pino-source-code / artifacts /odour_taxonomy_coverage_census_v8.json
Matthew Ford
pimt v8 diagnostics and qa artifacts
ac9ca3b
Raw
History Blame Contribute Delete
26.8 kB
{
"arctander_parse_counts": {
"arctander_source_available_masked_no_clean_crosswalk_hit": 27,
"parsed_from_arctander": 57,
"parsed_from_arctander_multihot": 28
},
"class_z_carriers": [
"142-91-6",
"25265-71-8",
"64-17-5",
"84-66-2",
"SMILES:CC(O)CO"
],
"coverage_table": {
"class_z_carriers_character_excluded": 5,
"materials_with_authoritative_character_label_taxonomy_reference_plus_parsed_from_source_excluding_z": 89,
"materials_with_both_axes_excluding_z": 20,
"materials_with_neither_axis_excluding_z": 502,
"materials_with_substantivity_measured_poucher_model_ready": 170,
"per_class_character_counts": {
"A": 6,
"B": 8,
"C": 5,
"D": 2,
"E": 2,
"F": 10,
"G": 17,
"H": 12,
"I": 3,
"J": 2,
"K": 2,
"L": 3,
"M": 3,
"N": 0,
"O": 0,
"P": 4,
"Q": 7,
"R": 7,
"S": 5,
"T": 0,
"U": 3,
"V": 3,
"W": 17,
"X": 7,
"Y": 1,
"Z": 0
}
},
"crosswalk_version": "v8.1",
"dataset_scope": [
"data/empirical_dataset_v8.jsonl"
],
"discrimination_precheck": {
"formula_labelled_by_genre": {
"amber_oriental": 523,
"citrus_cologne": 548,
"floral_woody": 483,
"fougere": 489,
"wildcard": 974
},
"genre_profiles": {
"amber_oriental": [
"B",
"C",
"F",
"G",
"H",
"L",
"P",
"Q",
"R",
"S",
"W",
"X"
],
"citrus_cologne": [
"A",
"B",
"C",
"D",
"E",
"F",
"G",
"H",
"P",
"Q",
"R",
"S",
"V",
"W",
"X"
],
"floral_woody": [
"A",
"B",
"C",
"F",
"G",
"H",
"P",
"Q",
"R",
"S",
"V",
"W",
"X"
],
"fougere": [
"A",
"B",
"C",
"F",
"G",
"H",
"L",
"M",
"P",
"Q",
"R",
"S",
"W",
"X"
],
"wildcard": [
"B",
"C",
"F",
"G",
"H",
"I",
"J",
"K",
"L",
"M",
"Q",
"R",
"S",
"V",
"W",
"X"
]
},
"mean_pairwise_jaccard": 0.7177742763772176,
"method": "per-genre formula-level set Jaccard over 26-class character labels; class active if present in >=5% of labelled formulas for genre",
"pairwise": [
{
"intersection": [
"B",
"C",
"F",
"G",
"H",
"P",
"Q",
"R",
"S",
"W",
"X"
],
"jaccard": 0.6875,
"left": "amber_oriental",
"right": "citrus_cologne",
"union": [
"A",
"B",
"C",
"D",
"E",
"F",
"G",
"H",
"L",
"P",
"Q",
"R",
"S",
"V",
"W",
