{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VMFF3LH6YBUMAZ6RGYHGULG3B3","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":"1a8cfc3578a01441559fce79db52720312e073f0cd33f680a808bd261c9ab46b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-12T11:39:21Z","title_canon_sha256":"f7b1648be9dcb7158f45a6838cde70aa9d11cd8859d5f4630aa942a9607a060f"},"schema_version":"1.0","source":{"id":"2506.12095","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12095","created_at":"2026-07-05T11:21:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12095v1","created_at":"2026-07-05T11:21:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12095","created_at":"2026-07-05T11:21:16Z"},{"alias_kind":"pith_short_12","alias_value":"VMFF3LH6YBUM","created_at":"2026-07-05T11:21:16Z"},{"alias_kind":"pith_short_16","alias_value":"VMFF3LH6YBUMAZ6R","created_at":"2026-07-05T11:21:16Z"},{"alias_kind":"pith_short_8","alias_value":"VMFF3LH6","created_at":"2026-07-05T11:21:16Z"}],"graph_snapshots":[{"event_id":"sha256:584dc0dd8f0976bffd9a67c3dd91550f4ae8a4cfb71ad0229e7f20c29c4d059d","target":"graph","created_at":"2026-07-05T11:21:16Z","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/2506.12095/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Achieving robust robot learning for humanoid locomotion is a fundamental challenge in model-based reinforcement learning (MBRL), where environmental stochasticity and randomness can hinder efficient exploration and learning stability. The environmental, so-called aleatoric, uncertainty can be amplified in high-dimensional action spaces with complex contact dynamics, and further entangled with epistemic uncertainty in the models during learning phases. In this work, we propose DoublyAware, an uncertainty-aware extension of Temporal Difference Model Predictive Control (TD-MPC) that explicitly de","authors_text":"An T. Le, Jan Peters, Khang Nguyen, Minh Nhat Vu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-12T11:39:21Z","title":"DoublyAware: Dual Planning and Policy Awareness for Temporal Difference Learning in Humanoid Locomotion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12095","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":"sha256:65a06a61a5c12baf8c4c89665183bb0bfcee1d555d8f3060897ab52749a99552","target":"record","created_at":"2026-07-05T11:21:16Z","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":"1a8cfc3578a01441559fce79db52720312e073f0cd33f680a808bd261c9ab46b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-12T11:39:21Z","title_canon_sha256":"f7b1648be9dcb7158f45a6838cde70aa9d11cd8859d5f4630aa942a9607a060f"},"schema_version":"1.0","source":{"id":"2506.12095","kind":"arxiv","version":1}},"canonical_sha256":"ab0a5dacfec068c067d1360e6a2cdb0ec560c657d6083a8b3ab82e39ca21831c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab0a5dacfec068c067d1360e6a2cdb0ec560c657d6083a8b3ab82e39ca21831c","first_computed_at":"2026-07-05T11:21:16.968485Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:16.968485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y0KVzb348BUZRHN7ut6nnEA/6q7HQaDQtkkIPlSSxFqDzhQZIw01fikNo58S22Qlqq9Mfqy1lb8A9UBCanZWCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:16.968873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12095","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65a06a61a5c12baf8c4c89665183bb0bfcee1d555d8f3060897ab52749a99552","sha256:584dc0dd8f0976bffd9a67c3dd91550f4ae8a4cfb71ad0229e7f20c29c4d059d"],"state_sha256":"a7c018cedd2bcafdd44c6b4e30197f3609dfac25ab78a101eb53d662a909ffc1"}