{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BJD7WPBZHBGKWQ762DJL6DNGM2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c99bd01bb1b475c1eb238e5342690b49c0d9e956695307528a8deb1609276b02","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-13T19:38:14Z","title_canon_sha256":"fa6e10bf77ae83e46dd401fbd5070fb1f7251a6bcdcf27b3965d6e3328b7959e"},"schema_version":"1.0","source":{"id":"1711.04810","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.04810","created_at":"2026-05-18T00:30:29Z"},{"alias_kind":"arxiv_version","alias_value":"1711.04810v2","created_at":"2026-05-18T00:30:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04810","created_at":"2026-05-18T00:30:29Z"},{"alias_kind":"pith_short_12","alias_value":"BJD7WPBZHBGK","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BJD7WPBZHBGKWQ76","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BJD7WPBZ","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:bd2d568e14e9c14526faa2e244132713be3d3795f86973ff9e68482fd9b81142","target":"graph","created_at":"2026-05-18T00:30:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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 ","authors_text":"Costas Bekas, David Lanyi, Philippe Schwaller, Teodoro Laino, Theophile Gaudin","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-13T19:38:14Z","title":"\"Found in Translation\": Predicting Outcomes of Complex Organic Chemistry Reactions using Neural Sequence-to-Sequence Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04810","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d51fb2fd4d16d1265a3f25215745a91c309a5a0ca67a2ecae6b434574eb04e83","target":"record","created_at":"2026-05-18T00:30:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c99bd01bb1b475c1eb238e5342690b49c0d9e956695307528a8deb1609276b02","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-13T19:38:14Z","title_canon_sha256":"fa6e10bf77ae83e46dd401fbd5070fb1f7251a6bcdcf27b3965d6e3328b7959e"},"schema_version":"1.0","source":{"id":"1711.04810","kind":"arxiv","version":2}},"canonical_sha256":"0a47fb3c39384cab43fed0d2bf0da666b70e6d5732df5fa5df7a1bd670a45986","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a47fb3c39384cab43fed0d2bf0da666b70e6d5732df5fa5df7a1bd670a45986","first_computed_at":"2026-05-18T00:30:29.892824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:29.892824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AkD8SHCZl8Cc9J1DJzLFJz9yFJ/VwCcEaFwaFDZzbUvsrW8rdTxuDYQTpMUJCoDmcm+lRmYlUKa0aR8K+KH1DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:29.893545Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.04810","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d51fb2fd4d16d1265a3f25215745a91c309a5a0ca67a2ecae6b434574eb04e83","sha256:bd2d568e14e9c14526faa2e244132713be3d3795f86973ff9e68482fd9b81142"],"state_sha256":"ab3885509dc19f6fbe9ed86b1c9217b6cbb96ef605a716f717ddda1b1d7042b3"}