"X"
]
},
{
"intersection": [
"B",
"C",
"F",
"G",
"H",
"P",
"Q",
"R",
"S",
"W",
"X"
],
"jaccard": 0.7857142857142857,
"left": "amber_oriental",
"right": "floral_woody",
"union": [
"A",
"B",
"C",
"F",
"G",
"H",
"L",
"P",
"Q",
"R",
"S",
"V",
"W",
"X"
]
},
{
"intersection": [
"B",
"C",
"F",
"G",
"H",
"L",
"P",
"Q",
"R",
"S",
"W",
"X"
],
"jaccard": 0.8571428571428571,
"left": "amber_oriental",
"right": "fougere",
"union": [
"A",
"B",
"C",
"F",
"G",
"H",
"L",
"M",
"P",
"Q",
"R",
"S",
"W",
"X"
]
},
{
"intersection": [
"B",
"C",
"F",
"G",
"H",
"L",
"Q",
"R",
"S",
"W",
"X"
],
"jaccard": 0.6470588235294118,
"left": "amber_oriental",
"right": "wildcard",
"union": [
"B",
"C",
"F",
"G",
"H",
"I",
"J",
"K",
"L",
"M",
"P",
"Q",
"R",
"S",
"V",
"W",
"X"
]
},
{
"intersection": [
"A",
"B",
"C",
"F",
"G",
"H",
"P",
"Q",
"R",
"S",
"V",
"W",
"X"
],
"jaccard": 0.8666666666666667,
"left": "citrus_cologne",
"right": "floral_woody",
"union": [
"A",
"B",
"C",
"D",
"E",
"F",
"G",
"H",
"P",
"Q",
"R",
"S",
"V",
"W",
"X"
]
},
{
"intersection": [
"A",
"B",
"C",
"F",
"G",
"H",
"P",
"Q",
"R",
"S",
"W",
"X"
],
"jaccard": 0.7058823529411765,
"left": "citrus_cologne",
"right": "fougere",
"union": [
"A",
"B",
"C",
"D",
"E",
"F",
"G",
"H",
"L",
"M",
"P",
"Q",
"R",
"S",
"V",
"W",
"X"
]
},
{
"intersection": [
"B",
"C",
"F",
"G",
"H",
"Q",
"R",
"S",
"V",
"W",
"X"
],
"jaccard": 0.55,
"left": "citrus_cologne",
"right": "wildcard",
"union": [
"A",
"B",
"C",
"D",
"E",
"F",
"G",
"H",
"I",
"J",
"K",
"L",
"M",
"P",
"Q",
"R",
"S",
"V",
"W",
"X"
]
},
{
"intersection": [
"A",
"B",
"C",
"F",
"G",
"H",
"P",
"Q",
"R",
"S",
"W",
"X"
],
"jaccard": 0.8,
"left": "floral_woody",
"right": "fougere",
"union": [
"A",
"B",
"C",
"F",
"G",
"H",
"L",
"M",
"P",
"Q",
"R",
"S",
"V",
"W",
"X"
]
},
{
"intersection": [
"B",
"C",
"F",
"G",
"H",
"Q",
"R",
"S",
"V",
"W",
"X"
],
"jaccard": 0.6111111111111112,
"left": "floral_woody",
"right": "wildcard",
"union": [
"A",
"B",
"C",
"F",
"G",
"H",
"I",
"J",
"K",
"L",
"M",
"P",
"Q",
"R",
"S",
"V",
"W",
"X"
]
},
{
"intersection": [
"B",
"C",
"F",
"G",
"H",
"L",
"M",
"Q",
"R",
"S",
"W",
"X"
],
"jaccard": 0.6666666666666666,
"left": "fougere",
