{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SOG6MVO4EYZTLQTUJN6OKP7K3Q","short_pith_number":"pith:SOG6MVO4","canonical_record":{"source":{"id":"2602.17831","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-19T20:49:15Z","cross_cats_sorted":[],"title_canon_sha256":"f6af8e5358cf4da324d66e498d577a06e6d638de030795952b0184f16b994c80","abstract_canon_sha256":"7015a60f64340df852d5093b26b515bee6bec55914e0d4ea508b949ba32dd554"},"schema_version":"1.0"},"canonical_sha256":"938de655dc263335c2744b7ce53feadc32c0350fa714a48cef87ab46679593a1","source":{"kind":"arxiv","id":"2602.17831","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.17831","created_at":"2026-05-20T00:02:09Z"},{"alias_kind":"arxiv_version","alias_value":"2602.17831v2","created_at":"2026-05-20T00:02:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17831","created_at":"2026-05-20T00:02:09Z"},{"alias_kind":"pith_short_12","alias_value":"SOG6MVO4EYZT","created_at":"2026-05-20T00:02:09Z"},{"alias_kind":"pith_short_16","alias_value":"SOG6MVO4EYZTLQTU","created_at":"2026-05-20T00:02:09Z"},{"alias_kind":"pith_short_8","alias_value":"SOG6MVO4","created_at":"2026-05-20T00:02:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SOG6MVO4EYZTLQTUJN6OKP7K3Q","target":"record","payload":{"canonical_record":{"source":{"id":"2602.17831","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-19T20:49:15Z","cross_cats_sorted":[],"title_canon_sha256":"f6af8e5358cf4da324d66e498d577a06e6d638de030795952b0184f16b994c80","abstract_canon_sha256":"7015a60f64340df852d5093b26b515bee6bec55914e0d4ea508b949ba32dd554"},"schema_version":"1.0"},"canonical_sha256":"938de655dc263335c2744b7ce53feadc32c0350fa714a48cef87ab46679593a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:09.967153Z","signature_b64":"flGuP64W6ivmmp+n48XHhZceAOAz2cYR4G3Tr9psPPOJSQFmG8zdEAVE9l14pPv/eBjW6U5I1/S7G+jW03ktAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"938de655dc263335c2744b7ce53feadc32c0350fa714a48cef87ab46679593a1","last_reissued_at":"2026-05-20T00:02:09.966248Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:09.966248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.17831","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ilZI3u4btLDvu+v1uOKHYiaRYZmUF1v4n4anM+3YcGxxeeLzAC05wPtt682scXHTRXYLpTI0QXcHzv/fxJNKCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T22:35:56.560253Z"},"content_sha256":"c9ee8ce00a7433ad8f8220e5db0c95abec6e6c245a09a5fbb693ffe322fd2551","schema_version":"1.0","event_id":"sha256:c9ee8ce00a7433ad8f8220e5db0c95abec6e6c245a09a5fbb693ffe322fd2551"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SOG6MVO4EYZTLQTUJN6OKP7K3Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Token Games: Evaluating Language Model Reasoning with Puzzle Duels","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gabriel Poesia, Simon Henniger","submitted_at":"2026-02-19T20:49:15Z","abstract_excerpt":"Evaluating the reasoning capabilities of Large Language Models is increasingly challenging as models improve. Human curation of hard questions is highly expensive, especially in recent benchmarks using PhD-level domain knowledge to challenge the most capable models. Even then, there is always a concern about whether these questions test genuine reasoning or if similar problems have been seen during training. Here, we take inspiration from 16th-century mathematical duels to design The Token Games (TTG): an evaluation framework where models challenge each other by creating their own puzzles. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.17831","kind":"arxiv","version":2},"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/2602.17831/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":"2026-05-20T00:02:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DFJjI73ttcScdDaLVP9eGsg3Fg3BzGnpOZORthTnrq+WIW/cu13pmdfxp0BP54mlSSoZdPkbV0e8Rj7M0lcuDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T22:35:56.560799Z"},"content_sha256":"94d58dfc93d4b7cf979ae9a9fd5d0db23403bfdd35b50112a75d6620011bbb1f","schema_version":"1.0","event_id":"sha256:94d58dfc93d4b7cf979ae9a9fd5d0db23403bfdd35b50112a75d6620011bbb1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SOG6MVO4EYZTLQTUJN6OKP7K3Q/bundle.json","state_url":"https://pith.science/pith/SOG6MVO4EYZTLQTUJN6OKP7K3Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SOG6MVO4EYZTLQTUJN6OKP7K3Q/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":"2026-05-31T22:35:56Z","links":{"resolver":"https://pith.science/pith/SOG6MVO4EYZTLQTUJN6OKP7K3Q","bundle":"https://pith.science/pith/SOG6MVO4EYZTLQTUJN6OKP7K3Q/bundle.json","state":"https://pith.science/pith/SOG6MVO4EYZTLQTUJN6OKP7K3Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SOG6MVO4EYZTLQTUJN6OKP7K3Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SOG6MVO4EYZTLQTUJN6OKP7K3Q","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":"7015a60f64340df852d5093b26b515bee6bec55914e0d4ea508b949ba32dd554","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-19T20:49:15Z","title_canon_sha256":"f6af8e5358cf4da324d66e498d577a06e6d638de030795952b0184f16b994c80"},"schema_version":"1.0","source":{"id":"2602.17831","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.17831","created_at":"2026-05-20T00:02:09Z"},{"alias_kind":"arxiv_version","alias_value":"2602.17831v2","created_at":"2026-05-20T00:02:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17831","created_at":"2026-05-20T00:02:09Z"},{"alias_kind":"pith_short_12","alias_value":"SOG6MVO4EYZT","created_at":"2026-05-20T00:02:09Z"},{"alias_kind":"pith_short_16","alias_value":"SOG6MVO4EYZTLQTU","created_at":"2026-05-20T00:02:09Z"},{"alias_kind":"pith_short_8","alias_value":"SOG6MVO4","created_at":"2026-05-20T00:02:09Z"}],"graph_snapshots":[{"event_id":"sha256:94d58dfc93d4b7cf979ae9a9fd5d0db23403bfdd35b50112a75d6620011bbb1f","target":"graph","created_at":"2026-05-20T00:02:09Z","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/2602.17831/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating the reasoning capabilities of Large Language Models is increasingly challenging as models improve. Human curation of hard questions is highly expensive, especially in recent benchmarks using PhD-level domain knowledge to challenge the most capable models. Even then, there is always a concern about whether these questions test genuine reasoning or if similar problems have been seen during training. Here, we take inspiration from 16th-century mathematical duels to design The Token Games (TTG): an evaluation framework where models challenge each other by creating their own puzzles. We ","authors_text":"Gabriel Poesia, Simon Henniger","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-19T20:49:15Z","title":"The Token Games: Evaluating Language Model Reasoning with Puzzle Duels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.17831","kind":"arxiv","version":2},"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:c9ee8ce00a7433ad8f8220e5db0c95abec6e6c245a09a5fbb693ffe322fd2551","target":"record","created_at":"2026-05-20T00:02:09Z","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":"7015a60f64340df852d5093b26b515bee6bec55914e0d4ea508b949ba32dd554","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-19T20:49:15Z","title_canon_sha256":"f6af8e5358cf4da324d66e498d577a06e6d638de030795952b0184f16b994c80"},"schema_version":"1.0","source":{"id":"2602.17831","kind":"arxiv","version":2}},"canonical_sha256":"938de655dc263335c2744b7ce53feadc32c0350fa714a48cef87ab46679593a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"938de655dc263335c2744b7ce53feadc32c0350fa714a48cef87ab46679593a1","first_computed_at":"2026-05-20T00:02:09.966248Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:09.966248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"flGuP64W6ivmmp+n48XHhZceAOAz2cYR4G3Tr9psPPOJSQFmG8zdEAVE9l14pPv/eBjW6U5I1/S7G+jW03ktAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:09.967153Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.17831","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9ee8ce00a7433ad8f8220e5db0c95abec6e6c245a09a5fbb693ffe322fd2551","sha256:94d58dfc93d4b7cf979ae9a9fd5d0db23403bfdd35b50112a75d6620011bbb1f"],"state_sha256":"115a19ed2b235b5d2b2e2ad7cd603d37cb602495f4be02ccda7c068e1512a865"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fb3mK3nyj5o+cTvmQSATfKqu6IBNK6/mG9impRfge8foxS7iG6J3XL1S8UcyeJXRcqO1ATTqhrRMI6+nCU89Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T22:35:56.563986Z","bundle_sha256":"fda41d07ef07bc385d8e839b1e3b51eba827eaaed55dfcba3085d5e1b5140622"}}