{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:O54R3TFXS2IYPSVQIXVBT5G6SJ","short_pith_number":"pith:O54R3TFX","schema_version":"1.0","canonical_sha256":"77791dccb7969187cab045ea19f4de927beeb269cba54e8fa2d1216409219c96","source":{"kind":"arxiv","id":"1811.02633","version":2},"attestation_state":"computed","paper":{"title":"Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Alpha A Lee, Costas Bekas, Peter Bolgar, Philippe Schwaller, Teodoro Laino, Th\\'eophile Gaudin","submitted_at":"2018-11-06T20:53:09Z","abstract_excerpt":"Organic synthesis is one of the key stumbling blocks in medicinal chemistry. A necessary yet unsolved step in planning synthesis is solving the forward problem: given reactants and reagents, predict the products. Similar to other work, we treat reaction prediction as a machine translation problem between SMILES strings of reactants-reagents and the products. We show that a multi-head attention Molecular Transformer model outperforms all algorithms in the literature, achieving a top-1 accuracy above 90% on a common benchmark dataset. Our algorithm requires no handcrafted rules, and accurately p"},"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":"1811.02633","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2018-11-06T20:53:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"599e613df4254b12154350e929271cc7acb24a9a4317c9929b223a9e8f09d1b7","abstract_canon_sha256":"523e25296a2fa8333a1ffa21080128658a10316e813939059ccae2d34fe2014b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:06.465589Z","signature_b64":"HOCgIOHmbIHqhg6ILVn7n1T8dGUntEU8rI1A+KwXqjjqZgfLb0g1XG2yTwLHp/lK8cS9ac0dIoEUm2ROsFyrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77791dccb7969187cab045ea19f4de927beeb269cba54e8fa2d1216409219c96","last_reissued_at":"2026-07-05T00:04:06.465097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:06.465097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Alpha A Lee, Costas Bekas, Peter Bolgar, Philippe Schwaller, Teodoro Laino, Th\\'eophile Gaudin","submitted_at":"2018-11-06T20:53:09Z","abstract_excerpt":"Organic synthesis is one of the key stumbling blocks in medicinal chemistry. A necessary yet unsolved step in planning synthesis is solving the forward problem: given reactants and reagents, predict the products. Similar to other work, we treat reaction prediction as a machine translation problem between SMILES strings of reactants-reagents and the products. We show that a multi-head attention Molecular Transformer model outperforms all algorithms in the literature, achieving a top-1 accuracy above 90% on a common benchmark dataset. Our algorithm requires no handcrafted rules, and accurately p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02633","kind":"arxiv","version":2},"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/1811.02633/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":"1811.02633","created_at":"2026-07-05T00:04:06.465156+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.02633v2","created_at":"2026-07-05T00:04:06.465156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02633","created_at":"2026-07-05T00:04:06.465156+00:00"},{"alias_kind":"pith_short_12","alias_value":"O54R3TFXS2IY","created_at":"2026-07-05T00:04:06.465156+00:00"},{"alias_kind":"pith_short_16","alias_value":"O54R3TFXS2IYPSVQ","created_at":"2026-07-05T00:04:06.465156+00:00"},{"alias_kind":"pith_short_8","alias_value":"O54R3TFX","created_at":"2026-07-05T00:04:06.465156+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.01356","citing_title":"Predicting Retrosynthetic Reaction using Self-Corrected Transformer Neural Networks","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O54R3TFXS2IYPSVQIXVBT5G6SJ","json":"https://pith.science/pith/O54R3TFXS2IYPSVQIXVBT5G6SJ.json","graph_json":"https://pith.science/api/pith-number/O54R3TFXS2IYPSVQIXVBT5G6SJ/graph.json","events_json":"https://pith.science/api/pith-number/O54R3TFXS2IYPSVQIXVBT5G6SJ/events.json","paper":"https://pith.science/paper/O54R3TFX"},"agent_actions":{"view_html":"https://pith.science/pith/O54R3TFXS2IYPSVQIXVBT5G6SJ","download_json":"https://pith.science/pith/O54R3TFXS2IYPSVQIXVBT5G6SJ.json","view_paper":"https://pith.science/paper/O54R3TFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.02633&json=true","fetch_graph":"https://pith.science/api/pith-number/O54R3TFXS2IYPSVQIXVBT5G6SJ/graph.json","fetch_events":"https://pith.science/api/pith-number/O54R3TFXS2IYPSVQIXVBT5G6SJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O54R3TFXS2IYPSVQIXVBT5G6SJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O54R3TFXS2IYPSVQIXVBT5G6SJ/action/storage_attestation","attest_author":"https://pith.science/pith/O54R3TFXS2IYPSVQIXVBT5G6SJ/action/author_attestation","sign_citation":"https://pith.science/pith/O54R3TFXS2IYPSVQIXVBT5G6SJ/action/citation_signature","submit_replication":"https://pith.science/pith/O54R3TFXS2IYPSVQIXVBT5G6SJ/action/replication_record"}},"created_at":"2026-07-05T00:04:06.465156+00:00","updated_at":"2026-07-05T00:04:06.465156+00:00"}