{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RSYEZRO3CFLWGOZIDPE7POAPKY","short_pith_number":"pith:RSYEZRO3","canonical_record":{"source":{"id":"2505.07215","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T04:01:03Z","cross_cats_sorted":[],"title_canon_sha256":"616b497a8ec8cba82f099a2a2720b8c880e0e0e6a99c5b06c33cf22ab7dae392","abstract_canon_sha256":"cb2ca01159d589cdd882d7cf458fd2bb820386780ba5c40fd6c2c189d4d6e4fe"},"schema_version":"1.0"},"canonical_sha256":"8cb04cc5db1157633b281bc9f7b80f5630fae0e5ecbd2437ed0ac23a536e8fc9","source":{"kind":"arxiv","id":"2505.07215","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07215","created_at":"2026-07-05T11:01:44Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07215v1","created_at":"2026-07-05T11:01:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07215","created_at":"2026-07-05T11:01:44Z"},{"alias_kind":"pith_short_12","alias_value":"RSYEZRO3CFLW","created_at":"2026-07-05T11:01:44Z"},{"alias_kind":"pith_short_16","alias_value":"RSYEZRO3CFLWGOZI","created_at":"2026-07-05T11:01:44Z"},{"alias_kind":"pith_short_8","alias_value":"RSYEZRO3","created_at":"2026-07-05T11:01:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RSYEZRO3CFLWGOZIDPE7POAPKY","target":"record","payload":{"canonical_record":{"source":{"id":"2505.07215","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T04:01:03Z","cross_cats_sorted":[],"title_canon_sha256":"616b497a8ec8cba82f099a2a2720b8c880e0e0e6a99c5b06c33cf22ab7dae392","abstract_canon_sha256":"cb2ca01159d589cdd882d7cf458fd2bb820386780ba5c40fd6c2c189d4d6e4fe"},"schema_version":"1.0"},"canonical_sha256":"8cb04cc5db1157633b281bc9f7b80f5630fae0e5ecbd2437ed0ac23a536e8fc9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:44.443692Z","signature_b64":"mYRTBYpD0Q+QW0vKd9tjYQ2cVwtGo1VwNiZm9xY7zph+IIg60MuPGH50ueUiPcqZCErqLvRJszQNLz8SmNpbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cb04cc5db1157633b281bc9f7b80f5630fae0e5ecbd2437ed0ac23a536e8fc9","last_reissued_at":"2026-07-05T11:01:44.443206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:44.443206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.07215","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:01:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RgLkXZAylwVRTmdTK5TuAsgF8XQTIq4Fn+YQkdLJezSU9QirxL1aMBIYb37HHwRUfJ/gqUJzcLR78Sey1AxxAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:05:55.144506Z"},"content_sha256":"8df5eba138a5ec7b67c0e84b7cad10fa36594190fff3d0b9246165ed85108ab4","schema_version":"1.0","event_id":"sha256:8df5eba138a5ec7b67c0e84b7cad10fa36594190fff3d0b9246165ed85108ab4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RSYEZRO3CFLWGOZIDPE7POAPKY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Measuring General Intelligence with Generated Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dan Klein, David Huang, Nicholas Tomlin, Vivek Verma, William Chen","submitted_at":"2025-05-12T04:01:03Z","abstract_excerpt":"We present gg-bench, a collection of game environments designed to evaluate general reasoning capabilities in language models. Unlike most static benchmarks, gg-bench is a data generating process where new evaluation instances can be generated at will. In particular, gg-bench is synthetically generated by (1) using a large language model (LLM) to generate natural language descriptions of novel games, (2) using the LLM to implement each game in code as a Gym environment, and (3) training reinforcement learning (RL) agents via self-play on the generated games. We evaluate language models by thei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07215","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/2505.07215/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":"2026-07-05T11:01:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hoENb7jDTRTWXWBne0VBAzWEKQ+QEhgPpM3NPAVLTLyrkVM6pAjOj25Px0YJ7RyE6WcEW97ppdPMfFx4Q7sqBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:05:55.145077Z"},"content_sha256":"5588c01b68b8a79c3ac14056e2e5ec8c56ccd48976a25535a24ec60f37982d0d","schema_version":"1.0","event_id":"sha256:5588c01b68b8a79c3ac14056e2e5ec8c56ccd48976a25535a24ec60f37982d0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RSYEZRO3CFLWGOZIDPE7POAPKY/bundle.json","state_url":"https://pith.science