{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OI6QZSLIU4XW36FXU3QMCI3LD3","short_pith_number":"pith:OI6QZSLI","canonical_record":{"source":{"id":"2505.15146","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-21T06:02:55Z","cross_cats_sorted":[],"title_canon_sha256":"5ea5e616461b067a5d222fed88b2e1aa45afe5edc0558eb173851d0ee163284a","abstract_canon_sha256":"39af4c16d010f54d48bc8c36a35b4c4f841e28bc627b7e2d70ba473e5ecbc660"},"schema_version":"1.0"},"canonical_sha256":"723d0cc968a72f6df8b7a6e0c1236b1ee319a37cdcf4a2556454afa204ed9fac","source":{"kind":"arxiv","id":"2505.15146","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15146","created_at":"2026-07-05T11:14:59Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15146v2","created_at":"2026-07-05T11:14:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15146","created_at":"2026-07-05T11:14:59Z"},{"alias_kind":"pith_short_12","alias_value":"OI6QZSLIU4XW","created_at":"2026-07-05T11:14:59Z"},{"alias_kind":"pith_short_16","alias_value":"OI6QZSLIU4XW36FX","created_at":"2026-07-05T11:14:59Z"},{"alias_kind":"pith_short_8","alias_value":"OI6QZSLI","created_at":"2026-07-05T11:14:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OI6QZSLIU4XW36FXU3QMCI3LD3","target":"record","payload":{"canonical_record":{"source":{"id":"2505.15146","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-21T06:02:55Z","cross_cats_sorted":[],"title_canon_sha256":"5ea5e616461b067a5d222fed88b2e1aa45afe5edc0558eb173851d0ee163284a","abstract_canon_sha256":"39af4c16d010f54d48bc8c36a35b4c4f841e28bc627b7e2d70ba473e5ecbc660"},"schema_version":"1.0"},"canonical_sha256":"723d0cc968a72f6df8b7a6e0c1236b1ee319a37cdcf4a2556454afa204ed9fac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:59.922182Z","signature_b64":"BeuQzW58uqEeuDUIqiTtU2YN4uoYa7cvNdW0HxC54hvFvFcHyavyD+hmF5T3otmBMsMB71WmxOPaR84Nt9ZZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"723d0cc968a72f6df8b7a6e0c1236b1ee319a37cdcf4a2556454afa204ed9fac","last_reissued_at":"2026-07-05T11:14:59.921689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:59.921689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.15146","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":"2026-07-05T11:14:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qnYni0InO6GGcvZcT9unIwW+RlSWWy0tWI0qqbMTYDGDruhgusJTPdPfJZ0iatv/054VZUs1OJ8SUIl5KPiFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:14:27.159282Z"},"content_sha256":"62e4074fba774f0ce93cb7a9c9cae1fdb442e19d5e23db0560b97ff2b591043e","schema_version":"1.0","event_id":"sha256:62e4074fba774f0ce93cb7a9c9cae1fdb442e19d5e23db0560b97ff2b591043e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OI6QZSLIU4XW36FXU3QMCI3LD3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"lmgame-Bench: How Good are LLMs at Playing Games?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Eric P. Xing, Haojian Jin, Haoyang Yu, Hao Zhang, Ion Stoica, Lanxiang Hu, Mingjia Huo, Tajana Rosing, Yuxuan Zhang","submitted_at":"2025-05-21T06:02:55Z","abstract_excerpt":"Playing video games requires perception, memory, and planning, exactly the faculties modern large language model (LLM) agents are expected to master. We study the major challenges in using popular video games to evaluate modern LLMs and find that directly dropping LLMs into games cannot make an effective evaluation, for three reasons -- brittle vision perception, prompt sensitivity, and potential data contamination. We introduce lmgame-Bench to turn games into reliable evaluations. lmgame-Bench features a suite of platformer, puzzle, and narrative games delivered through a unified Gym-style AP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15146","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/2505.15146/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":"2026-07-05T11:14:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z81ygeKOqHCc6pExRLq6pJq4rDXmwCMQp0BXguyuJX1ikSVzjEG+FIjeXAWWiganF2+ax4MTpOI+p+nv34wyDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:14:27.159775Z"},"content_sha256":"9f39f7733e2f63e63147710dad3522e6deb691d91ce515ba90c3517b06f7c6de","schema_version":"1.0","event_id":"sha256:9f39f7733e2f63e63147710dad3522e6deb691d91ce515ba90c3517b06f7c6de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OI6QZSLIU4XW36FXU3QMCI3LD3/bundle.json","state_url":"https://pith.science