{"paper":{"title":"From Feasible to Practical: Pareto-Optimal Synthesis Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MORetro* recovers the true Pareto front of synthesis routes for any fixed single-step retrosynthesis model.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Antonio del Rio Chanona, Dongda Zhang, Friedrich Hastedt","submitted_at":"2026-05-08T09:53:30Z","abstract_excerpt":"Current computer-aided synthesis planning (CASP) methods often treat retrosynthesis as solved once a single feasible route is identified, focusing primarily on convergence or shortest-path metrics. This view is misaligned with real-world practice, where chemists must balance competing objectives such as cost, sustainability, toxicity, and overall yield. To address this, we formulate synthesis planning as a multi-objective search problem and introduce MORetro*, an algorithm that generates a Pareto front of synthesis routes to explicitly capture trade-offs among user-defined criteria. MORetro* u"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Building on multi-objective A*-search, we provide optimality guarantees showing that, for a fixed single-step model, MORetro* recovers the true Pareto front.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the single-step retrosynthesis model is fixed and sufficiently accurate, and that user-defined criteria can be meaningfully scalarized via weights without missing important non-convex trade-offs.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MORetro* uses weighted scalarization and BO-informed sampling on multi-objective A* search to produce Pareto-optimal synthesis routes with optimality guarantees for fixed single-step models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MORetro* recovers the true Pareto front of synthesis routes for any fixed single-step retrosynthesis model.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"decf3acbd17ec65c386fed53d4af0085e36ec79fe7d15c911116d3d4aed16d20"},"source":{"id":"2605.07521","kind":"arxiv","version":2},"verdict":{"id":"8e56530f-496e-4e7f-ac09-4a7fd604bba7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T01:48:05.362093Z","strongest_claim":"Building on multi-objective A*-search, we provide optimality guarantees showing that, for a fixed single-step model, MORetro* recovers the true Pareto front.","one_line_summary":"MORetro* uses weighted scalarization and BO-informed sampling on multi-objective A* search to produce Pareto-optimal synthesis routes with optimality guarantees for fixed single-step models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the single-step retrosynthesis model is fixed and sufficiently accurate, and that user-defined criteria can be meaningfully scalarized via weights without missing important non-convex trade-offs.","pith_extraction_headline":"MORetro* recovers the true Pareto front of synthesis routes for any fixed single-step retrosynthesis model."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.07521/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T10:42:02.883750Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T05:41:18.962820Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T16:31:18.715554Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T11:43:01.460095Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"8fa3cdbda794ca6b8f75f04bd3ace2651bcf6dedded783a06d082fa899b62c7d"},"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"}