{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OENFZFZXMO33P5IBSYTB3QOKYP","short_pith_number":"pith:OENFZFZX","schema_version":"1.0","canonical_sha256":"711a5c973763b7b7f50196261dc1cac3e411cc336d702b2c4f0658a3ca039f5a","source":{"kind":"arxiv","id":"2508.18066","version":1},"attestation_state":"computed","paper":{"title":"Arnold: a generalist muscle transformer policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.QM"],"primary_cat":"cs.RO","authors_text":"Alberto Silvio Chiappa, Alexander Mathis, Boshi An, Chengkun Li, Merkourios Simos","submitted_at":"2025-08-25T14:22:40Z","abstract_excerpt":"Controlling high-dimensional and nonlinear musculoskeletal models of the human body is a foundational scientific challenge. Recent machine learning breakthroughs have heralded policies that master individual skills like reaching, object manipulation and locomotion in musculoskeletal systems with many degrees of freedom. However, these agents are merely \"specialists\", achieving high performance for a single skill. In this work, we develop Arnold, a generalist policy that masters multiple tasks and embodiments. Arnold combines behavior cloning and fine-tuning with PPO to achieve expert or super-"},"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":"2508.18066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-25T14:22:40Z","cross_cats_sorted":["cs.AI","cs.LG","q-bio.QM"],"title_canon_sha256":"730093cc06b3be794ecfe1b8dc63183558cbcfb8e537eb35b006eeba65d8d49f","abstract_canon_sha256":"b476b25003f816dbb28f5a48cee3b8ea835b512e92f04e9ae86693b3b6abf831"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:53.070745Z","signature_b64":"QoZwv6XPzAlI0j6btCQR/+YHF7TYb5t6QhLvX6/RqJz6QeUrWlatQ8NzVrIi6Oqgs3MsPFr5InMtmNKeulJaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"711a5c973763b7b7f50196261dc1cac3e411cc336d702b2c4f0658a3ca039f5a","last_reissued_at":"2026-07-05T11:58:53.070259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:53.070259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Arnold: a generalist muscle transformer policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.QM"],"primary_cat":"cs.RO","authors_text":"Alberto Silvio Chiappa, Alexander Mathis, Boshi An, Chengkun Li, Merkourios Simos","submitted_at":"2025-08-25T14:22:40Z","abstract_excerpt":"Controlling high-dimensional and nonlinear musculoskeletal models of the human body is a foundational scientific challenge. Recent machine learning breakthroughs have heralded policies that master individual skills like reaching, object manipulation and locomotion in musculoskeletal systems with many degrees of freedom. However, these agents are merely \"specialists\", achieving high performance for a single skill. In this work, we develop Arnold, a generalist policy that masters multiple tasks and embodiments. Arnold combines behavior cloning and fine-tuning with PPO to achieve expert or super-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18066","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/2508.18066/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":"2508.18066","created_at":"2026-07-05T11:58:53.070329+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18066v1","created_at":"2026-07-05T11:58:53.070329+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18066","created_at":"2026-07-05T11:58:53.070329+00:00"},{"alias_kind":"pith_short_12","alias_value":"OENFZFZXMO33","created_at":"2026-07-05T11:58:53.070329+00:00"},{"alias_kind":"pith_short_16","alias_value":"OENFZFZXMO33P5IB","created_at":"2026-07-05T11:58:53.070329+00:00"},{"alias_kind":"pith_short_8","alias_value":"OENFZFZX","created_at":"2026-07-05T11:58:53.070329+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.15650","citing_title":"MyoChallenge 2025: A New Benchmark for Human Athletic Intelligence","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OENFZFZXMO33P5IBSYTB3QOKYP","json":"https://pith.science/pith/OENFZFZXMO33P5IBSYTB3QOKYP.json","graph_json":"https://pith.science/api/pith-number/OENFZFZXMO33P5IBSYTB3QOKYP/graph.json","events_json":"https://pith.science/api/pith-number/OENFZFZXMO33P5IBSYTB3QOKYP/events.json","paper":"https://pith.science/paper/OENFZFZX"},"agent_actions":{"view_html":"https://pith.science/pith/OENFZFZXMO33P5IBSYTB3QOKYP","download_json":"https://pith.science/pith/OENFZFZXMO33P5IBSYTB3QOKYP.json","view_paper":"https://pith.science/paper/OENFZFZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18066&json=true","fetch_graph":"https://pith.science/api/pith-number/OENFZFZXMO33P5IBSYTB3QOKYP/graph.json","fetch_events":"https://pith.science/api/pith-number/OENFZFZXMO33P5IBSYTB3QOKYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OENFZFZXMO33P5IBSYTB3QOKYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OENFZFZXMO33P5IBSYTB3QOKYP/action/storage_attestation","attest_author":"https://pith.science/pith/OENFZFZXMO33P5IBSYTB3QOKYP/action/author_attestation","sign_citation":"https://pith.science/pith/OENFZFZXMO33P5IBSYTB3QOKYP/action/citation_signature","submit_replication":"https://pith.science/pith/OENFZFZXMO33P5IBSYTB3QOKYP/action/replication_record"}},"created_at":"2026-07-05T11:58:53.070329+00:00","updated_at":"2026-07-05T11:58:53.070329+00:00"}