{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6FU5WRCZ4J2GHACWJN5IKI5GW4","short_pith_number":"pith:6FU5WRCZ","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"},"canonical_sha256":"f169db4459e2746380564b7a8523a6b72cec1f167b69dc1871e010c0cead4a5c","source":{"kind":"arxiv","id":"2605.00222","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.00222","created_at":"2026-05-29T02:05:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.00222v2","created_at":"2026-05-29T02:05:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.00222","created_at":"2026-05-29T02:05:45Z"},{"alias_kind":"pith_short_12","alias_value":"6FU5WRCZ4J2G","created_at":"2026-05-29T02:05:45Z"},{"alias_kind":"pith_short_16","alias_value":"6FU5WRCZ4J2GHACW","created_at":"2026-05-29T02:05:45Z"},{"alias_kind":"pith_short_8","alias_value":"6FU5WRCZ","created_at":"2026-05-29T02:05:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6FU5WRCZ4J2GHACWJN5IKI5GW4","target":"record","payload":{"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"},"canonical_sha256":"f169db4459e2746380564b7a8523a6b72cec1f167b69dc1871e010c0cead4a5c","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"},"source_kind":"arxiv","source_id":"2605.00222","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T02:05:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zBt3m1f2pUT2OIC2X3+FqncYY8wOpvy2SCH7oH9rOYC7VgW515wd4bUs+kAGh8fDtzxqnu+/cP5EuiCbCB0TDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T09:52:40.264896Z"},"content_sha256":"c658ae9f17c1b8b146d8f92839d457833a49eab919631d53c6aa05b9f78f0103","schema_version":"1.0","event_id":"sha256:c658ae9f17c1b8b146d8f92839d457833a49eab919631d53c6aa05b9f78f0103"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6FU5WRCZ4J2GHACWJN5IKI5GW4","target":"graph","payload":{"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"},"verdict_id":"8d7f6282-82c6-4c44-9c35-720926e345d8"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T02:05:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K4n1RDt/Bgqp1h8rkCXZPTNpEfgZVRzVvRPkBqAF7lnEsfJyDHTH/7CM+wXsNjax+eQhS4aXeAVBMGag4x/KCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T09:52:40.265385Z"},"content_sha256":"6e7f732609703bad001e5c4bd7cee5d00d9d4bbfc63c0959136b65370def801b","schema_version":"1.0","event_id":"sha256:6e7f732609703bad001e5c4bd7cee5d00d9d4bbfc63c0959136b65370def801b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6FU5WRCZ4J2GHACWJN5IKI5GW4/bundle.json","state_url":"https://pith.science/pith/6FU5WRCZ4J2GHACWJN5IKI5GW4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6FU5WRCZ4J2GHACWJN5IKI5GW4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-30T09:52:40Z","links":{"resolver":"https://pith.science/pith/6FU5WRCZ4J2GHACWJN5IKI5GW4","bundle":"https://pith.science/pith/6FU5WRCZ4J2GHACWJN5IKI5GW4/bundle.json","state":"https://pith.science/pith/6FU5WRCZ4J2GHACWJN5IKI5GW4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6FU5WRCZ4J2GHACWJN5IKI5GW4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6FU5WRCZ4J2GHACWJN5IKI5GW4","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":"0574f6a5e3b35b1f1ddf2a9ac409585f825550f843868f06b8cfb46ebcc15bce","cross_cats_sorted":["physics.chem-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-30T20:53:29Z","title_canon_sha256":"26df00a54b1ba3629dea698fc0814732b03d551af609c69fbd3dfdf369cd1115"},"schema_version":"1.0","source":{"id":"2605.00222","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.00222","created_at":"2026-05-29T02:05:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.00222v2","created_at":"2026-05-29T02:05:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.00222","created_at":"2026-05-29T02:05:45Z"},{"alias_kind":"pith_short_12","alias_value":"6FU5WRCZ4J2G","created_at":"2026-05-29T02:05:45Z"},{"alias_kind":"pith_short_16","alias_value":"6FU5WRCZ4J2GHACW","created_at":"2026-05-29T02:05:45Z"},{"alias_kind":"pith_short_8","alias_value":"6FU5WRCZ","created_at":"2026-05-29T02:05:45Z"}],"graph_snapshots":[{"event_id":"sha256:6e7f732609703bad001e5c4bd7cee5d00d9d4bbfc63c0959136b65370def801b","target":"graph","created_at":"2026-05-29T02:05:45Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A new benchmark and constrained model complete missing parts of chemical reactions from open databases at up to 99% accuracy."}],"snapshot_sha256":"07dadd953d2019d886863ec69e834a4e94aaa4a79e61ae43ff695bb3b0a757e4"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.00222/integrity.json","findings":[],"snapshot_sha256":"9fdee4fdb3dee89547fe11968961ff5ff6295298a73f49f1d8c786220315c5ab","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Evgeny Pidko, Gabriel Vogel, Jana M. Weber, Minouk Noordsij","cross_cats":["physics.chem-ph"],"headline":"A new benchmark and constrained model complete missing parts of chemical reactions from open databases at up to 99% accuracy.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-30T20:53:29Z","title":"CompleteRXN: Toward Completing Open Chemical Reaction Databases"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.00222","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-09T20:22:01.714639Z","id":"8d7f6282-82c6-4c44-9c35-720926e345d8","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"A new benchmark and constrained model complete missing parts of chemical reactions from open databases at up to 99% accuracy.","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.","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."}},"verdict_id":"8d7f6282-82c6-4c44-9c35-720926e345d8"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c658ae9f17c1b8b146d8f92839d457833a49eab919631d53c6aa05b9f78f0103","target":"record","created_at":"2026-05-29T02:05:45Z","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":"0574f6a5e3b35b1f1ddf2a9ac409585f825550f843868f06b8cfb46ebcc15bce","cross_cats_sorted":["physics.chem-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-30T20:53:29Z","title_canon_sha256":"26df00a54b1ba3629dea698fc0814732b03d551af609c69fbd3dfdf369cd1115"},"schema_version":"1.0","source":{"id":"2605.00222","kind":"arxiv","version":2}},"canonical_sha256":"f169db4459e2746380564b7a8523a6b72cec1f167b69dc1871e010c0cead4a5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f169db4459e2746380564b7a8523a6b72cec1f167b69dc1871e010c0cead4a5c","first_computed_at":"2026-05-29T02:05:45.388308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:45.388308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bg8ChCzgGaBtEnft0W6oo3xqW3v6aGLfyg3C3KApOxX33kPi1bQrn217N3aLau2LCt3hRGhmlKWeLnFeuE/QAA==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:45.388877Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.00222","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c658ae9f17c1b8b146d8f92839d457833a49eab919631d53c6aa05b9f78f0103","sha256:6e7f732609703bad001e5c4bd7cee5d00d9d4bbfc63c0959136b65370def801b"],"state_sha256":"39ac8a1b8040a377ede9fa5e5eb719dee52736ccf304f4aabccb3e4c2829504b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gx0V/aemro70Lr/YlnnbAmDhGGjWZPsvLxuM59/1fpwo7xb5pIo+R0sHM2mjYCuILUPnwXXgNFff4rry4M8OAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T09:52:40.267719Z","bundle_sha256":"03fe837b916abea85109967ea4028e7b08642c19c80a751f9e3fd126de35180d"}}