{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LYWOBDGVZ5H6OOPOAES6JAYFVI","short_pith_number":"pith:LYWOBDGV","canonical_record":{"source":{"id":"2505.03570","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-06T14:29:47Z","cross_cats_sorted":[],"title_canon_sha256":"f8b422722a4b99666af646d810da58e70efb50037e69e01429df16ca8238cd0f","abstract_canon_sha256":"256c810b3bf4902a595373c3b6721e3aaefe8740da232c6e5c704d8e65cd550a"},"schema_version":"1.0"},"canonical_sha256":"5e2ce08cd5cf4fe739ee0125e48305aa1a3cc26e7c880f13f3e9dbaf0af4f75c","source":{"kind":"arxiv","id":"2505.03570","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03570","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03570v1","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03570","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"pith_short_12","alias_value":"LYWOBDGVZ5H6","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"pith_short_16","alias_value":"LYWOBDGVZ5H6OOPO","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"pith_short_8","alias_value":"LYWOBDGV","created_at":"2026-07-05T10:59:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LYWOBDGVZ5H6OOPOAES6JAYFVI","target":"record","payload":{"canonical_record":{"source":{"id":"2505.03570","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-06T14:29:47Z","cross_cats_sorted":[],"title_canon_sha256":"f8b422722a4b99666af646d810da58e70efb50037e69e01429df16ca8238cd0f","abstract_canon_sha256":"256c810b3bf4902a595373c3b6721e3aaefe8740da232c6e5c704d8e65cd550a"},"schema_version":"1.0"},"canonical_sha256":"5e2ce08cd5cf4fe739ee0125e48305aa1a3cc26e7c880f13f3e9dbaf0af4f75c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:18.450435Z","signature_b64":"1mx32c2QMn3MF6+fY5iUasG3lTn/AxaqSfhJHjo61afXzmqlVlF17z7+t0HupelHeayz6oV9xS2aqIyht+L9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e2ce08cd5cf4fe739ee0125e48305aa1a3cc26e7c880f13f3e9dbaf0af4f75c","last_reissued_at":"2026-07-05T10:59:18.449960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:18.449960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.03570","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":"2026-07-05T10:59:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cyf8GotSwC7gz9cWZflcZctSOkNeZI0xA23vUBBgtL07lieD2dmD710/PMN3uCyZ2O3vQDYKZ8/UtLN4YxYgDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:59:48.639787Z"},"content_sha256":"3ec84cbe809d69b4a8c854d8ee06b9d02522cb54a85520c84429d3040825aaa2","schema_version":"1.0","event_id":"sha256:3ec84cbe809d69b4a8c854d8ee06b9d02522cb54a85520c84429d3040825aaa2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LYWOBDGVZ5H6OOPOAES6JAYFVI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OSUniverse: Benchmark for Multimodal GUI-navigation AI Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Arturo M\\'arquez Flores, Daniel Jeffries, Mariya Davydova, Patrick Barker, Sin\\'ead Ryan","submitted_at":"2025-05-06T14:29:47Z","abstract_excerpt":"In this paper, we introduce OSUniverse: a benchmark of complex, multimodal desktop-oriented tasks for advanced GUI-navigation AI agents that focuses on ease of use, extensibility, comprehensive coverage of test cases, and automated validation. We divide the tasks in increasing levels of complexity, from basic precision clicking to multistep, multiapplication tests requiring dexterity, precision, and clear thinking from the agent. In version one of the benchmark, presented here, we have calibrated the complexity of the benchmark test cases to ensure that the SOTA (State of the Art) agents (at t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03570","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/2505.03570/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":"2026-07-05T10:59:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SPZJHcjdPUl9KPG+wwnFswlKSdeOkWBr8WydmvUK5aTA4RGtuP1aifXTQYeRqiJS7A7wvHDkhS/3yjmTM0UmAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:59:48.640662Z"},"content_sha256":"b5333e4cb61cc00cebcab6602471833dfcf53bff2597f8bcae4c09ac18e24b59","schema_version":"1.0","event_id":"sha256:b5333e4cb61cc00cebcab6602471833dfcf53bff2597f8bcae4c09ac18e24b59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LYWOBDGVZ5H6OOPOAES6JAYFVI/bundle.json","state_url":