{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2VPXXQJ3O5X6IFENVUM2PRHFFS","short_pith_number":"pith:2VPXXQJ3","schema_version":"1.0","canonical_sha256":"d55f7bc13b776fe4148dad19a7c4e52cb59e4911e6dc093c96d31347816c6bd9","source":{"kind":"arxiv","id":"2508.02936","version":1},"attestation_state":"computed","paper":{"title":"AQUAH: Automatic Quantification and Unified Agent in Hydrology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jie Cao, Mengye Chen, Mofan Zhang, Siyu Zhu, Songkun Yan, Yang Hong, Yixin Wen, Zhi Li","submitted_at":"2025-08-04T22:26:50Z","abstract_excerpt":"We introduce AQUAH, the first end-to-end language-based agent designed specifically for hydrologic modeling. Starting from a simple natural-language prompt (e.g., 'simulate floods for the Little Bighorn basin from 2020 to 2022'), AQUAH autonomously retrieves the required terrain, forcing, and gauge data; configures a hydrologic model; runs the simulation; and generates a self-contained PDF report. The workflow is driven by vision-enabled large language models, which interpret maps and rasters on the fly and steer key decisions such as outlet selection, parameter initialization, and uncertainty"},"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":"2508.02936","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-04T22:26:50Z","cross_cats_sorted":[],"title_canon_sha256":"12e9634a3bc87b1830763f7144550549002387ffc096ffdf8764301ed3e4700f","abstract_canon_sha256":"8a86752b385f50055cb66e3cf08dee7109af1dee8638fe185b5d67bda04a0fee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:33.218772Z","signature_b64":"Gsxo3MX4q43z1Ma5EWdDTI1ew2FT3IZ2PQSbSRgBkfXwVdtzGTynSveNJhhBTvz20i5iQZ9HIR4S0PpTXqxICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d55f7bc13b776fe4148dad19a7c4e52cb59e4911e6dc093c96d31347816c6bd9","last_reissued_at":"2026-07-05T11:48:33.218174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:33.218174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AQUAH: Automatic Quantification and Unified Agent in Hydrology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jie Cao, Mengye Chen, Mofan Zhang, Siyu Zhu, Songkun Yan, Yang Hong, Yixin Wen, Zhi Li","submitted_at":"2025-08-04T22:26:50Z","abstract_excerpt":"We introduce AQUAH, the first end-to-end language-based agent designed specifically for hydrologic modeling. Starting from a simple natural-language prompt (e.g., 'simulate floods for the Little Bighorn basin from 2020 to 2022'), AQUAH autonomously retrieves the required terrain, forcing, and gauge data; configures a hydrologic model; runs the simulation; and generates a self-contained PDF report. The workflow is driven by vision-enabled large language models, which interpret maps and rasters on the fly and steer key decisions such as outlet selection, parameter initialization, and uncertainty"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02936","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/2508.02936/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":"2508.02936","created_at":"2026-07-05T11:48:33.218239+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.02936v1","created_at":"2026-07-05T11:48:33.218239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02936","created_at":"2026-07-05T11:48:33.218239+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VPXXQJ3O5X6","created_at":"2026-07-05T11:48:33.218239+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VPXXQJ3O5X6IFEN","created_at":"2026-07-05T11:48:33.218239+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VPXXQJ3","created_at":"2026-07-05T11:48:33.218239+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17792","citing_title":"HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2VPXXQJ3O5X6IFENVUM2PRHFFS","json":"https://pith.science/pith/2VPXXQJ3O5X6IFENVUM2PRHFFS.json","graph_json":"https://pith.science/api/pith-number/2VPXXQJ3O5X6IFENVUM2PRHFFS/graph.json","events_json":"https://pith.science/api/pith-number/2VPXXQJ3O5X6IFENVUM2PRHFFS/events.json","paper":"https://pith.science/paper/2VPXXQJ3"},"agent_actions":{"view_html":"https://pith.science/pith/2VPXXQJ3O5X6IFENVUM2PRHFFS","download_json":"https://pith.science/pith/2VPXXQJ3O5X6IFENVUM2PRHFFS.json","view_paper":"https://pith.science/paper/2VPXXQJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.02936&json=true","fetch_graph":"https://pith.science/api/pith-number/2VPXXQJ3O5X6IFENVUM2PRHFFS/graph.json","fetch_events":"https://pith.science/api/pith-number/2VPXXQJ3O5X6IFENVUM2PRHFFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VPXXQJ3O5X6IFENVUM2PRHFFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VPXXQJ3O5X6IFENVUM2PRHFFS/action/storage_attestation","attest_author":"https://pith.science/pith/2VPXXQJ3O5X6IFENVUM2PRHFFS/action/author_attestation","sign_citation":"https://pith.science/pith/2VPXXQJ3O5X6IFENVUM2PRHFFS/action/citation_signature","submit_replication":"https://pith.science/pith/2VPXXQJ3O5X6IFENVUM2PRHFFS/action/replication_record"}},"created_at":"2026-07-05T11:48:33.218239+00:00","updated_at":"2026-07-05T11:48:33.218239+00:00"}