{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FSOJHDWVPDGJI7RSJB4NLOCOTP","short_pith_number":"pith:FSOJHDWV","canonical_record":{"source":{"id":"2402.01874","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T20:01:15Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"61c3fd952ee48b47f58551a84ec941c1d844c8cde1bfc095e01777e972b91ff3","abstract_canon_sha256":"a9ae3e35c9e888814553936766a6fd743ee06f15f3849eedb7b899c069afe6a8"},"schema_version":"1.0"},"canonical_sha256":"2c9c938ed578cc947e324878d5b84e9bc425cd04236636d334c92a65ba2c4d48","source":{"kind":"arxiv","id":"2402.01874","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01874","created_at":"2026-07-05T09:00:01Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01874v1","created_at":"2026-07-05T09:00:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01874","created_at":"2026-07-05T09:00:01Z"},{"alias_kind":"pith_short_12","alias_value":"FSOJHDWVPDGJ","created_at":"2026-07-05T09:00:01Z"},{"alias_kind":"pith_short_16","alias_value":"FSOJHDWVPDGJI7RS","created_at":"2026-07-05T09:00:01Z"},{"alias_kind":"pith_short_8","alias_value":"FSOJHDWV","created_at":"2026-07-05T09:00:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FSOJHDWVPDGJI7RSJB4NLOCOTP","target":"record","payload":{"canonical_record":{"source":{"id":"2402.01874","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T20:01:15Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"61c3fd952ee48b47f58551a84ec941c1d844c8cde1bfc095e01777e972b91ff3","abstract_canon_sha256":"a9ae3e35c9e888814553936766a6fd743ee06f15f3849eedb7b899c069afe6a8"},"schema_version":"1.0"},"canonical_sha256":"2c9c938ed578cc947e324878d5b84e9bc425cd04236636d334c92a65ba2c4d48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:01.599586Z","signature_b64":"DjLz9TSlChJ03ESSlbRQ1R2q1M8AatVv06DXLGhsA/sTPi8si8aTAecxNPpFiX8cODc1HM1Hna+rcc2rvd9OAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c9c938ed578cc947e324878d5b84e9bc425cd04236636d334c92a65ba2c4d48","last_reissued_at":"2026-07-05T09:00:01.599083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:01.599083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.01874","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:00:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WuRwwq7G6kuEQVFs2vAU/RsrOySHzSL+FwCWcEy1m/cxNTD0LlRczpX0FK/6fFI6UBy0B5vTj+fx/olfI4W4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:42:51.940748Z"},"content_sha256":"078fe08260aec52425bdee6292e030a02f65206f9085e149a526fdb9f0815d5b","schema_version":"1.0","event_id":"sha256:078fe08260aec52425bdee6292e030a02f65206f9085e149a526fdb9f0815d5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FSOJHDWVPDGJI7RSJB4NLOCOTP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CL","authors_text":"Abir Chakraborty, Kebei Jiang, Mirco Milletari, Moschoula Pternea, Prerna Singh, Sayli Bapat, Yagna Oruganti","submitted_at":"2024-02-02T20:01:15Z","abstract_excerpt":"In this work, we review research studies that combine Reinforcement Learning (RL) and Large Language Models (LLMs), two areas that owe their momentum to the development of deep neural networks. We propose a novel taxonomy of three main classes based on the way that the two model types interact with each other. The first class, RL4LLM, includes studies where RL is leveraged to improve the performance of LLMs on tasks related to Natural Language Processing. L4LLM is divided into two sub-categories depending on whether RL is used to directly fine-tune an existing LLM or to improve the prompt of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01874","kind":"arxiv","version":1},"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/2402.01874/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":"2026-07-05T09:00:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tYMOxQYZ6KwZLatm/0Nk2sYiIGl897tmHrfcIqZ9rDvC3Xo2E70GMlHcO17xnAEA/DTTi8gk0+R4oawcnF32Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:42:51.941122Z"},"content_sha256":"a4445a766d9e927612676f250179cb7b1e966f7ae494ab2bd88a9060d1015664","schema_version":"1.0","event_id":"sha256:a4445a766d9e927612676f250179cb7b1e966f7ae494ab2bd88a9060d1015664"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FSOJHDWVPDGJI7RSJB4NLOCOTP/bundle.json","state_url":"https://pith.science