{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7EH7MX3MJZO3ISTKIR2EUMSDGN","short_pith_number":"pith:7EH7MX3M","schema_version":"1.0","canonical_sha256":"f90ff65f6c4e5db44a6a44744a3243336f779220a728e0d508302635e114899e","source":{"kind":"arxiv","id":"2503.12533","version":2},"attestation_state":"computed","paper":{"title":"Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Bohan Zhou, B\\\"orje F. Karlsson, Haoqi Yuan, Xinrun Xu, Yicheng Feng, Yi Zhan, Yu Bai, Yuhui Fu, Zongqing Lu","submitted_at":"2025-03-16T14:53:53Z","abstract_excerpt":"Building autonomous robotic agents capable of achieving human-level performance in real-world embodied tasks is an ultimate goal in humanoid robot research. Recent advances have made significant progress in high-level cognition with Foundation Models (FMs) and low-level skill development for humanoid robots. However, directly combining these components often results in poor robustness and efficiency due to compounding errors in long-horizon tasks and the varied latency of different modules. We introduce Being-0, a hierarchical agent framework that integrates an FM with a modular skill library."},"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":"2503.12533","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-16T14:53:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7873326bf4d2ca28dcf783b75e5b4aedbbe41616d8968d917fba3265ea269844","abstract_canon_sha256":"7e41017b5fcc5accd5502ed89ee361b1158dbb8ad8692dcec7ef59bbd74bca16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:33.080065Z","signature_b64":"7vA2e9zgQyuYC2RSZNOPgeRTRWwCAtcb+gWqo1IaBbrngse+jQ1VOap8/B7F5n5NfLRQi9J9rfF0jGJ3aIlfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f90ff65f6c4e5db44a6a44744a3243336f779220a728e0d508302635e114899e","last_reissued_at":"2026-07-05T11:01:33.079674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:33.079674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Bohan Zhou, B\\\"orje F. Karlsson, Haoqi Yuan, Xinrun Xu, Yicheng Feng, Yi Zhan, Yu Bai, Yuhui Fu, Zongqing Lu","submitted_at":"2025-03-16T14:53:53Z","abstract_excerpt":"Building autonomous robotic agents capable of achieving human-level performance in real-world embodied tasks is an ultimate goal in humanoid robot research. Recent advances have made significant progress in high-level cognition with Foundation Models (FMs) and low-level skill development for humanoid robots. However, directly combining these components often results in poor robustness and efficiency due to compounding errors in long-horizon tasks and the varied latency of different modules. We introduce Being-0, a hierarchical agent framework that integrates an FM with a modular skill library."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12533","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/2503.12533/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":"2503.12533","created_at":"2026-07-05T11:01:33.079731+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.12533v2","created_at":"2026-07-05T11:01:33.079731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12533","created_at":"2026-07-05T11:01:33.079731+00:00"},{"alias_kind":"pith_short_12","alias_value":"7EH7MX3MJZO3","created_at":"2026-07-05T11:01:33.079731+00:00"},{"alias_kind":"pith_short_16","alias_value":"7EH7MX3MJZO3ISTK","created_at":"2026-07-05T11:01:33.079731+00:00"},{"alias_kind":"pith_short_8","alias_value":"7EH7MX3M","created_at":"2026-07-05T11:01:33.079731+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06493","citing_title":"HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15157","citing_title":"Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21133","citing_title":"Humanoid Whole-Body Manipulation via Active Spatial Brain and Generalizable Action Cerebellum","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15157","citing_title":"Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15671","citing_title":"Long-Term Memory for VLA-based Agents in Open-World Task Execution","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7EH7MX3MJZO3ISTKIR2EUMSDGN","json":"https://pith.science/pith/7EH7MX3MJZO3ISTKIR2EUMSDGN.json","graph_json":"https://pith.science/api/pith-number/7EH7MX3MJZO3ISTKIR2EUMSDGN/graph.json","events_json":"https://pith.science/api/pith-number/7EH7MX3MJZO3ISTKIR2EUMSDGN/events.json","paper":"https://pith.science/paper/7EH7MX3M"},"agent_actions":{"view_html":"https://pith.science/pith/7EH7MX3MJZO3ISTKIR2EUMSDGN","download_json":"https://pith.science/pith/7EH7MX3MJZO3ISTKIR2EUMSDGN.json","view_paper":"https://pith.science/paper/7EH7MX3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.12533&json=true","fetch_graph":"https://pith.science/api/pith-number/7EH7MX3MJZO3ISTKIR2EUMSDGN/graph.json","fetch_events":"https://pith.science/api/pith-number/7EH7MX3MJZO3ISTKIR2EUMSDGN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7EH7MX3MJZO3ISTKIR2EUMSDGN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7EH7MX3MJZO3ISTKIR2EUMSDGN/action/storage_attestation","attest_author":"https://pith.science/pith/7EH7MX3MJZO3ISTKIR2EUMSDGN/action/author_attestation","sign_citation":"https://pith.science/pith/7EH7MX3MJZO3ISTKIR2EUMSDGN/action/citation_signature","submit_replication":"https://pith.science/pith/7EH7MX3MJZO3ISTKIR2EUMSDGN/action/replication_record"}},"created_at":"2026-07-05T11:01:33.079731+00:00","updated_at":"2026-07-05T11:01:33.079731+00:00"}