{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:55D3N7NH75VAPZTJKMH3CII4JX","short_pith_number":"pith:55D3N7NH","canonical_record":{"source":{"id":"2210.01241","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-03T21:38:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"74bd7df0b4a90877838254155174abb485c17553e1b4f9552882117ecbff9dda","abstract_canon_sha256":"3d8885c3ea7a90d7f929dacf2aa09d05651af47f0050831c3b7604ec8b10bc3b"},"schema_version":"1.0"},"canonical_sha256":"ef47b6fda7ff6a07e669530fb1211c4dea7f8dee9f172b3a5ec6a6605120c980","source":{"kind":"arxiv","id":"2210.01241","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.01241","created_at":"2026-07-05T07:19:41Z"},{"alias_kind":"arxiv_version","alias_value":"2210.01241v3","created_at":"2026-07-05T07:19:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01241","created_at":"2026-07-05T07:19:41Z"},{"alias_kind":"pith_short_12","alias_value":"55D3N7NH75VA","created_at":"2026-07-05T07:19:41Z"},{"alias_kind":"pith_short_16","alias_value":"55D3N7NH75VAPZTJ","created_at":"2026-07-05T07:19:41Z"},{"alias_kind":"pith_short_8","alias_value":"55D3N7NH","created_at":"2026-07-05T07:19:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:55D3N7NH75VAPZTJKMH3CII4JX","target":"record","payload":{"canonical_record":{"source":{"id":"2210.01241","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-03T21:38:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"74bd7df0b4a90877838254155174abb485c17553e1b4f9552882117ecbff9dda","abstract_canon_sha256":"3d8885c3ea7a90d7f929dacf2aa09d05651af47f0050831c3b7604ec8b10bc3b"},"schema_version":"1.0"},"canonical_sha256":"ef47b6fda7ff6a07e669530fb1211c4dea7f8dee9f172b3a5ec6a6605120c980","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:41.845338Z","signature_b64":"3Q/S6tx+cRgD/pMSsGuqQmJbWXGJVH1//lr/wwKfGrOsoc4wRFp0jkH6XMcfgfe5yZE4AVTBIBQOxPri8QD3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef47b6fda7ff6a07e669530fb1211c4dea7f8dee9f172b3a5ec6a6605120c980","last_reissued_at":"2026-07-05T07:19:41.844857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:41.844857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.01241","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":"2026-07-05T07:19:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yPgLc0zIYEH/UA/ouUWzmpmnlQszARWC9JtZQu4TdSZ4Vmdy2CJOC5QieAgmicSB7TAGJA2eWbSAAgKSb4sSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:34:34.622502Z"},"content_sha256":"80b997e5f1f3c514caa9b6a964e866aa0e572119ce9f01d34a2a655133a2a773","schema_version":"1.0","event_id":"sha256:80b997e5f1f3c514caa9b6a964e866aa0e572119ce9f01d34a2a655133a2a773"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:55D3N7NH75VAPZTJKMH3CII4JX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Christian Bauckhage, Hannaneh Hajishirzi, Jack Hessel, Kiant\\'e Brantley, Prithviraj Ammanabrolu, Rafet Sifa, Rajkumar Ramamurthy, Yejin Choi","submitted_at":"2022-10-03T21:38:29Z","abstract_excerpt":"We tackle the problem of aligning pre-trained large language models (LMs) with human preferences. If we view text generation as a sequential decision-making problem, reinforcement learning (RL) appears to be a natural conceptual framework. However, using RL for LM-based generation faces empirical challenges, including training instability due to the combinatorial action space, as well as a lack of open-source libraries and benchmarks customized for LM alignment. Thus, a question rises in the research community: is RL a practical paradigm for NLP?\n  To help answer this, we first introduce an op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01241","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/2210.01241/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":"2026-07-05T07:19:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A3YhlwOLD2epyuoWLUEjl+EnEDykULdigNVwtYPYndrQPwVyDkgJHMcC/s1MQo4UrISzJW2LhPMxiYFh9zVqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:34:34.622999Z"},"content_sha256":"43213af4f20d83c4b3895f82fbf60a46d2e295ef06b0a9f9dfea838228493392","schema_version":"1.0","event_id":"sha256:43213af4f20d83c4b3895f82fbf60a46d2e295ef06b0a9f9dfea838228493392"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/55D3N7NH75VAPZTJKMH3CII4JX/bundle.json","state_url":"https://pith.science/pith/55D3N7NH75