{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CS5ZHYPLNFHSBUBRJE7M7Q27GR","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":"1372cfed2315a05f80ed66cdff915e4910a8eb049f6afe955e0ecb9bb293ed3f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-18T17:51:51Z","title_canon_sha256":"15ab21bcb7c8d557e46a39a7d7906a6f959485dbba15f885894f7752be53eee7"},"schema_version":"1.0","source":{"id":"2410.14660","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14660","created_at":"2026-07-05T09:22:35Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14660v1","created_at":"2026-07-05T09:22:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14660","created_at":"2026-07-05T09:22:35Z"},{"alias_kind":"pith_short_12","alias_value":"CS5ZHYPLNFHS","created_at":"2026-07-05T09:22:35Z"},{"alias_kind":"pith_short_16","alias_value":"CS5ZHYPLNFHSBUBR","created_at":"2026-07-05T09:22:35Z"},{"alias_kind":"pith_short_8","alias_value":"CS5ZHYPL","created_at":"2026-07-05T09:22:35Z"}],"graph_snapshots":[{"event_id":"sha256:4590daf200f9c2408181958fcf5d34ae4061c9eec6a9cdc124d566e33d051d98","target":"graph","created_at":"2026-07-05T09:22:35Z","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/2410.14660/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown significant potential in designing reward functions for Reinforcement Learning (RL) tasks. However, obtaining high-quality reward code often involves human intervention, numerous LLM queries, or repetitive RL training. To address these issues, we propose CARD, a LLM-driven Reward Design framework that iteratively generates and improves reward function code. Specifically, CARD includes a Coder that generates and verifies the code, while a Evaluator provides dynamic feedback to guide the Coder in improving the code, eliminating the need for human feedback.","authors_text":"Jiafei Lyu, Jing-Wen Yang, Liangpeng Zhang, Runze Liu, Shengjie Sun, Xiu Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-18T17:51:51Z","title":"A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14660","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:c4ad5a431caa1a80f4b7d95859ce236dbe8d631a801595699be88fa74a8746e5","target":"record","created_at":"2026-07-05T09:22:35Z","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":"1372cfed2315a05f80ed66cdff915e4910a8eb049f6afe955e0ecb9bb293ed3f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-18T17:51:51Z","title_canon_sha256":"15ab21bcb7c8d557e46a39a7d7906a6f959485dbba15f885894f7752be53eee7"},"schema_version":"1.0","source":{"id":"2410.14660","kind":"arxiv","version":1}},"canonical_sha256":"14bb93e1eb694f20d031493ecfc35f346a183e5a8a7b146c7d246e982021c8e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14bb93e1eb694f20d031493ecfc35f346a183e5a8a7b146c7d246e982021c8e9","first_computed_at":"2026-07-05T09:22:35.022791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:35.022791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uLrz4xugbmfcFpYOCR8zP76A1vKq0zAs8BoGORoeHSaKm7DdfSbTb3hzqK3OxiN26GAeO+lBdNdzXQv6nHdTAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:35.023292Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.14660","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4ad5a431caa1a80f4b7d95859ce236dbe8d631a801595699be88fa74a8746e5","sha256:4590daf200f9c2408181958fcf5d34ae4061c9eec6a9cdc124d566e33d051d98"],"state_sha256":"2ec1d38116330cc4fda3e089fb32ee8167c5c3b346959355ebe1800982697411"}