{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5NIZO4ZJOXNHUHSGP2NCPWXVZX","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":"6134d75817e9f57b1f4ac23dc1b54e03a7f062e5212c5582b7d3da6359daedf7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-09-12T17:56:43Z","title_canon_sha256":"9828db3fda786215059d5fc71ae832b2809152f2891279174aea3d676fe81afe"},"schema_version":"1.0","source":{"id":"2409.08264","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08264","created_at":"2026-07-05T09:07:03Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08264v2","created_at":"2026-07-05T09:07:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08264","created_at":"2026-07-05T09:07:03Z"},{"alias_kind":"pith_short_12","alias_value":"5NIZO4ZJOXNH","created_at":"2026-07-05T09:07:03Z"},{"alias_kind":"pith_short_16","alias_value":"5NIZO4ZJOXNHUHSG","created_at":"2026-07-05T09:07:03Z"},{"alias_kind":"pith_short_8","alias_value":"5NIZO4ZJ","created_at":"2026-07-05T09:07:03Z"}],"graph_snapshots":[{"event_id":"sha256:7a0ce225db42cb699a4dedce2854e21a472b5a303517246f408fbe7e73b4eb4c","target":"graph","created_at":"2026-07-05T09:07:03Z","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/2409.08264/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) show remarkable potential to act as computer agents, enhancing human productivity and software accessibility in multi-modal tasks that require planning and reasoning. However, measuring agent performance in realistic environments remains a challenge since: (i) most benchmarks are limited to specific modalities or domains (e.g. text-only, web navigation, Q&A, coding) and (ii) full benchmark evaluations are slow (on order of magnitude of days) given the multi-step sequential nature of tasks. To address these challenges, we introduce the Windows Agent Arena: a reprodu","authors_text":"Arthur Bucker, Dan Zhao, Dillon Dupont, Francesco Bonacci, Justin Wagle, Kazuhito Koishida, Lawrence Jang, Rogerio Bonatti, Sara Abdali, Yadong Lu, Yinheng Li, Zack Hui","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-09-12T17:56:43Z","title":"Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08264","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":"sha256:4e5659f09bb0d7ce0cf9967fd14a4cb54fdb0a3cf077a2a87d752e01db4f4a12","target":"record","created_at":"2026-07-05T09:07:03Z","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":"6134d75817e9f57b1f4ac23dc1b54e03a7f062e5212c5582b7d3da6359daedf7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-09-12T17:56:43Z","title_canon_sha256":"9828db3fda786215059d5fc71ae832b2809152f2891279174aea3d676fe81afe"},"schema_version":"1.0","source":{"id":"2409.08264","kind":"arxiv","version":2}},"canonical_sha256":"eb5197732975da7a1e467e9a27daf5cdfe9f718797e31ee233900eac0515a6b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb5197732975da7a1e467e9a27daf5cdfe9f718797e31ee233900eac0515a6b6","first_computed_at":"2026-07-05T09:07:03.926221Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:07:03.926221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I1hplO83eXVoPDhBcwSoWPkxpnIkgBsiO4NcqJsIA3tGzDAwOic44OKBpTjkzgrsWjRQ6y31SPvIzuncfmh4Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:07:03.926711Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08264","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e5659f09bb0d7ce0cf9967fd14a4cb54fdb0a3cf077a2a87d752e01db4f4a12","sha256:7a0ce225db42cb699a4dedce2854e21a472b5a303517246f408fbe7e73b4eb4c"],"state_sha256":"f9588b05cd846d962f59bacf142093985558b8eebe8a58dc97d90349186abb0b"}