{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FJBEMJ57YUJWOSKPDMRV65DWGD","short_pith_number":"pith:FJBEMJ57","schema_version":"1.0","canonical_sha256":"2a424627bfc51367494f1b235f747630ec757a048f50dc099c9805f4e318c807","source":{"kind":"arxiv","id":"2111.10874","version":1},"attestation_state":"computed","paper":{"title":"Dataset of Solution-based Inorganic Materials Synthesis Recipes Extracted from the Scientific Literature","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Gerbrand Ceder, Haoyan Huo, Kevin Cruse, Olga Kononova, Tanjin He, Wenhao Sun, Yan Zeng, Yingzhi Sun, Yuxing Fei, Zheren Wang, Zijian Cai","submitted_at":"2021-11-21T18:41:28Z","abstract_excerpt":"The development of a materials synthesis route is usually based on heuristics and experience. A possible new approach would be to apply data-driven approaches to learn the patterns of synthesis from past experience and use them to predict the syntheses of novel materials. However, this route is impeded by the lack of a large-scale database of synthesis formulations. In this work, we applied advanced machine learning and natural language processing techniques to construct a dataset of 35,675 solution-based synthesis \"recipes\" extracted from the scientific literature. Each recipe contains essent"},"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":"2111.10874","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2021-11-21T18:41:28Z","cross_cats_sorted":[],"title_canon_sha256":"85ea070fa8de35106c75e63cd15ea0ab5864f054b83d226d3b1d9823d918ef82","abstract_canon_sha256":"bb87b5f288d6f9cf31f327f4066e5f06750dfcc7224f08e51878fcc47017bba0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:57.791366Z","signature_b64":"uHwywygrniQI6LhoUVYRG8PO3KcBJRCgg9StYfgBdPPacZAmcWCryiuz5CO/InHKorDX3Rz/M84MN6KVHuuEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a424627bfc51367494f1b235f747630ec757a048f50dc099c9805f4e318c807","last_reissued_at":"2026-07-05T03:33:57.790897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:57.790897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dataset of Solution-based Inorganic Materials Synthesis Recipes Extracted from the Scientific Literature","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Gerbrand Ceder, Haoyan Huo, Kevin Cruse, Olga Kononova, Tanjin He, Wenhao Sun, Yan Zeng, Yingzhi Sun, Yuxing Fei, Zheren Wang, Zijian Cai","submitted_at":"2021-11-21T18:41:28Z","abstract_excerpt":"The development of a materials synthesis route is usually based on heuristics and experience. A possible new approach would be to apply data-driven approaches to learn the patterns of synthesis from past experience and use them to predict the syntheses of novel materials. However, this route is impeded by the lack of a large-scale database of synthesis formulations. In this work, we applied advanced machine learning and natural language processing techniques to construct a dataset of 35,675 solution-based synthesis \"recipes\" extracted from the scientific literature. Each recipe contains essent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10874","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/2111.10874/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":"2111.10874","created_at":"2026-07-05T03:33:57.790951+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.10874v1","created_at":"2026-07-05T03:33:57.790951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10874","created_at":"2026-07-05T03:33:57.790951+00:00"},{"alias_kind":"pith_short_12","alias_value":"FJBEMJ57YUJW","created_at":"2026-07-05T03:33:57.790951+00:00"},{"alias_kind":"pith_short_16","alias_value":"FJBEMJ57YUJWOSKP","created_at":"2026-07-05T03:33:57.790951+00:00"},{"alias_kind":"pith_short_8","alias_value":"FJBEMJ57","created_at":"2026-07-05T03:33:57.790951+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/FJBEMJ57YUJWOSKPDMRV65DWGD","json":"https://pith.science/pith/FJBEMJ57YUJWOSKPDMRV65DWGD.json","graph_json":"https://pith.science/api/pith-number/FJBEMJ57YUJWOSKPDMRV65DWGD/graph.json","events_json":"https://pith.science/api/pith-number/FJBEMJ57YUJWOSKPDMRV65DWGD/events.json","paper":"https://pith.science/paper/FJBEMJ57"},"agent_actions":{"view_html":"https://pith.science/pith/FJBEMJ57YUJWOSKPDMRV65DWGD","download_json":"https://pith.science/pith/FJBEMJ57YUJWOSKPDMRV65DWGD.json","view_paper":"https://pith.science/paper/FJBEMJ57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.10874&json=true","fetch_graph":"https://pith.science/api/pith-number/FJBEMJ57YUJWOSKPDMRV65DWGD/graph.json","fetch_events":"https://pith.science/api/pith-number/FJBEMJ57YUJWOSKPDMRV65DWGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FJBEMJ57YUJWOSKPDMRV65DWGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FJBEMJ57YUJWOSKPDMRV65DWGD/action/storage_attestation","attest_author":"https://pith.science/pith/FJBEMJ57YUJWOSKPDMRV65DWGD/action/author_attestation","sign_citation":"https://pith.science/pith/FJBEMJ57YUJWOSKPDMRV65DWGD/action/citation_signature","submit_replication":"https://pith.science/pith/FJBEMJ57YUJWOSKPDMRV65DWGD/action/replication_record"}},"created_at":"2026-07-05T03:33:57.790951+00:00","updated_at":"2026-07-05T03:33:57.790951+00:00"}