{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y2QNNRKVLPDCJT6INMMMUEPOQO","short_pith_number":"pith:Y2QNNRKV","canonical_record":{"source":{"id":"2412.06394","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-09T11:22:59Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8da389d30dacf13974cfd180018759311b3992e4cd98efb6b4fea5a0be733aea","abstract_canon_sha256":"6db79d22bb9baf6aa8f1e9201112700269d3c0f4d908901f151dc26f799d0b23"},"schema_version":"1.0"},"canonical_sha256":"c6a0d6c5555bc624cfc86b18ca11ee839017c1fb1f355ec558cabb4e11682d77","source":{"kind":"arxiv","id":"2412.06394","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06394","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06394v5","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06394","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"pith_short_12","alias_value":"Y2QNNRKVLPDC","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"pith_short_16","alias_value":"Y2QNNRKVLPDCJT6I","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"pith_short_8","alias_value":"Y2QNNRKV","created_at":"2026-07-05T10:14:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y2QNNRKVLPDCJT6INMMMUEPOQO","target":"record","payload":{"canonical_record":{"source":{"id":"2412.06394","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-09T11:22:59Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8da389d30dacf13974cfd180018759311b3992e4cd98efb6b4fea5a0be733aea","abstract_canon_sha256":"6db79d22bb9baf6aa8f1e9201112700269d3c0f4d908901f151dc26f799d0b23"},"schema_version":"1.0"},"canonical_sha256":"c6a0d6c5555bc624cfc86b18ca11ee839017c1fb1f355ec558cabb4e11682d77","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:48.731608Z","signature_b64":"UmQigv0Ixkwo4iEH7LfU79AijSrh8EDyW0qPEIl5/69NIwlWwO8ZCBfjQL2+woELVKZScg4YUj5hUn8z5idcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6a0d6c5555bc624cfc86b18ca11ee839017c1fb1f355ec558cabb4e11682d77","last_reissued_at":"2026-07-05T10:14:48.731122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:48.731122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.06394","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:14:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iY2zS1QmNYaKDXHkUa8DF2voDKA5W5cwOHgMA0yNMxUfIArS58/zITRu1Nh4XsC3UFOEFjp2Y42GhIVDW+IICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:45:26.892863Z"},"content_sha256":"d30b17167411f3399c8003dc8ba771b811a36bb003e17eccb5518679b8b229ef","schema_version":"1.0","event_id":"sha256:d30b17167411f3399c8003dc8ba771b811a36bb003e17eccb5518679b8b229ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y2QNNRKVLPDCJT6INMMMUEPOQO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GameArena: Evaluating LLM Reasoning through Live Computer Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Anze Xie, Haojian Jin, Hao Zhang, Ion Stoica, Lanxiang Hu, Nan Jiang, Qiyu Li","submitted_at":"2024-12-09T11:22:59Z","abstract_excerpt":"Evaluating the reasoning abilities of large language models (LLMs) is challenging. Existing benchmarks often depend on static datasets, which are vulnerable to data contamination and may get saturated over time, or on binary live human feedback that conflates reasoning with other abilities. As the most prominent dynamic benchmark, Chatbot Arena evaluates open-ended questions in real-world settings, but lacks the granularity in assessing specific reasoning capabilities. We introduce GameArena, a dynamic benchmark designed to evaluate LLM reasoning capabilities through interactive gameplay with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06394","kind":"arxiv","version":5},"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/2412.06394/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":"2026-07-05T10:14:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nGlvR57eqWxiAP5IBm2KMRzWkNghpj5fr6ucVdjIPiBqZcUUOAM6n72chD4bfJnhHPJgv+kFDaZQuosYyAqhCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:45:26.893401Z"},"content_sha256":"ffb6d8e21d0a674bfe97ba7b3b38362f311f9ed4659e73604591a932f4ce3721","schema_version":"1.0","event_id":"sha256:ffb6d8e21d0a674bfe97ba7b3b38362f311f9ed4659e73604591a932f4ce3721"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y2QNNRKVLPDCJT6INMMMUEPOQO/bundle.json","state_url":"https://pith.