{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UWP2HW5HC7K63CHYSZOCX5QA4X","short_pith_number":"pith:UWP2HW5H","schema_version":"1.0","canonical_sha256":"a59fa3dba717d5ed88f8965c2bf600e5e9be78ff90be27cd67f5b9e2c17acd06","source":{"kind":"arxiv","id":"2510.16590","version":2},"attestation_state":"computed","paper":{"title":"Atom-anchored LLMs speak Chemistry: A Retrosynthesis Demonstration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Alan Kai Hassen, Andrius Bernatavicius, Antonius P. A. Janssen, Djork-Arn\\'e Clevert, Gerard J. P. van Westen, Mike Preuss","submitted_at":"2025-10-18T17:27:44Z","abstract_excerpt":"Applications of machine learning in chemistry are often limited by the scarcity and expense of labeled data, restricting traditional supervised methods. In this work, we introduce a framework for molecular reasoning using general-purpose Large Language Models (LLMs) that operates without requiring task-specific model training. Our method anchors chain-of-thought reasoning to the molecular structure by using unique atomic identifiers. First, the LLM performs a zero-shot task to identify relevant fragments and their associated chemical labels or transformation classes. In an optional second step"},"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":"2510.16590","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-18T17:27:44Z","cross_cats_sorted":["cs.AI","q-bio.BM"],"title_canon_sha256":"42b227744538fa277c614a79194ab40813fe9f6f361c0606e4a71837bb8bb498","abstract_canon_sha256":"c253ea4d3f48079e163a5ad820d0d7f84b0854d8eef75a3d1fc5ffb2d36011f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T02:04:37.351802Z","signature_b64":"jxUQmt+NE4k4jo9f0ivCcm/mZSsslf85WLWqURcosGvEgJ9/JqL5qjST9nPe+NweZHzMKBSAEmH3kq0Tf2hhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a59fa3dba717d5ed88f8965c2bf600e5e9be78ff90be27cd67f5b9e2c17acd06","last_reissued_at":"2026-05-22T02:04:37.350758Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T02:04:37.350758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Atom-anchored LLMs speak Chemistry: A Retrosynthesis Demonstration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Alan Kai Hassen, Andrius Bernatavicius, Antonius P. A. Janssen, Djork-Arn\\'e Clevert, Gerard J. P. van Westen, Mike Preuss","submitted_at":"2025-10-18T17:27:44Z","abstract_excerpt":"Applications of machine learning in chemistry are often limited by the scarcity and expense of labeled data, restricting traditional supervised methods. In this work, we introduce a framework for molecular reasoning using general-purpose Large Language Models (LLMs) that operates without requiring task-specific model training. Our method anchors chain-of-thought reasoning to the molecular structure by using unique atomic identifiers. First, the LLM performs a zero-shot task to identify relevant fragments and their associated chemical labels or transformation classes. In an optional second step"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.16590","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/2510.16590/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":"2510.16590","created_at":"2026-05-22T02:04:37.350896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.16590v2","created_at":"2026-05-22T02:04:37.350896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.16590","created_at":"2026-05-22T02:04:37.350896+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWP2HW5HC7K6","created_at":"2026-05-22T02:04:37.350896+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWP2HW5HC7K63CHY","created_at":"2026-05-22T02:04:37.350896+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWP2HW5H","created_at":"2026-05-22T02:04:37.350896+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/UWP2HW5HC7K63CHYSZOCX5QA4X","json":"https://pith.science/pith/UWP2HW5HC7K63CHYSZOCX5QA4X.json","graph_json":"https://pith.science/api/pith-number/UWP2HW5HC7K63CHYSZOCX5QA4X/graph.json","events_json":"https://pith.science/api/pith-number/UWP2HW5HC7K63CHYSZOCX5QA4X/events.json","paper":"https://pith.science/paper/UWP2HW5H"},"agent_actions":{"view_html":"https://pith.science/pith/UWP2HW5HC7K63CHYSZOCX5QA4X","download_json":"https://pith.science/pith/UWP2HW5HC7K63CHYSZOCX5QA4X.json","view_paper":"https://pith.science/paper/UWP2HW5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.16590&json=true","fetch_graph":"https://pith.science/api/pith-number/UWP2HW5HC7K63CHYSZOCX5QA4X/graph.json","fetch_events":"https://pith.science/api/pith-number/UWP2HW5HC7K63CHYSZOCX5QA4X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWP2HW5HC7K63CHYSZOCX5QA4X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWP2HW5HC7K63CHYSZOCX5QA4X/action/storage_attestation","attest_author":"https://pith.science/pith/UWP2HW5HC7K63CHYSZOCX5QA4X/action/author_attestation","sign_citation":"https://pith.science/pith/UWP2HW5HC7K63CHYSZOCX5QA4X/action/citation_signature","submit_replication":"https://pith.science/pith/UWP2HW5HC7K63CHYSZOCX5QA4X/action/replication_record"}},"created_at":"2026-05-22T02:04:37.350896+00:00","updated_at":"2026-05-22T02:04:37.350896+00:00"}