{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:73HR5KXQJPPTUS65VBESQXLEJS","short_pith_number":"pith:73HR5KXQ","schema_version":"1.0","canonical_sha256":"fecf1eaaf04bdf3a4bdda849285d644c8712b98770ba9e5f34a826bdb5b8f783","source":{"kind":"arxiv","id":"2411.03484","version":1},"attestation_state":"computed","paper":{"title":"Automated, LLM enabled extraction of synthesis details for reticular materials from scientific literature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Alexandre Rademaker, Anaximandro Souza, Breno W. Carvalho, Carmen Nilda Paz, Gabriela de Valnisio, Geisa Lima, Jo\\~ao Pedro Souza, Krystelle Lionti, Marcelo Archanjo, Mathias Steiner, Renato Cerqueira, Rodrigo Neumann, Ronaldo Giro, Sandro Fiorini, Viviane Torres da Silva","submitted_at":"2024-11-05T20:08:23Z","abstract_excerpt":"Automated knowledge extraction from scientific literature can potentially accelerate materials discovery. We have investigated an approach for extracting synthesis protocols for reticular materials from scientific literature using large language models (LLMs). To that end, we introduce a Knowledge Extraction Pipeline (KEP) that automatizes LLM-assisted paragraph classification and information extraction. By applying prompt engineering with in-context learning (ICL) to a set of open-source LLMs, we demonstrate that LLMs can retrieve chemical information from PDF documents, without the need for "},"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":"2411.03484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2024-11-05T20:08:23Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"4c228d7a85e30198ec78c02bc5e256220eca10c1c3a9fddda93f6bb84fd82bb4","abstract_canon_sha256":"2bc2704d87605434e75e6a74a175696d7becf39495b1ece777cb4562136b483b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:52.464491Z","signature_b64":"3B0yGUOybeAS3TwjTQ+dedNTdLw9BXMZQWqtKaNsJ7vEtBr1C4hOyA+33vq71u1hs4/TXlFZZHW/78DOIMJOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fecf1eaaf04bdf3a4bdda849285d644c8712b98770ba9e5f34a826bdb5b8f783","last_reissued_at":"2026-07-05T09:31:52.464073Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:52.464073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated, LLM enabled extraction of synthesis details for reticular materials from scientific literature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Alexandre Rademaker, Anaximandro Souza, Breno W. Carvalho, Carmen Nilda Paz, Gabriela de Valnisio, Geisa Lima, Jo\\~ao Pedro Souza, Krystelle Lionti, Marcelo Archanjo, Mathias Steiner, Renato Cerqueira, Rodrigo Neumann, Ronaldo Giro, Sandro Fiorini, Viviane Torres da Silva","submitted_at":"2024-11-05T20:08:23Z","abstract_excerpt":"Automated knowledge extraction from scientific literature can potentially accelerate materials discovery. We have investigated an approach for extracting synthesis protocols for reticular materials from scientific literature using large language models (LLMs). To that end, we introduce a Knowledge Extraction Pipeline (KEP) that automatizes LLM-assisted paragraph classification and information extraction. By applying prompt engineering with in-context learning (ICL) to a set of open-source LLMs, we demonstrate that LLMs can retrieve chemical information from PDF documents, without the need for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03484","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/2411.03484/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":"2411.03484","created_at":"2026-07-05T09:31:52.464129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03484v1","created_at":"2026-07-05T09:31:52.464129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03484","created_at":"2026-07-05T09:31:52.464129+00:00"},{"alias_kind":"pith_short_12","alias_value":"73HR5KXQJPPT","created_at":"2026-07-05T09:31:52.464129+00:00"},{"alias_kind":"pith_short_16","alias_value":"73HR5KXQJPPTUS65","created_at":"2026-07-05T09:31:52.464129+00:00"},{"alias_kind":"pith_short_8","alias_value":"73HR5KXQ","created_at":"2026-07-05T09:31:52.464129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":115,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/73HR5KXQJPPTUS65VBESQXLEJS","json":"https://pith.science/pith/73HR5KXQJPPTUS65VBESQXLEJS.json","graph_json":"https://pith.science/api/pith-number/73HR5KXQJPPTUS65VBESQXLEJS/graph.json","events_json":"https://pith.science/api/pith-number/73HR5KXQJPPTUS65VBESQXLEJS/events.json","paper":"https://pith.science/paper/73HR5KXQ"},"agent_actions":{"view_html":"https://pith.science/pith/73HR5KXQJPPTUS65VBESQXLEJS","download_json":"https://pith.science/pith/73HR5KXQJPPTUS65VBESQXLEJS.json","view_paper":"https://pith.science/paper/73HR5KXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03484&json=true","fetch_graph":"https://pith.science/api/pith-number/73HR5KXQJPPTUS65VBESQXLEJS/graph.json","fetch_events":"https://pith.science/api/pith-number/73HR5KXQJPPTUS65VBESQXLEJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73HR5KXQJPPTUS65VBESQXLEJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73HR5KXQJPPTUS65VBESQXLEJS/action/storage_attestation","attest_author":"https://pith.science/pith/73HR5KXQJPPTUS65VBESQXLEJS/action/author_attestation","sign_citation":"https://pith.science/pith/73HR5KXQJPPTUS65VBESQXLEJS/action/citation_signature","submit_replication":"https://pith.science/pith/73HR5KXQJPPTUS65VBESQXLEJS/action/replication_record"}},"created_at":"2026-07-05T09:31:52.464129+00:00","updated_at":"2026-07-05T09:31:52.464129+00:00"}