{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LBLNG3LJBCVAFBTSZDOWLVOWCP","short_pith_number":"pith:LBLNG3LJ","schema_version":"1.0","canonical_sha256":"5856d36d6908aa028672c8dd65d5d613dc7381b0d1fa5b31330c512caa22af99","source":{"kind":"arxiv","id":"2508.16821","version":1},"attestation_state":"computed","paper":{"title":"PuzzleJAX: A Benchmark for Reasoning and Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ahmed Khalifa, Andrzej Banburski-Fahey, Graham Todd, Julian Togelius, Muhammad Umair Nasir, Sam Earle, Yuchen Li, Zehua Jiang","submitted_at":"2025-08-22T22:40:58Z","abstract_excerpt":"We introduce PuzzleJAX, a GPU-accelerated puzzle game engine and description language designed to support rapid benchmarking of tree search, reinforcement learning, and LLM reasoning abilities. Unlike existing GPU-accelerated learning environments that provide hard-coded implementations of fixed sets of games, PuzzleJAX allows dynamic compilation of any game expressible in its domain-specific language (DSL). This DSL follows PuzzleScript, which is a popular and accessible online game engine for designing puzzle games. In this paper, we validate in PuzzleJAX several hundred of the thousands of "},"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":"2508.16821","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-22T22:40:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fe478aa095a5a045a32dea60fd945316c3e6abcad430aa24456299218687a7ef","abstract_canon_sha256":"4f53a7c26bcd3395db5103c8a3e55fc353420d51ea4d3e0064478a73f0b6e617"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:04.500154Z","signature_b64":"DardrOBa039AqRzmWxMinD1gRpnXTyUr5S9hcxf6L94ENzotddlniHMMSzA0gIrCU/Pp3ejuPgwVQwatNDiVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5856d36d6908aa028672c8dd65d5d613dc7381b0d1fa5b31330c512caa22af99","last_reissued_at":"2026-07-05T11:58:04.499693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:04.499693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PuzzleJAX: A Benchmark for Reasoning and Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ahmed Khalifa, Andrzej Banburski-Fahey, Graham Todd, Julian Togelius, Muhammad Umair Nasir, Sam Earle, Yuchen Li, Zehua Jiang","submitted_at":"2025-08-22T22:40:58Z","abstract_excerpt":"We introduce PuzzleJAX, a GPU-accelerated puzzle game engine and description language designed to support rapid benchmarking of tree search, reinforcement learning, and LLM reasoning abilities. Unlike existing GPU-accelerated learning environments that provide hard-coded implementations of fixed sets of games, PuzzleJAX allows dynamic compilation of any game expressible in its domain-specific language (DSL). This DSL follows PuzzleScript, which is a popular and accessible online game engine for designing puzzle games. In this paper, we validate in PuzzleJAX several hundred of the thousands of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16821","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/2508.16821/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":"2508.16821","created_at":"2026-07-05T11:58:04.499755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.16821v1","created_at":"2026-07-05T11:58:04.499755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16821","created_at":"2026-07-05T11:58:04.499755+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBLNG3LJBCVA","created_at":"2026-07-05T11:58:04.499755+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBLNG3LJBCVAFBTS","created_at":"2026-07-05T11:58:04.499755+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBLNG3LJ","created_at":"2026-07-05T11:58:04.499755+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.08827","citing_title":"A Survey of Reinforcement Learning for Large Reasoning Models","ref_index":124,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LBLNG3LJBCVAFBTSZDOWLVOWCP","json":"https://pith.science/pith/LBLNG3LJBCVAFBTSZDOWLVOWCP.json","graph_json":"https://pith.science/api/pith-number/LBLNG3LJBCVAFBTSZDOWLVOWCP/graph.json","events_json":"https://pith.science/api/pith-number/LBLNG3LJBCVAFBTSZDOWLVOWCP/events.json","paper":"https://pith.science/paper/LBLNG3LJ"},"agent_actions":{"view_html":"https://pith.science/pith/LBLNG3LJBCVAFBTSZDOWLVOWCP","download_json":"https://pith.science/pith/LBLNG3LJBCVAFBTSZDOWLVOWCP.json","view_paper":"https://pith.science/paper/LBLNG3LJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.16821&json=true","fetch_graph":"https://pith.science/api/pith-number/LBLNG3LJBCVAFBTSZDOWLVOWCP/graph.json","fetch_events":"https://pith.science/api/pith-number/LBLNG3LJBCVAFBTSZDOWLVOWCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBLNG3LJBCVAFBTSZDOWLVOWCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBLNG3LJBCVAFBTSZDOWLVOWCP/action/storage_attestation","attest_author":"https://pith.science/pith/LBLNG3LJBCVAFBTSZDOWLVOWCP/action/author_attestation","sign_citation":"https://pith.science/pith/LBLNG3LJBCVAFBTSZDOWLVOWCP/action/citation_signature","submit_replication":"https://pith.science/pith/LBLNG3LJBCVAFBTSZDOWLVOWCP/action/replication_record"}},"created_at":"2026-07-05T11:58:04.499755+00:00","updated_at":"2026-07-05T11:58:04.499755+00:00"}