# ORD validator output for govor2024_gbb_ord_dataset.pb.gz
# sha256 fccbd06fb79e1c49ea3aa7f9410622e2167b26918bfe76675bf9026dd3485c23
# ord-schema 0.8.3, rdkit 2026.09.1

$ python -m ord_schema.scripts.validate_dataset --input_pattern govor2024_gbb_ord_dataset.pb.gz
INFO 2026-10-14 04:09:44,470 validate_dataset.py:155: Found 1 datasets
  0%|          | 0/1 [00:00<?, ?it/s]
100%|██████████| 1/1 [00:03<00:00,  3.85s/it]
100%|██████████| 1/1 [00:03<00:00,  3.85s/it]
exit status: 0

$ python -m ord_schema.scripts.validate_dataset --validate_ids ...  (not run: ids are assigned by ORD on submission; the dataset intentionally has none)

# Per-reaction validations.validate_message tally (errors and warnings)
reactions: 2052; dataset_id set: False; reactions with reaction_id: 0
errors: 0
warnings: 74 (55 distinct)
  [6x] Reaction.inputs["aldehyde"].components[0]: structural identifiers are inconsistent: ['O=C[C@@H]1C[C@H]1C1OCCO1', 'O=C[C@H]1C[C@@H]1C1OCCO1 |&1:2,4|']
  [5x] Reaction.inputs["isonitrile"].components[0]: structural identifiers are inconsistent: ['[C-]#[N+][C@H]1CC[C@@H](C(=O)OC)C1', '[C-]#[N+][C@H]1CC[C@@H](C(=O)OC)C1 |&1:2,5|']
  [3x] Reaction.inputs["aldehyde"].components[0]: structural identifiers are inconsistent: ['Cn1nccc1[C@@H]1C[C@H]1C=O', 'Cn1nccc1[C@@H]1C[C@H]1C=O |&1:6,8|']
  [3x] Reaction.inputs["aldehyde"].components[0]: structural identifiers are inconsistent: ['C[C@@H]1C[C@@H]1CCC=O', 'C[C@H]1C[C@H]1CCC=O |&1:1,3|']
  [3x] Reaction.inputs["aldehyde"].components[0]: structural identifiers are inconsistent: ['Cn1ccnc1[C@@H]1OCCC[C@H]1C=O', 'Cn1ccnc1[C@@H]1OCCC[C@H]1C=O |&1:6,11|']
  [2x] Reaction.inputs["aldehyde"].components[0]: structural identifiers are inconsistent: ['CC(C)(C)OC(=O)[C@@H]1C[C@H]1C=O', 'CC(C)(C)OC(=O)[C@@H]1C[C@H]1C=O |&1:7,9|']
  [2x] Reaction.inputs["aldehyde"].components[0]: structural identifiers are inconsistent: ['COC(=O)[C@@H]1CC[C@H](C=O)C1', 'COC(=O)[C@@H]1CC[C@H](C=O)C1 |&1:4,7|']
  [2x] Reaction.inputs["aldehyde"].components[0]: structural identifiers are inconsistent: ['C[C@@H]1[C@@H](C=O)C1(F)F', 'C[C@H]1[C@H](C=O)C1(F)F |&1:1,2|']
  [2x] Reaction.inputs["aldehyde"].components[0]: structural identifiers are inconsistent: ['O=C[C@@H]1CCCC[C@H]1C(F)(F)F', 'O=C[C@H]1CCCC[C@@H]1C(F)(F)F |&1:2,7|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['COc1c(C)ccn2c(NC3CCOC3)c([C@@H]3C[C@H]3c3ccnn3C)nc12', 'COc1c(C)ccn2c(NC3CCOC3)c([C@H]3C[C@@H]3c3ccnn3C)nc12 |&1:16,18|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['CSCCNc1c([C@@H]2C[C@H]2C2OCCO2)nc2cc(C(F)F)c(Cl)cn12', 'CSCCNc1c([C@H]2C[C@@H]2C2OCCO2)nc2cc(C(F)F)c(Cl)cn12 |&1:7,9|']
