{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:D4XCIDOLZNSYRRWAHW6ACUKMDZ","short_pith_number":"pith:D4XCIDOL","schema_version":"1.0","canonical_sha256":"1f2e240dcbcb6588c6c03dbc01514c1e5a8608e061f77f61aa9cbfe6df92147e","source":{"kind":"arxiv","id":"2601.21570","version":2},"attestation_state":"computed","paper":{"title":"From Digital to Physical: Digital Agents as Autonomous Coaches for Physical Intelligence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Bo Zhao, Chuan Wen, Genjia Liu, Jixian Wu, Qipeng Liu, Shanghang Zhang, Siheng Chen, Sixiang Chen, Weixin Li, Wenzhao Lian, Yuanshuo Zhang, Yunhong Wang, Yuzhu Cai, Zixing Lei","submitted_at":"2026-01-29T11:33:49Z","abstract_excerpt":"The field of Embodied AI is witnessing a rapid evolution toward general-purpose robotic systems, fueled by high-fidelity simulation and large-scale data collection. However, this scaling capability remains severely bottlenecked by a reliance on labor-intensive manual oversight from intricate reward shaping to hyperparameter tuning across heterogeneous backends. Inspired by LLMs' success in software automation and science discovery, we introduce \\textsc{EmboCoach-Bench}, a benchmark evaluating the capacity of LLM agents to autonomously engineer embodied policies. Spanning 32 expert-curated RL a"},"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":"2601.21570","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-01-29T11:33:49Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"6194a5ec3f183d09608acfa9da0210db4e037fb3cc04c05e3c5aff199a2e443a","abstract_canon_sha256":"2574c58982d9711d5c451ff56f10779e9305bf85f326c2e78ba3852dacfa7530"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:21.122336Z","signature_b64":"i01YP9Z9waxbO+7btZdQTfS13ycqFi+QQOtw3eQK3G0QwweoJZ98FQ8bYFWUtOGk/32EobMKzcx43XGHXdlJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f2e240dcbcb6588c6c03dbc01514c1e5a8608e061f77f61aa9cbfe6df92147e","last_reissued_at":"2026-06-12T01:09:21.121677Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:21.121677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Digital to Physical: Digital Agents as Autonomous Coaches for Physical Intelligence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Bo Zhao, Chuan Wen, Genjia Liu, Jixian Wu, Qipeng Liu, Shanghang Zhang, Siheng Chen, Sixiang Chen, Weixin Li, Wenzhao Lian, Yuanshuo Zhang, Yunhong Wang, Yuzhu Cai, Zixing Lei","submitted_at":"2026-01-29T11:33:49Z","abstract_excerpt":"The field of Embodied AI is witnessing a rapid evolution toward general-purpose robotic systems, fueled by high-fidelity simulation and large-scale data collection. However, this scaling capability remains severely bottlenecked by a reliance on labor-intensive manual oversight from intricate reward shaping to hyperparameter tuning across heterogeneous backends. Inspired by LLMs' success in software automation and science discovery, we introduce \\textsc{EmboCoach-Bench}, a benchmark evaluating the capacity of LLM agents to autonomously engineer embodied policies. Spanning 32 expert-curated RL a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21570","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/2601.21570/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":"2601.21570","created_at":"2026-06-12T01:09:21.121754+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.21570v2","created_at":"2026-06-12T01:09:21.121754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21570","created_at":"2026-06-12T01:09:21.121754+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4XCIDOLZNSY","created_at":"2026-06-12T01:09:21.121754+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4XCIDOLZNSYRRWA","created_at":"2026-06-12T01:09:21.121754+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4XCIDOL","created_at":"2026-06-12T01:09:21.121754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.17406","citing_title":"EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D4XCIDOLZNSYRRWAHW6ACUKMDZ","json":"https://pith.science/pith/D4XCIDOLZNSYRRWAHW6ACUKMDZ.json","graph_json":"https://pith.science/api/pith-number/D4XCIDOLZNSYRRWAHW6ACUKMDZ/graph.json","events_json":"https://pith.science/api/pith-number/D4XCIDOLZNSYRRWAHW6ACUKMDZ/events.json","paper":"https://pith.science/paper/D4XCIDOL"},"agent_actions":{"view_html":"https://pith.science/pith/D4XCIDOLZNSYRRWAHW6ACUKMDZ","download_json":"https://pith.science/pith/D4XCIDOLZNSYRRWAHW6ACUKMDZ.json","view_paper":"https://pith.science/paper/D4XCIDOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.21570&json=true","fetch_graph":"https://pith.science/api/pith-number/D4XCIDOLZNSYRRWAHW6ACUKMDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/D4XCIDOLZNSYRRWAHW6ACUKMDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4XCIDOLZNSYRRWAHW6ACUKMDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4XCIDOLZNSYRRWAHW6ACUKMDZ/action/storage_attestation","attest_author":"https://pith.science/pith/D4XCIDOLZNSYRRWAHW6ACUKMDZ/action/author_attestation","sign_citation":"https://pith.science/pith/D4XCIDOLZNSYRRWAHW6ACUKMDZ/action/citation_signature","submit_replication":"https://pith.science/pith/D4XCIDOLZNSYRRWAHW6ACUKMDZ/action/replication_record"}},"created_at":"2026-06-12T01:09:21.121754+00:00","updated_at":"2026-06-12T01:09:21.121754+00:00"}