{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KGSCSLI63ZKHG56LZB5EYAFGO5","short_pith_number":"pith:KGSCSLI6","schema_version":"1.0","canonical_sha256":"51a4292d1ede547377cbc87a4c00a6776bbe2792915951fb7b29ab91c1dcda50","source":{"kind":"arxiv","id":"2407.18338","version":1},"attestation_state":"computed","paper":{"title":"SMiCRM: A Benchmark Dataset of Mechanistic Molecular Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV","q-bio.BM"],"primary_cat":"cs.CV","authors_text":"Ching Ting Leung, Hanyu Gao, Yufan Chen","submitted_at":"2024-07-25T18:52:10Z","abstract_excerpt":"Optical chemical structure recognition (OCSR) systems aim to extract the molecular structure information, usually in the form of molecular graph or SMILES, from images of chemical molecules. While many tools have been developed for this purpose, challenges still exist due to different types of noises that might exist in the images. Specifically, we focus on the 'arrow-pushing' diagrams, a typical type of chemical images to demonstrate electron flow in mechanistic steps. We present Structural molecular identifier of Molecular images in Chemical Reaction Mechanisms (SMiCRM), a dataset designed t"},"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":"2407.18338","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-25T18:52:10Z","cross_cats_sorted":["eess.IV","q-bio.BM"],"title_canon_sha256":"21cae6c372e85655d7388a25004566b7f6f7d19bf1914b7ee63bc4e0c08039cb","abstract_canon_sha256":"7921e8befc9ecb949a75d5776968ffd44908ab6afd7c02286744fcb2691a10b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:48.118782Z","signature_b64":"8RXdTgLOameFnt5XIUWNAxAWDGIY2BYD98LmYvEJLBnWzKWN0ZOYRFcODEN46X7bXN/DFVgNZXQNLKqV0JK3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51a4292d1ede547377cbc87a4c00a6776bbe2792915951fb7b29ab91c1dcda50","last_reissued_at":"2026-07-05T08:48:48.118181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:48.118181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMiCRM: A Benchmark Dataset of Mechanistic Molecular Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV","q-bio.BM"],"primary_cat":"cs.CV","authors_text":"Ching Ting Leung, Hanyu Gao, Yufan Chen","submitted_at":"2024-07-25T18:52:10Z","abstract_excerpt":"Optical chemical structure recognition (OCSR) systems aim to extract the molecular structure information, usually in the form of molecular graph or SMILES, from images of chemical molecules. While many tools have been developed for this purpose, challenges still exist due to different types of noises that might exist in the images. Specifically, we focus on the 'arrow-pushing' diagrams, a typical type of chemical images to demonstrate electron flow in mechanistic steps. We present Structural molecular identifier of Molecular images in Chemical Reaction Mechanisms (SMiCRM), a dataset designed t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18338","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/2407.18338/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":"2407.18338","created_at":"2026-07-05T08:48:48.118243+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.18338v1","created_at":"2026-07-05T08:48:48.118243+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18338","created_at":"2026-07-05T08:48:48.118243+00:00"},{"alias_kind":"pith_short_12","alias_value":"KGSCSLI63ZKH","created_at":"2026-07-05T08:48:48.118243+00:00"},{"alias_kind":"pith_short_16","alias_value":"KGSCSLI63ZKHG56L","created_at":"2026-07-05T08:48:48.118243+00:00"},{"alias_kind":"pith_short_8","alias_value":"KGSCSLI6","created_at":"2026-07-05T08:48:48.118243+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.05444","citing_title":"Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KGSCSLI63ZKHG56LZB5EYAFGO5","json":"https://pith.science/pith/KGSCSLI63ZKHG56LZB5EYAFGO5.json","graph_json":"https://pith.science/api/pith-number/KGSCSLI63ZKHG56LZB5EYAFGO5/graph.json","events_json":"https://pith.science/api/pith-number/KGSCSLI63ZKHG56LZB5EYAFGO5/events.json","paper":"https://pith.science/paper/KGSCSLI6"},"agent_actions":{"view_html":"https://pith.science/pith/KGSCSLI63ZKHG56LZB5EYAFGO5","download_json":"https://pith.science/pith/KGSCSLI63ZKHG56LZB5EYAFGO5.json","view_paper":"https://pith.science/paper/KGSCSLI6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.18338&json=true","fetch_graph":"https://pith.science/api/pith-number/KGSCSLI63ZKHG56LZB5EYAFGO5/graph.json","fetch_events":"https://pith.science/api/pith-number/KGSCSLI63ZKHG56LZB5EYAFGO5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KGSCSLI63ZKHG56LZB5EYAFGO5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KGSCSLI63ZKHG56LZB5EYAFGO5/action/storage_attestation","attest_author":"https://pith.science/pith/KGSCSLI63ZKHG56LZB5EYAFGO5/action/author_attestation","sign_citation":"https://pith.science/pith/KGSCSLI63ZKHG56LZB5EYAFGO5/action/citation_signature","submit_replication":"https://pith.science/pith/KGSCSLI63ZKHG56LZB5EYAFGO5/action/replication_record"}},"created_at":"2026-07-05T08:48:48.118243+00:00","updated_at":"2026-07-05T08:48:48.118243+00:00"}