{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BJD7WPBZHBGKWQ762DJL6DNGM2","short_pith_number":"pith:BJD7WPBZ","schema_version":"1.0","canonical_sha256":"0a47fb3c39384cab43fed0d2bf0da666b70e6d5732df5fa5df7a1bd670a45986","source":{"kind":"arxiv","id":"1711.04810","version":2},"attestation_state":"computed","paper":{"title":"\"Found in Translation\": Predicting Outcomes of Complex Organic Chemistry Reactions using Neural Sequence-to-Sequence Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Costas Bekas, David Lanyi, Philippe Schwaller, Teodoro Laino, Theophile Gaudin","submitted_at":"2017-11-13T19:38:14Z","abstract_excerpt":"There is an intuitive analogy of an organic chemist's understanding of a compound and a language speaker's understanding of a word. Consequently, it is possible to introduce the basic concepts and analyze potential impacts of linguistic analysis to the world of organic chemistry. In this work, we cast the reaction prediction task as a translation problem by introducing a template-free sequence-to-sequence model, trained end-to-end and fully data-driven. We propose a novel way of tokenization, which is arbitrarily extensible with reaction information. With this approach, we demonstrate results "},"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":"1711.04810","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-13T19:38:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fa6e10bf77ae83e46dd401fbd5070fb1f7251a6bcdcf27b3965d6e3328b7959e","abstract_canon_sha256":"c99bd01bb1b475c1eb238e5342690b49c0d9e956695307528a8deb1609276b02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:29.893545Z","signature_b64":"AkD8SHCZl8Cc9J1DJzLFJz9yFJ/VwCcEaFwaFDZzbUvsrW8rdTxuDYQTpMUJCoDmcm+lRmYlUKa0aR8K+KH1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a47fb3c39384cab43fed0d2bf0da666b70e6d5732df5fa5df7a1bd670a45986","last_reissued_at":"2026-05-18T00:30:29.892824Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:29.892824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\"Found in Translation\": Predicting Outcomes of Complex Organic Chemistry Reactions using Neural Sequence-to-Sequence Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Costas Bekas, David Lanyi, Philippe Schwaller, Teodoro Laino, Theophile Gaudin","submitted_at":"2017-11-13T19:38:14Z","abstract_excerpt":"There is an intuitive analogy of an organic chemist's understanding of a compound and a language speaker's understanding of a word. Consequently, it is possible to introduce the basic concepts and analyze potential impacts of linguistic analysis to the world of organic chemistry. In this work, we cast the reaction prediction task as a translation problem by introducing a template-free sequence-to-sequence model, trained end-to-end and fully data-driven. We propose a novel way of tokenization, which is arbitrarily extensible with reaction information. With this approach, we demonstrate results "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04810","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":""},"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":"1711.04810","created_at":"2026-05-18T00:30:29.892944+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.04810v2","created_at":"2026-05-18T00:30:29.892944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04810","created_at":"2026-05-18T00:30:29.892944+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJD7WPBZHBGK","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJD7WPBZHBGKWQ76","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJD7WPBZ","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJD7WPBZHBGKWQ762DJL6DNGM2","json":"https://pith.science/pith/BJD7WPBZHBGKWQ762DJL6DNGM2.json","graph_json":"https://pith.science/api/pith-number/BJD7WPBZHBGKWQ762DJL6DNGM2/graph.json","events_json":"https://pith.science/api/pith-number/BJD7WPBZHBGKWQ762DJL6DNGM2/events.json","paper":"https://pith.science/paper/BJD7WPBZ"},"agent_actions":{"view_html":"https://pith.science/pith/BJD7WPBZHBGKWQ762DJL6DNGM2","download_json":"https://pith.science/pith/BJD7WPBZHBGKWQ762DJL6DNGM2.json","view_paper":"https://pith.science/paper/BJD7WPBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.04810&json=true","fetch_graph":"https://pith.science/api/pith-number/BJD7WPBZHBGKWQ762DJL6DNGM2/graph.json","fetch_events":"https://pith.science/api/pith-number/BJD7WPBZHBGKWQ762DJL6DNGM2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJD7WPBZHBGKWQ762DJL6DNGM2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJD7WPBZHBGKWQ762DJL6DNGM2/action/storage_attestation","attest_author":"https://pith.science/pith/BJD7WPBZHBGKWQ762DJL6DNGM2/action/author_attestation","sign_citation":"https://pith.science/pith/BJD7WPBZHBGKWQ762DJL6DNGM2/action/citation_signature","submit_replication":"https://pith.science/pith/BJD7WPBZHBGKWQ762DJL6DNGM2/action/replication_record"}},"created_at":"2026-05-18T00:30:29.892944+00:00","updated_at":"2026-05-18T00:30:29.892944+00:00"}