  [1x] Reaction.inputs["aldehyde"].components[0]: structural identifiers are inconsistent: ['Cn1cc([C@@H]2OCC[C@H]2C=O)cn1', 'Cn1cc([C@@H]2OCC[C@H]2C=O)cn1 |&1:4,8|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['Cc1ccccc1Nc1c([C@@H]2CCO[C@H]2c2cnn(C)c2)nc2ccc(CN3CCOCC3)cn12', 'Cc1ccccc1Nc1c([C@H]2CCO[C@@H]2c2cnn(C)c2)nc2ccc(CN3CCOCC3)cn12 |&1:10,14|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['CC(C)(C)OC(=O)[C@@H]1C[C@H]1c1nc2cc(OCCO)ccn2c1NC1COC1', 'CC(C)(C)OC(=O)[C@H]1C[C@@H]1c1nc2cc(OCCO)ccn2c1NC1COC1 |&1:7,9|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['OCCc1ccc2nc([C@@H]3C[C@H]3C3OCCO3)c(NCc3ccc(F)cc3)n2c1', 'OCCc1ccc2nc([C@H]3C[C@@H]3C3OCCO3)c(NCc3ccc(F)cc3)n2c1 |&1:9,11|']
  [1x] Reaction.inputs["aldehyde"].components[0]: structural identifiers are inconsistent: ['CCn1cc([C@@H]2OCC[C@H]2C=O)cn1', 'CCn1cc([C@@H]2OCC[C@H]2C=O)cn1 |&1:5,9|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['CCn1cc([C@@H]2OCC[C@H]2c2nc3cc(CN(C)CCOC)ccn3c2NC(C)C)cn1', 'CCn1cc([C@@H]2OCC[C@H]2c2nc3cc(CN(C)CCOC)ccn3c2NC(C)C)cn1 |&1:5,9|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['CCOCCNc1c([C@@H]2CC[C@H](C(=O)OC)C2)nc2cccc(C(F)F)n12', 'CCOCCNc1c([C@@H]2CC[C@H](C(=O)OC)C2)nc2cccc(C(F)F)n12 |&1:8,11|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['C[C@@H]1C[C@@H]1CCc1nc2cc(P(C)(C)=O)ccn2c1NC1CCOCC1', 'C[C@H]1C[C@H]1CCc1nc2cc(P(C)(C)=O)ccn2c1NC1CCOCC1 |&1:1,3|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['COC(=O)[C@@H]1CC[C@H](Nc2c(-c3ccc(-n4ccnc4)cc3C)nc3ccc(S(=O)(=O)O)cn23)C1', 'COC(=O)[C@@H]1CC[C@H](Nc2c(-c3ccc(-n4ccnc4)cc3C)nc3ccc(S(=O)(=O)O)cn23)C1 |&1:4,7|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['COC(=O)[C@@H]1CC[C@H](Nc2c(-c3ccc(C)c(F)c3)nc3ccc(S(=O)(=O)O)cn23)C1', 'COC(=O)[C@@H]1CC[C@H](Nc2c(-c3ccc(C)c(F)c3)nc3ccc(S(=O)(=O)O)cn23)C1 |&1:4,7|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['COC(=O)[C@@H]1CC[C@H](Nc2c(-c3cncc(OC)c3)nc3cc4cn[nH]c4cn23)C1', 'COC(=O)[C@@H]1CC[C@H](Nc2c(-c3cncc(OC)c3)nc3cc4cn[nH]c4cn23)C1 |&1:4,7|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['COC(=O)[C@@H]1CC[C@H](Nc2c(C3CCCCC3)nc3ccc(S(=O)(=O)O)cn23)C1', 'COC(=O)[C@@H]1CC[C@H](Nc2c(C3CCCCC3)nc3ccc(S(=O)(=O)O)cn23)C1 |&1:4,7|']
  [1x] Reaction.inputs["aldehyde"].components[0]: structural identifiers are inconsistent: ['CC(C)(C)OC(=O)N[C@@H]1C(C=O)[C@H]2CC[C@@H]1C2', 'CC(C)(C)OC(=O)N[C@@H]1C(C=O)[C@H]2CC[C@@H]1C2 |&1:8,12,15|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['CCNc1c(C2[C@H]3CC[C@H](C3)[C@@H]2NC(=O)OC(C)(C)C)nc2cccc(S(C)(=O)=O)n12', 'CCNc1c(C2[C@H]3CC[C@H](C3)[C@@H]2NC(=O)OC(C)(C)C)nc2cccc(S(C)(=O)=O)n12 |&1:6,9,11|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['COc1ccccc1CNc1c([C@@H]2CCCO[C@H]2c2nccn2C)nc2cc([N+](=O)[O-])ccn12', 'COc1ccccc1CNc1c([C@H]2CCCO[C@@H]2c2nccn2C)nc2cc([N+](=O)[O-])ccn12 |&1:12,17|']
