{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G3RPO4EW75ZJPTNBY45CFQIFKD","short_pith_number":"pith:G3RPO4EW","schema_version":"1.0","canonical_sha256":"36e2f77096ff7297cda1c73a22c10550df3eef12f83c6dc2ac9cd3179d5d6437","source":{"kind":"arxiv","id":"2505.19662","version":4},"attestation_state":"computed","paper":{"title":"FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"FieldWorkArena uses real factory and retail photos to test whether agentic AI can spot safety hazards and rule violations on site.","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Akiyoshi Uchida, Atsunori Moteki, Fan Yang, Graham Neubig, Hiroyuki Ishida, Ikuo Kusajima, Jun Takahashi, Kanji Uchino, Koki Nakagawa, Shan Jiang, Shoichi Masui, Yasuto Watanabe, Yonatan Bisk, Yueqi Song","submitted_at":"2025-05-26T08:21:46Z","abstract_excerpt":"This paper introduces FieldWorkArena, a benchmark for agentic AI targeting real-world field work. With the recent increase in demand for agentic AI, they are built to detect and document safety hazards, procedural violations, and other critical incidents across real-world manufacturing and retail environments. Whereas most agentic AI benchmarks focus on performance in simulated or digital environments, our work addresses the fundamental challenge of evaluating agents in the real-world. In this paper, we improve the evaluation function from previous methods to assess the performance of agentic "},"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":"2505.19662","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-26T08:21:46Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"061a781c0d1f2abecb28708a3c1c766d094299596be3fb43553a38286a2fce65","abstract_canon_sha256":"80937a264f776a71d0908a4c1b8e2aaa0d8b65b57033dd5834526d08a5ee610c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:06.743378Z","signature_b64":"2w3PsMA4M0DIQMZJN7zhXH5GaIbaYqniI604IZom/pAP9y2IhgVUhPkY/D1+xt2rzdOMXxsqSnZVtXHLkOiYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36e2f77096ff7297cda1c73a22c10550df3eef12f83c6dc2ac9cd3179d5d6437","last_reissued_at":"2026-06-09T01:05:06.742875Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:06.742875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"FieldWorkArena uses real factory and retail photos to test whether agentic AI can spot safety hazards and rule violations on site.","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Akiyoshi Uchida, Atsunori Moteki, Fan Yang, Graham Neubig, Hiroyuki Ishida, Ikuo Kusajima, Jun Takahashi, Kanji Uchino, Koki Nakagawa, Shan Jiang, Shoichi Masui, Yasuto Watanabe, Yonatan Bisk, Yueqi Song","submitted_at":"2025-05-26T08:21:46Z","abstract_excerpt":"This paper introduces FieldWorkArena, a benchmark for agentic AI targeting real-world field work. With the recent increase in demand for agentic AI, they are built to detect and document safety hazards, procedural violations, and other critical incidents across real-world manufacturing and retail environments. Whereas most agentic AI benchmarks focus on performance in simulated or digital environments, our work addresses the fundamental challenge of evaluating agents in the real-world. In this paper, we improve the evaluation function from previous methods to assess the performance of agentic "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Evaluation results confirmed that performance evaluation considering the characteristics of Multimodal LLM (MLLM) such as GPT-4o is feasible.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that on-site captured images/videos from factories, warehouses and retails combined with tasks developed through interviews with site workers and managers provide a representative and sufficient basis for evaluating agentic AI performance in real-world conditions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A new benchmark dataset and evaluation framework for testing multimodal AI agents on real field work tasks derived from on-site data and worker interviews.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"FieldWorkArena uses real factory and retail photos to test whether agentic AI can spot safety hazards and rule violations on site.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"deac717ef9882310340abf5bfe6c65388b6385bf56fe38f6d3256015f9a6e130"},"source":{"id":"2505.19662","kind":"arxiv","version":4},"verdict":{"id":"637eb298-c243-42f2-84d0-1c504a78d1de","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T14:32:07.079733Z","strongest_claim":"Evaluation results confirmed that performance evaluation considering the characteristics of Multimodal LLM (MLLM) such as GPT-4o is feasible.","one_line_summary":"A new benchmark dataset and evaluation framework for testing multimodal AI agents on real field work tasks derived from on-site data and worker interviews.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that on-site captured images/videos from factories, warehouses and retails combined with tasks developed through interviews with site workers and managers provide a representative and sufficient basis for evaluating agentic AI performance in real-world conditions.","pith_extraction_headline":"FieldWorkArena uses real factory and retail photos to test whether agentic AI can spot safety hazards and rule violations on site."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.19662/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":"2505.19662","created_at":"2026-06-09T01:05:06.742932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19662v4","created_at":"2026-06-09T01:05:06.742932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19662","created_at":"2026-06-09T01:05:06.742932+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3RPO4EW75ZJ","created_at":"2026-06-09T01:05:06.742932+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3RPO4EW75ZJPTNB","created_at":"2026-06-09T01:05:06.742932+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3RPO4EW","created_at":"2026-06-09T01:05:06.742932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.12673","citing_title":"Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G3RPO4EW75ZJPTNBY45CFQIFKD","json":"https://pith.science/pith/G3RPO4EW75ZJPTNBY45CFQIFKD.json","graph_json":"https://pith.science/api/pith-number/G3RPO4EW75ZJPTNBY45CFQIFKD/graph.json","events_json":"https://pith.science/api/pith-number/G3RPO4EW75ZJPTNBY45CFQIFKD/events.json","paper":"https://pith.science/paper/G3RPO4EW"},"agent_actions":{"view_html":"https://pith.science/pith/G3RPO4EW75ZJPTNBY45CFQIFKD","download_json":"https://pith.science/pith/G3RPO4EW75ZJPTNBY45CFQIFKD.json","view_paper":"https://pith.science/paper/G3RPO4EW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19662&json=true","fetch_graph":"https://pith.science/api/pith-number/G3RPO4EW75ZJPTNBY45CFQIFKD/graph.json","fetch_events":"https://pith.science/api/pith-number/G3RPO4EW75ZJPTNBY45CFQIFKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3RPO4EW75ZJPTNBY45CFQIFKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3RPO4EW75ZJPTNBY45CFQIFKD/action/storage_attestation","attest_author":"https://pith.science/pith/G3RPO4EW75ZJPTNBY45CFQIFKD/action/author_attestation","sign_citation":"https://pith.science/pith/G3RPO4EW75ZJPTNBY45CFQIFKD/action/citation_signature","submit_replication":"https://pith.science/pith/G3RPO4EW75ZJPTNBY45CFQIFKD/action/replication_record"}},"created_at":"2026-06-09T01:05:06.742932+00:00","updated_at":"2026-06-09T01:05:06.742932+00:00"}