{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q3UNYMKFFICWH5HXGYYG2EJG5J","short_pith_number":"pith:Q3UNYMKF","schema_version":"1.0","canonical_sha256":"86e8dc31452a0563f4f736306d1126ea4edba853f177a6b7ccc9d0ab224c2263","source":{"kind":"arxiv","id":"2607.01061","version":1},"attestation_state":"computed","paper":{"title":"Agentic generation of verifiable rules for deterministic, self-expanding reaction classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Daniel Armstrong, Helena Avila, J\\'er\\^ome Waser, Maarten Dobbelaere, Octavian Susanu, Philippe Schwaller, Valentas Olikauskas","submitted_at":"2026-07-01T15:24:06Z","abstract_excerpt":"Computer-assisted synthesis planning breaks target molecules into accessible precursors using large libraries of reaction rules that assign each transformation a deterministic, interpretable label. But chemistry is long-tailed, making manual encoding intractable, and existing tools rely on fixed rulesets that cannot adapt to new chemistries. Here we present a fully automated pipeline in which a multi-agent framework of large language models (LLMs) classifies reactions and writes the rules themselves across 665,901 US patent reactions, generating each rule under a verification loop that tests i"},"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":"2607.01061","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-01T15:24:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a4d5b0367db29986a41c7f2389422e01819b26db9cc1f8431a6ee37d81dd515e","abstract_canon_sha256":"8559f8206127def0e2a5fb82ac6b32c9b89790b1d14d1fb6a942de94fd9e7296"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:27.671786Z","signature_b64":"r8Z0+D9f4LH45ZZBoxgj1lW5L2oZrHl6EecCuYV2/VUuthJ0HG3GoZJhLUeNKOCZNgbGLVpIyo2BGabNweqUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86e8dc31452a0563f4f736306d1126ea4edba853f177a6b7ccc9d0ab224c2263","last_reissued_at":"2026-07-02T01:18:27.671404Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:27.671404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agentic generation of verifiable rules for deterministic, self-expanding reaction classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Daniel Armstrong, Helena Avila, J\\'er\\^ome Waser, Maarten Dobbelaere, Octavian Susanu, Philippe Schwaller, Valentas Olikauskas","submitted_at":"2026-07-01T15:24:06Z","abstract_excerpt":"Computer-assisted synthesis planning breaks target molecules into accessible precursors using large libraries of reaction rules that assign each transformation a deterministic, interpretable label. But chemistry is long-tailed, making manual encoding intractable, and existing tools rely on fixed rulesets that cannot adapt to new chemistries. Here we present a fully automated pipeline in which a multi-agent framework of large language models (LLMs) classifies reactions and writes the rules themselves across 665,901 US patent reactions, generating each rule under a verification loop that tests i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01061","kind":"arxiv","version":1},"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/2607.01061/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":"2607.01061","created_at":"2026-07-02T01:18:27.671466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01061v1","created_at":"2026-07-02T01:18:27.671466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01061","created_at":"2026-07-02T01:18:27.671466+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3UNYMKFFICW","created_at":"2026-07-02T01:18:27.671466+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3UNYMKFFICWH5HX","created_at":"2026-07-02T01:18:27.671466+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3UNYMKF","created_at":"2026-07-02T01:18:27.671466+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/Q3UNYMKFFICWH5HXGYYG2EJG5J","json":"https://pith.science/pith/Q3UNYMKFFICWH5HXGYYG2EJG5J.json","graph_json":"https://pith.science/api/pith-number/Q3UNYMKFFICWH5HXGYYG2EJG5J/graph.json","events_json":"https://pith.science/api/pith-number/Q3UNYMKFFICWH5HXGYYG2EJG5J/events.json","paper":"https://pith.science/paper/Q3UNYMKF"},"agent_actions":{"view_html":"https://pith.science/pith/Q3UNYMKFFICWH5HXGYYG2EJG5J","download_json":"https://pith.science/pith/Q3UNYMKFFICWH5HXGYYG2EJG5J.json","view_paper":"https://pith.science/paper/Q3UNYMKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01061&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3UNYMKFFICWH5HXGYYG2EJG5J/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3UNYMKFFICWH5HXGYYG2EJG5J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3UNYMKFFICWH5HXGYYG2EJG5J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3UNYMKFFICWH5HXGYYG2EJG5J/action/storage_attestation","attest_author":"https://pith.science/pith/Q3UNYMKFFICWH5HXGYYG2EJG5J/action/author_attestation","sign_citation":"https://pith.science/pith/Q3UNYMKFFICWH5HXGYYG2EJG5J/action/citation_signature","submit_replication":"https://pith.science/pith/Q3UNYMKFFICWH5HXGYYG2EJG5J/action/replication_record"}},"created_at":"2026-07-02T01:18:27.671466+00:00","updated_at":"2026-07-02T01:18:27.671466+00:00"}