{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ESUXJ6WVEESE7FHQEEKXXP32M7","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":"602b046a1e89d1f8f77aa61a0f2913508cfb6086b34220c450ca6c160d1f9b55","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-12T17:53:03Z","title_canon_sha256":"172db8c838cc1e1fced8c3b16ea61c8f9e2b4080c0e922d98b4be018b489e54a"},"schema_version":"1.0","source":{"id":"2508.09124","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.09124","created_at":"2026-07-05T11:52:39Z"},{"alias_kind":"arxiv_version","alias_value":"2508.09124v1","created_at":"2026-07-05T11:52:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09124","created_at":"2026-07-05T11:52:39Z"},{"alias_kind":"pith_short_12","alias_value":"ESUXJ6WVEESE","created_at":"2026-07-05T11:52:39Z"},{"alias_kind":"pith_short_16","alias_value":"ESUXJ6WVEESE7FHQ","created_at":"2026-07-05T11:52:39Z"},{"alias_kind":"pith_short_8","alias_value":"ESUXJ6WV","created_at":"2026-07-05T11:52:39Z"}],"graph_snapshots":[{"event_id":"sha256:ff954e47b5c60aede04d87a65537e85228ed769a4b3574d372799fd5976f1626","target":"graph","created_at":"2026-07-05T11:52:39Z","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/2508.09124/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autonomous agents powered by large language models (LLMs) are increasingly deployed in real-world applications requiring complex, long-horizon workflows. However, existing benchmarks predominantly focus on atomic tasks that are self-contained and independent, failing to capture the long-term contextual dependencies and multi-interaction coordination required in realistic scenarios. To address this gap, we introduce OdysseyBench, a comprehensive benchmark for evaluating LLM agents on long-horizon workflows across diverse office applications including Word, Excel, PDF, Email, and Calendar. Our b","authors_text":"Daniel Madrigal Diaz, Dongge Han, Jin Xu, Saravan Rajmohan, Victor R\\\"uhle, Weixuan Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-12T17:53:03Z","title":"OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09124","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:ade67560973301443a95af10d5a00a7970c9812f902e607308ca98c3f096b689","target":"record","created_at":"2026-07-05T11:52:39Z","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":"602b046a1e89d1f8f77aa61a0f2913508cfb6086b34220c450ca6c160d1f9b55","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-12T17:53:03Z","title_canon_sha256":"172db8c838cc1e1fced8c3b16ea61c8f9e2b4080c0e922d98b4be018b489e54a"},"schema_version":"1.0","source":{"id":"2508.09124","kind":"arxiv","version":1}},"canonical_sha256":"24a974fad521244f94f021157bbf7a67d8eb2684ca3ce221a45357400ac0c35f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24a974fad521244f94f021157bbf7a67d8eb2684ca3ce221a45357400ac0c35f","first_computed_at":"2026-07-05T11:52:39.971539Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:39.971539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rr/lIsEJbiwCjTA3EYdQVptBTv3R9LUT+i9Hgn0BnnfBu7nxOMMO94THfOISwlyPRAVDVhyZ8vZPODumdZHtBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:39.972024Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.09124","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ade67560973301443a95af10d5a00a7970c9812f902e607308ca98c3f096b689","sha256:ff954e47b5c60aede04d87a65537e85228ed769a4b3574d372799fd5976f1626"],"state_sha256":"fcaf15b0d5a07872dba8e99e0b901d2aa0e82091c162810fb0932410c01fd9d1"}