{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3I4AICDGLPKJU6MDOKEAVLDVON","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":"ab177d0bdb2d7f7e9115cebb39a10a8c839f1c6728d345515785045b2cee5eb8","cross_cats_sorted":["cs.AI","cs.CE","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-19T14:08:05Z","title_canon_sha256":"05b0cd3adecf87c846cf6b922b4eb751c7ddbbfa4cec4610e678e75360bf98dd"},"schema_version":"1.0","source":{"id":"2608.18940","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.18940","created_at":"2026-08-20T01:24:26Z"},{"alias_kind":"arxiv_version","alias_value":"2608.18940v1","created_at":"2026-08-20T01:24:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.18940","created_at":"2026-08-20T01:24:26Z"},{"alias_kind":"pith_short_12","alias_value":"3I4AICDGLPKJ","created_at":"2026-08-20T01:24:26Z"},{"alias_kind":"pith_short_16","alias_value":"3I4AICDGLPKJU6MD","created_at":"2026-08-20T01:24:26Z"},{"alias_kind":"pith_short_8","alias_value":"3I4AICDG","created_at":"2026-08-20T01:24:26Z"}],"graph_snapshots":[{"event_id":"sha256:b75817055d663372987e20863239529cf78de3c7559841385225a0b48ddb94df","target":"graph","created_at":"2026-08-20T01:24:26Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.18940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Single-step retrosynthesis is a central component of computer-aided synthesis planning, yet its intrinsically one-to-many nature is poorly captured by single-answer evaluation and benchmarking protocols. To address this, we introduce Top-K prompting as a robust training and inference paradigm to better capture diverse, plausible reaction predictions. We compile CREED-CCV-2+USPTO-XL, an ultra-large-scale dataset of ~45.6 million verified reactions to train the C3LM (Chemistry Constraint-Consistent Language Model). By integrating fine-tuning with ChemCensor-based and novelty-oriented rewards, ou","authors_text":"Alex Aliper, Alex Zhavoronkov, Bogdan Zagribelnyy, Ivan Ilin, Maksim Kuznetsov, Mathieu Reymond, Nikita Bondarev, Vladimir Aladinskiy","cross_cats":["cs.AI","cs.CE","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-19T14:08:05Z","title":"Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.18940","kind":"arxiv","version":1},"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:c4f9eba957fb24cd600a86980164e0c0e1ccd435961a6a25be0ec52ff6c0a8bb","target":"record","created_at":"2026-08-20T01:24:26Z","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":"ab177d0bdb2d7f7e9115cebb39a10a8c839f1c6728d345515785045b2cee5eb8","cross_cats_sorted":["cs.AI","cs.CE","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-19T14:08:05Z","title_canon_sha256":"05b0cd3adecf87c846cf6b922b4eb751c7ddbbfa4cec4610e678e75360bf98dd"},"schema_version":"1.0","source":{"id":"2608.18940","kind":"arxiv","version":1}},"canonical_sha256":"da380408665bd49a798372880aac757376bafe1d9b5cb5d3f517a77c368fd32f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da380408665bd49a798372880aac757376bafe1d9b5cb5d3f517a77c368fd32f","first_computed_at":"2026-08-20T01:24:26.147409Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-20T01:24:26.147409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gxMthBPW5yje5QKhhhBFIf8hJDaKkfcisEQh27fXw4xLnNYPJbCF6EZY3TV811MjIo+jetwp2bE9md0JefbwAQ==","signature_status":"signed_v1","signed_at":"2026-08-20T01:24:26.149647Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.18940","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4f9eba957fb24cd600a86980164e0c0e1ccd435961a6a25be0ec52ff6c0a8bb","sha256:b75817055d663372987e20863239529cf78de3c7559841385225a0b48ddb94df"],"state_sha256":"b94abb28ae9b1d8c989fbef06609c7d14c728ab5366ad11a60393f99e8e1f817"}