/pith/FSOJHDWVPDGJI7RSJB4NLOCOTP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FSOJHDWVPDGJI7RSJB4NLOCOTP/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":"2026-07-06T20:42:51Z","links":{"resolver":"https://pith.science/pith/FSOJHDWVPDGJI7RSJB4NLOCOTP","bundle":"https://pith.science/pith/FSOJHDWVPDGJI7RSJB4NLOCOTP/bundle.json","state":"https://pith.science/pith/FSOJHDWVPDGJI7RSJB4NLOCOTP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FSOJHDWVPDGJI7RSJB4NLOCOTP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FSOJHDWVPDGJI7RSJB4NLOCOTP","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":"a9ae3e35c9e888814553936766a6fd743ee06f15f3849eedb7b899c069afe6a8","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T20:01:15Z","title_canon_sha256":"61c3fd952ee48b47f58551a84ec941c1d844c8cde1bfc095e01777e972b91ff3"},"schema_version":"1.0","source":{"id":"2402.01874","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01874","created_at":"2026-07-05T09:00:01Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01874v1","created_at":"2026-07-05T09:00:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01874","created_at":"2026-07-05T09:00:01Z"},{"alias_kind":"pith_short_12","alias_value":"FSOJHDWVPDGJ","created_at":"2026-07-05T09:00:01Z"},{"alias_kind":"pith_short_16","alias_value":"FSOJHDWVPDGJI7RS","created_at":"2026-07-05T09:00:01Z"},{"alias_kind":"pith_short_8","alias_value":"FSOJHDWV","created_at":"2026-07-05T09:00:01Z"}],"graph_snapshots":[{"event_id":"sha256:a4445a766d9e927612676f250179cb7b1e966f7ae494ab2bd88a9060d1015664","target":"graph","created_at":"2026-07-05T09:00:01Z","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/2402.01874/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we review research studies that combine Reinforcement Learning (RL) and Large Language Models (LLMs), two areas that owe their momentum to the development of deep neural networks. We propose a novel taxonomy of three main classes based on the way that the two model types interact with each other. The first class, RL4LLM, includes studies where RL is leveraged to improve the performance of LLMs on tasks related to Natural Language Processing. L4LLM is divided into two sub-categories depending on whether RL is used to directly fine-tune an existing LLM or to improve the prompt of t","authors_text":"Abir Chakraborty, Kebei Jiang, Mirco Milletari, Moschoula Pternea, Prerna Singh, Sayli Bapat, Yagna Oruganti","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T20:01:15Z","title":"The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01874","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":"sha256:078fe08260aec52425bdee6292e030a02f65206f9085e149a526fdb9f0815d5b","target":"record","created_at":"2026-07-05T09:00:01Z","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":"a9ae3e35c9e888814553936766a6fd743ee06f15f3849eedb7b899c069afe6a8","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T20:01:15Z","title_canon_sha256":"61c3fd952ee48b47f58551a84ec941c1d844c8cde1bfc095e01777e972b91ff3"},"schema_version":"1.0","source":{"id":"2402.01874","kind":"arxiv","version":1}},"canonical_sha256":"2c9c938ed578cc947e324878d5b84e9bc425cd04236636d334c92a65ba2c4d48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c9c938ed578cc947e324878d5b84e9bc425cd04236636d334c92a65ba2c4d48","first_computed_at":"2026-07-05T09:00:01.599083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:01.599083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DjLz9TSlChJ03ESSlbRQ1R2q1M8AatVv06DXLGhsA/sTPi8si8aTAecxNPpFiX8cODc1HM1Hna+rcc2rvd9OAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:01.599586Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01874","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:078fe08260aec52425bdee6292e030a02f65206f9085e149a526fdb9f0815d5b","sha256:a4445a766d9e927612676f250179cb7b1e966f7ae494ab2bd88a9060d1015664"],"state_sha256":"12f54ca68543a255a93614d394c19aa1d8a5a33f51176d23abe2a76d3f8fe347"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rz8pJaWNjm5stwd+pyhQIIQQfJ6NKpmvA6nFrSVs/iVSdQOUCo4IbuSlm8hlEozq+9liUJSBGOKul2/qyDlJDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:42:51.943363Z","bundle_sha256":"d7835e97da9931de4f859d166cde2b5557accc29cf812b1ba71222972ed63969"}}