{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XB5J3CZYXNEQNWLTEK7MPXMJVO","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":"5aeb3f6d5083fc30830f56a7c8f9ba267757cf27994df8c02d0e824743e46459","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T04:01:53Z","title_canon_sha256":"e5bb09c12aa879de0392071ec31bb5adedc576b2fac23f5738fcfb665be06dc7"},"schema_version":"1.0","source":{"id":"2608.09100","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09100","created_at":"2026-08-11T02:21:47Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09100v1","created_at":"2026-08-11T02:21:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09100","created_at":"2026-08-11T02:21:47Z"},{"alias_kind":"pith_short_12","alias_value":"XB5J3CZYXNEQ","created_at":"2026-08-11T02:21:47Z"},{"alias_kind":"pith_short_16","alias_value":"XB5J3CZYXNEQNWLT","created_at":"2026-08-11T02:21:47Z"},{"alias_kind":"pith_short_8","alias_value":"XB5J3CZY","created_at":"2026-08-11T02:21:47Z"}],"graph_snapshots":[{"event_id":"sha256:33f32c0515424c5b2255f3ec78ed8f142510b347c25079169a23dc09077f1fc5","target":"graph","created_at":"2026-08-11T02:21:47Z","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/2608.09100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Millions of chemical structures appear in patents and papers only as drawings, and using that information at scale requires reading the drawings. OCSR appears nearly solved on synthetic images yet remains difficult on real documents: the starting recognizer, Qwen2.5-VL-7B, exceeds 91% accuracy on synthetic renders but falls below 16% on three real-world benchmarks (ACS, CLEF-IP, USPTO). To identify the main source of improvement, 21 recognizers were fine-tuned on mixtures of synthetically rendered structures and labeled real depictions from patents, journal figures, and hand-drawn collections,","authors_text":"Dan Hannah, Dengpan Dong, Kang Xu, Shuang Luo, Yani Guan, Yumin Zhang, Zi Wei","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T04:01:53Z","title":"Real Data Closes Synthetic-to-Real Gap in Optical Chemical Structure Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09100","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":"sha256:0b49b755603e51b46bf9dcc4c9d9a7538244797842acbc1f75fbbc89f1055611","target":"record","created_at":"2026-08-11T02:21:47Z","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":"5aeb3f6d5083fc30830f56a7c8f9ba267757cf27994df8c02d0e824743e46459","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T04:01:53Z","title_canon_sha256":"e5bb09c12aa879de0392071ec31bb5adedc576b2fac23f5738fcfb665be06dc7"},"schema_version":"1.0","source":{"id":"2608.09100","kind":"arxiv","version":1}},"canonical_sha256":"b87a9d8b38bb4906d97322bec7dd89abb6594ee2f87b19825fdbda54236b21f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b87a9d8b38bb4906d97322bec7dd89abb6594ee2f87b19825fdbda54236b21f8","first_computed_at":"2026-08-11T02:21:47.929822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:21:47.929822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gLWVyZpQIXQEIlUC+ZIXq9p3aMO3/ey2xnqXEwvl34ft6NDIdZGw4c3J60GhDG1Q6bzrHqamL8R8jzX7i+evDA==","signature_status":"signed_v1","signed_at":"2026-08-11T02:21:47.931475Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09100","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b49b755603e51b46bf9dcc4c9d9a7538244797842acbc1f75fbbc89f1055611","sha256:33f32c0515424c5b2255f3ec78ed8f142510b347c25079169a23dc09077f1fc5"],"state_sha256":"5c334093112de65710e684b34f593eac5f0dc318700c3a0060968a6cd58d1af3"}