science/pith/Y2QNNRKVLPDCJT6INMMMUEPOQO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y2QNNRKVLPDCJT6INMMMUEPOQO/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":"2026-08-07T22:45:26Z","links":{"resolver":"https://pith.science/pith/Y2QNNRKVLPDCJT6INMMMUEPOQO","bundle":"https://pith.science/pith/Y2QNNRKVLPDCJT6INMMMUEPOQO/bundle.json","state":"https://pith.science/pith/Y2QNNRKVLPDCJT6INMMMUEPOQO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y2QNNRKVLPDCJT6INMMMUEPOQO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y2QNNRKVLPDCJT6INMMMUEPOQO","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":"6db79d22bb9baf6aa8f1e9201112700269d3c0f4d908901f151dc26f799d0b23","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-09T11:22:59Z","title_canon_sha256":"8da389d30dacf13974cfd180018759311b3992e4cd98efb6b4fea5a0be733aea"},"schema_version":"1.0","source":{"id":"2412.06394","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06394","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06394v5","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06394","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"pith_short_12","alias_value":"Y2QNNRKVLPDC","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"pith_short_16","alias_value":"Y2QNNRKVLPDCJT6I","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"pith_short_8","alias_value":"Y2QNNRKV","created_at":"2026-07-05T10:14:48Z"}],"graph_snapshots":[{"event_id":"sha256:ffb6d8e21d0a674bfe97ba7b3b38362f311f9ed4659e73604591a932f4ce3721","target":"graph","created_at":"2026-07-05T10:14:48Z","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/2412.06394/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating the reasoning abilities of large language models (LLMs) is challenging. Existing benchmarks often depend on static datasets, which are vulnerable to data contamination and may get saturated over time, or on binary live human feedback that conflates reasoning with other abilities. As the most prominent dynamic benchmark, Chatbot Arena evaluates open-ended questions in real-world settings, but lacks the granularity in assessing specific reasoning capabilities. We introduce GameArena, a dynamic benchmark designed to evaluate LLM reasoning capabilities through interactive gameplay with ","authors_text":"Anze Xie, Haojian Jin, Hao Zhang, Ion Stoica, Lanxiang Hu, Nan Jiang, Qiyu Li","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-09T11:22:59Z","title":"GameArena: Evaluating LLM Reasoning through Live Computer Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06394","kind":"arxiv","version":5},"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:d30b17167411f3399c8003dc8ba771b811a36bb003e17eccb5518679b8b229ef","target":"record","created_at":"2026-07-05T10:14:48Z","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":"6db79d22bb9baf6aa8f1e9201112700269d3c0f4d908901f151dc26f799d0b23","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-09T11:22:59Z","title_canon_sha256":"8da389d30dacf13974cfd180018759311b3992e4cd98efb6b4fea5a0be733aea"},"schema_version":"1.0","source":{"id":"2412.06394","kind":"arxiv","version":5}},"canonical_sha256":"c6a0d6c5555bc624cfc86b18ca11ee839017c1fb1f355ec558cabb4e11682d77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6a0d6c5555bc624cfc86b18ca11ee839017c1fb1f355ec558cabb4e11682d77","first_computed_at":"2026-07-05T10:14:48.731122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:48.731122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UmQigv0Ixkwo4iEH7LfU79AijSrh8EDyW0qPEIl5/69NIwlWwO8ZCBfjQL2+woELVKZScg4YUj5hUn8z5idcBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:48.731608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06394","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d30b17167411f3399c8003dc8ba771b811a36bb003e17eccb5518679b8b229ef","sha256:ffb6d8e21d0a674bfe97ba7b3b38362f311f9ed4659e73604591a932f4ce3721"],"state_sha256":"193bda5b375a3cb7f58cf6db2cdcd2158dfe17d24c8dbfbfddd4d6b4eec01f8c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3xoNSGgatUmdNXT1pYidXEeUBL6t80kszgnJxyA8iM376IjZHJ83xykn8J+qvcWQK1WTTGnKvgTQE9TVgt6QBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:45:26.902975Z","bundle_sha256":"62af71cc94061f8f3df32b08902bf0206d60c2eedd82ced8826ad40400d837e0"}}