{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BW6CVDN5WLTPWTT5SP6QMRMDS3","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":"16f0d90ee11d9dc67ca8882655f636178e983b2bbdb2e198d8951a1d945d9a94","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-13T15:15:45Z","title_canon_sha256":"038276005c306a37ef954896105e63c6b86b8533845b364785be368335d7c5f5"},"schema_version":"1.0","source":{"id":"2409.08904","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08904","created_at":"2026-07-05T10:18:41Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08904v2","created_at":"2026-07-05T10:18:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08904","created_at":"2026-07-05T10:18:41Z"},{"alias_kind":"pith_short_12","alias_value":"BW6CVDN5WLTP","created_at":"2026-07-05T10:18:41Z"},{"alias_kind":"pith_short_16","alias_value":"BW6CVDN5WLTPWTT5","created_at":"2026-07-05T10:18:41Z"},{"alias_kind":"pith_short_8","alias_value":"BW6CVDN5","created_at":"2026-07-05T10:18:41Z"}],"graph_snapshots":[{"event_id":"sha256:32f46ea8434069f4b9ce0b98ab7ede3ccc0c17800733c2e1471745d6f0adb1a7","target":"graph","created_at":"2026-07-05T10:18:41Z","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/2409.08904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training and deploying reinforcement learning (RL) policies for robots, especially in accomplishing specific tasks, presents substantial challenges. Recent advancements have explored diverse reward function designs, training techniques, simulation-to-reality (sim-to-real) transfers, and performance analysis methodologies, yet these still require significant human intervention. This paper introduces an end-to-end framework for training and deploying RL policies, guided by Large Language Models (LLMs), and evaluates its effectiveness on bipedal robots. The framework consists of three interconnec","authors_text":"Chenyu Gu, Fuwei Tan, Jiaheng Du, Junguo Lu, Wentao He, Yifei Yao, Zhen Zhu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-13T15:15:45Z","title":"AnyBipe: An End-to-End Framework for Training and Deploying Bipedal Robots Guided by Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08904","kind":"arxiv","version":2},"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:feb3de92a59a3fdc6d424a4a1b1d98b62aeb75bf7e0c17f22db282cb7cdbef95","target":"record","created_at":"2026-07-05T10:18:41Z","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":"16f0d90ee11d9dc67ca8882655f636178e983b2bbdb2e198d8951a1d945d9a94","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-13T15:15:45Z","title_canon_sha256":"038276005c306a37ef954896105e63c6b86b8533845b364785be368335d7c5f5"},"schema_version":"1.0","source":{"id":"2409.08904","kind":"arxiv","version":2}},"canonical_sha256":"0dbc2a8dbdb2e6fb4e7d93fd06458396de76e54258aacba08ff94ef75a3395de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dbc2a8dbdb2e6fb4e7d93fd06458396de76e54258aacba08ff94ef75a3395de","first_computed_at":"2026-07-05T10:18:41.478532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:41.478532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pVResYCPvFkTGey0itG0JVp9HfSvz3B5Dutiocef9aYZzuD87J625f4KFx9qW5tu/8MM06KcnKopBwN3/jYgDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:41.478985Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08904","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:feb3de92a59a3fdc6d424a4a1b1d98b62aeb75bf7e0c17f22db282cb7cdbef95","sha256:32f46ea8434069f4b9ce0b98ab7ede3ccc0c17800733c2e1471745d6f0adb1a7"],"state_sha256":"fddbbd361b45c7de8c23e6b2c7ad7d99acafddb11d71c74a63d877bb24b6f6d7"}