{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ROXZ4YP4EYRTTZTPFV5DEB27NH","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":"c54a2d33e02b1918d35b7f2ad8da2cdf48d52e5d4a084dc7a9d4994b5063bdb7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-28T17:08:56Z","title_canon_sha256":"e3fd94fef78c772f56d91e0552255c1406c8fe1d7fc3d8b004a6a6961c9e3d34"},"schema_version":"1.0","source":{"id":"2408.15950","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15950","created_at":"2026-07-05T09:42:29Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15950v2","created_at":"2026-07-05T09:42:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15950","created_at":"2026-07-05T09:42:29Z"},{"alias_kind":"pith_short_12","alias_value":"ROXZ4YP4EYRT","created_at":"2026-07-05T09:42:29Z"},{"alias_kind":"pith_short_16","alias_value":"ROXZ4YP4EYRTTZTP","created_at":"2026-07-05T09:42:29Z"},{"alias_kind":"pith_short_8","alias_value":"ROXZ4YP4","created_at":"2026-07-05T09:42:29Z"}],"graph_snapshots":[{"event_id":"sha256:bff1aaa69b2cd10b56d93347c855e4dfe8141bc30cf8d351b3b53b2542e85704","target":"graph","created_at":"2026-07-05T09:42:29Z","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/2408.15950/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models (LLMs) have expanded their capabilities beyond traditional text-based tasks to multimodal domains, integrating visual, auditory, and textual data. While multimodal LLMs have been extensively explored for high-level planning in domains like robotics and games, their potential as low-level controllers remains largely untapped. In this paper, we introduce a novel benchmark aimed at testing the emergent capabilities of multimodal LLMs as low-level policies in Atari games. Unlike traditional reinforcement learning (RL) methods that require training for e","authors_text":"Devin White, MD Sunbeam, Nicholas R. Waytowich, Vinicius G. Goecks","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-28T17:08:56Z","title":"Atari-GPT: Benchmarking Multimodal Large Language Models as Low-Level Policies in Atari Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15950","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":"sha256:3efc670c13ce36e48e941fbe9a862429a673e5a9808737a59142094f18befe30","target":"record","created_at":"2026-07-05T09:42:29Z","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":"c54a2d33e02b1918d35b7f2ad8da2cdf48d52e5d4a084dc7a9d4994b5063bdb7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-28T17:08:56Z","title_canon_sha256":"e3fd94fef78c772f56d91e0552255c1406c8fe1d7fc3d8b004a6a6961c9e3d34"},"schema_version":"1.0","source":{"id":"2408.15950","kind":"arxiv","version":2}},"canonical_sha256":"8baf9e61fc262339e66f2d7a32075f69f432dcbc86b327c4df166d0d111935e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8baf9e61fc262339e66f2d7a32075f69f432dcbc86b327c4df166d0d111935e2","first_computed_at":"2026-07-05T09:42:29.637601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:29.637601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"md3cqC3Jh+4kyJSr4+kWTXJyDvjDQA/PbNgcSgBJZtxcBNTnt1csaL1G+DYl2FGQ80ffTW0kngm5YJdb1XGrCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:29.638124Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.15950","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3efc670c13ce36e48e941fbe9a862429a673e5a9808737a59142094f18befe30","sha256:bff1aaa69b2cd10b56d93347c855e4dfe8141bc30cf8d351b3b53b2542e85704"],"state_sha256":"57d6861f4ad832231ee6d3ca9b0b267abbe8406bf21e53ab94b6d455e823b519"}