{"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"}