{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G6PKJUTNYZBIEPKY6C32VCU4VY","short_pith_number":"pith:G6PKJUTN","schema_version":"1.0","canonical_sha256":"379ea4d26dc642823d58f0b7aa8a9cae3ce93cfc49fa6ed397d92274d9c462e8","source":{"kind":"arxiv","id":"2505.17139","version":3},"attestation_state":"computed","paper":{"title":"EarthSE: A Benchmark for Evaluating Earth Scientific Exploration Capability of LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ben Fei, Fenghua Ling, Lei Bai, Wanghan Xu, Wenlong Zhang, Xiangyu Zhao, Xiaoyu Yue, Yuhao Zhou","submitted_at":"2025-05-22T06:46:08Z","abstract_excerpt":"Advancements in Large Language Models (LLMs) drive interest in scientific applications, necessitating specialized benchmarks such as Earth science. Existing benchmarks either present a general science focus devoid of Earth science specificity or cover isolated subdomains, lacking holistic evaluation. Furthermore, current benchmarks typically neglect the assessment of LLMs' capabilities in open-ended scientific exploration. In this paper, we present a comprehensive and professional benchmark for the Earth sciences, designed to evaluate the capabilities of LLMs in scientific exploration within t"},"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":"2505.17139","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T06:46:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4f2be83de22ddfa84939edd04981b27bfc350740f07e6d3f1647adcd96e64fc7","abstract_canon_sha256":"e72940e501cf0bb2ab79c8c28386a47827e25be787b5cddff5b96f98ed022bbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:32.918719Z","signature_b64":"SFter6i9nyURPQ3wBcshj8vgiXYacenjuHtVi56img80jlXoER4AG4YCF6gA0By0Vt+B8KJMReZbBZZbXmCwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"379ea4d26dc642823d58f0b7aa8a9cae3ce93cfc49fa6ed397d92274d9c462e8","last_reissued_at":"2026-07-05T11:12:32.918131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:32.918131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EarthSE: A Benchmark for Evaluating Earth Scientific Exploration Capability of LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ben Fei, Fenghua Ling, Lei Bai, Wanghan Xu, Wenlong Zhang, Xiangyu Zhao, Xiaoyu Yue, Yuhao Zhou","submitted_at":"2025-05-22T06:46:08Z","abstract_excerpt":"Advancements in Large Language Models (LLMs) drive interest in scientific applications, necessitating specialized benchmarks such as Earth science. Existing benchmarks either present a general science focus devoid of Earth science specificity or cover isolated subdomains, lacking holistic evaluation. Furthermore, current benchmarks typically neglect the assessment of LLMs' capabilities in open-ended scientific exploration. In this paper, we present a comprehensive and professional benchmark for the Earth sciences, designed to evaluate the capabilities of LLMs in scientific exploration within t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17139","kind":"arxiv","version":3},"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/2505.17139/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":"2505.17139","created_at":"2026-07-05T11:12:32.918199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17139v3","created_at":"2026-07-05T11:12:32.918199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17139","created_at":"2026-07-05T11:12:32.918199+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6PKJUTNYZBI","created_at":"2026-07-05T11:12:32.918199+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6PKJUTNYZBIEPKY","created_at":"2026-07-05T11:12:32.918199+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6PKJUTN","created_at":"2026-07-05T11:12:32.918199+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14345","citing_title":"A Vision for Geo-Temporal Deep Research Systems: Towards Comprehensive, Transparent, and Reproducible Geo-Temporal Information Synthesis","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6PKJUTNYZBIEPKY6C32VCU4VY","json":"https://pith.science/pith/G6PKJUTNYZBIEPKY6C32VCU4VY.json","graph_json":"https://pith.science/api/pith-number/G6PKJUTNYZBIEPKY6C32VCU4VY/graph.json","events_json":"https://pith.science/api/pith-number/G6PKJUTNYZBIEPKY6C32VCU4VY/events.json","paper":"https://pith.science/paper/G6PKJUTN"},"agent_actions":{"view_html":"https://pith.science/pith/G6PKJUTNYZBIEPKY6C32VCU4VY","download_json":"https://pith.science/pith/G6PKJUTNYZBIEPKY6C32VCU4VY.json","view_paper":"https://pith.science/paper/G6PKJUTN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17139&json=true","fetch_graph":"https://pith.science/api/pith-number/G6PKJUTNYZBIEPKY6C32VCU4VY/graph.json","fetch_events":"https://pith.science/api/pith-number/G6PKJUTNYZBIEPKY6C32VCU4VY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6PKJUTNYZBIEPKY6C32VCU4VY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6PKJUTNYZBIEPKY6C32VCU4VY/action/storage_attestation","attest_author":"https://pith.science/pith/G6PKJUTNYZBIEPKY6C32VCU4VY/action/author_attestation","sign_citation":"https://pith.science/pith/G6PKJUTNYZBIEPKY6C32VCU4VY/action/citation_signature","submit_replication":"https://pith.science/pith/G6PKJUTNYZBIEPKY6C32VCU4VY/action/replication_record"}},"created_at":"2026-07-05T11:12:32.918199+00:00","updated_at":"2026-07-05T11:12:32.918199+00:00"}