{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QBB22QNJJBN3DXHYCIABH3IZTF","short_pith_number":"pith:QBB22QNJ","canonical_record":{"source":{"id":"2411.14251","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T15:57:02Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"2730f12c8ea64b6b5a2cf8d1b0e0e2766b970f0598984d8a414a930985835a6f","abstract_canon_sha256":"50fbf9e03d93d387d1831b6d2b1983b9ccba73f6f511755183457e59f79b9a8e"},"schema_version":"1.0"},"canonical_sha256":"8043ad41a9485bb1dcf8120013ed199954d162ae158ab4831346f6a2c4208df2","source":{"kind":"arxiv","id":"2411.14251","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14251","created_at":"2026-07-05T11:10:48Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14251v3","created_at":"2026-07-05T11:10:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14251","created_at":"2026-07-05T11:10:48Z"},{"alias_kind":"pith_short_12","alias_value":"QBB22QNJJBN3","created_at":"2026-07-05T11:10:48Z"},{"alias_kind":"pith_short_16","alias_value":"QBB22QNJJBN3DXHY","created_at":"2026-07-05T11:10:48Z"},{"alias_kind":"pith_short_8","alias_value":"QBB22QNJ","created_at":"2026-07-05T11:10:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QBB22QNJJBN3DXHYCIABH3IZTF","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14251","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T15:57:02Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"2730f12c8ea64b6b5a2cf8d1b0e0e2766b970f0598984d8a414a930985835a6f","abstract_canon_sha256":"50fbf9e03d93d387d1831b6d2b1983b9ccba73f6f511755183457e59f79b9a8e"},"schema_version":"1.0"},"canonical_sha256":"8043ad41a9485bb1dcf8120013ed199954d162ae158ab4831346f6a2c4208df2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:48.990676Z","signature_b64":"yieXrR6XnDNeY649PvdotLD2VRXbVbNFyNLuFeo6vdUNjAJrPIr3YT2jBvSamMZ8CZZ6UdkxRKJk1NqbCU1aBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8043ad41a9485bb1dcf8120013ed199954d162ae158ab4831346f6a2c4208df2","last_reissued_at":"2026-07-05T11:10:48.990185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:48.990185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14251","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pVlTnCXde3qPYuryowpUh46GxSGeadp2i7nWy6wEPnwClrF0E3HRKHVFR7H3ijYktmpDRMNukDe48w1I3P5FAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T16:33:35.215368Z"},"content_sha256":"f3df3421dcdd3ef0ee79024b484f681cd74b7f74c8e70529e3a8635fb671b86a","schema_version":"1.0","event_id":"sha256:f3df3421dcdd3ef0ee79024b484f681cd74b7f74c8e70529e3a8635fb671b86a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QBB22QNJJBN3DXHYCIABH3IZTF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Natural Language Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Girish A. Koushik, Haotian Fu, Jun Wang, Mengyue Yang, Xidong Feng, Yan Song, Ying Wen, Zhiyuan Hu, Ziyu Wan","submitted_at":"2024-11-21T15:57:02Z","abstract_excerpt":"Artificial intelligence progresses towards the \"Era of Experience,\" where agents are expected to learn from continuous, grounded interaction. We argue that traditional Reinforcement Learning (RL), which typically represents value as a scalar, can restrict agent's deep understanding of environments and hinders the active, deliberative learning crucial for navigating this new paradigm. To address the issue, we introduce Natural Language Reinforcement Learning (NLRL), a framework that extends RL principles into natural language counterparts. Central to NLRL is the Language Value Function (LVF), w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14251","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.14251/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b4Z3TK/hq4ts0rlpSI8ay9R0V13hrDeFERNRJo7+ETYz8VEHsIYIvW7DU7rr5Q4tYHRurKO5Mgi7nEeg5339Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T16:33:35.216161Z"},"content_sha256":"0766dfd248930f708234187913f45d1e80e15d3978d113484db4d4da59610abe","schema_version":"1.0","event_id":"sha256:0766dfd248930f708234187913f45d1e80e15d3978d113484db4d4da59610abe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QBB22QNJJBN3DXHYCIABH3IZTF/bundle.json","state_url":"https://pith.science/pith/QBB22QNJJBN3DXHYCIABH3IZTF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