VAPZTJKMH3CII4JX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/55D3N7NH75VAPZTJKMH3CII4JX/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":"2026-08-08T02:34:34Z","links":{"resolver":"https://pith.science/pith/55D3N7NH75VAPZTJKMH3CII4JX","bundle":"https://pith.science/pith/55D3N7NH75VAPZTJKMH3CII4JX/bundle.json","state":"https://pith.science/pith/55D3N7NH75VAPZTJKMH3CII4JX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/55D3N7NH75VAPZTJKMH3CII4JX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:55D3N7NH75VAPZTJKMH3CII4JX","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":"3d8885c3ea7a90d7f929dacf2aa09d05651af47f0050831c3b7604ec8b10bc3b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-03T21:38:29Z","title_canon_sha256":"74bd7df0b4a90877838254155174abb485c17553e1b4f9552882117ecbff9dda"},"schema_version":"1.0","source":{"id":"2210.01241","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.01241","created_at":"2026-07-05T07:19:41Z"},{"alias_kind":"arxiv_version","alias_value":"2210.01241v3","created_at":"2026-07-05T07:19:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01241","created_at":"2026-07-05T07:19:41Z"},{"alias_kind":"pith_short_12","alias_value":"55D3N7NH75VA","created_at":"2026-07-05T07:19:41Z"},{"alias_kind":"pith_short_16","alias_value":"55D3N7NH75VAPZTJ","created_at":"2026-07-05T07:19:41Z"},{"alias_kind":"pith_short_8","alias_value":"55D3N7NH","created_at":"2026-07-05T07:19:41Z"}],"graph_snapshots":[{"event_id":"sha256:43213af4f20d83c4b3895f82fbf60a46d2e295ef06b0a9f9dfea838228493392","target":"graph","created_at":"2026-07-05T07:19:41Z","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/2210.01241/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We tackle the problem of aligning pre-trained large language models (LMs) with human preferences. If we view text generation as a sequential decision-making problem, reinforcement learning (RL) appears to be a natural conceptual framework. However, using RL for LM-based generation faces empirical challenges, including training instability due to the combinatorial action space, as well as a lack of open-source libraries and benchmarks customized for LM alignment. Thus, a question rises in the research community: is RL a practical paradigm for NLP?\n  To help answer this, we first introduce an op","authors_text":"Christian Bauckhage, Hannaneh Hajishirzi, Jack Hessel, Kiant\\'e Brantley, Prithviraj Ammanabrolu, Rafet Sifa, Rajkumar Ramamurthy, Yejin Choi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-03T21:38:29Z","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01241","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":"sha256:80b997e5f1f3c514caa9b6a964e866aa0e572119ce9f01d34a2a655133a2a773","target":"record","created_at":"2026-07-05T07:19:41Z","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":"3d8885c3ea7a90d7f929dacf2aa09d05651af47f0050831c3b7604ec8b10bc3b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-03T21:38:29Z","title_canon_sha256":"74bd7df0b4a90877838254155174abb485c17553e1b4f9552882117ecbff9dda"},"schema_version":"1.0","source":{"id":"2210.01241","kind":"arxiv","version":3}},"canonical_sha256":"ef47b6fda7ff6a07e669530fb1211c4dea7f8dee9f172b3a5ec6a6605120c980","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef47b6fda7ff6a07e669530fb1211c4dea7f8dee9f172b3a5ec6a6605120c980","first_computed_at":"2026-07-05T07:19:41.844857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:19:41.844857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3Q/S6tx+cRgD/pMSsGuqQmJbWXGJVH1//lr/wwKfGrOsoc4wRFp0jkH6XMcfgfe5yZE4AVTBIBQOxPri8QD3BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:19:41.845338Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.01241","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80b997e5f1f3c514caa9b6a964e866aa0e572119ce9f01d34a2a655133a2a773","sha256:43213af4f20d83c4b3895f82fbf60a46d2e295ef06b0a9f9dfea838228493392"],"state_sha256":"58b907e865580cd032e459e0c0d926f0a78588e2637760ddcaab2d7da7ecdfa6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+5BMSvgn7+HmJpGvDM6ASke4w+u/RSYe9KExjnPmowgN9ESGCovjrGj1t7d2axWeNfplukpElyyH0uLgtANRCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:34:34.627011Z","bundle_sha256":"171c860fc1dc3b88c93711c6c1c8cc5ed5edc3acb5baac5427a348a6bb51b808"}}