"https://pith.science/pith/LYWOBDGVZ5H6OOPOAES6JAYFVI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LYWOBDGVZ5H6OOPOAES6JAYFVI/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":"2026-08-11T01:59:48Z","links":{"resolver":"https://pith.science/pith/LYWOBDGVZ5H6OOPOAES6JAYFVI","bundle":"https://pith.science/pith/LYWOBDGVZ5H6OOPOAES6JAYFVI/bundle.json","state":"https://pith.science/pith/LYWOBDGVZ5H6OOPOAES6JAYFVI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LYWOBDGVZ5H6OOPOAES6JAYFVI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LYWOBDGVZ5H6OOPOAES6JAYFVI","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":"256c810b3bf4902a595373c3b6721e3aaefe8740da232c6e5c704d8e65cd550a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-06T14:29:47Z","title_canon_sha256":"f8b422722a4b99666af646d810da58e70efb50037e69e01429df16ca8238cd0f"},"schema_version":"1.0","source":{"id":"2505.03570","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03570","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03570v1","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03570","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"pith_short_12","alias_value":"LYWOBDGVZ5H6","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"pith_short_16","alias_value":"LYWOBDGVZ5H6OOPO","created_at":"2026-07-05T10:59:18Z"},{"alias_kind":"pith_short_8","alias_value":"LYWOBDGV","created_at":"2026-07-05T10:59:18Z"}],"graph_snapshots":[{"event_id":"sha256:b5333e4cb61cc00cebcab6602471833dfcf53bff2597f8bcae4c09ac18e24b59","target":"graph","created_at":"2026-07-05T10:59:18Z","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/2505.03570/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce OSUniverse: a benchmark of complex, multimodal desktop-oriented tasks for advanced GUI-navigation AI agents that focuses on ease of use, extensibility, comprehensive coverage of test cases, and automated validation. We divide the tasks in increasing levels of complexity, from basic precision clicking to multistep, multiapplication tests requiring dexterity, precision, and clear thinking from the agent. In version one of the benchmark, presented here, we have calibrated the complexity of the benchmark test cases to ensure that the SOTA (State of the Art) agents (at t","authors_text":"Arturo M\\'arquez Flores, Daniel Jeffries, Mariya Davydova, Patrick Barker, Sin\\'ead Ryan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-06T14:29:47Z","title":"OSUniverse: Benchmark for Multimodal GUI-navigation AI Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03570","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":"sha256:3ec84cbe809d69b4a8c854d8ee06b9d02522cb54a85520c84429d3040825aaa2","target":"record","created_at":"2026-07-05T10:59:18Z","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":"256c810b3bf4902a595373c3b6721e3aaefe8740da232c6e5c704d8e65cd550a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-06T14:29:47Z","title_canon_sha256":"f8b422722a4b99666af646d810da58e70efb50037e69e01429df16ca8238cd0f"},"schema_version":"1.0","source":{"id":"2505.03570","kind":"arxiv","version":1}},"canonical_sha256":"5e2ce08cd5cf4fe739ee0125e48305aa1a3cc26e7c880f13f3e9dbaf0af4f75c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e2ce08cd5cf4fe739ee0125e48305aa1a3cc26e7c880f13f3e9dbaf0af4f75c","first_computed_at":"2026-07-05T10:59:18.449960Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:18.449960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1mx32c2QMn3MF6+fY5iUasG3lTn/AxaqSfhJHjo61afXzmqlVlF17z7+t0HupelHeayz6oV9xS2aqIyht+L9Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:18.450435Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03570","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ec84cbe809d69b4a8c854d8ee06b9d02522cb54a85520c84429d3040825aaa2","sha256:b5333e4cb61cc00cebcab6602471833dfcf53bff2597f8bcae4c09ac18e24b59"],"state_sha256":"adee41e07b7dcc84cdaa86df81be4cfc3323cbadcc6b656d54c1a25ef46d628b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tbt8MFPaK7nrt3XuN6ZKGpzjBmUKb0Lnc4TPcAoNXFMPYfDZ5cictuu2e6EYGbE6EaI4UZFIgjohUIe4mDGuBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:59:48.647109Z","bundle_sha256":"7012866ebd420c906fbc2a0a4b0dad50e32393c27590e764e2cbebad7ffa44a7"}}