/pith/RSYEZRO3CFLWGOZIDPE7POAPKY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RSYEZRO3CFLWGOZIDPE7POAPKY/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":"2026-08-06T15:05:55Z","links":{"resolver":"https://pith.science/pith/RSYEZRO3CFLWGOZIDPE7POAPKY","bundle":"https://pith.science/pith/RSYEZRO3CFLWGOZIDPE7POAPKY/bundle.json","state":"https://pith.science/pith/RSYEZRO3CFLWGOZIDPE7POAPKY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RSYEZRO3CFLWGOZIDPE7POAPKY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RSYEZRO3CFLWGOZIDPE7POAPKY","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":"cb2ca01159d589cdd882d7cf458fd2bb820386780ba5c40fd6c2c189d4d6e4fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T04:01:03Z","title_canon_sha256":"616b497a8ec8cba82f099a2a2720b8c880e0e0e6a99c5b06c33cf22ab7dae392"},"schema_version":"1.0","source":{"id":"2505.07215","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07215","created_at":"2026-07-05T11:01:44Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07215v1","created_at":"2026-07-05T11:01:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07215","created_at":"2026-07-05T11:01:44Z"},{"alias_kind":"pith_short_12","alias_value":"RSYEZRO3CFLW","created_at":"2026-07-05T11:01:44Z"},{"alias_kind":"pith_short_16","alias_value":"RSYEZRO3CFLWGOZI","created_at":"2026-07-05T11:01:44Z"},{"alias_kind":"pith_short_8","alias_value":"RSYEZRO3","created_at":"2026-07-05T11:01:44Z"}],"graph_snapshots":[{"event_id":"sha256:5588c01b68b8a79c3ac14056e2e5ec8c56ccd48976a25535a24ec60f37982d0d","target":"graph","created_at":"2026-07-05T11:01:44Z","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/2505.07215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present gg-bench, a collection of game environments designed to evaluate general reasoning capabilities in language models. Unlike most static benchmarks, gg-bench is a data generating process where new evaluation instances can be generated at will. In particular, gg-bench is synthetically generated by (1) using a large language model (LLM) to generate natural language descriptions of novel games, (2) using the LLM to implement each game in code as a Gym environment, and (3) training reinforcement learning (RL) agents via self-play on the generated games. We evaluate language models by thei","authors_text":"Dan Klein, David Huang, Nicholas Tomlin, Vivek Verma, William Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T04:01:03Z","title":"Measuring General Intelligence with Generated Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07215","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":"sha256:8df5eba138a5ec7b67c0e84b7cad10fa36594190fff3d0b9246165ed85108ab4","target":"record","created_at":"2026-07-05T11:01:44Z","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":"cb2ca01159d589cdd882d7cf458fd2bb820386780ba5c40fd6c2c189d4d6e4fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T04:01:03Z","title_canon_sha256":"616b497a8ec8cba82f099a2a2720b8c880e0e0e6a99c5b06c33cf22ab7dae392"},"schema_version":"1.0","source":{"id":"2505.07215","kind":"arxiv","version":1}},"canonical_sha256":"8cb04cc5db1157633b281bc9f7b80f5630fae0e5ecbd2437ed0ac23a536e8fc9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8cb04cc5db1157633b281bc9f7b80f5630fae0e5ecbd2437ed0ac23a536e8fc9","first_computed_at":"2026-07-05T11:01:44.443206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:44.443206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mYRTBYpD0Q+QW0vKd9tjYQ2cVwtGo1VwNiZm9xY7zph+IIg60MuPGH50ueUiPcqZCErqLvRJszQNLz8SmNpbCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:44.443692Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07215","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8df5eba138a5ec7b67c0e84b7cad10fa36594190fff3d0b9246165ed85108ab4","sha256:5588c01b68b8a79c3ac14056e2e5ec8c56ccd48976a25535a24ec60f37982d0d"],"state_sha256":"b4df72f166af29710064b159323210b78ebfa38dc5771f959921318cf08762eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kKmR02rs8ElZB0InsGdY+aCdMozDYqxSiBRREtiWgHjDQMX+6NoScyqMPVSY3u+G5tztga/eCD1QYfpq8VgmBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T15:05:55.151193Z","bundle_sha256":"36a0c2648860cb80e584a30fd180dfe5e796980bea5f479a1af1299e8ac04ec2"}}