{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OIKLPDFWNA7E2WK4TMLGB2TUP5","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":"33811b8fd1893f0e8f282a77e3f47406276b1409d0a9c195794431a7e7fa9f3e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-16T14:19:25Z","title_canon_sha256":"a45439b53200eead007207aa6c0b2bb524392ea1318240ff49dba67ee6f9e552"},"schema_version":"1.0","source":{"id":"2504.12110","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12110","created_at":"2026-07-05T12:11:17Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12110v2","created_at":"2026-07-05T12:11:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12110","created_at":"2026-07-05T12:11:17Z"},{"alias_kind":"pith_short_12","alias_value":"OIKLPDFWNA7E","created_at":"2026-07-05T12:11:17Z"},{"alias_kind":"pith_short_16","alias_value":"OIKLPDFWNA7E2WK4","created_at":"2026-07-05T12:11:17Z"},{"alias_kind":"pith_short_8","alias_value":"OIKLPDFW","created_at":"2026-07-05T12:11:17Z"}],"graph_snapshots":[{"event_id":"sha256:f26bb3d8b69250e8a987a351335a27083157cd8dd9309c1d584e5604a45b3124","target":"graph","created_at":"2026-07-05T12:11:17Z","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/2504.12110/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Earth Observation (EO) provides critical planetary data for environmental monitoring, disaster management, climate science, and other scientific domains. Here we ask: Are AI systems ready for reliable Earth Observation? We introduce \\datasetnamenospace, a benchmark of 140 yes/no questions from NASA Earth Observatory articles across 13 topics and 17 satellite sensors. Using Google Earth Engine API as a tool, LLM agents can only achieve an accuracy of 33% because the code fails to run over 58% of the time. We improve the failure rate for open models by fine-tuning synthetic data, allowing much s","authors_text":"Bharath Hariharan, Carl Vondrick, Cheng Perng Phoo, Chia Hsiang Kao, Kavita Bala, Rajeev Datta, Samuel Speas, Shreelekha Revankar, Snehal Bhagat, Utkarsh Mall, Wenting Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-16T14:19:25Z","title":"Towards LLM Agents for Earth Observation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12110","kind":"arxiv","version":2},"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":"sha256:8972cd063918c5d8f21f422d81216c25af6ab84d073495622ee25d3b731e1dbe","target":"record","created_at":"2026-07-05T12:11:17Z","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":"33811b8fd1893f0e8f282a77e3f47406276b1409d0a9c195794431a7e7fa9f3e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-16T14:19:25Z","title_canon_sha256":"a45439b53200eead007207aa6c0b2bb524392ea1318240ff49dba67ee6f9e552"},"schema_version":"1.0","source":{"id":"2504.12110","kind":"arxiv","version":2}},"canonical_sha256":"7214b78cb6683e4d595c9b1660ea747f4bf2f6aeda9141c1883727ce5dfed45e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7214b78cb6683e4d595c9b1660ea747f4bf2f6aeda9141c1883727ce5dfed45e","first_computed_at":"2026-07-05T12:11:17.105640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:11:17.105640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uLKN83jI0lh7xQR5RbNwgq5ZFOXpvTTDLPOorqkr2wUYvSYe2WDK+YJZNcCwHqS+vCBEiYYK6Nom7xR5G3QWAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:11:17.106280Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.12110","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8972cd063918c5d8f21f422d81216c25af6ab84d073495622ee25d3b731e1dbe","sha256:f26bb3d8b69250e8a987a351335a27083157cd8dd9309c1d584e5604a45b3124"],"state_sha256":"8f56a3ae3a2bd4b7735efdcc48ec3e342b6c0bc3a352dde27df462aaac4bd7b7"}