{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EV2TIXO3QAPCRKLWSZHUL6SLOB","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":"eb83beb4ea0a7055aa1086c30a4cd2651df6334544b6fceeae22d4da2db14c62","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T22:24:14Z","title_canon_sha256":"f1385b23a1ddc0fa75df333d38c44c9b349e1eb318022bbf6b07c18f929f1012"},"schema_version":"1.0","source":{"id":"2403.07191","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.07191","created_at":"2026-07-05T07:55:00Z"},{"alias_kind":"arxiv_version","alias_value":"2403.07191v1","created_at":"2026-07-05T07:55:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07191","created_at":"2026-07-05T07:55:00Z"},{"alias_kind":"pith_short_12","alias_value":"EV2TIXO3QAPC","created_at":"2026-07-05T07:55:00Z"},{"alias_kind":"pith_short_16","alias_value":"EV2TIXO3QAPCRKLW","created_at":"2026-07-05T07:55:00Z"},{"alias_kind":"pith_short_8","alias_value":"EV2TIXO3","created_at":"2026-07-05T07:55:00Z"}],"graph_snapshots":[{"event_id":"sha256:94e4308539fc21276a4e4700c9c6e5d4ae7ece5d20d9a1e7ceaf9109fba70a86","target":"graph","created_at":"2026-07-05T07:55:00Z","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/2403.07191/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in reinforcement learning (RL) algorithms aim to enhance the performance of language models at scale. Yet, there is a noticeable absence of a cost-effective and standardized testbed tailored to evaluating and comparing these algorithms. To bridge this gap, we present a generalized version of the 24-Puzzle: the $(N,K)$-Puzzle, which challenges language models to reach a target value $K$ with $N$ integers. We evaluate the effectiveness of established RL algorithms such as Proximal Policy Optimization (PPO), alongside novel approaches like Identity Policy Optimization (IPO) and Di","authors_text":"Boyi Liu, Hongxia Yang, Liyu Chen, Qiwen Cui, Yingxiang Yang, Yufeng Zhang, Yunzhe Tao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T22:24:14Z","title":"$\\mathbf{(N,K)}$-Puzzle: A Cost-Efficient Testbed for Benchmarking Reinforcement Learning Algorithms in Generative Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07191","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:cf25979609a685d12e3641226db591fe3f5b88bc22a2b26e763e9426b07ffc9e","target":"record","created_at":"2026-07-05T07:55:00Z","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":"eb83beb4ea0a7055aa1086c30a4cd2651df6334544b6fceeae22d4da2db14c62","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T22:24:14Z","title_canon_sha256":"f1385b23a1ddc0fa75df333d38c44c9b349e1eb318022bbf6b07c18f929f1012"},"schema_version":"1.0","source":{"id":"2403.07191","kind":"arxiv","version":1}},"canonical_sha256":"2575345ddb801e28a976964f45fa4b706df0d74898fa3beea94ee0543fa32477","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2575345ddb801e28a976964f45fa4b706df0d74898fa3beea94ee0543fa32477","first_computed_at":"2026-07-05T07:55:00.426096Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:00.426096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ybHKRWxMkrbzpvixcl3/5b1n3IcjFVTyzFJHSN3LiYXYrgkT/EzUJ6AEmNKvGAfTAjxHZo67kK0F31AZG/rxBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:00.426619Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.07191","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf25979609a685d12e3641226db591fe3f5b88bc22a2b26e763e9426b07ffc9e","sha256:94e4308539fc21276a4e4700c9c6e5d4ae7ece5d20d9a1e7ceaf9109fba70a86"],"state_sha256":"f7745eb52d973a969b572cf4c018c2ffce1c413217a0a31efd9c3988655c2de1"}