{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DUAMBV5RFKIZQYFARP4WI34TMF","short_pith_number":"pith:DUAMBV5R","schema_version":"1.0","canonical_sha256":"1d00c0d7b12a919860a08bf9646f936149e677b0e16834bc4f4fe71c124fca2b","source":{"kind":"arxiv","id":"2605.17792","version":1},"attestation_state":"computed","paper":{"title":"HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.geo-ph"],"primary_cat":"cs.LG","authors_text":"Anjiang Wei, Jie Cao, Jinwoong Yoo, Mofan Zhang, Songkun Yan, Yang Hong, Zhi Li","submitted_at":"2026-05-18T03:17:38Z","abstract_excerpt":"Calibrating distributed hydrologic models is a critical bottleneck across operational water resources management - streamflow prediction, reservoir operation, drought monitoring, infrastructure design, and flood forecasting all depend on it. Each basin demands an expert to translate hydrograph signatures into adjustments of a high-dimensional parameter vector, and the resulting workflow does not transfer between watersheds. We ask: can frontier large language model (LLM) agents replace the human hydrologic modeler, and if not, what would it take? We benchmark nine frontier LLM agents - Claude "},"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":"2605.17792","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T03:17:38Z","cross_cats_sorted":["physics.geo-ph"],"title_canon_sha256":"06ce0bc46a6ed7a94eae381fed666aa5554653db0a993b150ea25585538e4934","abstract_canon_sha256":"4c954b39e3ea6e418c82c7f5e57159801e0b4ba64b36225fb5f5faa4004aefa4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:58.573218Z","signature_b64":"L9ncCiPNlNf3424n1SN7744NtWSQ5qQw7C2oLUxJmraIE8hOxAhTCClhChfFr74mbCXDtbsLANYTnsB4zy4VBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d00c0d7b12a919860a08bf9646f936149e677b0e16834bc4f4fe71c124fca2b","last_reissued_at":"2026-05-20T00:04:58.571991Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:58.571991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.geo-ph"],"primary_cat":"cs.LG","authors_text":"Anjiang Wei, Jie Cao, Jinwoong Yoo, Mofan Zhang, Songkun Yan, Yang Hong, Zhi Li","submitted_at":"2026-05-18T03:17:38Z","abstract_excerpt":"Calibrating distributed hydrologic models is a critical bottleneck across operational water resources management - streamflow prediction, reservoir operation, drought monitoring, infrastructure design, and flood forecasting all depend on it. Each basin demands an expert to translate hydrograph signatures into adjustments of a high-dimensional parameter vector, and the resulting workflow does not transfer between watersheds. We ask: can frontier large language model (LLM) agents replace the human hydrologic modeler, and if not, what would it take? We benchmark nine frontier LLM agents - Claude "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17792","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/2605.17792/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":"2605.17792","created_at":"2026-05-20T00:04:58.572119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17792v1","created_at":"2026-05-20T00:04:58.572119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17792","created_at":"2026-05-20T00:04:58.572119+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUAMBV5RFKIZ","created_at":"2026-05-20T00:04:58.572119+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUAMBV5RFKIZQYFA","created_at":"2026-05-20T00:04:58.572119+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUAMBV5R","created_at":"2026-05-20T00:04:58.572119+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/DUAMBV5RFKIZQYFARP4WI34TMF","json":"https://pith.science/pith/DUAMBV5RFKIZQYFARP4WI34TMF.json","graph_json":"https://pith.science/api/pith-number/DUAMBV5RFKIZQYFARP4WI34TMF/graph.json","events_json":"https://pith.science/api/pith-number/DUAMBV5RFKIZQYFARP4WI34TMF/events.json","paper":"https://pith.science/paper/DUAMBV5R"},"agent_actions":{"view_html":"https://pith.science/pith/DUAMBV5RFKIZQYFARP4WI34TMF","download_json":"https://pith.science/pith/DUAMBV5RFKIZQYFARP4WI34TMF.json","view_paper":"https://pith.science/paper/DUAMBV5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17792&json=true","fetch_graph":"https://pith.science/api/pith-number/DUAMBV5RFKIZQYFARP4WI34TMF/graph.json","fetch_events":"https://pith.science/api/pith-number/DUAMBV5RFKIZQYFARP4WI34TMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUAMBV5RFKIZQYFARP4WI34TMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUAMBV5RFKIZQYFARP4WI34TMF/action/storage_attestation","attest_author":"https://pith.science/pith/DUAMBV5RFKIZQYFARP4WI34TMF/action/author_attestation","sign_citation":"https://pith.science/pith/DUAMBV5RFKIZQYFARP4WI34TMF/action/citation_signature","submit_replication":"https://pith.science/pith/DUAMBV5RFKIZQYFARP4WI34TMF/action/replication_record"}},"created_at":"2026-05-20T00:04:58.572119+00:00","updated_at":"2026-05-20T00:04:58.572119+00:00"}