{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YYA2Q6B3H44ZWPNH445U5NLPV5","short_pith_number":"pith:YYA2Q6B3","schema_version":"1.0","canonical_sha256":"c601a8783b3f399b3da7e73b4eb56faf604bbadae984cde0b4aa30385d86ebe6","source":{"kind":"arxiv","id":"2505.08529","version":1},"attestation_state":"computed","paper":{"title":"ExEBench: Benchmarking Foundation Models on Extreme Earth Events","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jie Zhao, Shan Zhao, Xiao Xiang Zhu, Zhitong Xiong","submitted_at":"2025-05-13T13:02:04Z","abstract_excerpt":"Our planet is facing increasingly frequent extreme events, which pose major risks to human lives and ecosystems. Recent advances in machine learning (ML), especially with foundation models (FMs) trained on extensive datasets, excel in extracting features and show promise in disaster management. Nevertheless, these models often inherit biases from training data, challenging their performance over extreme values. To explore the reliability of FM in the context of extreme events, we introduce \\textbf{ExE}Bench (\\textbf{Ex}treme \\textbf{E}arth Benchmark), a collection of seven extreme event catego"},"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":"2505.08529","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-13T13:02:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c58fcd60be778c8ec45efefd30f5f2b5defa3a77bf28f460a157e018272b85f6","abstract_canon_sha256":"8f10e9438ab85eb112d0c2d4c358227e2c148586215426a905cc41b9abf650eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:31.915521Z","signature_b64":"T4UXjF4VINQORQhNkuokGxje9qa5jAU1LVc2N1b0eV+e7Xk2+X+wRTWYnKOT+s7Gt3Wr3g6G3oXXCkjT0MJvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c601a8783b3f399b3da7e73b4eb56faf604bbadae984cde0b4aa30385d86ebe6","last_reissued_at":"2026-07-05T11:02:31.914957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:31.914957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ExEBench: Benchmarking Foundation Models on Extreme Earth Events","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jie Zhao, Shan Zhao, Xiao Xiang Zhu, Zhitong Xiong","submitted_at":"2025-05-13T13:02:04Z","abstract_excerpt":"Our planet is facing increasingly frequent extreme events, which pose major risks to human lives and ecosystems. Recent advances in machine learning (ML), especially with foundation models (FMs) trained on extensive datasets, excel in extracting features and show promise in disaster management. Nevertheless, these models often inherit biases from training data, challenging their performance over extreme values. To explore the reliability of FM in the context of extreme events, we introduce \\textbf{ExE}Bench (\\textbf{Ex}treme \\textbf{E}arth Benchmark), a collection of seven extreme event catego"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08529","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/2505.08529/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":"2505.08529","created_at":"2026-07-05T11:02:31.915020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.08529v1","created_at":"2026-07-05T11:02:31.915020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08529","created_at":"2026-07-05T11:02:31.915020+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYA2Q6B3H44Z","created_at":"2026-07-05T11:02:31.915020+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYA2Q6B3H44ZWPNH","created_at":"2026-07-05T11:02:31.915020+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYA2Q6B3","created_at":"2026-07-05T11:02:31.915020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07758","citing_title":"Scalable and Trustworthy Earth Observation Foundation Models","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2511.10370","citing_title":"SHRUG-FM: Reliability-Aware Foundation Models for Earth Observation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18906","citing_title":"Instability-Aware Steering of an Extreme Atmospheric River in an AI Weather Foundation Model","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YYA2Q6B3H44ZWPNH445U5NLPV5","json":"https://pith.science/pith/YYA2Q6B3H44ZWPNH445U5NLPV5.json","graph_json":"https://pith.science/api/pith-number/YYA2Q6B3H44ZWPNH445U5NLPV5/graph.json","events_json":"https://pith.science/api/pith-number/YYA2Q6B3H44ZWPNH445U5NLPV5/events.json","paper":"https://pith.science/paper/YYA2Q6B3"},"agent_actions":{"view_html":"https://pith.science/pith/YYA2Q6B3H44ZWPNH445U5NLPV5","download_json":"https://pith.science/pith/YYA2Q6B3H44ZWPNH445U5NLPV5.json","view_paper":"https://pith.science/paper/YYA2Q6B3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.08529&json=true","fetch_graph":"https://pith.science/api/pith-number/YYA2Q6B3H44ZWPNH445U5NLPV5/graph.json","fetch_events":"https://pith.science/api/pith-number/YYA2Q6B3H44ZWPNH445U5NLPV5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYA2Q6B3H44ZWPNH445U5NLPV5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYA2Q6B3H44ZWPNH445U5NLPV5/action/storage_attestation","attest_author":"https://pith.science/pith/YYA2Q6B3H44ZWPNH445U5NLPV5/action/author_attestation","sign_citation":"https://pith.science/pith/YYA2Q6B3H44ZWPNH445U5NLPV5/action/citation_signature","submit_replication":"https://pith.science/pith/YYA2Q6B3H44ZWPNH445U5NLPV5/action/replication_record"}},"created_at":"2026-07-05T11:02:31.915020+00:00","updated_at":"2026-07-05T11:02:31.915020+00:00"}