{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6FU5WRCZ4J2GHACWJN5IKI5GW4","short_pith_number":"pith:6FU5WRCZ","schema_version":"1.0","canonical_sha256":"f169db4459e2746380564b7a8523a6b72cec1f167b69dc1871e010c0cead4a5c","source":{"kind":"arxiv","id":"2605.00222","version":2},"attestation_state":"computed","paper":{"title":"CompleteRXN: Toward Completing Open Chemical Reaction Databases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A new benchmark and constrained model complete missing parts of chemical reactions from open databases at up to 99% accuracy.","cross_cats":["physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Evgeny Pidko, Gabriel Vogel, Jana M. Weber, Minouk Noordsij","submitted_at":"2026-04-30T20:53:29Z","abstract_excerpt":"Chemical reaction datasets such as USPTO suffer from substantial incompleteness, frequently missing byproducts, co-reactants, and stoichiometric coefficients. This limits their applicability and reliability in downstream applications. Here, we introduce CompleteRXN, a large-scale supervised benchmark for reaction completion under realistic missing-data conditions. We construct a dataset of aligned incomplete and atom-balanced reactions by mapping USPTO records to curated mechanistic reactions. We evaluate representative baselines, including a novel encoder-decoder reaction completion model wit"},"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":"2605.00222","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-30T20:53:29Z","cross_cats_sorted":["physics.chem-ph"],"title_canon_sha256":"26df00a54b1ba3629dea698fc0814732b03d551af609c69fbd3dfdf369cd1115","abstract_canon_sha256":"0574f6a5e3b35b1f1ddf2a9ac409585f825550f843868f06b8cfb46ebcc15bce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:45.388877Z","signature_b64":"Bg8ChCzgGaBtEnft0W6oo3xqW3v6aGLfyg3C3KApOxX33kPi1bQrn217N3aLau2LCt3hRGhmlKWeLnFeuE/QAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f169db4459e2746380564b7a8523a6b72cec1f167b69dc1871e010c0cead4a5c","last_reissued_at":"2026-05-29T02:05:45.388308Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:45.388308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CompleteRXN: Toward Completing Open Chemical Reaction Databases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A new benchmark and constrained model complete missing parts of chemical reactions from open databases at up to 99% accuracy.","cross_cats":["physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Evgeny Pidko, Gabriel Vogel, Jana M. Weber, Minouk Noordsij","submitted_at":"2026-04-30T20:53:29Z","abstract_excerpt":"Chemical reaction datasets such as USPTO suffer from substantial incompleteness, frequently missing byproducts, co-reactants, and stoichiometric coefficients. This limits their applicability and reliability in downstream applications. Here, we introduce CompleteRXN, a large-scale supervised benchmark for reaction completion under realistic missing-data conditions. We construct a dataset of aligned incomplete and atom-balanced reactions by mapping USPTO records to curated mechanistic reactions. We evaluate representative baselines, including a novel encoder-decoder reaction completion model wit"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On our CompleteRXN benchmark, the CRB achieves high performance across splits of increasing difficulty, reaching 99.20% equivalence accuracy on the random split and 91.12% on the extreme out-of-distribution split.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The dataset of aligned incomplete and atom-balanced reactions constructed by mapping USPTO records to curated mechanistic reactions accurately captures realistic missing-data conditions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The paper presents the CompleteRXN benchmark for reaction completion and shows that a novel Constrained Reaction Balancer model reaches 99.20% accuracy on random splits but drops to 91.12% on extreme out-of-distribution cases and further on uncurated data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A new benchmark and constrained model complete missing parts of chemical reactions from open databases at up to 99% accuracy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"07dadd953d2019d886863ec69e834a4e94aaa4a79e61ae43ff695bb3b0a757e4"},"source":{"id":"2605.00222","kind":"arxiv","version":2},"verdict":{"id":"8d7f6282-82c6-4c44-9c35-720926e345d8","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T20:22:01.714639Z","strongest_claim":"On our CompleteRXN benchmark, the CRB achieves high performance across splits of increasing difficulty, reaching 99.20% equivalence accuracy on the random split and 91.12% on the extreme out-of-distribution split.","one_line_summary":"The paper presents the CompleteRXN benchmark for reaction completion and shows that a novel Constrained Reaction Balancer model reaches 99.20% accuracy on random splits but drops to 91.12% on extreme out-of-distribution cases and further on uncurated data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The dataset of aligned incomplete and atom-balanced reactions constructed by mapping USPTO records to curated mechanistic reactions accurately captures realistic missing-data conditions.","pith_extraction_headline":"A new benchmark and constrained model complete missing parts of chemical reactions from open databases at up to 99% accuracy."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.00222/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T20:36:25.141035Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T18:23:15.168047Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"9fdee4fdb3dee89547fe11968961ff5ff6295298a73f49f1d8c786220315c5ab"},"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":"2605.00222","created_at":"2026-05-29T02:05:45.388414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.00222v2","created_at":"2026-05-29T02:05:45.388414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.00222","created_at":"2026-05-29T02:05:45.388414+00:00"},{"alias_kind":"pith_short_12","alias_value":"6FU5WRCZ4J2G","created_at":"2026-05-29T02:05:45.388414+00:00"},{"alias_kind":"pith_short_16","alias_value":"6FU5WRCZ4J2GHACW","created_at":"2026-05-29T02:05:45.388414+00:00"},{"alias_kind":"pith_short_8","alias_value":"6FU5WRCZ","created_at":"2026-05-29T02:05:45.388414+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/6FU5WRCZ4J2GHACWJN5IKI5GW4","json":"https://pith.science/pith/6FU5WRCZ4J2GHACWJN5IKI5GW4.json","graph_json":"https://pith.science/api/pith-number/6FU5WRCZ4J2GHACWJN5IKI5GW4/graph.json","events_json":"https://pith.science/api/pith-number/6FU5WRCZ4J2GHACWJN5IKI5GW4/events.json","paper":"https://pith.science/paper/6FU5WRCZ"},"agent_actions":{"view_html":"https://pith.science/pith/6FU5WRCZ4J2GHACWJN5IKI5GW4","download_json":"https://pith.science/pith/6FU5WRCZ4J2GHACWJN5IKI5GW4.json","view_paper":"https://pith.science/paper/6FU5WRCZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.00222&json=true","fetch_graph":"https://pith.science/api/pith-number/6FU5WRCZ4J2GHACWJN5IKI5GW4/graph.json","fetch_events":"https://pith.science/api/pith-number/6FU5WRCZ4J2GHACWJN5IKI5GW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6FU5WRCZ4J2GHACWJN5IKI5GW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6FU5WRCZ4J2GHACWJN5IKI5GW4/action/storage_attestation","attest_author":"https://pith.science/pith/6FU5WRCZ4J2GHACWJN5IKI5GW4/action/author_attestation","sign_citation":"https://pith.science/pith/6FU5WRCZ4J2GHACWJN5IKI5GW4/action/citation_signature","submit_replication":"https://pith.science/pith/6FU5WRCZ4J2GHACWJN5IKI5GW4/action/replication_record"}},"created_at":"2026-05-29T02:05:45.388414+00:00","updated_at":"2026-05-29T02:05:45.388414+00:00"}