{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IATWHDZTWYYKUZKZ4CV35OYX43","short_pith_number":"pith:IATWHDZT","schema_version":"1.0","canonical_sha256":"4027638f33b630aa6559e0abbebb17e6c632b110a3911d0d5ec802de7be91382","source":{"kind":"arxiv","id":"2401.00434","version":2},"attestation_state":"computed","paper":{"title":"GeoGalactica: A Scientific Large Language Model in Geoscience","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Beiya Dai, Bo Xue, Boyi Zeng, Cheng Deng, Chenghu Zhou, Junxian He, Le Zhou, Luoyi Fu, Qiyuan Chen, Shu Wang, Tianhang Zhang, Weinan Zhang, Xinbing Wang, Yi Xu, Yuanyuan Shi, Yunchong Song, Yunqiang Zhu, Yutong Xu, Yuxun Miao, Zhongmou He, Zhouhan Lin","submitted_at":"2023-12-31T09:22:54Z","abstract_excerpt":"Large language models (LLMs) have achieved huge success for their general knowledge and ability to solve a wide spectrum of tasks in natural language processing (NLP). Due to their impressive abilities, LLMs have shed light on potential inter-discipline applications to foster scientific discoveries of a specific domain by using artificial intelligence (AI for science, AI4S). In the meantime, utilizing NLP techniques in geoscience research and practice is wide and convoluted, contributing from knowledge extraction and document classification to question answering and knowledge discovery. In thi"},"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":"2401.00434","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-31T09:22:54Z","cross_cats_sorted":[],"title_canon_sha256":"396b150a04d5ddc37a0052315d21127176f5d2966a0d543859eacb3e5c76c1ff","abstract_canon_sha256":"10245284682e2155c3b741232a9aa435846a33b152a009fe71fb707204e9a053"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:32.208482Z","signature_b64":"TeCaRk/M26nDBTNg5ZHkHG/2bJs4wcMAb3zOgOWR86DtzA+62JU0Z1WI8kuXC6LxXpWjqAsG9vUXDWSlw58nAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4027638f33b630aa6559e0abbebb17e6c632b110a3911d0d5ec802de7be91382","last_reissued_at":"2026-07-05T08:07:32.207997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:32.207997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoGalactica: A Scientific Large Language Model in Geoscience","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Beiya Dai, Bo Xue, Boyi Zeng, Cheng Deng, Chenghu Zhou, Junxian He, Le Zhou, Luoyi Fu, Qiyuan Chen, Shu Wang, Tianhang Zhang, Weinan Zhang, Xinbing Wang, Yi Xu, Yuanyuan Shi, Yunchong Song, Yunqiang Zhu, Yutong Xu, Yuxun Miao, Zhongmou He, Zhouhan Lin","submitted_at":"2023-12-31T09:22:54Z","abstract_excerpt":"Large language models (LLMs) have achieved huge success for their general knowledge and ability to solve a wide spectrum of tasks in natural language processing (NLP). Due to their impressive abilities, LLMs have shed light on potential inter-discipline applications to foster scientific discoveries of a specific domain by using artificial intelligence (AI for science, AI4S). In the meantime, utilizing NLP techniques in geoscience research and practice is wide and convoluted, contributing from knowledge extraction and document classification to question answering and knowledge discovery. In thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00434","kind":"arxiv","version":2},"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/2401.00434/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":"2401.00434","created_at":"2026-07-05T08:07:32.208058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.00434v2","created_at":"2026-07-05T08:07:32.208058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00434","created_at":"2026-07-05T08:07:32.208058+00:00"},{"alias_kind":"pith_short_12","alias_value":"IATWHDZTWYYK","created_at":"2026-07-05T08:07:32.208058+00:00"},{"alias_kind":"pith_short_16","alias_value":"IATWHDZTWYYKUZKZ","created_at":"2026-07-05T08:07:32.208058+00:00"},{"alias_kind":"pith_short_8","alias_value":"IATWHDZT","created_at":"2026-07-05T08:07:32.208058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24346","citing_title":"PETRA: Transforming Web Text for Petroleum-Engineering Domain Adaptation","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25000","citing_title":"Geo-Strat-RL: Learning Geological Event Reasoning from Verifiable Tasks","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09774","citing_title":"Auto-Configuring Scientific Simulators with Lightweight Coding-Agent Adapters","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12542","citing_title":"Earth Science Foundation Models: From Perception to Reasoning and Discovery","ref_index":59,"is_internal_anchor":false},{"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":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12542","citing_title":"Earth Science Foundation Models: From Perception to Reasoning and Discovery","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21501","citing_title":"GeoMind: An Agentic Workflow for Lithology Classification with Reasoned Tool Invocation","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IATWHDZTWYYKUZKZ4CV35OYX43","json":"https://pith.science/pith/IATWHDZTWYYKUZKZ4CV35OYX43.json","graph_json":"https://pith.science/api/pith-number/IATWHDZTWYYKUZKZ4CV35OYX43/graph.json","events_json":"https://pith.science/api/pith-number/IATWHDZTWYYKUZKZ4CV35OYX43/events.json","paper":"https://pith.science/paper/IATWHDZT"},"agent_actions":{"view_html":"https://pith.science/pith/IATWHDZTWYYKUZKZ4CV35OYX43","download_json":"https://pith.science/pith/IATWHDZTWYYKUZKZ4CV35OYX43.json","view_paper":"https://pith.science/paper/IATWHDZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.00434&json=true","fetch_graph":"https://pith.science/api/pith-number/IATWHDZTWYYKUZKZ4CV35OYX43/graph.json","fetch_events":"https://pith.science/api/pith-number/IATWHDZTWYYKUZKZ4CV35OYX43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IATWHDZTWYYKUZKZ4CV35OYX43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IATWHDZTWYYKUZKZ4CV35OYX43/action/storage_attestation","attest_author":"https://pith.science/pith/IATWHDZTWYYKUZKZ4CV35OYX43/action/author_attestation","sign_citation":"https://pith.science/pith/IATWHDZTWYYKUZKZ4CV35OYX43/action/citation_signature","submit_replication":"https://pith.science/pith/IATWHDZTWYYKUZKZ4CV35OYX43/action/replication_record"}},"created_at":"2026-07-05T08:07:32.208058+00:00","updated_at":"2026-07-05T08:07:32.208058+00:00"}