{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N5XLWGZCURQZAXMAWJCRVDCQTP","short_pith_number":"pith:N5XLWGZC","schema_version":"1.0","canonical_sha256":"6f6ebb1b22a461905d80b2451a8c509bcfb4598575ebe2616e2abf7814441af3","source":{"kind":"arxiv","id":"2605.22366","version":1},"attestation_state":"computed","paper":{"title":"AgroTools: A Benchmark for Tool-Augmented Multimodal Agents in Agriculture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Shi, Haohuan Fu, Jianxi Huang, Jiarui Zhang, Jing Wu, Juepeng Zheng, Kun Zeng, Xiaoya Fan, Xinyu Zhang, Yibin Wen, Yutong Lu, Zi Ye, Zurong Mai","submitted_at":"2026-05-21T11:58:54Z","abstract_excerpt":"Agricultural decision-making increasingly requires multimodal systems that can transform visual observations into reliable, executable actions. However, existing agricultural multimodal benchmarks mainly evaluate final-answer correctness and provide limited support for assessing whether models can use external tools to complete precision-sensitive workflows. In this paper, we introduce AgroTools, a benchmark for evaluating tool-augmented multimodal agents in agriculture. AgroTools contains 539 question-answer instances paired with 1,097 heterogeneous agricultural images, spanning five task fam"},"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":"2605.22366","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T11:58:54Z","cross_cats_sorted":[],"title_canon_sha256":"095f7ca5330c2b442b62f470aad80678238c1e058314cec4637347bedc95f38b","abstract_canon_sha256":"1bc54f040c86e42cb343b15ea6d665a13a570a757101363a4767e8830fb7e487"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:39.957630Z","signature_b64":"gdKCbH6viRFip7L+uQ0NchaYnGJTQExLjR4v7bOpsx70//vF5kx8E7XSEBNLmwSl7aQT8V4u+bgQzwGptE6mAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f6ebb1b22a461905d80b2451a8c509bcfb4598575ebe2616e2abf7814441af3","last_reissued_at":"2026-05-22T01:04:39.956878Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:39.956878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgroTools: A Benchmark for Tool-Augmented Multimodal Agents in Agriculture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Shi, Haohuan Fu, Jianxi Huang, Jiarui Zhang, Jing Wu, Juepeng Zheng, Kun Zeng, Xiaoya Fan, Xinyu Zhang, Yibin Wen, Yutong Lu, Zi Ye, Zurong Mai","submitted_at":"2026-05-21T11:58:54Z","abstract_excerpt":"Agricultural decision-making increasingly requires multimodal systems that can transform visual observations into reliable, executable actions. However, existing agricultural multimodal benchmarks mainly evaluate final-answer correctness and provide limited support for assessing whether models can use external tools to complete precision-sensitive workflows. In this paper, we introduce AgroTools, a benchmark for evaluating tool-augmented multimodal agents in agriculture. AgroTools contains 539 question-answer instances paired with 1,097 heterogeneous agricultural images, spanning five task fam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22366","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/2605.22366/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":"2605.22366","created_at":"2026-05-22T01:04:39.957014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22366v1","created_at":"2026-05-22T01:04:39.957014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22366","created_at":"2026-05-22T01:04:39.957014+00:00"},{"alias_kind":"pith_short_12","alias_value":"N5XLWGZCURQZ","created_at":"2026-05-22T01:04:39.957014+00:00"},{"alias_kind":"pith_short_16","alias_value":"N5XLWGZCURQZAXMA","created_at":"2026-05-22T01:04:39.957014+00:00"},{"alias_kind":"pith_short_8","alias_value":"N5XLWGZC","created_at":"2026-05-22T01:04:39.957014+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N5XLWGZCURQZAXMAWJCRVDCQTP","json":"https://pith.science/pith/N5XLWGZCURQZAXMAWJCRVDCQTP.json","graph_json":"https://pith.science/api/pith-number/N5XLWGZCURQZAXMAWJCRVDCQTP/graph.json","events_json":"https://pith.science/api/pith-number/N5XLWGZCURQZAXMAWJCRVDCQTP/events.json","paper":"https://pith.science/paper/N5XLWGZC"},"agent_actions":{"view_html":"https://pith.science/pith/N5XLWGZCURQZAXMAWJCRVDCQTP","download_json":"https://pith.science/pith/N5XLWGZCURQZAXMAWJCRVDCQTP.json","view_paper":"https://pith.science/paper/N5XLWGZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22366&json=true","fetch_graph":"https://pith.science/api/pith-number/N5XLWGZCURQZAXMAWJCRVDCQTP/graph.json","fetch_events":"https://pith.science/api/pith-number/N5XLWGZCURQZAXMAWJCRVDCQTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N5XLWGZCURQZAXMAWJCRVDCQTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N5XLWGZCURQZAXMAWJCRVDCQTP/action/storage_attestation","attest_author":"https://pith.science/pith/N5XLWGZCURQZAXMAWJCRVDCQTP/action/author_attestation","sign_citation":"https://pith.science/pith/N5XLWGZCURQZAXMAWJCRVDCQTP/action/citation_signature","submit_replication":"https://pith.science/pith/N5XLWGZCURQZAXMAWJCRVDCQTP/action/replication_record"}},"created_at":"2026-05-22T01:04:39.957014+00:00","updated_at":"2026-05-22T01:04:39.957014+00:00"}