{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BQINAGSAUIIXCHLNFB3MDCBOBP","short_pith_number":"pith:BQINAGSA","schema_version":"1.0","canonical_sha256":"0c10d01a40a211711d6d2876c1882e0bc023dcd60f99ff1c951b11d1821dab15","source":{"kind":"arxiv","id":"2109.04202","version":1},"attestation_state":"computed","paper":{"title":"IMG2SMI: Translating Molecular Structure Images to Simplified Molecular-input Line-entry System","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.IV"],"primary_cat":"q-bio.QM","authors_text":"Daniel Campos, Heng Ji","submitted_at":"2021-09-03T19:57:07Z","abstract_excerpt":"Like many scientific fields, new chemistry literature has grown at a staggering pace, with thousands of papers released every month. A large portion of chemistry literature focuses on new molecules and reactions between molecules. Most vital information is conveyed through 2-D images of molecules, representing the underlying molecules or reactions described. In order to ensure reproducible and machine-readable molecule representations, text-based molecule descriptors like SMILES and SELFIES were created. These text-based molecule representations provide molecule generation but are unfortunatel"},"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":"2109.04202","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"q-bio.QM","submitted_at":"2021-09-03T19:57:07Z","cross_cats_sorted":["cs.CV","cs.LG","eess.IV"],"title_canon_sha256":"6b1dc0fa8278b0cde363110055ecc9848d240e72d78c96a98d3d0be7dc7539e9","abstract_canon_sha256":"1125e7fa063224fe865b0742b4261a11a8c36f7268a0b69012a251dae43abc38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:56.263105Z","signature_b64":"GeXHCz3AnssjpULWV43Cv6THxyfmd9Sw+vuIFwfEWJMy4Np2dBHqGi5HxeTSjhg54Z5z5bZt4hy8Fp2rAtzzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c10d01a40a211711d6d2876c1882e0bc023dcd60f99ff1c951b11d1821dab15","last_reissued_at":"2026-07-05T03:12:56.262692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:56.262692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IMG2SMI: Translating Molecular Structure Images to Simplified Molecular-input Line-entry System","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.IV"],"primary_cat":"q-bio.QM","authors_text":"Daniel Campos, Heng Ji","submitted_at":"2021-09-03T19:57:07Z","abstract_excerpt":"Like many scientific fields, new chemistry literature has grown at a staggering pace, with thousands of papers released every month. A large portion of chemistry literature focuses on new molecules and reactions between molecules. Most vital information is conveyed through 2-D images of molecules, representing the underlying molecules or reactions described. In order to ensure reproducible and machine-readable molecule representations, text-based molecule descriptors like SMILES and SELFIES were created. These text-based molecule representations provide molecule generation but are unfortunatel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04202","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/2109.04202/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":"2109.04202","created_at":"2026-07-05T03:12:56.262748+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.04202v1","created_at":"2026-07-05T03:12:56.262748+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04202","created_at":"2026-07-05T03:12:56.262748+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQINAGSAUIIX","created_at":"2026-07-05T03:12:56.262748+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQINAGSAUIIXCHLN","created_at":"2026-07-05T03:12:56.262748+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQINAGSA","created_at":"2026-07-05T03:12:56.262748+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10912","citing_title":"Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BQINAGSAUIIXCHLNFB3MDCBOBP","json":"https://pith.science/pith/BQINAGSAUIIXCHLNFB3MDCBOBP.json","graph_json":"https://pith.science/api/pith-number/BQINAGSAUIIXCHLNFB3MDCBOBP/graph.json","events_json":"https://pith.science/api/pith-number/BQINAGSAUIIXCHLNFB3MDCBOBP/events.json","paper":"https://pith.science/paper/BQINAGSA"},"agent_actions":{"view_html":"https://pith.science/pith/BQINAGSAUIIXCHLNFB3MDCBOBP","download_json":"https://pith.science/pith/BQINAGSAUIIXCHLNFB3MDCBOBP.json","view_paper":"https://pith.science/paper/BQINAGSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.04202&json=true","fetch_graph":"https://pith.science/api/pith-number/BQINAGSAUIIXCHLNFB3MDCBOBP/graph.json","fetch_events":"https://pith.science/api/pith-number/BQINAGSAUIIXCHLNFB3MDCBOBP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQINAGSAUIIXCHLNFB3MDCBOBP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQINAGSAUIIXCHLNFB3MDCBOBP/action/storage_attestation","attest_author":"https://pith.science/pith/BQINAGSAUIIXCHLNFB3MDCBOBP/action/author_attestation","sign_citation":"https://pith.science/pith/BQINAGSAUIIXCHLNFB3MDCBOBP/action/citation_signature","submit_replication":"https://pith.science/pith/BQINAGSAUIIXCHLNFB3MDCBOBP/action/replication_record"}},"created_at":"2026-07-05T03:12:56.262748+00:00","updated_at":"2026-07-05T03:12:56.262748+00:00"}