{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G3RPO4EW75ZJPTNBY45CFQIFKD","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":"80937a264f776a71d0908a4c1b8e2aaa0d8b65b57033dd5834526d08a5ee610c","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-26T08:21:46Z","title_canon_sha256":"061a781c0d1f2abecb28708a3c1c766d094299596be3fb43553a38286a2fce65"},"schema_version":"1.0","source":{"id":"2505.19662","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19662","created_at":"2026-06-09T01:05:06Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19662v4","created_at":"2026-06-09T01:05:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19662","created_at":"2026-06-09T01:05:06Z"},{"alias_kind":"pith_short_12","alias_value":"G3RPO4EW75ZJ","created_at":"2026-06-09T01:05:06Z"},{"alias_kind":"pith_short_16","alias_value":"G3RPO4EW75ZJPTNB","created_at":"2026-06-09T01:05:06Z"},{"alias_kind":"pith_short_8","alias_value":"G3RPO4EW","created_at":"2026-06-09T01:05:06Z"}],"graph_snapshots":[{"event_id":"sha256:e41c9ab8a4d28cbf06c6f8ec5987552b60039285d5536f51e1c2c315a33b174e","target":"graph","created_at":"2026-06-09T01:05:06Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Evaluation results confirmed that performance evaluation considering the characteristics of Multimodal LLM (MLLM) such as GPT-4o is feasible."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"FieldWorkArena uses real factory and retail photos to test whether agentic AI can spot safety hazards and rule violations on site."}],"snapshot_sha256":"deac717ef9882310340abf5bfe6c65388b6385bf56fe38f6d3256015f9a6e130"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.19662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","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","cross_cats":["cs.CV"],"headline":"FieldWorkArena uses real factory and retail photos to test whether agentic AI can spot safety hazards and rule violations on site.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-26T08:21:46Z","title":"FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19662","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-19T14:32:07.079733Z","id":"637eb298-c243-42f2-84d0-1c504a78d1de","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"FieldWorkArena uses real factory and retail photos to test whether agentic AI can spot safety hazards and rule violations on site.","strongest_claim":"Evaluation results confirmed that performance evaluation considering the characteristics of Multimodal LLM (MLLM) such as GPT-4o is feasible.","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."}},"verdict_id":"637eb298-c243-42f2-84d0-1c504a78d1de"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a70880fe6a4b5643a54e536400645cfbebb8bf0dafc28e0d912e428c76c0d53a","target":"record","created_at":"2026-06-09T01:05:06Z","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":"80937a264f776a71d0908a4c1b8e2aaa0d8b65b57033dd5834526d08a5ee610c","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-26T08:21:46Z","title_canon_sha256":"061a781c0d1f2abecb28708a3c1c766d094299596be3fb43553a38286a2fce65"},"schema_version":"1.0","source":{"id":"2505.19662","kind":"arxiv","version":4}},"canonical_sha256":"36e2f77096ff7297cda1c73a22c10550df3eef12f83c6dc2ac9cd3179d5d6437","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36e2f77096ff7297cda1c73a22c10550df3eef12f83c6dc2ac9cd3179d5d6437","first_computed_at":"2026-06-09T01:05:06.742875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:06.742875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2w3PsMA4M0DIQMZJN7zhXH5GaIbaYqniI604IZom/pAP9y2IhgVUhPkY/D1+xt2rzdOMXxsqSnZVtXHLkOiYCQ==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:06.743378Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19662","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a70880fe6a4b5643a54e536400645cfbebb8bf0dafc28e0d912e428c76c0d53a","sha256:e41c9ab8a4d28cbf06c6f8ec5987552b60039285d5536f51e1c2c315a33b174e"],"state_sha256":"46fb279d3429c8b198b900e40d7b2ca504f5433ada7952649ce8a1176e15b298"}