"right": "wildcard",
"union": [
"A",
"B",
"C",
"F",
"G",
"H",
"I",
"J",
"K",
"L",
"M",
"P",
"Q",
"R",
"S",
"V",
"W",
"X"
]
}
]
},
"effective_n": {
"both_axes_materials_excluding_z": 20,
"character_head_materials_excluding_z": 89,
"substantivity_head_materials": 170
},
"go_no_go_frame": {
"amber": "character axis too sparse, substantivity axis strong -> publish/ship substantivity forward result first and grow character coverage separately",
"green": "character coverage + per-class counts sufficient -> proceed to Phase 2.5 gate then Phase 3 training",
"red": "discrimination probe high -> do not train"
},
"label_provenance_counts_in_universe": {
"parsed-from-source": 57,
"taxonomy-reference": 37
},
"masked_unlabelled_materials_excluding_z": [
"100-51-6",
"100-52-7",
"100-86-7",
"10031-93-5",
"10031-96-6",
"101-41-7",
"101-48-4",
"101-81-5",
"101-84-8",
"101-94-0",
"101-97-3",
"102-13-6",
"102-16-9",
"102-20-5",
"103-26-4",
"103-36-6",
"103-41-3",
"103-45-7",
"103-48-0",
"103-53-7",
"103-54-8",
"103-56-0",
"103-61-7",
"103-82-2",
"103-95-7",
"104-21-2",
"104-53-0",
"104-54-1",
"104-55-2",
"104-57-4",
"104-62-1",
"104-65-4",
"104-67-6",
"10482-77-6",
"10486-14-3",
"105-13-5",
"105-53-3",
"105-85-1",
"105-86-2",
"105-87-3",
"105-95-3",
"106-21-8",
"106-24-1",
"106-25-2",
"106-26-3",
"106-29-6",
"106-30-9",
"110-17-8",
"110-19-0",
"110-41-8",
"110-44-1",
"111-12-6",
"111-79-5",
"112-14-1",
"112-17-4",
"112-30-1",
"112-44-7",
"112-53-8",
"1132639-46-3",
"115-95-7",
"115-99-1",
"117-98-6",
"118-58-1",
"118-61-6",
"119-36-8",
"120-50-3",
"120-51-4",
"120-72-9",
"121-32-4",
"121-33-5",
"121-34-6",
"121-98-2",
"122-00-9",
"122-03-2",
"122-40-7",
"122-44-1",
"122-57-6",
"122-63-4",
"122-67-8",
"122-70-3",
"122-74-7",
"122-78-1",
"122-97-4",
"123-08-0",
"123-11-5",
"123-72-8",
"124-19-6",
"126-64-7",
"127-41-3",
"127-42-4",
"127-51-5",
"1335-46-2",
"134-20-3",
"138-86-3",
"139-02-6",
"140-39-6",
"141-12-8",
"141-14-0",
"141-25-3",
"141-78-6",
"141-97-9",
"143-08-8",
"143-13-5",
"144-39-8",
"14901-07-6",
"150-78-7",
"150-84-5",
"1551-44-6",
"16409-43-1",
"17283-81-7",
"19870-74-7",
"2039-67-0",
"2049-96-9",
"2050-08-0",
