{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QP6NMCGEXIEI6EII4YTODMNNUD","short_pith_number":"pith:QP6NMCGE","schema_version":"1.0","canonical_sha256":"83fcd608c4ba088f1108e626e1b1ada0c2af46beafc334355475a244107b28ea","source":{"kind":"arxiv","id":"2606.12821","version":1},"attestation_state":"computed","paper":{"title":"GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.ET"],"primary_cat":"cs.AI","authors_text":"Devika Jain, Diego Prieto-Herr\\'aez, Gabriel Diaz-Ireland, Javier Vel\\'azquez, Mario Garc\\'ia Peces","submitted_at":"2026-06-11T02:35:20Z","abstract_excerpt":"Environmental scientists spend disproportionate effort on data wrangling rather than analysis, and AI agents that automate geospatial workflows remain unvalidated: no benchmark evaluates agents operating through structured tool calling against real APIs. We introduce the GeoNatureAgent Benchmark, the first benchmark for environmental analysis agents that operate via structured tool calls to a production-style geospatial API. It comprises 93 tasks across 18 categories, covering municipality analysis, multi-turn conversation, spatial reasoning, cross-indicator synthesis, error handling and recov"},"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":"2606.12821","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T02:35:20Z","cross_cats_sorted":["cs.ET"],"title_canon_sha256":"40b8833f61f8ac2c13d904a420634ba66bbf3e215b20e8f20e72bc0719539422","abstract_canon_sha256":"6225b0d6929cfd0da82c666a29b8adce77e2941195055961728d9363a78a6a0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:08:52.735160Z","signature_b64":"bp5gQyOylscZ3ZFp/Rf1Adpb+csAjQfDlyUQGkCo04ePyB+kAGG0ZnrkjnwWsV4P4+Lf70Ny0rHhITW73nENAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83fcd608c4ba088f1108e626e1b1ada0c2af46beafc334355475a244107b28ea","last_reissued_at":"2026-06-12T01:08:52.734335Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:08:52.734335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.ET"],"primary_cat":"cs.AI","authors_text":"Devika Jain, Diego Prieto-Herr\\'aez, Gabriel Diaz-Ireland, Javier Vel\\'azquez, Mario Garc\\'ia Peces","submitted_at":"2026-06-11T02:35:20Z","abstract_excerpt":"Environmental scientists spend disproportionate effort on data wrangling rather than analysis, and AI agents that automate geospatial workflows remain unvalidated: no benchmark evaluates agents operating through structured tool calling against real APIs. We introduce the GeoNatureAgent Benchmark, the first benchmark for environmental analysis agents that operate via structured tool calls to a production-style geospatial API. It comprises 93 tasks across 18 categories, covering municipality analysis, multi-turn conversation, spatial reasoning, cross-indicator synthesis, error handling and recov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12821","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/2606.12821/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":"2606.12821","created_at":"2026-06-12T01:08:52.734466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12821v1","created_at":"2026-06-12T01:08:52.734466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12821","created_at":"2026-06-12T01:08:52.734466+00:00"},{"alias_kind":"pith_short_12","alias_value":"QP6NMCGEXIEI","created_at":"2026-06-12T01:08:52.734466+00:00"},{"alias_kind":"pith_short_16","alias_value":"QP6NMCGEXIEI6EII","created_at":"2026-06-12T01:08:52.734466+00:00"},{"alias_kind":"pith_short_8","alias_value":"QP6NMCGE","created_at":"2026-06-12T01:08:52.734466+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/QP6NMCGEXIEI6EII4YTODMNNUD","json":"https://pith.science/pith/QP6NMCGEXIEI6EII4YTODMNNUD.json","graph_json":"https://pith.science/api/pith-number/QP6NMCGEXIEI6EII4YTODMNNUD/graph.json","events_json":"https://pith.science/api/pith-number/QP6NMCGEXIEI6EII4YTODMNNUD/events.json","paper":"https://pith.science/paper/QP6NMCGE"},"agent_actions":{"view_html":"https://pith.science/pith/QP6NMCGEXIEI6EII4YTODMNNUD","download_json":"https://pith.science/pith/QP6NMCGEXIEI6EII4YTODMNNUD.json","view_paper":"https://pith.science/paper/QP6NMCGE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12821&json=true","fetch_graph":"https://pith.science/api/pith-number/QP6NMCGEXIEI6EII4YTODMNNUD/graph.json","fetch_events":"https://pith.science/api/pith-number/QP6NMCGEXIEI6EII4YTODMNNUD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QP6NMCGEXIEI6EII4YTODMNNUD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QP6NMCGEXIEI6EII4YTODMNNUD/action/storage_attestation","attest_author":"https://pith.science/pith/QP6NMCGEXIEI6EII4YTODMNNUD/action/author_attestation","sign_citation":"https://pith.science/pith/QP6NMCGEXIEI6EII4YTODMNNUD/action/citation_signature","submit_replication":"https://pith.science/pith/QP6NMCGEXIEI6EII4YTODMNNUD/action/replication_record"}},"created_at":"2026-06-12T01:08:52.734466+00:00","updated_at":"2026-06-12T01:08:52.734466+00:00"}