{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VPKM4MHLSTBQTJWPMJW6PDQUGP","short_pith_number":"pith:VPKM4MHL","schema_version":"1.0","canonical_sha256":"abd4ce30eb94c309a6cf626de78e1433cb09a2a72ace730a630664e4d8f23473","source":{"kind":"arxiv","id":"2404.13053","version":1},"attestation_state":"computed","paper":{"title":"Harnessing Large Language Model to collect and analyze Metal-organic framework property dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Jihan Kim, Taeun Bae, Wonseok Lee, Yeonghun Kang","submitted_at":"2024-03-31T12:47:24Z","abstract_excerpt":"This research was focused on the efficient collection of experimental Metal-Organic Framework (MOF) data from scientific literature to address the challenges of accessing hard-to-find data and improving the quality of information available for machine learning studies in materials science. Utilizing a chain of advanced Large Language Models (LLMs), we developed a systematic approach to extract and organize MOF data into a structured format. Our methodology successfully compiled information from more than 40,000 research articles, creating a comprehensive and ready-to-use dataset. The findings "},"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":"2404.13053","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2024-03-31T12:47:24Z","cross_cats_sorted":[],"title_canon_sha256":"fcbd3c614f31041c8509cbc89982cec684e0241cd86e22d5cf3456d3f88d5a29","abstract_canon_sha256":"b2836b98370341ddd4ba04b6d0183dc68a6c1e1a8aaac1980b29440eced46033"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:02.487561Z","signature_b64":"rguNBwT3Tb7+KW4x9fI8QdJxh27fvn09TGnFSkHz7i/s5FPDHdacALGlE59ulGecl1iLPD7po1zJfMLb9jZHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abd4ce30eb94c309a6cf626de78e1433cb09a2a72ace730a630664e4d8f23473","last_reissued_at":"2026-07-05T08:10:02.487090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:02.487090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing Large Language Model to collect and analyze Metal-organic framework property dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Jihan Kim, Taeun Bae, Wonseok Lee, Yeonghun Kang","submitted_at":"2024-03-31T12:47:24Z","abstract_excerpt":"This research was focused on the efficient collection of experimental Metal-Organic Framework (MOF) data from scientific literature to address the challenges of accessing hard-to-find data and improving the quality of information available for machine learning studies in materials science. Utilizing a chain of advanced Large Language Models (LLMs), we developed a systematic approach to extract and organize MOF data into a structured format. Our methodology successfully compiled information from more than 40,000 research articles, creating a comprehensive and ready-to-use dataset. The findings "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13053","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/2404.13053/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":"2404.13053","created_at":"2026-07-05T08:10:02.487145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.13053v1","created_at":"2026-07-05T08:10:02.487145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13053","created_at":"2026-07-05T08:10:02.487145+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPKM4MHLSTBQ","created_at":"2026-07-05T08:10:02.487145+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPKM4MHLSTBQTJWP","created_at":"2026-07-05T08:10:02.487145+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPKM4MHL","created_at":"2026-07-05T08:10:02.487145+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09565","citing_title":"MDCrow: Automating Molecular Dynamics Workflows with Large Language Models","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VPKM4MHLSTBQTJWPMJW6PDQUGP","json":"https://pith.science/pith/VPKM4MHLSTBQTJWPMJW6PDQUGP.json","graph_json":"https://pith.science/api/pith-number/VPKM4MHLSTBQTJWPMJW6PDQUGP/graph.json","events_json":"https://pith.science/api/pith-number/VPKM4MHLSTBQTJWPMJW6PDQUGP/events.json","paper":"https://pith.science/paper/VPKM4MHL"},"agent_actions":{"view_html":"https://pith.science/pith/VPKM4MHLSTBQTJWPMJW6PDQUGP","download_json":"https://pith.science/pith/VPKM4MHLSTBQTJWPMJW6PDQUGP.json","view_paper":"https://pith.science/paper/VPKM4MHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.13053&json=true","fetch_graph":"https://pith.science/api/pith-number/VPKM4MHLSTBQTJWPMJW6PDQUGP/graph.json","fetch_events":"https://pith.science/api/pith-number/VPKM4MHLSTBQTJWPMJW6PDQUGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPKM4MHLSTBQTJWPMJW6PDQUGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPKM4MHLSTBQTJWPMJW6PDQUGP/action/storage_attestation","attest_author":"https://pith.science/pith/VPKM4MHLSTBQTJWPMJW6PDQUGP/action/author_attestation","sign_citation":"https://pith.science/pith/VPKM4MHLSTBQTJWPMJW6PDQUGP/action/citation_signature","submit_replication":"https://pith.science/pith/VPKM4MHLSTBQTJWPMJW6PDQUGP/action/replication_record"}},"created_at":"2026-07-05T08:10:02.487145+00:00","updated_at":"2026-07-05T08:10:02.487145+00:00"}