{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C3Y3NMN24PTCCGFMDKP3YH6BFZ","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":"d3fcbcbf72ac045bdb94ed5d53046790d2e8cf491d6aa059797980dfd2081e0a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-19T04:32:14Z","title_canon_sha256":"acc892a7c9341923b63a1841d1a3c0ed16845efeeb89e7f937f0424e93f4b689"},"schema_version":"1.0","source":{"id":"2505.13549","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13549","created_at":"2026-07-05T11:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13549v1","created_at":"2026-07-05T11:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13549","created_at":"2026-07-05T11:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"C3Y3NMN24PTC","created_at":"2026-07-05T11:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"C3Y3NMN24PTCCGFM","created_at":"2026-07-05T11:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"C3Y3NMN2","created_at":"2026-07-05T11:05:47Z"}],"graph_snapshots":[{"event_id":"sha256:beb2d10dcb9e2f6df85042d58848c7ea5409cc901f626fe11e8b592fd4fcca46","target":"graph","created_at":"2026-07-05T11:05:47Z","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/2505.13549/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robot learning in high-dimensional control settings, such as humanoid locomotion, presents persistent challenges for reinforcement learning (RL) algorithms due to unstable dynamics, complex contact interactions, and sensitivity to distributional shifts during training. Model-based methods, \\textit{e.g.}, Temporal-Difference Model Predictive Control (TD-MPC), have demonstrated promising results by combining short-horizon planning with value-based learning, enabling efficient solutions for basic locomotion tasks. However, these approaches remain ineffective in addressing policy mismatch and inst","authors_text":"An T. Le, Jan Peters, Khai Nguyen, Khang Nguyen, Manfred Huber, Minh Nhat Vu, Ngo Anh Vien","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-19T04:32:14Z","title":"TD-GRPC: Temporal Difference Learning with Group Relative Policy Constraint for Humanoid Locomotion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13549","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":"sha256:1be4f321da681fb8ad7563176fc625e5f582e16c5a521b34df565d16a02ac5b9","target":"record","created_at":"2026-07-05T11:05:47Z","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":"d3fcbcbf72ac045bdb94ed5d53046790d2e8cf491d6aa059797980dfd2081e0a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-19T04:32:14Z","title_canon_sha256":"acc892a7c9341923b63a1841d1a3c0ed16845efeeb89e7f937f0424e93f4b689"},"schema_version":"1.0","source":{"id":"2505.13549","kind":"arxiv","version":1}},"canonical_sha256":"16f1b6b1bae3e62118ac1a9fbc1fc12e74ef7c8cfc310f0a8dd0da6f23bd823c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16f1b6b1bae3e62118ac1a9fbc1fc12e74ef7c8cfc310f0a8dd0da6f23bd823c","first_computed_at":"2026-07-05T11:05:47.600913Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:47.600913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bf6V+YHFZpB4KNgmJ7vwcei8BRPIDBHnokCqtYMiCYRGppHvLy4i5EEBWDTU+J3K7iwckNUW+Kj9WqObeWLFBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:47.601424Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13549","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1be4f321da681fb8ad7563176fc625e5f582e16c5a521b34df565d16a02ac5b9","sha256:beb2d10dcb9e2f6df85042d58848c7ea5409cc901f626fe11e8b592fd4fcca46"],"state_sha256":"e7adf1ea8d22f7dfeba821f7e2a829271686bdebe237f31ebb7028e941fc1f5c"}