"21145-77-7",
"2173-56-0",
"2216-51-5",
"2244-16-8",
"23696-85-7",
"24851-98-7",
"32388-55-9",
"328-50-7",
"33704-61-9",
"43052-87-5",
"4602-84-0",
"501-52-0",
"507-70-0",
"513-86-0",
"5137-52-0",
"515-03-7",
"515-69-5",
"5392-40-1",
"540-18-1",
"541-91-3",
"54452-50-3",
"5451-52-5",
"56-12-2",
"562-74-3",
"60-35-5",
"600-18-0",
"606-09-1",
"615-90-3",
"623-42-7",
"62395-45-3",
"624-15-7",
"624-54-4",
"6259-76-3",
"628-63-7",
"6382-14-5",
"64-19-7",
"6485-40-1",
"65-85-0",
"65405-77-8",
"66068-84-6",
"67-63-0",
"67-64-1",
"67-66-3",
"674-86-6",
"6790-58-5",
"6790-58-9",
"68039-33-4",
"68127-65-1",
"68606-83-7",
"68916-26-7",
"6938-46-1",
"706-14-9",
"7143-69-3",
"7149-26-0",
"7462-86-6",
"75-07-0",
"76-49-3",
"77-54-3",
"77-83-8",
"78-37-5",
"79-69-6",
"80-56-8",
"8000-25-7",
"8000-27-9",
"8000-28-0",
"8000-34-8",
"8000-42-8",
"8000-46-2",
"8002-73-1",
"8006-78-8",
"8006-81-3",
"8006-87-9",
"8007-00-9",
"8007-01-0",
"8007-06-5",
"8007-46-3",
"8007-75-8",
"8007-80-5",
"8008-31-9",
"8008-45-5",
"8008-56-8",
"8008-57-9",
"8013-76-1",
"8014-09-3",
"8014-17-3",
"8015-01-0",
"8015-61-0",
"8015-77-8",
"8016-26-0",
"8016-38-4",
"8016-63-5",
"8016-78-2",
"8016-96-4",
"8022-96-6",
"8023-75-2",
"8023-79-2",
"8023-91-4",
"8024-13-1",
"8024-43-9",
"8031-03-6",
"8032-35-1",
"8046-19-3",
"8047-24-3",
"8050-07-5",
"81-15-2",
"816-66-0",
"83-54-5",
"83-66-9",
"84012-66-8",
"85-91-6",
"85409-36-9",
"85940-31-4",
"87-19-4",
"87-22-9",
"87-25-2",
"89-43-0",
"89-86-1",
"89997-75-1",
"90-17-5",
"9000-50-4",
"9000-64-0",
"9000-64-2",
"9000-72-0",
"928-97-2",
"93-15-2",
"93-28-7",
"93-58-3",
"93-89-0",
"94-30-4",
"94-47-3",
"94-48-4",
"94-59-7",
"94-90-6",
"97-54-1",
"99-50-3",
"99-96-7",
"NATURAL:68916-26-7",
"NATURAL:8000-25-7",
"NATURAL:8000-28-0",
"NATURAL:8000-46-2",
"NATURAL:8000-66-6",
"NATURAL:8006-87-9",
"NATURAL:8007-01-0",
"NATURAL:8007-35-0",
"NATURAL:8008-52-4",
"NATURAL:8008-56-8",
"NATURAL:8008-57-9",
"NATURAL:8014-17-3",
"NATURAL:8016-23-7",
"NATURAL:8016-37-3",
"NATURAL:8016-96-4",
"NATURAL:8023-83-4",
"NATURAL:8029-66-5",
"NATURAL:9000-05-9",
"NATURAL:9000-78-6",
"SMILES:BrC=Cc1ccccc1",
"SMILES:C#CCO",
"SMILES:C(CCC(=O)O)CC(=O)O",