  [1x] Reaction.inputs["aldehyde"].components[0]: structural identifiers are inconsistent: ['O=C[C@@H]1C[C@H]1c1ccc(F)cc1', 'O=C[C@H]1C[C@@H]1c1ccc(F)cc1 |&1:2,4|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['NC(=O)c1ccc2nc([C@@H]3C[C@H]3c3ccc(F)cc3)c(NC3CCOCC3)n2c1', 'NC(=O)c1ccc2nc([C@@H]3C[C@H]3c3ccc(F)cc3)c(NC3CCOCC3)n2c1 |&1:9,11|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['COCCNc1c([C@@H]2[C@@H](C)C2(F)F)nc2c(N3CCOCC3)cccn12', 'COCCNc1c([C@H]2[C@H](C)C2(F)F)nc2c(N3CCOCC3)cccn12 |&1:7,8|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['COC(=O)[C@@H]1CC[C@H](c2nc3c(OCCCC#N)cccn3c2NCC2CCOC2)C1', 'COC(=O)[C@H]1CC[C@@H](c2nc3c(OCCCC#N)cccn3c2NCC2CCOC2)C1 |&1:4,7|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['COc1cc(Br)c(C)n2c(NC3CCOC3)c([C@@H]3C[C@H]3c3ccnn3C)nc12', 'COc1cc(Br)c(C)n2c(NC3CCOC3)c([C@H]3C[C@@H]3c3ccnn3C)nc12 |&1:17,19|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['Cc1ccccc1Nc1c([C@@H]2CCCO[C@H]2c2nccn2C)nc2ccc(CN3CCOCC3)cn12', 'Cc1ccccc1Nc1c([C@H]2CCCO[C@@H]2c2nccn2C)nc2ccc(CN3CCOCC3)cn12 |&1:10,15|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['COc1ccc(C)c2nc([C@@H]3C[C@H]3C3OCCO3)c(NC(C)(C)C)n12', 'COc1ccc(C)c2nc([C@H]3C[C@@H]3C3OCCO3)c(NC(C)(C)C)n12 |&1:10,12|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['NC(=O)c1ccc2nc([C@@H]3CCCC[C@H]3C(F)(F)F)c(Nc3ccc4c(c3)OCCO4)n2n1', 'NC(=O)c1ccc2nc([C@H]3CCCC[C@@H]3C(F)(F)F)c(Nc3ccc4c(c3)OCCO4)n2n1 |&1:9,14|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['C[C@@H]1C[C@@H]1CCc1nc2cccc(-c3nn[nH]n3)n2c1NC1CCOCC1', 'C[C@H]1C[C@H]1CCc1nc2cccc(-c3nn[nH]n3)n2c1NC1CCOCC1 |&1:1,3|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['COCCCCc1nc2c(Br)cc(C(=O)N(C)C)cn2c1N[C@@H]1CC[C@H](C(=O)OC)C1', 'COCCCCc1nc2c(Br)cc(C(=O)N(C)C)cn2c1N[C@H]1CC[C@@H](C(=O)OC)C1 |&1:22,25|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['C=C(C)CNc1c([C@@H]2C[C@H]2c2ccnn2C)nc2c(OC(C)C)nccn12', 'C=C(C)CNc1c([C@H]2C[C@@H]2c2ccnn2C)nc2c(OC(C)C)nccn12 |&1:7,9|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['CC(C)(C)Nc1c([C@@H]2C[C@H]2C2OCCO2)nc2ccc(P(C)(C)=O)cn12', 'CC(C)(C)Nc1c([C@H]2C[C@@H]2C2OCCO2)nc2ccc(P(C)(C)=O)cn12 |&1:7,9|']
  [1x] Reaction.inputs["aldehyde"].components[0]: structural identifiers are inconsistent: ['CC[C@@H]1C[C@H]1C=O', 'CC[C@@H]1C[C@H]1C=O |&1:2,4|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['CC[C@@H]1C[C@H]1c1nc2ccc(P(C)(C)=O)cn2c1NCc1ccc(F)cc1', 'CC[C@H]1C[C@@H]1c1nc2ccc(P(C)(C)=O)cn2c1NCc1ccc(F)cc1 |&1:2,4|']
