{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CCOC7XNKBQJYJH62W6WRT5N5ZW","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":"5c57eb89adb5d2bbffab3a8c4bd4f6f13e1264f29ad6ed6b770c26562aa8c01e","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T17:37:28Z","title_canon_sha256":"41f03e7094efa73c93783c2e64dabb8564f8ba82730998815c72d8f4581b8326"},"schema_version":"1.0","source":{"id":"2305.11845","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11845","created_at":"2026-07-05T06:11:51Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11845v1","created_at":"2026-07-05T06:11:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11845","created_at":"2026-07-05T06:11:51Z"},{"alias_kind":"pith_short_12","alias_value":"CCOC7XNKBQJY","created_at":"2026-07-05T06:11:51Z"},{"alias_kind":"pith_short_16","alias_value":"CCOC7XNKBQJYJH62","created_at":"2026-07-05T06:11:51Z"},{"alias_kind":"pith_short_8","alias_value":"CCOC7XNK","created_at":"2026-07-05T06:11:51Z"}],"graph_snapshots":[{"event_id":"sha256:8c4c9105cf4b0ceaaa3f377a333ba629b62640f15d7f97edcdaecd1b0aa39046","target":"graph","created_at":"2026-07-05T06:11:51Z","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/2305.11845/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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% ","authors_text":"Connor W. Coley, Jiang Guo, Regina Barzilay, Yujie Qian, Zhengkai Tu","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T17:37:28Z","title":"RxnScribe: A Sequence Generation Model for Reaction Diagram Parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11845","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":"sha256:09c9b8c0834bde21b7f71eb694a86d50413eec0d722464216c0deee3c2d4714f","target":"record","created_at":"2026-07-05T06:11:51Z","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":"5c57eb89adb5d2bbffab3a8c4bd4f6f13e1264f29ad6ed6b770c26562aa8c01e","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T17:37:28Z","title_canon_sha256":"41f03e7094efa73c93783c2e64dabb8564f8ba82730998815c72d8f4581b8326"},"schema_version":"1.0","source":{"id":"2305.11845","kind":"arxiv","version":1}},"canonical_sha256":"109c2fddaa0c13849fdab7ad19f5bdcdb4dbd7233ea353d999a12c5c087a75eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"109c2fddaa0c13849fdab7ad19f5bdcdb4dbd7233ea353d999a12c5c087a75eb","first_computed_at":"2026-07-05T06:11:51.862490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:51.862490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nu+ozatyX/g+27SRlVWFcL2lkBsXRZH0LbsHAwgwu6LQOoHYHQsdMx4G+rUgPsWrfIT94W01GH8LjRFBPLT6Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:51.862926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.11845","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09c9b8c0834bde21b7f71eb694a86d50413eec0d722464216c0deee3c2d4714f","sha256:8c4c9105cf4b0ceaaa3f377a333ba629b62640f15d7f97edcdaecd1b0aa39046"],"state_sha256":"48761d702e5f34b54a0e4f8562ad2a62c3fa0aae5c90a83a206759d2bd5c9a40"}