QBB22QNJJBN3DXHYCIABH3IZTF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T16:33:35Z","links":{"resolver":"https://pith.science/pith/QBB22QNJJBN3DXHYCIABH3IZTF","bundle":"https://pith.science/pith/QBB22QNJJBN3DXHYCIABH3IZTF/bundle.json","state":"https://pith.science/pith/QBB22QNJJBN3DXHYCIABH3IZTF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QBB22QNJJBN3DXHYCIABH3IZTF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QBB22QNJJBN3DXHYCIABH3IZTF","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":"50fbf9e03d93d387d1831b6d2b1983b9ccba73f6f511755183457e59f79b9a8e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T15:57:02Z","title_canon_sha256":"2730f12c8ea64b6b5a2cf8d1b0e0e2766b970f0598984d8a414a930985835a6f"},"schema_version":"1.0","source":{"id":"2411.14251","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14251","created_at":"2026-07-05T11:10:48Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14251v3","created_at":"2026-07-05T11:10:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14251","created_at":"2026-07-05T11:10:48Z"},{"alias_kind":"pith_short_12","alias_value":"QBB22QNJJBN3","created_at":"2026-07-05T11:10:48Z"},{"alias_kind":"pith_short_16","alias_value":"QBB22QNJJBN3DXHY","created_at":"2026-07-05T11:10:48Z"},{"alias_kind":"pith_short_8","alias_value":"QBB22QNJ","created_at":"2026-07-05T11:10:48Z"}],"graph_snapshots":[{"event_id":"sha256:0766dfd248930f708234187913f45d1e80e15d3978d113484db4d4da59610abe","target":"graph","created_at":"2026-07-05T11:10:48Z","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/2411.14251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Artificial intelligence progresses towards the \"Era of Experience,\" where agents are expected to learn from continuous, grounded interaction. We argue that traditional Reinforcement Learning (RL), which typically represents value as a scalar, can restrict agent's deep understanding of environments and hinders the active, deliberative learning crucial for navigating this new paradigm. To address the issue, we introduce Natural Language Reinforcement Learning (NLRL), a framework that extends RL principles into natural language counterparts. Central to NLRL is the Language Value Function (LVF), w","authors_text":"Bo Liu, Girish A. Koushik, Haotian Fu, Jun Wang, Mengyue Yang, Xidong Feng, Yan Song, Ying Wen, Zhiyuan Hu, Ziyu Wan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T15:57:02Z","title":"Natural Language Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14251","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:f3df3421dcdd3ef0ee79024b484f681cd74b7f74c8e70529e3a8635fb671b86a","target":"record","created_at":"2026-07-05T11:10:48Z","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":"50fbf9e03d93d387d1831b6d2b1983b9ccba73f6f511755183457e59f79b9a8e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T15:57:02Z","title_canon_sha256":"2730f12c8ea64b6b5a2cf8d1b0e0e2766b970f0598984d8a414a930985835a6f"},"schema_version":"1.0","source":{"id":"2411.14251","kind":"arxiv","version":3}},"canonical_sha256":"8043ad41a9485bb1dcf8120013ed199954d162ae158ab4831346f6a2c4208df2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8043ad41a9485bb1dcf8120013ed199954d162ae158ab4831346f6a2c4208df2","first_computed_at":"2026-07-05T11:10:48.990185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:48.990185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yieXrR6XnDNeY649PvdotLD2VRXbVbNFyNLuFeo6vdUNjAJrPIr3YT2jBvSamMZ8CZZ6UdkxRKJk1NqbCU1aBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:48.990676Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14251","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3df3421dcdd3ef0ee79024b484f681cd74b7f74c8e70529e3a8635fb671b86a","sha256:0766dfd248930f708234187913f45d1e80e15d3978d113484db4d4da59610abe"],"state_sha256":"071f665592263145d509a7fa3faa4cb5bf84ebc22cc807e6e3110a5998483e89"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xCye9wjCCrTUOa3P4zQMOQXhIR6qKITamsmEe13feUTmJtisjCC6/f3gXR6j7xNpjzbqnRLjN+LLuHgyyQNaCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T16:33:35.220969Z","bundle_sha256":"32d70afc67ce0d1e70d5ca984d1e0458d19c2bbb7184404dfea458528d49df45"}}