{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GHPD3SEFQWFLH2MDZ2GRLKOHZR","short_pith_number":"pith:GHPD3SEF","schema_version":"1.0","canonical_sha256":"31de3dc885858ab3e983ce8d15a9c7cc6efa9063da8ffe22665436dd7e83a97a","source":{"kind":"arxiv","id":"2501.06669","version":1},"attestation_state":"computed","paper":{"title":"Challenging reaction prediction models to generalize to novel chemistry","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Anji Zhang, Babak Mahjour, Connor W. Coley, David E. Graff, John Bradshaw, Marwin H.S. Segler","submitted_at":"2025-01-11T23:49:14Z","abstract_excerpt":"Deep learning models for anticipating the products of organic reactions have found many use cases, including validating retrosynthetic pathways and constraining synthesis-based molecular design tools. Despite compelling performance on popular benchmark tasks, strange and erroneous predictions sometimes ensue when using these models in practice. The core issue is that common benchmarks test models in an in-distribution setting, whereas many real-world uses for these models are in out-of-distribution settings and require a greater degree of extrapolation. To better understand how current reactio"},"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":"2501.06669","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-11T23:49:14Z","cross_cats_sorted":["physics.chem-ph"],"title_canon_sha256":"65344668deb1445e22a9c133949de8e55bc524a53c2513258069471221a61a8e","abstract_canon_sha256":"cecd03ff6321ad17d4430d8bc845c516aa90aee79252c9c08dc7f9823307eab5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:28.146086Z","signature_b64":"c0nqvoRsVl+7gi9Omk5QDhjXdaYpZ8dhbJsAiMMHZNNSxZmVUSzpS9c8FQP6YFovkKSFQ+mOqL2MUzl/GhnMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31de3dc885858ab3e983ce8d15a9c7cc6efa9063da8ffe22665436dd7e83a97a","last_reissued_at":"2026-07-05T10:00:28.145581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:28.145581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Challenging reaction prediction models to generalize to novel chemistry","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Anji Zhang, Babak Mahjour, Connor W. Coley, David E. Graff, John Bradshaw, Marwin H.S. Segler","submitted_at":"2025-01-11T23:49:14Z","abstract_excerpt":"Deep learning models for anticipating the products of organic reactions have found many use cases, including validating retrosynthetic pathways and constraining synthesis-based molecular design tools. Despite compelling performance on popular benchmark tasks, strange and erroneous predictions sometimes ensue when using these models in practice. The core issue is that common benchmarks test models in an in-distribution setting, whereas many real-world uses for these models are in out-of-distribution settings and require a greater degree of extrapolation. To better understand how current reactio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06669","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/2501.06669/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":"2501.06669","created_at":"2026-07-05T10:00:28.145641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.06669v1","created_at":"2026-07-05T10:00:28.145641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06669","created_at":"2026-07-05T10:00:28.145641+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHPD3SEFQWFL","created_at":"2026-07-05T10:00:28.145641+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHPD3SEFQWFLH2MD","created_at":"2026-07-05T10:00:28.145641+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHPD3SEF","created_at":"2026-07-05T10:00:28.145641+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04289","citing_title":"Retro-Rank-In: A Ranking-Based Approach for Inorganic Materials Synthesis Planning","ref_index":2020,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GHPD3SEFQWFLH2MDZ2GRLKOHZR","json":"https://pith.science/pith/GHPD3SEFQWFLH2MDZ2GRLKOHZR.json","graph_json":"https://pith.science/api/pith-number/GHPD3SEFQWFLH2MDZ2GRLKOHZR/graph.json","events_json":"https://pith.science/api/pith-number/GHPD3SEFQWFLH2MDZ2GRLKOHZR/events.json","paper":"https://pith.science/paper/GHPD3SEF"},"agent_actions":{"view_html":"https://pith.science/pith/GHPD3SEFQWFLH2MDZ2GRLKOHZR","download_json":"https://pith.science/pith/GHPD3SEFQWFLH2MDZ2GRLKOHZR.json","view_paper":"https://pith.science/paper/GHPD3SEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.06669&json=true","fetch_graph":"https://pith.science/api/pith-number/GHPD3SEFQWFLH2MDZ2GRLKOHZR/graph.json","fetch_events":"https://pith.science/api/pith-number/GHPD3SEFQWFLH2MDZ2GRLKOHZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHPD3SEFQWFLH2MDZ2GRLKOHZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHPD3SEFQWFLH2MDZ2GRLKOHZR/action/storage_attestation","attest_author":"https://pith.science/pith/GHPD3SEFQWFLH2MDZ2GRLKOHZR/action/author_attestation","sign_citation":"https://pith.science/pith/GHPD3SEFQWFLH2MDZ2GRLKOHZR/action/citation_signature","submit_replication":"https://pith.science/pith/GHPD3SEFQWFLH2MDZ2GRLKOHZR/action/replication_record"}},"created_at":"2026-07-05T10:00:28.145641+00:00","updated_at":"2026-07-05T10:00:28.145641+00:00"}