{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:COB3EHCQNSZCGGJSNJOXVGSKKR","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":"87b9b42c92f9f03a221359f6441059d80652400597663ecec06b9de06f55b090","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-20T18:54:32Z","title_canon_sha256":"b9a97646981814e2e98e8c3bf34eedb7bb5142867040266c8bf1e16d51eea563"},"schema_version":"1.0","source":{"id":"2411.13543","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13543","created_at":"2026-07-05T10:42:39Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13543v2","created_at":"2026-07-05T10:42:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13543","created_at":"2026-07-05T10:42:39Z"},{"alias_kind":"pith_short_12","alias_value":"COB3EHCQNSZC","created_at":"2026-07-05T10:42:39Z"},{"alias_kind":"pith_short_16","alias_value":"COB3EHCQNSZCGGJS","created_at":"2026-07-05T10:42:39Z"},{"alias_kind":"pith_short_8","alias_value":"COB3EHCQ","created_at":"2026-07-05T10:42:39Z"}],"graph_snapshots":[{"event_id":"sha256:4dd084d180f1319b6dd5a676b6bb1af94d7fabcdb2b0aaf9926155b6a6a8f2f0","target":"graph","created_at":"2026-07-05T10:42:39Z","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/2411.13543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) and Vision Language Models (VLMs) possess extensive knowledge and exhibit promising reasoning abilities, however, they still struggle to perform well in complex, dynamic environments. Real-world tasks require handling intricate interactions, advanced spatial reasoning, long-term planning, and continuous exploration of new strategies-areas in which we lack effective methodologies for comprehensively evaluating these capabilities. To address this gap, we introduce BALROG, a novel benchmark designed to assess the agentic capabilities of LLMs and VLMs through a diverse","authors_text":"Akbir Khan, Bart{\\l}omiej Cupia{\\l}, Davide Paglieri, Eduardo Pignatelli, Jack Parker-Holder, Jakob Nicolaus Foerster, Lerrel Pinto, {\\L}ukasz Kuci\\'nski, Maciej Wolczyk, Rob Fergus, Samuel Coward, Tim Rockt\\\"aschel, Ulyana Piterbarg","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-20T18:54:32Z","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13543","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":"sha256:1737ab23d0d88936014626271ee7b9d223d26cc685e35de7e1254307264ca73b","target":"record","created_at":"2026-07-05T10:42:39Z","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":"87b9b42c92f9f03a221359f6441059d80652400597663ecec06b9de06f55b090","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-20T18:54:32Z","title_canon_sha256":"b9a97646981814e2e98e8c3bf34eedb7bb5142867040266c8bf1e16d51eea563"},"schema_version":"1.0","source":{"id":"2411.13543","kind":"arxiv","version":2}},"canonical_sha256":"1383b21c506cb22319326a5d7a9a4a546ae928460fffc7746a95d715f10910a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1383b21c506cb22319326a5d7a9a4a546ae928460fffc7746a95d715f10910a7","first_computed_at":"2026-07-05T10:42:39.280009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:39.280009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Az4aefS2sTS/xspZcxWZpBtYKvzfVr+tkl6ydYv+yHq71PjfXDpqjRyQr1wscNOuFd5CV0DVE4gmlI+xnC/vBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:39.280541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.13543","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1737ab23d0d88936014626271ee7b9d223d26cc685e35de7e1254307264ca73b","sha256:4dd084d180f1319b6dd5a676b6bb1af94d7fabcdb2b0aaf9926155b6a6a8f2f0"],"state_sha256":"9bdbd8122325a24a55de0f0852c3683e2d55cd30d58472f0c6828daaa0443413"}