{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EV2TIXO3QAPCRKLWSZHUL6SLOB","short_pith_number":"pith:EV2TIXO3","schema_version":"1.0","canonical_sha256":"2575345ddb801e28a976964f45fa4b706df0d74898fa3beea94ee0543fa32477","source":{"kind":"arxiv","id":"2403.07191","version":1},"attestation_state":"computed","paper":{"title":"$\\mathbf{(N,K)}$-Puzzle: A Cost-Efficient Testbed for Benchmarking Reinforcement Learning Algorithms in Generative Language Model","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Boyi Liu, Hongxia Yang, Liyu Chen, Qiwen Cui, Yingxiang Yang, Yufeng Zhang, Yunzhe Tao","submitted_at":"2024-03-11T22:24:14Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.07191","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T22:24:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f1385b23a1ddc0fa75df333d38c44c9b349e1eb318022bbf6b07c18f929f1012","abstract_canon_sha256":"eb83beb4ea0a7055aa1086c30a4cd2651df6334544b6fceeae22d4da2db14c62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:00.426619Z","signature_b64":"ybHKRWxMkrbzpvixcl3/5b1n3IcjFVTyzFJHSN3LiYXYrgkT/EzUJ6AEmNKvGAfTAjxHZo67kK0F31AZG/rxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2575345ddb801e28a976964f45fa4b706df0d74898fa3beea94ee0543fa32477","last_reissued_at":"2026-07-05T07:55:00.426096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:00.426096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$\\mathbf{(N,K)}$-Puzzle: A Cost-Efficient Testbed for Benchmarking Reinforcement Learning Algorithms in Generative Language Model","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Boyi Liu, Hongxia Yang, Liyu Chen, Qiwen Cui, Yingxiang Yang, Yufeng Zhang, Yunzhe Tao","submitted_at":"2024-03-11T22:24:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07191","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/2403.07191/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.07191","created_at":"2026-07-05T07:55:00.426153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.07191v1","created_at":"2026-07-05T07:55:00.426153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07191","created_at":"2026-07-05T07:55:00.426153+00:00"},{"alias_kind":"pith_short_12","alias_value":"EV2TIXO3QAPC","created_at":"2026-07-05T07:55:00.426153+00:00"},{"alias_kind":"pith_short_16","alias_value":"EV2TIXO3QAPCRKLW","created_at":"2026-07-05T07:55:00.426153+00:00"},{"alias_kind":"pith_short_8","alias_value":"EV2TIXO3","created_at":"2026-07-05T07:55:00.426153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EV2TIXO3QAPCRKLWSZHUL6SLOB","json":"https://pith.science/pith/EV2TIXO3QAPCRKLWSZHUL6SLOB.json","graph_json":"https://pith.science/api/pith-number/EV2TIXO3QAPCRKLWSZHUL6SLOB/graph.json","events_json":"https://pith.science/api/pith-number/EV2TIXO3QAPCRKLWSZHUL6SLOB/events.json","paper":"https://pith.science/paper/EV2TIXO3"},"agent_actions":{"view_html":"https://pith.science/pith/EV2TIXO3QAPCRKLWSZHUL6SLOB","download_json":"https://pith.science/pith/EV2TIXO3QAPCRKLWSZHUL6SLOB.json","view_paper":"https://pith.science/paper/EV2TIXO3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.07191&json=true","fetch_graph":"https://pith.science/api/pith-number/EV2TIXO3QAPCRKLWSZHUL6SLOB/graph.json","fetch_events":"https://pith.science/api/pith-number/EV2TIXO3QAPCRKLWSZHUL6SLOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EV2TIXO3QAPCRKLWSZHUL6SLOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EV2TIXO3QAPCRKLWSZHUL6SLOB/action/storage_attestation","attest_author":"https://pith.science/pith/EV2TIXO3QAPCRKLWSZHUL6SLOB/action/author_attestation","sign_citation":"https://pith.science/pith/EV2TIXO3QAPCRKLWSZHUL6SLOB/action/citation_signature","submit_replication":"https://pith.science/pith/EV2TIXO3QAPCRKLWSZHUL6SLOB/action/replication_record"}},"created_at":"2026-07-05T07:55:00.426153+00:00","updated_at":"2026-07-05T07:55:00.426153+00:00"}