{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JXZKVIQV3C4NG5CEZ464GZWIMY","short_pith_number":"pith:JXZKVIQV","schema_version":"1.0","canonical_sha256":"4df2aaa215d8b8d37444cf3dc366c8661a2a7e29d033caccbad31e77fdefa5fc","source":{"kind":"arxiv","id":"2407.05291","version":2},"attestation_state":"computed","paper":{"title":"WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexandre Drouin, Alexandre Lacoste, L\\'eo Boisvert, Massimo Caccia, Maxime Gasse, Megh Thakkar, Nicolas Chapados, Quentin Cappart, Thibault Le Sellier De Chezelles","submitted_at":"2024-07-07T07:15:49Z","abstract_excerpt":"The ability of large language models (LLMs) to mimic human-like intelligence has led to a surge in LLM-based autonomous agents. Though recent LLMs seem capable of planning and reasoning given user instructions, their effectiveness in applying these capabilities for autonomous task solving remains underexplored. This is especially true in enterprise settings, where automated agents hold the promise of a high impact. To fill this gap, we propose WorkArena++, a novel benchmark consisting of 682 tasks corresponding to realistic workflows routinely performed by knowledge workers. WorkArena++ is des"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.05291","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-07T07:15:49Z","cross_cats_sorted":[],"title_canon_sha256":"9a0077beef8a8fa0b400346ea9cf9a3fb401cd96db259954ae31ec68a11e9b1f","abstract_canon_sha256":"62b3b2670b36a1795fde7183c68a64fc5797cb87f590eb79693a8ae8952f1bf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:08.254081Z","signature_b64":"CXwrwHHmxsr8md5WaDCVE9+N4XcOSgkQrxRvCVJIWqbHkpS7BizKmNtDJhLVfasHXMBsrJPGt4qknFZfE4VeAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4df2aaa215d8b8d37444cf3dc366c8661a2a7e29d033caccbad31e77fdefa5fc","last_reissued_at":"2026-07-05T10:10:08.253570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:08.253570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexandre Drouin, Alexandre Lacoste, L\\'eo Boisvert, Massimo Caccia, Maxime Gasse, Megh Thakkar, Nicolas Chapados, Quentin Cappart, Thibault Le Sellier De Chezelles","submitted_at":"2024-07-07T07:15:49Z","abstract_excerpt":"The ability of large language models (LLMs) to mimic human-like intelligence has led to a surge in LLM-based autonomous agents. Though recent LLMs seem capable of planning and reasoning given user instructions, their effectiveness in applying these capabilities for autonomous task solving remains underexplored. This is especially true in enterprise settings, where automated agents hold the promise of a high impact. To fill this gap, we propose WorkArena++, a novel benchmark consisting of 682 tasks corresponding to realistic workflows routinely performed by knowledge workers. WorkArena++ is des"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05291","kind":"arxiv","version":2},"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/2407.05291/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.05291","created_at":"2026-07-05T10:10:08.253635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05291v2","created_at":"2026-07-05T10:10:08.253635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05291","created_at":"2026-07-05T10:10:08.253635+00:00"},{"alias_kind":"pith_short_12","alias_value":"JXZKVIQV3C4N","created_at":"2026-07-05T10:10:08.253635+00:00"},{"alias_kind":"pith_short_16","alias_value":"JXZKVIQV3C4NG5CE","created_at":"2026-07-05T10:10:08.253635+00:00"},{"alias_kind":"pith_short_8","alias_value":"JXZKVIQV","created_at":"2026-07-05T10:10:08.253635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23049","citing_title":"PhoneBuddy: Training Open Models for Agentic Phone Use","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21654","citing_title":"ChainWorld: Composing Long-Horizon Desktop Workloads from Atomic OSWorld Tasks","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06708","citing_title":"Signal-Driven Observation for Long-Horizon Web Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19662","citing_title":"FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08761","citing_title":"Beyond the All-in-One Agent: Benchmarking Role-Specialized Multi-Agent Collaboration in Enterprise Workflows","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08516","citing_title":"MolmoWeb: Open Visual Web Agent and Open Data for the Open Web","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21375","citing_title":"VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JXZKVIQV3C4NG5CEZ464GZWIMY","json":"https://pith.science/pith/JXZKVIQV3C4NG5CEZ464GZWIMY.json","graph_json":"https://pith.science/api/pith-number/JXZKVIQV3C4NG5CEZ464GZWIMY/graph.json","events_json":"https://pith.science/api/pith-number/JXZKVIQV3C4NG5CEZ464GZWIMY/events.json","paper":"https://pith.science/paper/JXZKVIQV"},"agent_actions":{"view_html":"https://pith.science/pith/JXZKVIQV3C4NG5CEZ464GZWIMY","download_json":"https://pith.science/pith/JXZKVIQV3C4NG5CEZ464GZWIMY.json","view_paper":"https://pith.science/paper/JXZKVIQV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05291&json=true","fetch_graph":"https://pith.science/api/pith-number/JXZKVIQV3C4NG5CEZ464GZWIMY/graph.json","fetch_events":"https://pith.science/api/pith-number/JXZKVIQV3C4NG5CEZ464GZWIMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JXZKVIQV3C4NG5CEZ464GZWIMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JXZKVIQV3C4NG5CEZ464GZWIMY/action/storage_attestation","attest_author":"https://pith.science/pith/JXZKVIQV3C4NG5CEZ464GZWIMY/action/author_attestation","sign_citation":"https://pith.science/pith/JXZKVIQV3C4NG5CEZ464GZWIMY/action/citation_signature","submit_replication":"https://pith.science/pith/JXZKVIQV3C4NG5CEZ464GZWIMY/action/replication_record"}},"created_at":"2026-07-05T10:10:08.253635+00:00","updated_at":"2026-07-05T10:10:08.253635+00:00"}