/pith/OI6QZSLIU4XW36FXU3QMCI3LD3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OI6QZSLIU4XW36FXU3QMCI3LD3/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":"2026-08-06T01:14:27Z","links":{"resolver":"https://pith.science/pith/OI6QZSLIU4XW36FXU3QMCI3LD3","bundle":"https://pith.science/pith/OI6QZSLIU4XW36FXU3QMCI3LD3/bundle.json","state":"https://pith.science/pith/OI6QZSLIU4XW36FXU3QMCI3LD3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OI6QZSLIU4XW36FXU3QMCI3LD3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OI6QZSLIU4XW36FXU3QMCI3LD3","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":"39af4c16d010f54d48bc8c36a35b4c4f841e28bc627b7e2d70ba473e5ecbc660","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-21T06:02:55Z","title_canon_sha256":"5ea5e616461b067a5d222fed88b2e1aa45afe5edc0558eb173851d0ee163284a"},"schema_version":"1.0","source":{"id":"2505.15146","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15146","created_at":"2026-07-05T11:14:59Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15146v2","created_at":"2026-07-05T11:14:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15146","created_at":"2026-07-05T11:14:59Z"},{"alias_kind":"pith_short_12","alias_value":"OI6QZSLIU4XW","created_at":"2026-07-05T11:14:59Z"},{"alias_kind":"pith_short_16","alias_value":"OI6QZSLIU4XW36FX","created_at":"2026-07-05T11:14:59Z"},{"alias_kind":"pith_short_8","alias_value":"OI6QZSLI","created_at":"2026-07-05T11:14:59Z"}],"graph_snapshots":[{"event_id":"sha256:9f39f7733e2f63e63147710dad3522e6deb691d91ce515ba90c3517b06f7c6de","target":"graph","created_at":"2026-07-05T11:14:59Z","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/2505.15146/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Playing video games requires perception, memory, and planning, exactly the faculties modern large language model (LLM) agents are expected to master. We study the major challenges in using popular video games to evaluate modern LLMs and find that directly dropping LLMs into games cannot make an effective evaluation, for three reasons -- brittle vision perception, prompt sensitivity, and potential data contamination. We introduce lmgame-Bench to turn games into reliable evaluations. lmgame-Bench features a suite of platformer, puzzle, and narrative games delivered through a unified Gym-style AP","authors_text":"Eric P. Xing, Haojian Jin, Haoyang Yu, Hao Zhang, Ion Stoica, Lanxiang Hu, Mingjia Huo, Tajana Rosing, Yuxuan Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-21T06:02:55Z","title":"lmgame-Bench: How Good are LLMs at Playing Games?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15146","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":"sha256:62e4074fba774f0ce93cb7a9c9cae1fdb442e19d5e23db0560b97ff2b591043e","target":"record","created_at":"2026-07-05T11:14:59Z","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":"39af4c16d010f54d48bc8c36a35b4c4f841e28bc627b7e2d70ba473e5ecbc660","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-21T06:02:55Z","title_canon_sha256":"5ea5e616461b067a5d222fed88b2e1aa45afe5edc0558eb173851d0ee163284a"},"schema_version":"1.0","source":{"id":"2505.15146","kind":"arxiv","version":2}},"canonical_sha256":"723d0cc968a72f6df8b7a6e0c1236b1ee319a37cdcf4a2556454afa204ed9fac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"723d0cc968a72f6df8b7a6e0c1236b1ee319a37cdcf4a2556454afa204ed9fac","first_computed_at":"2026-07-05T11:14:59.921689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:59.921689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BeuQzW58uqEeuDUIqiTtU2YN4uoYa7cvNdW0HxC54hvFvFcHyavyD+hmF5T3otmBMsMB71WmxOPaR84Nt9ZZAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:59.922182Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15146","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62e4074fba774f0ce93cb7a9c9cae1fdb442e19d5e23db0560b97ff2b591043e","sha256:9f39f7733e2f63e63147710dad3522e6deb691d91ce515ba90c3517b06f7c6de"],"state_sha256":"5d5e7b285ca1bb5503be44344cf471c064134561cd9150c03b7b9b16a994ca59"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"63BUiqLOQK15suTv50yNvQbPyYuMDELH2DLivKoISy6KWfG8CjHs6VWl8plR/GythZA2aiItyQlcF/WDE0p5Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:14:27.163355Z","bundle_sha256":"b23ca71b66eaf2d71dbd448879599963a1dd2ce930ed7e42d23721a39915bfc2"}}