{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MEG7LJEHXTQIK2ISENVLNE3VDG","short_pith_number":"pith:MEG7LJEH","schema_version":"1.0","canonical_sha256":"610df5a487bce0856912236ab69375199919e6f2bd2a7ff53316839be0e3a20a","source":{"kind":"arxiv","id":"2507.20519","version":1},"attestation_state":"computed","paper":{"title":"AgroBench: Vision-Language Model Benchmark in Agriculture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hirokatsu Kataoka, Masaki Onishi, Nakamasa Inoue, Risa Shinoda, Yoshitaka Ushiku","submitted_at":"2025-07-28T04:58:29Z","abstract_excerpt":"Precise automated understanding of agricultural tasks such as disease identification is essential for sustainable crop production. Recent advances in vision-language models (VLMs) are expected to further expand the range of agricultural tasks by facilitating human-model interaction through easy, text-based communication. Here, we introduce AgroBench (Agronomist AI Benchmark), a benchmark for evaluating VLM models across seven agricultural topics, covering key areas in agricultural engineering and relevant to real-world farming. Unlike recent agricultural VLM benchmarks, AgroBench is annotated "},"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":"2507.20519","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T04:58:29Z","cross_cats_sorted":[],"title_canon_sha256":"aa858e95e9bce6a475d32e1c2e4288c115d26dd418f012bd100558a3e1430dfe","abstract_canon_sha256":"798472c6b5c2e0013865a6d1d6a3704a7c5d955db70566aa898695955bc81875"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:20.870792Z","signature_b64":"ogGa52WIKLlZLbXfKOuMmLG/zgrxqu9Yu0P80OA26BQtoRuXNDw2aiamDaamebkbTY7B//vXHeHvWKwDvVocCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"610df5a487bce0856912236ab69375199919e6f2bd2a7ff53316839be0e3a20a","last_reissued_at":"2026-07-05T11:44:20.870276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:20.870276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgroBench: Vision-Language Model Benchmark in Agriculture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hirokatsu Kataoka, Masaki Onishi, Nakamasa Inoue, Risa Shinoda, Yoshitaka Ushiku","submitted_at":"2025-07-28T04:58:29Z","abstract_excerpt":"Precise automated understanding of agricultural tasks such as disease identification is essential for sustainable crop production. Recent advances in vision-language models (VLMs) are expected to further expand the range of agricultural tasks by facilitating human-model interaction through easy, text-based communication. Here, we introduce AgroBench (Agronomist AI Benchmark), a benchmark for evaluating VLM models across seven agricultural topics, covering key areas in agricultural engineering and relevant to real-world farming. Unlike recent agricultural VLM benchmarks, AgroBench is annotated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20519","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/2507.20519/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":"2507.20519","created_at":"2026-07-05T11:44:20.870343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20519v1","created_at":"2026-07-05T11:44:20.870343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20519","created_at":"2026-07-05T11:44:20.870343+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEG7LJEHXTQI","created_at":"2026-07-05T11:44:20.870343+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEG7LJEHXTQIK2IS","created_at":"2026-07-05T11:44:20.870343+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEG7LJEH","created_at":"2026-07-05T11:44:20.870343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08034","citing_title":"Sci-Rho: A Multilingual Visually-Grounded Symbolic Benchmark for STEM Problems","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22034","citing_title":"AgroVG: A Large-Scale Multi-Source Benchmark for Agricultural Visual Grounding","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2512.15977","citing_title":"Are vision-language models ready to zero-shot replace supervised classification models in agriculture?","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03259","citing_title":"CropVLM: A Domain-Adapted Vision-Language Model for Open-Set Crop Analysis","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MEG7LJEHXTQIK2ISENVLNE3VDG","json":"https://pith.science/pith/MEG7LJEHXTQIK2ISENVLNE3VDG.json","graph_json":"https://pith.science/api/pith-number/MEG7LJEHXTQIK2ISENVLNE3VDG/graph.json","events_json":"https://pith.science/api/pith-number/MEG7LJEHXTQIK2ISENVLNE3VDG/events.json","paper":"https://pith.science/paper/MEG7LJEH"},"agent_actions":{"view_html":"https://pith.science/pith/MEG7LJEHXTQIK2ISENVLNE3VDG","download_json":"https://pith.science/pith/MEG7LJEHXTQIK2ISENVLNE3VDG.json","view_paper":"https://pith.science/paper/MEG7LJEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20519&json=true","fetch_graph":"https://pith.science/api/pith-number/MEG7LJEHXTQIK2ISENVLNE3VDG/graph.json","fetch_events":"https://pith.science/api/pith-number/MEG7LJEHXTQIK2ISENVLNE3VDG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEG7LJEHXTQIK2ISENVLNE3VDG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEG7LJEHXTQIK2ISENVLNE3VDG/action/storage_attestation","attest_author":"https://pith.science/pith/MEG7LJEHXTQIK2ISENVLNE3VDG/action/author_attestation","sign_citation":"https://pith.science/pith/MEG7LJEHXTQIK2ISENVLNE3VDG/action/citation_signature","submit_replication":"https://pith.science/pith/MEG7LJEHXTQIK2ISENVLNE3VDG/action/replication_record"}},"created_at":"2026-07-05T11:44:20.870343+00:00","updated_at":"2026-07-05T11:44:20.870343+00:00"}