{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7QBAE2IWRPZPIQY6UD4BLA7UNW","short_pith_number":"pith:7QBAE2IW","schema_version":"1.0","canonical_sha256":"fc020269168bf2f4431ea0f81583f46da5afd37c94c193af62e0776de9bed368","source":{"kind":"arxiv","id":"2506.23520","version":2},"attestation_state":"computed","paper":{"title":"ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Feng Zhu, Jiapeng Liu, Jidong Tian, Ruijie Yu, Xiaokang Yang, Yanyan Xu, Yaohui Jin, Yu Zhang","submitted_at":"2025-06-30T05:11:19Z","abstract_excerpt":"With the increasing interest in robotic synthesis in the context of organic chemistry, the automated extraction of chemical procedures from literature is critical. However, this task remains challenging due to the inherent ambiguity of chemical language and the high cost of human annotation required for developing reliable computer-aided extraction protocols. Here, we present ChemActor, a fully fine-tuned large language model (LLM), as a chemical executor to convert between unstructured experimental procedures and structured action sequences. We propose a sequential LLM-generated data framewor"},"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":"2506.23520","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-30T05:11:19Z","cross_cats_sorted":[],"title_canon_sha256":"158d2c1b65088281f631cfe8d1f61eb5b620e2c5a3fe1c0ae50076ccd3640ae0","abstract_canon_sha256":"4206bc08b6e56eed356ec6f5f2f9f72726791a869554dc12218d4186d43732c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:03.935697Z","signature_b64":"WeN2p8dhoAMzcim9sXwZGrEFs5MwPqHtjQQM2fYxC6grt8HYC/Uyo7H3TJcplFeMzjXsHFRhd4ILjmWRaGoJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc020269168bf2f4431ea0f81583f46da5afd37c94c193af62e0776de9bed368","last_reissued_at":"2026-07-05T11:30:03.935200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:03.935200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Feng Zhu, Jiapeng Liu, Jidong Tian, Ruijie Yu, Xiaokang Yang, Yanyan Xu, Yaohui Jin, Yu Zhang","submitted_at":"2025-06-30T05:11:19Z","abstract_excerpt":"With the increasing interest in robotic synthesis in the context of organic chemistry, the automated extraction of chemical procedures from literature is critical. However, this task remains challenging due to the inherent ambiguity of chemical language and the high cost of human annotation required for developing reliable computer-aided extraction protocols. Here, we present ChemActor, a fully fine-tuned large language model (LLM), as a chemical executor to convert between unstructured experimental procedures and structured action sequences. We propose a sequential LLM-generated data framewor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23520","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/2506.23520/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":"2506.23520","created_at":"2026-07-05T11:30:03.935257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23520v2","created_at":"2026-07-05T11:30:03.935257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23520","created_at":"2026-07-05T11:30:03.935257+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QBAE2IWRPZP","created_at":"2026-07-05T11:30:03.935257+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QBAE2IWRPZPIQY6","created_at":"2026-07-05T11:30:03.935257+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QBAE2IW","created_at":"2026-07-05T11:30:03.935257+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19704","citing_title":"RefiningGPT: Specialized language Models for Automated Refinery Unit-level Process Diagram Synthesis","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7QBAE2IWRPZPIQY6UD4BLA7UNW","json":"https://pith.science/pith/7QBAE2IWRPZPIQY6UD4BLA7UNW.json","graph_json":"https://pith.science/api/pith-number/7QBAE2IWRPZPIQY6UD4BLA7UNW/graph.json","events_json":"https://pith.science/api/pith-number/7QBAE2IWRPZPIQY6UD4BLA7UNW/events.json","paper":"https://pith.science/paper/7QBAE2IW"},"agent_actions":{"view_html":"https://pith.science/pith/7QBAE2IWRPZPIQY6UD4BLA7UNW","download_json":"https://pith.science/pith/7QBAE2IWRPZPIQY6UD4BLA7UNW.json","view_paper":"https://pith.science/paper/7QBAE2IW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23520&json=true","fetch_graph":"https://pith.science/api/pith-number/7QBAE2IWRPZPIQY6UD4BLA7UNW/graph.json","fetch_events":"https://pith.science/api/pith-number/7QBAE2IWRPZPIQY6UD4BLA7UNW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QBAE2IWRPZPIQY6UD4BLA7UNW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QBAE2IWRPZPIQY6UD4BLA7UNW/action/storage_attestation","attest_author":"https://pith.science/pith/7QBAE2IWRPZPIQY6UD4BLA7UNW/action/author_attestation","sign_citation":"https://pith.science/pith/7QBAE2IWRPZPIQY6UD4BLA7UNW/action/citation_signature","submit_replication":"https://pith.science/pith/7QBAE2IWRPZPIQY6UD4BLA7UNW/action/replication_record"}},"created_at":"2026-07-05T11:30:03.935257+00:00","updated_at":"2026-07-05T11:30:03.935257+00:00"}