{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QP6NMCGEXIEI6EII4YTODMNNUD","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":"6225b0d6929cfd0da82c666a29b8adce77e2941195055961728d9363a78a6a0d","cross_cats_sorted":["cs.ET"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T02:35:20Z","title_canon_sha256":"40b8833f61f8ac2c13d904a420634ba66bbf3e215b20e8f20e72bc0719539422"},"schema_version":"1.0","source":{"id":"2606.12821","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12821","created_at":"2026-06-12T01:08:52Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12821v1","created_at":"2026-06-12T01:08:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12821","created_at":"2026-06-12T01:08:52Z"},{"alias_kind":"pith_short_12","alias_value":"QP6NMCGEXIEI","created_at":"2026-06-12T01:08:52Z"},{"alias_kind":"pith_short_16","alias_value":"QP6NMCGEXIEI6EII","created_at":"2026-06-12T01:08:52Z"},{"alias_kind":"pith_short_8","alias_value":"QP6NMCGE","created_at":"2026-06-12T01:08:52Z"}],"graph_snapshots":[{"event_id":"sha256:80b35a1fdf79d5ce63426d791f0bd153312f3d7c641fd2573d6cc1e906f2d931","target":"graph","created_at":"2026-06-12T01:08:52Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.12821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Devika Jain, Diego Prieto-Herr\\'aez, Gabriel Diaz-Ireland, Javier Vel\\'azquez, Mario Garc\\'ia Peces","cross_cats":["cs.ET"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T02:35:20Z","title":"GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12821","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d11e8e989c39ac39c443b7c215d6558262f7a4abec2774c4adddec7efc273c3c","target":"record","created_at":"2026-06-12T01:08:52Z","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":"6225b0d6929cfd0da82c666a29b8adce77e2941195055961728d9363a78a6a0d","cross_cats_sorted":["cs.ET"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T02:35:20Z","title_canon_sha256":"40b8833f61f8ac2c13d904a420634ba66bbf3e215b20e8f20e72bc0719539422"},"schema_version":"1.0","source":{"id":"2606.12821","kind":"arxiv","version":1}},"canonical_sha256":"83fcd608c4ba088f1108e626e1b1ada0c2af46beafc334355475a244107b28ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83fcd608c4ba088f1108e626e1b1ada0c2af46beafc334355475a244107b28ea","first_computed_at":"2026-06-12T01:08:52.734335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:08:52.734335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bp5gQyOylscZ3ZFp/Rf1Adpb+csAjQfDlyUQGkCo04ePyB+kAGG0ZnrkjnwWsV4P4+Lf70Ny0rHhITW73nENAA==","signature_status":"signed_v1","signed_at":"2026-06-12T01:08:52.735160Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12821","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d11e8e989c39ac39c443b7c215d6558262f7a4abec2774c4adddec7efc273c3c","sha256:80b35a1fdf79d5ce63426d791f0bd153312f3d7c641fd2573d6cc1e906f2d931"],"state_sha256":"02604d3ab625a2749b7c8d5ba4f9000510425b8e8440cd9f47977d48c8d5d2cc"}