{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XQU2KGED6YLCC35QX2TNQHGXFG","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":"a78eb14deb35082812d65bf62980abddadce2e6c2507732eac256d48b834923f","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-20T17:39:13Z","title_canon_sha256":"af16c92cf8c86dde30d5c540836063fc23dd44d85a8966f5b62c1b7b019b1582"},"schema_version":"1.0","source":{"id":"2309.11489","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.11489","created_at":"2026-07-05T08:23:12Z"},{"alias_kind":"arxiv_version","alias_value":"2309.11489v3","created_at":"2026-07-05T08:23:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11489","created_at":"2026-07-05T08:23:12Z"},{"alias_kind":"pith_short_12","alias_value":"XQU2KGED6YLC","created_at":"2026-07-05T08:23:12Z"},{"alias_kind":"pith_short_16","alias_value":"XQU2KGED6YLCC35Q","created_at":"2026-07-05T08:23:12Z"},{"alias_kind":"pith_short_8","alias_value":"XQU2KGED","created_at":"2026-07-05T08:23:12Z"}],"graph_snapshots":[{"event_id":"sha256:3f070665e87e8c9e40126e3760a60974208f2c0b132754144d0852398b0aaa7f","target":"graph","created_at":"2026-07-05T08:23:12Z","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/2309.11489/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing reward functions is a longstanding challenge in reinforcement learning (RL); it requires specialized knowledge or domain data, leading to high costs for development. To address this, we introduce Text2Reward, a data-free framework that automates the generation and shaping of dense reward functions based on large language models (LLMs). Given a goal described in natural language, Text2Reward generates shaped dense reward functions as an executable program grounded in a compact representation of the environment. Unlike inverse RL and recent work that uses LLMs to write sparse reward co","authors_text":"Chen Henry Wu, Qian Luo, Siheng Zhao, Tao Yu, Tianbao Xie, Victor Zhong, Yanchao Yang, Yitao Liu","cross_cats":["cs.AI","cs.CL","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-20T17:39:13Z","title":"Text2Reward: Reward Shaping with Language Models for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11489","kind":"arxiv","version":3},"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:ca1466fc7e691e32f42c8a2dd7b5067f1585fac1299e2f71bd7665162588a73c","target":"record","created_at":"2026-07-05T08:23:12Z","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":"a78eb14deb35082812d65bf62980abddadce2e6c2507732eac256d48b834923f","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-20T17:39:13Z","title_canon_sha256":"af16c92cf8c86dde30d5c540836063fc23dd44d85a8966f5b62c1b7b019b1582"},"schema_version":"1.0","source":{"id":"2309.11489","kind":"arxiv","version":3}},"canonical_sha256":"bc29a51883f616216fb0bea6d81cd729b1cfa2c4428fd8d39b7a7c36430be89a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc29a51883f616216fb0bea6d81cd729b1cfa2c4428fd8d39b7a7c36430be89a","first_computed_at":"2026-07-05T08:23:12.143612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:12.143612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CxXupDUTGQNiacsHLZTjjTTTMYPhhtCBsXoZQwle/SD2QVQ+/2zQ7z/wLsBPTmUnfBOy2dDkCrlB+3NkfafNDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:12.144110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.11489","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca1466fc7e691e32f42c8a2dd7b5067f1585fac1299e2f71bd7665162588a73c","sha256:3f070665e87e8c9e40126e3760a60974208f2c0b132754144d0852398b0aaa7f"],"state_sha256":"13bd4d7565c703706f7471c33b8b9e2df6b0ebf0a3740121fb42722fabcf3bc2"}