{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:K6O24LVFZNCOTBMBQWHBSIUM7F","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c2f7d6518d25c1715db7c04a02d97726cc623c6a9c284a89718ee9ec079af114","cross_cats_sorted":["cond-mat.mtrl-sci"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-10T07:51:52Z","title_canon_sha256":"53eca6312e1cbec1cea9a31169af97be782b13fe85d6b5314ec8447f6ab0117b"},"schema_version":"1.0","source":{"id":"2212.05238","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.05238","created_at":"2026-07-05T05:24:01Z"},{"alias_kind":"arxiv_version","alias_value":"2212.05238v1","created_at":"2026-07-05T05:24:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.05238","created_at":"2026-07-05T05:24:01Z"},{"alias_kind":"pith_short_12","alias_value":"K6O24LVFZNCO","created_at":"2026-07-05T05:24:01Z"},{"alias_kind":"pith_short_16","alias_value":"K6O24LVFZNCOTBMB","created_at":"2026-07-05T05:24:01Z"},{"alias_kind":"pith_short_8","alias_value":"K6O24LVF","created_at":"2026-07-05T05:24:01Z"}],"graph_snapshots":[{"event_id":"sha256:666eec629c0375c0397485a2042b0a592577d86f76dad5ac4ed23797ec073b2b","target":"graph","created_at":"2026-07-05T05:24:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2212.05238/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Intelligently extracting and linking complex scientific information from unstructured text is a challenging endeavor particularly for those inexperienced with natural language processing. Here, we present a simple sequence-to-sequence approach to joint named entity recognition and relation extraction for complex hierarchical information in scientific text. The approach leverages a pre-trained large language model (LLM), GPT-3, that is fine-tuned on approximately 500 pairs of prompts (inputs) and completions (outputs). Information is extracted either from single sentences or across sentences in","authors_text":"Alexander Dunn, Andrew S. Rosen, Anubhav Jain, Gerbrand Ceder, John Dagdelen, Kristin Persson, Nicholas Walker, Sanghoon Lee","cross_cats":["cond-mat.mtrl-sci"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-10T07:51:52Z","title":"Structured information extraction from complex scientific text with fine-tuned large language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.05238","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:921654acce6e3b4f5c150d7981295025ce7a13373be77f66be141dd4c10ed2f7","target":"record","created_at":"2026-07-05T05:24:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c2f7d6518d25c1715db7c04a02d97726cc623c6a9c284a89718ee9ec079af114","cross_cats_sorted":["cond-mat.mtrl-sci"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-10T07:51:52Z","title_canon_sha256":"53eca6312e1cbec1cea9a31169af97be782b13fe85d6b5314ec8447f6ab0117b"},"schema_version":"1.0","source":{"id":"2212.05238","kind":"arxiv","version":1}},"canonical_sha256":"579dae2ea5cb44e98581858e19228cf95115de448b9f97b6fdac6107ebdf4270","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"579dae2ea5cb44e98581858e19228cf95115de448b9f97b6fdac6107ebdf4270","first_computed_at":"2026-07-05T05:24:01.820873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:24:01.820873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+c8grgT3sNz9K7N8SzQpvkADQ5PO3PexzlngHAzLeBTPuZDklSY5E3FrVSmD5VRcbS4nZok+itBdfbg4glVeBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:24:01.821384Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.05238","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:921654acce6e3b4f5c150d7981295025ce7a13373be77f66be141dd4c10ed2f7","sha256:666eec629c0375c0397485a2042b0a592577d86f76dad5ac4ed23797ec073b2b"],"state_sha256":"8db222d4b0df17b882a36e1fb1c50a3277768f5eeb8133251f6aaad353a6b86e"}