{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:URYCINJ4FNQL6VVSCFOKPE5UAU","short_pith_number":"pith:URYCINJ4","schema_version":"1.0","canonical_sha256":"a47024353c2b60bf56b2115ca793b405255d6b4360b3a92e554dadb67cf86289","source":{"kind":"arxiv","id":"2412.05269","version":2},"attestation_state":"computed","paper":{"title":"Chemist-aligned retrosynthesis by ensembling diverse inductive bias models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Aleksei Kornev, Austin Tripp, Guoqing Liu, Holger Hoefling, Hubert Misztela, Junren Li, Krzysztof Maziarz, Marwin Segler, Mike Fortunato, Piotr Gai\\'nski, Rishi Gupta","submitted_at":"2024-12-06T18:55:19Z","abstract_excerpt":"Chemical synthesis remains a critical bottleneck in the discovery and manufacture of functional small molecules. AI-based synthesis planning models could be a potential remedy to find effective syntheses, and have made progress in recent years. However, they still struggle with less frequent, yet critical reactions for synthetic strategy, as well as hallucinated, incorrect predictions. This hampers multi-step search algorithms that rely on models, and leads to misalignment with chemists' expectations. Here we propose RetroChimera: a frontier retrosynthesis model, built upon two newly developed"},"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":"2412.05269","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-06T18:55:19Z","cross_cats_sorted":["cs.AI","q-bio.QM"],"title_canon_sha256":"9fd20726eec8acf045d953470e4e6c2c7d9cfc00810006642301d0533846f4d2","abstract_canon_sha256":"0b1efdae006e9537b31fc0bacb19ef21803716e8f6674727d9cbb38c39eef6eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:16.596179Z","signature_b64":"VpGU93de8sjJHnCgelfmjhi2glYoHo5i4VMhwolhYXjDCva7mR5DoThOGRAPrPnYeLsWHGyI/vsx0G+EnzP4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a47024353c2b60bf56b2115ca793b405255d6b4360b3a92e554dadb67cf86289","last_reissued_at":"2026-07-05T11:52:16.595572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:16.595572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chemist-aligned retrosynthesis by ensembling diverse inductive bias models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Aleksei Kornev, Austin Tripp, Guoqing Liu, Holger Hoefling, Hubert Misztela, Junren Li, Krzysztof Maziarz, Marwin Segler, Mike Fortunato, Piotr Gai\\'nski, Rishi Gupta","submitted_at":"2024-12-06T18:55:19Z","abstract_excerpt":"Chemical synthesis remains a critical bottleneck in the discovery and manufacture of functional small molecules. AI-based synthesis planning models could be a potential remedy to find effective syntheses, and have made progress in recent years. However, they still struggle with less frequent, yet critical reactions for synthetic strategy, as well as hallucinated, incorrect predictions. This hampers multi-step search algorithms that rely on models, and leads to misalignment with chemists' expectations. Here we propose RetroChimera: a frontier retrosynthesis model, built upon two newly developed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05269","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/2412.05269/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":"2412.05269","created_at":"2026-07-05T11:52:16.595650+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05269v2","created_at":"2026-07-05T11:52:16.595650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05269","created_at":"2026-07-05T11:52:16.595650+00:00"},{"alias_kind":"pith_short_12","alias_value":"URYCINJ4FNQL","created_at":"2026-07-05T11:52:16.595650+00:00"},{"alias_kind":"pith_short_16","alias_value":"URYCINJ4FNQL6VVS","created_at":"2026-07-05T11:52:16.595650+00:00"},{"alias_kind":"pith_short_8","alias_value":"URYCINJ4","created_at":"2026-07-05T11:52:16.595650+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24184","citing_title":"Project Ariadne: Prompt-Conditioned Route Generation for Synthesis Planning","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07181","citing_title":"RETROSPECT: RETROsynthesis via Sequential Prediction, and Chemically Transformed-ranking","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02618","citing_title":"Closed-Loop Molecular Design with Calibrated Deference","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/URYCINJ4FNQL6VVSCFOKPE5UAU","json":"https://pith.science/pith/URYCINJ4FNQL6VVSCFOKPE5UAU.json","graph_json":"https://pith.science/api/pith-number/URYCINJ4FNQL6VVSCFOKPE5UAU/graph.json","events_json":"https://pith.science/api/pith-number/URYCINJ4FNQL6VVSCFOKPE5UAU/events.json","paper":"https://pith.science/paper/URYCINJ4"},"agent_actions":{"view_html":"https://pith.science/pith/URYCINJ4FNQL6VVSCFOKPE5UAU","download_json":"https://pith.science/pith/URYCINJ4FNQL6VVSCFOKPE5UAU.json","view_paper":"https://pith.science/paper/URYCINJ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05269&json=true","fetch_graph":"https://pith.science/api/pith-number/URYCINJ4FNQL6VVSCFOKPE5UAU/graph.json","fetch_events":"https://pith.science/api/pith-number/URYCINJ4FNQL6VVSCFOKPE5UAU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URYCINJ4FNQL6VVSCFOKPE5UAU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URYCINJ4FNQL6VVSCFOKPE5UAU/action/storage_attestation","attest_author":"https://pith.science/pith/URYCINJ4FNQL6VVSCFOKPE5UAU/action/author_attestation","sign_citation":"https://pith.science/pith/URYCINJ4FNQL6VVSCFOKPE5UAU/action/citation_signature","submit_replication":"https://pith.science/pith/URYCINJ4FNQL6VVSCFOKPE5UAU/action/replication_record"}},"created_at":"2026-07-05T11:52:16.595650+00:00","updated_at":"2026-07-05T11:52:16.595650+00:00"}