{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BDTDV26LLMIBTM7B3OALLNQUMO","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":"a5d3278c0f51506fe97adc1138c6d2033175cab2c67310178beb9682ec31d68d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-11T11:03:04Z","title_canon_sha256":"2730f12c8ea64b6b5a2cf8d1b0e0e2766b970f0598984d8a414a930985835a6f"},"schema_version":"1.0","source":{"id":"2402.07157","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07157","created_at":"2026-07-05T07:45:15Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07157v2","created_at":"2026-07-05T07:45:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07157","created_at":"2026-07-05T07:45:15Z"},{"alias_kind":"pith_short_12","alias_value":"BDTDV26LLMIB","created_at":"2026-07-05T07:45:15Z"},{"alias_kind":"pith_short_16","alias_value":"BDTDV26LLMIBTM7B","created_at":"2026-07-05T07:45:15Z"},{"alias_kind":"pith_short_8","alias_value":"BDTDV26L","created_at":"2026-07-05T07:45:15Z"}],"graph_snapshots":[{"event_id":"sha256:e8d4e61be44464c235a3ecb69514879c4447b1abbb4fce172a0818811c0d6dee","target":"graph","created_at":"2026-07-05T07:45:15Z","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/2402.07157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has shown remarkable abilities in learning policies for decision-making tasks. However, RL is often hindered by issues such as low sample efficiency, lack of interpretability, and sparse supervision signals. To tackle these limitations, we take inspiration from the human learning process and introduce Natural Language Reinforcement Learning (NLRL), which innovatively combines RL principles with natural language representation. Specifically, NLRL redefines RL concepts like task objectives, policy, value function, Bellman equation, and policy iteration in natural lang","authors_text":"Girish A. Koushik, Jun Wang, Mengyue Yang, Xidong Feng, Yali Du, Ying Wen, Ziyan Wang, Ziyu Wan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-11T11:03:04Z","title":"Natural Language Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07157","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":"sha256:1c6735f5e38d9c7c3f8ad7e8bc73c74256ba1bd53697569e5fbf8eab36fe2206","target":"record","created_at":"2026-07-05T07:45:15Z","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":"a5d3278c0f51506fe97adc1138c6d2033175cab2c67310178beb9682ec31d68d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-11T11:03:04Z","title_canon_sha256":"2730f12c8ea64b6b5a2cf8d1b0e0e2766b970f0598984d8a414a930985835a6f"},"schema_version":"1.0","source":{"id":"2402.07157","kind":"arxiv","version":2}},"canonical_sha256":"08e63aebcb5b1019b3e1db80b5b614638fb1bb96273d2e05f2c5a27b85d0ed3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08e63aebcb5b1019b3e1db80b5b614638fb1bb96273d2e05f2c5a27b85d0ed3a","first_computed_at":"2026-07-05T07:45:15.751245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:45:15.751245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nC0J3naCUo759UbGRdcssd941VFczTWDGZPwWqLIPfr1Lr6nRJqJoRylAHoWaIGabP4IS2OvHzUNYf4jgFw2BA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:45:15.751737Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07157","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c6735f5e38d9c7c3f8ad7e8bc73c74256ba1bd53697569e5fbf8eab36fe2206","sha256:e8d4e61be44464c235a3ecb69514879c4447b1abbb4fce172a0818811c0d6dee"],"state_sha256":"9c73907e2f9b05d35979fffe97c89441fb5ac6245274b5d128fe442698a7b493"}