{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:43UYQUIIGC3YOMIA4WW2T4JXFX","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":"f95062471aa359777a57ae59a7e298e06f1c761ca13ffc964cb2fb9fb51a2bb3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-18T04:20:33Z","title_canon_sha256":"608dcd298709fc5db4684eceaff6c76a6673fcffd60ef858f9634b8f6c4c11b2"},"schema_version":"1.0","source":{"id":"2412.13492","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13492","created_at":"2026-07-05T09:51:02Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13492v1","created_at":"2026-07-05T09:51:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13492","created_at":"2026-07-05T09:51:02Z"},{"alias_kind":"pith_short_12","alias_value":"43UYQUIIGC3Y","created_at":"2026-07-05T09:51:02Z"},{"alias_kind":"pith_short_16","alias_value":"43UYQUIIGC3YOMIA","created_at":"2026-07-05T09:51:02Z"},{"alias_kind":"pith_short_8","alias_value":"43UYQUII","created_at":"2026-07-05T09:51:02Z"}],"graph_snapshots":[{"event_id":"sha256:79a6f1d4761336ec7b70ff386a678fc319699f2d4fb53c95f9bfd12c6d3ef273","target":"graph","created_at":"2026-07-05T09:51:02Z","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/2412.13492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability to autonomously explore and resolve tasks with minimal human guidance is crucial for the self-development of embodied intelligence. Although reinforcement learning methods can largely ease human effort, it's challenging to design reward functions for real-world tasks, especially for high-dimensional robotic control, due to complex relationships among joints and tasks. Recent advancements large language models (LLMs) enable automatic reward function design. However, approaches evaluate reward functions by re-training policies from scratch placing an undue burden on the reward functi","authors_text":"Changxin Huang, Jianqiang Li, Junfan Lin, Junyang Liang, Runhao Zeng, Yanbin Chang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-18T04:20:33Z","title":"Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13492","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:e7c38e3bddfcc1b5d1b4b09e4e074bde00a1535bb8d1c9db5441d77e1cb40a4e","target":"record","created_at":"2026-07-05T09:51:02Z","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":"f95062471aa359777a57ae59a7e298e06f1c761ca13ffc964cb2fb9fb51a2bb3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-18T04:20:33Z","title_canon_sha256":"608dcd298709fc5db4684eceaff6c76a6673fcffd60ef858f9634b8f6c4c11b2"},"schema_version":"1.0","source":{"id":"2412.13492","kind":"arxiv","version":1}},"canonical_sha256":"e6e988510830b7873100e5ada9f1372de07e54d7aff4fda2848a0ffa80d726f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6e988510830b7873100e5ada9f1372de07e54d7aff4fda2848a0ffa80d726f6","first_computed_at":"2026-07-05T09:51:02.723848Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:02.723848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"56sdhYo7Qv3ZEhd+lNjULHHVhvvq1rSPPi15VAGi4MNMpF6VoDYIA2gTX+jDj8DXBzsq87n9F4iqSXpYDo30Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:02.724436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13492","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7c38e3bddfcc1b5d1b4b09e4e074bde00a1535bb8d1c9db5441d77e1cb40a4e","sha256:79a6f1d4761336ec7b70ff386a678fc319699f2d4fb53c95f9bfd12c6d3ef273"],"state_sha256":"845aca4726c65f43abc76deface1ad60f31dac229585b6bb5745d67d92acf6bd"}