdb2bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:02.251235Z","signature_b64":"vjvc7a7Kp5X+at8fMkePgd1HEEG54KAIjTmBp/Gm/cG/02MwmCRI704Gh/Pmvb3fur8xAcPrWt6AdIHFeqmlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28b84b82e976de0e802a7349e6e866679d8c1a3489e7ff2f0a0b4e8853d97d57","last_reissued_at":"2026-07-05T07:49:02.250818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:02.250818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Chaofan Tao, Chao Yang, Chongjian Ge, Haibao Yu, Jifeng Dai, Junting Chen, Mengkang Hu, Mingyu Ding, Peize Sun, Ping Luo, Qiaojun Yu, Qinglong Zhang, Runjian Chen, Shoufa Chen, Wenhai Wang, Wenqi Shao, Yao Mu, Yu Qiao, Zhixuan Liang","submitted_at":"2024-02-25T15:31:43Z","abstract_excerpt":"Robotic behavior synthesis, the problem of understanding multimodal inputs and generating precise physical control for robots, is an important part of Embodied AI. Despite successes in applying multimodal large language models for high-level understanding, it remains challenging to translate these conceptual understandings into detailed robotic actions while achieving generalization across various scenarios. In this paper, we propose a tree-structured multimodal code generation framework for generalized robotic behavior synthesis, termed RoboCodeX. RoboCodeX decomposes high-level human instruc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16117","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/2402.16117/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":"2402.16117","created_at":"2026-07-05T07:49:02.250878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16117v1","created_at":"2026-07-05T07:49:02.250878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16117","created_at":"2026-07-05T07:49:02.250878+00:00"},{"alias_kind":"pith_short_12","alias_value":"FC4EXAXJO3PA","created_at":"2026-07-05T07:49:02.250878+00:00"},{"alias_kind":"pith_short_16","alias_value":"FC4EXAXJO3PA5ABK","created_at":"2026-07-05T07:49:02.250878+00:00"},{"alias_kind":"pith_short_8","alias_value":"FC4EXAXJ","created_at":"2026-07-05T07:49:02.250878+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19419","citing_title":"Playful Agentic Robot Learning","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.15932","citing_title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18747","citing_title":"Code as Agent Harness","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FC4EXAXJO3PA5ABKONE6N2DGM6","json":"https://pith.science/pith/FC4EXAXJO3PA5ABKONE6N2DGM6.json","graph_json":"https://pith.science/api/pith-number/FC4EXAXJO3PA5ABKONE6N2DGM6/graph.json","events_json":"https://pith.science/api/pith-number/FC4EXAXJO3PA5ABKONE6N2DGM6/events.json","paper":"https://pith.science/paper/FC4EXAXJ"},"agent_actions":{"view_html":"https://pith.science/pith/FC4EXAXJO3PA5ABKONE6N2DGM6","download_json":"https://pith.science/pith/FC4EXAXJO3PA5ABKONE6N2DGM6.json","view_paper":"https://pith.science/paper/FC4EXAXJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16117&json=true","fetch_graph":"https://pith.science/api/pith-number/FC4EXAXJO3PA5ABKONE6N2DGM6/graph.json","fetch_events":"https://pith.science/api/pith-number/FC4EXAXJO3PA5ABKONE6N2DGM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FC4EXAXJO3PA5ABKONE6N2DGM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FC4EXAXJO3PA5ABKONE6N2DGM6/action/storage_attestation","attest_author":"https://pith.science/pith/FC4EXAXJO3PA5ABKONE6N2DGM6/action/author_attestation","sign_citation":"https://pith.science/pith/FC4EXAXJO3PA5ABKONE6N2DGM6/action/citation_signature","submit_replication":"https://pith.science/pith/FC4EXAXJO3PA5ABKONE6N2DGM6/action/replication_record"}},"created_at":"2026-07-05T07:49:02.250878+00:00","updated_at":"2026-07-05T07:49:02.250878+00:00"}