  [1x] Reaction.inputs["aldehyde"].components[0]: structural identifiers are inconsistent: ['O=C[C@@H]1C[C@H]1C1CC1', 'O=C[C@H]1C[C@@H]1C1CC1 |&1:2,4|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['CCNc1c([C@@H]2C[C@H]2C2CC2)nc2cc(C(C)(C)O)ccn12', 'CCNc1c([C@H]2C[C@@H]2C2CC2)nc2cc(C(C)(C)O)ccn12 |&1:5,7|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['C[C@@H]1C[C@@H]1CCc1nc2ccc(P(C)(C)=O)cn2c1NC(C)(C)C', 'C[C@H]1C[C@H]1CCc1nc2ccc(P(C)(C)=O)cn2c1NC(C)(C)C |&1:1,3|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['CCNc1c([C@@H]2C[C@H]2C(=O)OC(C)(C)C)nc2cc(C(C)(C)O)ccn12', 'CCNc1c([C@@H]2C[C@H]2C(=O)OC(C)(C)C)nc2cc(C(C)(C)O)ccn12 |&1:5,7|']
  [1x] Reaction.inputs["aldehyde"].components[0]: structural identifiers are inconsistent: ['O=C[C@@H]1C[C@H]1c1ccccc1', 'O=C[C@H]1C[C@@H]1c1ccccc1 |&1:2,4|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['COCCNc1c([C@@H]2C[C@H]2c2ccccc2)nc2cc(C(N)=O)ccn12', 'COCCNc1c([C@@H]2C[C@H]2c2ccccc2)nc2cc(C(N)=O)ccn12 |&1:7,9|']
  [1x] Reaction.inputs["aldehyde"].components[0]: structural identifiers are inconsistent: ['C[C@@H]1CCC[C@H](C=O)N1C(=O)OC(C)(C)C', 'C[C@H]1CCC[C@@H](C=O)N1C(=O)OC(C)(C)C |&1:1,5|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['CNC(=O)c1ccn2c(NC3CCOC3)c([C@@H]3CCC[C@H](C)N3C(=O)OC(C)(C)C)nc2c1', 'CNC(=O)c1ccn2c(NC3CCOC3)c([C@@H]3CCC[C@H](C)N3C(=O)OC(C)(C)C)nc2c1 |&1:16,20|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['NS(=O)(=O)c1cccc2nc([C@@H]3CCCC[C@H]3C(F)(F)F)c(NCC3CCCO3)n12', 'NS(=O)(=O)c1cccc2nc([C@H]3CCCC[C@@H]3C(F)(F)F)c(NCC3CCCO3)n12 |&1:11,16|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['C#Cc1ccc2nc([C@@H]3C[C@H]3C3OCCO3)c(NC(C)(C)C)n2c1C', 'C#Cc1ccc2nc([C@H]3C[C@@H]3C3OCCO3)c(NC(C)(C)C)n2c1C |&1:8,10|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['C[C@@H]1[C@@H](c2nc3cc(-c4ncon4)ccn3c2NC(C)(C)C)C1(F)F', 'C[C@H]1[C@H](c2nc3cc(-c4ncon4)ccn3c2NC(C)(C)C)C1(F)F |&1:1,2|']
  [1x] Reaction.inputs["aldehyde"].components[0]: structural identifiers are inconsistent: ['O=C[C@@H]1C[C@H]1c1ccsc1', 'O=C[C@H]1C[C@@H]1c1ccsc1 |&1:2,4|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['COC(=O)C1CC(Nc2c([C@@H]3C[C@H]3c3ccsc3)nc3ccc(C(=O)N(C)C)cn23)C1', 'COC(=O)C1CC(Nc2c([C@@H]3C[C@H]3c3ccsc3)nc3ccc(C(=O)N(C)C)cn23)C1 |&1:10,12|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['CC(C)Nc1c([C@@H]2CCCO[C@H]2c2nccn2C)nc2cccc(Cc3ccccn3)n12', 'CC(C)Nc1c([C@H]2CCCO[C@@H]2c2nccn2C)nc2cccc(Cc3ccccn3)n12 |&1:6,11|']
  [1x] Reaction.outcomes[0].products[0]: structural identifiers are inconsistent: ['C=Cc1cn2c(NCCSC)c([C@@H]3C[C@H]3C3OCCO3)nc2cc1F', 'C=Cc1cn2c(NCCSC)c([C@H]3C[C@@H]3C3OCCO3)nc2cc1F |&1:12,14|']