"SMILES:C(CN)C(=O)O",
"SMILES:C1=CC(=CC=C1CO)O",
"SMILES:C1CCSC1",
"SMILES:C1CNCCN1",
"SMILES:C=C(C)C(=O)OC",
"SMILES:C=C(C)C(=O)OCC",
"SMILES:C=C(C)C1CC=C(C)C(=O)C1",
"SMILES:C=C(C)C1CC=C(C)C(O)C1",
"SMILES:C=C(C)C1CC=C(C)C(OC(C)=O)C1",
"SMILES:C=C(C)CCCC(C)CCOC(=O)CC",
"SMILES:C=C(C)OC(C)=O",
"SMILES:C=C1C2CCC(C2)C1(C)C",
"SMILES:C=CC(C)(CCC=C(C)C)OC(=O)C(C)C",
"SMILES:C=CC(C)=O",
"SMILES:C=CC=O",
"SMILES:C=CCCC(C)=O",
"SMILES:C=CCCCCCC",
"SMILES:C=CCCCCCCCCC(=O)O",
"SMILES:C=CCCCCCCCCC(=O)OC",
"SMILES:C=CCCCCCCCCCO",
"SMILES:C=CCO",
"SMILES:C=CCOCCO",
"SMILES:C=CCc1ccc(OC(C)=O)c(OC)c1",
"SMILES:C=CCc1ccc(OC)c(OC)c1",
"SMILES:C=Cc1ccc(O)c(OC)c1",
"SMILES:CC(=O)C(=O)O",
"SMILES:CC(=O)C(C)=O",
"SMILES:CC(=O)C=O",
"SMILES:CC(=O)CC(=O)c1ccccc1",
"SMILES:CC(=O)CC(C)C",
"SMILES:CC(=O)OC(C)(C)C1CCC(C)CC1",
"SMILES:CC(=O)OC(C)(C)CCc1ccccc1",
"SMILES:CC(=O)OC(C)C",
"SMILES:CC(=O)OC(C)CC(C)C",
"SMILES:CC(=O)OC(c1ccccc1)C(Cl)(Cl)Cl",
"SMILES:CC(=O)OC1(C(C)C)C=CC(C)CC1",
"SMILES:CC(=O)OC1(C)CCC23CC1C(C)(C)[C@@H]2CC[C@H]3C",
"SMILES:CC(=O)OCC(C)C",
"SMILES:CC(=O)OCC(COC(C)=O)OC(C)=O",
"SMILES:CC(=O)OCC=Cc1ccccc1",
"SMILES:CC(=O)OCCOC(C)=O",
"SMILES:CC(=O)c1ccc(C)cc1C",
"SMILES:CC(=O)c1ccc(Cl)cc1",
"SMILES:CC(=O)c1ccc(O)cc1",
"SMILES:CC(=O)c1ccc2ccccc2c1",
"SMILES:CC(=O)c1cccs1",
"SMILES:CC(C)(C)C1CCC(=O)CC1",
"SMILES:CC(C)(C)C1CCC(O)CC1",
"SMILES:CC(C)(C)CC(C)(C)c1ccc(OCCO)cc1",
"SMILES:CC(C)(C)O",
"SMILES:CC(C)(C)c1ccc(O)c(O)c1",
"SMILES:CC(C)(C)c1ccc(O)cc1",
"SMILES:CC(C)(O)CCc1ccccc1",
"SMILES:CC(C)(O)Cc1ccccc1",
"SMILES:CC(C)(c1ccc(O)cc1)c1ccc(O)cc1",
"SMILES:CC(C)=C1CCC(C)C2=C(C1)C(C)CC2",
"SMILES:CC(C)=C1CCC(C)CC1=O",
"SMILES:CC(C)=CCCC(C)CC=O",
"SMILES:CC(C)=CCCC(C)CCOC=O",
"SMILES:CC(C)=CCCC(C)[C@H]1CC[C@@]2(C)C3=C(CC[C@]12C)[C@@]1(C)CC[C@H](O)C(C)(C)[C@@H]1CC3",
"SMILES:CC(C)=CCC[C@H](C)CCO",
"SMILES:CC(C)C(=O)O",
"SMILES:CC(C)C(=O)OCCCc1ccccc1",
"SMILES:CC(C)C(=O)OCCc1ccccc1",
"SMILES:CC(C)C(=O)OCc1ccccc1",
"SMILES:CC(C)C(N)C(=O)O",
"SMILES:CC(C)C=O",
"SMILES:CC(C)CC(=O)CC(C)C",
"SMILES:CC(C)CC(=O)OCc1ccccc1",
"SMILES:CC(C)CC(C)O",
"SMILES:CC(C)CC(N)C(=O)O",
"SMILES:CC(C)CC(O)CC(C)C",
"SMILES:CC(C)CCCC(C)CCO",
