{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CCOC7XNKBQJYJH62W6WRT5N5ZW","short_pith_number":"pith:CCOC7XNK","schema_version":"1.0","canonical_sha256":"109c2fddaa0c13849fdab7ad19f5bdcdb4dbd7233ea353d999a12c5c087a75eb","source":{"kind":"arxiv","id":"2305.11845","version":1},"attestation_state":"computed","paper":{"title":"RxnScribe: A Sequence Generation Model for Reaction Diagram Parsing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Connor W. Coley, Jiang Guo, Regina Barzilay, Yujie Qian, Zhengkai Tu","submitted_at":"2023-05-19T17:37:28Z","abstract_excerpt":"Reaction diagram parsing is the task of extracting reaction schemes from a diagram in the chemistry literature. The reaction diagrams can be arbitrarily complex, thus robustly parsing them into structured data is an open challenge. In this paper, we present RxnScribe, a machine learning model for parsing reaction diagrams of varying styles. We formulate this structured prediction task with a sequence generation approach, which condenses the traditional pipeline into an end-to-end model. We train RxnScribe on a dataset of 1,378 diagrams and evaluate it with cross validation, achieving an 80.0% "},"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":"2305.11845","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T17:37:28Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"41f03e7094efa73c93783c2e64dabb8564f8ba82730998815c72d8f4581b8326","abstract_canon_sha256":"5c57eb89adb5d2bbffab3a8c4bd4f6f13e1264f29ad6ed6b770c26562aa8c01e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:51.862926Z","signature_b64":"nu+ozatyX/g+27SRlVWFcL2lkBsXRZH0LbsHAwgwu6LQOoHYHQsdMx4G+rUgPsWrfIT94W01GH8LjRFBPLT6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"109c2fddaa0c13849fdab7ad19f5bdcdb4dbd7233ea353d999a12c5c087a75eb","last_reissued_at":"2026-07-05T06:11:51.862490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:51.862490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RxnScribe: A Sequence Generation Model for Reaction Diagram Parsing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Connor W. Coley, Jiang Guo, Regina Barzilay, Yujie Qian, Zhengkai Tu","submitted_at":"2023-05-19T17:37:28Z","abstract_excerpt":"Reaction diagram parsing is the task of extracting reaction schemes from a diagram in the chemistry literature. The reaction diagrams can be arbitrarily complex, thus robustly parsing them into structured data is an open challenge. In this paper, we present RxnScribe, a machine learning model for parsing reaction diagrams of varying styles. We formulate this structured prediction task with a sequence generation approach, which condenses the traditional pipeline into an end-to-end model. We train RxnScribe on a dataset of 1,378 diagrams and evaluate it with cross validation, achieving an 80.0% "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11845","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/2305.11845/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":"2305.11845","created_at":"2026-07-05T06:11:51.862548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11845v1","created_at":"2026-07-05T06:11:51.862548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11845","created_at":"2026-07-05T06:11:51.862548+00:00"},{"alias_kind":"pith_short_12","alias_value":"CCOC7XNKBQJY","created_at":"2026-07-05T06:11:51.862548+00:00"},{"alias_kind":"pith_short_16","alias_value":"CCOC7XNKBQJYJH62","created_at":"2026-07-05T06:11:51.862548+00:00"},{"alias_kind":"pith_short_8","alias_value":"CCOC7XNK","created_at":"2026-07-05T06:11:51.862548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17214","citing_title":"ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CCOC7XNKBQJYJH62W6WRT5N5ZW","json":"https://pith.science/pith/CCOC7XNKBQJYJH62W6WRT5N5ZW.json","graph_json":"https://pith.science/api/pith-number/CCOC7XNKBQJYJH62W6WRT5N5ZW/graph.json","events_json":"https://pith.science/api/pith-number/CCOC7XNKBQJYJH62W6WRT5N5ZW/events.json","paper":"https://pith.science/paper/CCOC7XNK"},"agent_actions":{"view_html":"https://pith.science/pith/CCOC7XNKBQJYJH62W6WRT5N5ZW","download_json":"https://pith.science/pith/CCOC7XNKBQJYJH62W6WRT5N5ZW.json","view_paper":"https://pith.science/paper/CCOC7XNK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11845&json=true","fetch_graph":"https://pith.science/api/pith-number/CCOC7XNKBQJYJH62W6WRT5N5ZW/graph.json","fetch_events":"https://pith.science/api/pith-number/CCOC7XNKBQJYJH62W6WRT5N5ZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CCOC7XNKBQJYJH62W6WRT5N5ZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CCOC7XNKBQJYJH62W6WRT5N5ZW/action/storage_attestation","attest_author":"https://pith.science/pith/CCOC7XNKBQJYJH62W6WRT5N5ZW/action/author_attestation","sign_citation":"https://pith.science/pith/CCOC7XNKBQJYJH62W6WRT5N5ZW/action/citation_signature","submit_replication":"https://pith.science/pith/CCOC7XNKBQJYJH62W6WRT5N5ZW/action/replication_record"}},"created_at":"2026-07-05T06:11:51.862548+00:00","updated_at":"2026-07-05T06:11:51.862548+00:00"}