{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HNGCSZAREOWKECC7ELVQJH66D5","short_pith_number":"pith:HNGCSZAR","schema_version":"1.0","canonical_sha256":"3b4c29641123aca2085f22eb049fde1f79cedd921403a90a8e575c63716ea850","source":{"kind":"arxiv","id":"1802.04903","version":1},"attestation_state":"computed","paper":{"title":"Molecular Structure Extraction From Documents Using Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Carolyn McQuaw, Joshua Staker, Kyle Marshall, Robert Abel","submitted_at":"2018-02-14T00:28:54Z","abstract_excerpt":"Chemical structure extraction from documents remains a hard problem due to both false positive identification of structures during segmentation and errors in the predicted structures. Current approaches rely on handcrafted rules and subroutines that perform reasonably well generally, but still routinely encounter situations where recognition rates are not yet satisfactory and systematic improvement is challenging. Complications impacting performance of current approaches include the diversity in visual styles used by various software to render structures, the frequent use of ad hoc annotations"},"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":"1802.04903","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T00:28:54Z","cross_cats_sorted":["physics.chem-ph"],"title_canon_sha256":"935b6238d074fadcc6520326b66d2dc8a8e017f1aacc5a0c0213afeea056f5e7","abstract_canon_sha256":"5302c651d0a967ee5b61da1b1c5c9014bd0ca0b2eba14c21175d2b77013b772d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:22.261030Z","signature_b64":"T/ddxgcBqMqy/UhsZI/DgKy4R8JK6H7mM63iFtMve3qypVmtPxsoJIWd0OmYHjdZ/sqfigizU668RbVtjBLpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b4c29641123aca2085f22eb049fde1f79cedd921403a90a8e575c63716ea850","last_reissued_at":"2026-05-18T00:23:22.260340Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:22.260340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Molecular Structure Extraction From Documents Using Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Carolyn McQuaw, Joshua Staker, Kyle Marshall, Robert Abel","submitted_at":"2018-02-14T00:28:54Z","abstract_excerpt":"Chemical structure extraction from documents remains a hard problem due to both false positive identification of structures during segmentation and errors in the predicted structures. Current approaches rely on handcrafted rules and subroutines that perform reasonably well generally, but still routinely encounter situations where recognition rates are not yet satisfactory and systematic improvement is challenging. Complications impacting performance of current approaches include the diversity in visual styles used by various software to render structures, the frequent use of ad hoc annotations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04903","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":""},"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":"1802.04903","created_at":"2026-05-18T00:23:22.260447+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.04903v1","created_at":"2026-05-18T00:23:22.260447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04903","created_at":"2026-05-18T00:23:22.260447+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNGCSZAREOWK","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNGCSZAREOWKECC7","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNGCSZAR","created_at":"2026-05-18T12:32:28.185984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05832","citing_title":"MolRecBench-Wild: A Real-World Benchmark for Optical Chemical Structure Recognition","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNGCSZAREOWKECC7ELVQJH66D5","json":"https://pith.science/pith/HNGCSZAREOWKECC7ELVQJH66D5.json","graph_json":"https://pith.science/api/pith-number/HNGCSZAREOWKECC7ELVQJH66D5/graph.json","events_json":"https://pith.science/api/pith-number/HNGCSZAREOWKECC7ELVQJH66D5/events.json","paper":"https://pith.science/paper/HNGCSZAR"},"agent_actions":{"view_html":"https://pith.science/pith/HNGCSZAREOWKECC7ELVQJH66D5","download_json":"https://pith.science/pith/HNGCSZAREOWKECC7ELVQJH66D5.json","view_paper":"https://pith.science/paper/HNGCSZAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.04903&json=true","fetch_graph":"https://pith.science/api/pith-number/HNGCSZAREOWKECC7ELVQJH66D5/graph.json","fetch_events":"https://pith.science/api/pith-number/HNGCSZAREOWKECC7ELVQJH66D5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNGCSZAREOWKECC7ELVQJH66D5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNGCSZAREOWKECC7ELVQJH66D5/action/storage_attestation","attest_author":"https://pith.science/pith/HNGCSZAREOWKECC7ELVQJH66D5/action/author_attestation","sign_citation":"https://pith.science/pith/HNGCSZAREOWKECC7ELVQJH66D5/action/citation_signature","submit_replication":"https://pith.science/pith/HNGCSZAREOWKECC7ELVQJH66D5/action/replication_record"}},"created_at":"2026-05-18T00:23:22.260447+00:00","updated_at":"2026-05-18T00:23:22.260447+00:00"}