{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:COIVWEKU63CRX6JJR476DZHSLD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"50c42c45c2f3bbd8ee91d0e96885e5f8245eb979f34a35e5b5783dde18c4b586","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-04T04:12:47Z","title_canon_sha256":"712550cddf86bc8a4cbb551b363f571aadbabc61ce0972db3f6d016e2c895d4b"},"schema_version":"1.0","source":{"id":"2606.05687","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05687","created_at":"2026-06-05T01:14:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05687v1","created_at":"2026-06-05T01:14:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05687","created_at":"2026-06-05T01:14:59Z"},{"alias_kind":"pith_short_12","alias_value":"COIVWEKU63CR","created_at":"2026-06-05T01:14:59Z"},{"alias_kind":"pith_short_16","alias_value":"COIVWEKU63CRX6JJ","created_at":"2026-06-05T01:14:59Z"},{"alias_kind":"pith_short_8","alias_value":"COIVWEKU","created_at":"2026-06-05T01:14:59Z"}],"graph_snapshots":[{"event_id":"sha256:00ab4a17b762b685ec30ba32785f7dc1582ff1799647c23b0be3e1a80effe6c4","target":"graph","created_at":"2026-06-05T01:14:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.05687/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In humanoid motion control, model predictive control (MPC) offers physically grounded prediction and constraint handling, while reinforcement learning (RL) enables robust whole-body skills through large-scale simulation. However, using MPC inside RL often requires time-consuming problem construction or excessive training overhead, making such frameworks difficult to justify in practice. This work studies efficient training-time MPC guidance for humanoid locomotion and manipulation, termed MPC-RL. We introduce a centroidal-dynamics MPC reward formulation that leverages guidance from MPC traject","authors_text":"Aaron D. Ames, J\\'an Drgo\\v{n}a, Junheng Li, Liang Wu, Lizhi Yang, Sergio A. Esteban","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-04T04:12:47Z","title":"Accelerating and Scaling MPC-Guided Reinforcement Learning for Humanoid Locomotion and Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05687","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:965bf6288847c18e6dd9ce5ed687443893419da9efebca4c5e1f78d10b4d4bfc","target":"record","created_at":"2026-06-05T01:14:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"50c42c45c2f3bbd8ee91d0e96885e5f8245eb979f34a35e5b5783dde18c4b586","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-04T04:12:47Z","title_canon_sha256":"712550cddf86bc8a4cbb551b363f571aadbabc61ce0972db3f6d016e2c895d4b"},"schema_version":"1.0","source":{"id":"2606.05687","kind":"arxiv","version":1}},"canonical_sha256":"13915b1154f6c51bf9298f3fe1e4f258e20dff2b7ec3b26bde990577aa53a0e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13915b1154f6c51bf9298f3fe1e4f258e20dff2b7ec3b26bde990577aa53a0e6","first_computed_at":"2026-06-05T01:14:59.323626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:14:59.323626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WLnSsHcA0JEgng9+4eZFIlQY19zD/wZ0FJOQ1HS16SJYqmVLlmDnLDCD45Paf2mfNWNr9JF5h6bKwTDnFO8vCQ==","signature_status":"signed_v1","signed_at":"2026-06-05T01:14:59.324257Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05687","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:965bf6288847c18e6dd9ce5ed687443893419da9efebca4c5e1f78d10b4d4bfc","sha256:00ab4a17b762b685ec30ba32785f7dc1582ff1799647c23b0be3e1a80effe6c4"],"state_sha256":"f4b5b7037a2eb376512ae6775d1ce83d0e4a5af4eb35ad5bb07a931f660a544b"}