"SMILES:CC(C)CCC[C@@H](C)[C@H]1CC[C@H]2[C@@H]3CC=C4C[C@@H](O)CC[C@]4(C)[C@H]3CC[C@]12C",
"SMILES:CC(C)CCN",
"SMILES:CC(C)CCOC(=O)Cc1ccccc1",
"SMILES:CC(C)CCOC(=O)c1ccccc1",
"SMILES:CC(C)CCOC(=O)c1ccccc1O",
"SMILES:CC(C)CCOC=O",
"SMILES:CC(C)CN",
"SMILES:CC(C)CO",
"SMILES:CC(C)COC(=O)C(C)C",
"SMILES:CC(C)COC(=O)c1ccccc1O",
"SMILES:CC(C)C[C@H](N)C(=O)O",
"SMILES:CC(C)Cc1ccc2ccccc2n1",
"SMILES:CC(C)N",
"SMILES:CC(C)[C@H](N)C(=O)O",
"SMILES:CC(C)c1ccc(C=O)cc1",
"SMILES:CC(C)c1ccc(CO)cc1",
"SMILES:CC(C)c1ccc(O)cc1",
"SMILES:CC(C)c1cccc(C(C)C)c1O",
"SMILES:CC(C)c1ccccc1O",
"SMILES:CC(C=O)=Cc1ccccc1",
"SMILES:CC(C=O)c1ccccc1",
"SMILES:CC(CC=O)c1ccc(C(C)(C)C)cc1",
"SMILES:CC(CN)O",
"SMILES:CC(N)C(=O)O",
"SMILES:CC(O)C(=O)O",
"SMILES:CC(O)C(C)O",
"SMILES:CC(O)CC(C)(C)O",
"SMILES:CC(O)CCO",
"SMILES:CC(O)CNCC(C)O",
"SMILES:CC(O)COCC(C)O",
"SMILES:CC(O)c1ccccc1",
"SMILES:CC1=C(O)C(=O)CC1",
"SMILES:CC1=CC(=O)CC(C)(C)C1",
"SMILES:CC1=CC=C(C(C)C)CC1",
"SMILES:CC1=CCC2CC1C2(C)C",
"SMILES:CC1CCC(C(C)C)C(=O)C1",
"SMILES:CC1CCC(C(C)C)C(OC(=O)c2ccccc2O)C1",
"SMILES:CC1CCC(C(C)C)CC1",
"SMILES:CC1CCCC2(C)CCCCC12O",
"SMILES:CC1CCCCN1",
"SMILES:CC1CO1",
"SMILES:CC1COC(=O)O1",
"SMILES:CC1OC1C1CCC2(C)OC2C1",
"SMILES:CC=CC=CCO",
"SMILES:CC=Cc1ccc(OC(C)=O)c(OC)c1",
"SMILES:CC=Cc1ccc(OC)c(OC)c1",
"SMILES:CCC(=O)CC",
"SMILES:CCC(=O)O",
"SMILES:CCC(=O)OCC=Cc1ccccc1",
"SMILES:CCC(=O)OCCC(C)C",
"SMILES:CCC(C)(C)O",
"SMILES:CCC(C)(O)CC",
"SMILES:CCC(C)(O)CCCC(C)C",
"SMILES:CCC(C)=O",
"SMILES:CCC(C)C",
"SMILES:CCC(C)C(N)C(=O)O",
"SMILES:CCC(C)C=O",
"SMILES:CCC(C)CC(=O)O",
"SMILES:CCC(C)CN",
"SMILES:CCC(C)O",
"SMILES:CCC(C)OC(C)=O",
"SMILES:CCC(C=O)CC",
"SMILES:CCC(CC)C(=O)O",
"SMILES:CCC(CC)CO",
"SMILES:CCC(O)c1ccccc1",
"SMILES:CCC=O",
"SMILES:CCCC(=O)O",
"SMILES:CCCC(=O)OCC",
"SMILES:CCCC(=O)OCC(COC(=O)CCC)OC(=O)CCC",
"SMILES:CCCC(=O)OCC=Cc1ccccc1",
"SMILES:CCCC(=O)OCCC(C)C",
"SMILES:CCCC(=O)OCCc1ccccc1",
"SMILES:CCCC(=O)OCc1ccccc1",
"SMILES:CCCC(C)=O",
"SMILES:CCCC(O)C(CC)CO",
"SMILES:CCCC1CCC(=O)O1",
"SMILES:CCCCC(=O)CC",
"SMILES:CCCCC(=O)O",
"SMILES:CCCCC(CC)CO",
"SMILES:CCCCC(CC)COC(C)=O",
"SMILES:CCCCC1CCC(=O)O1",
"SMILES:CCCCCC#CC(=O)OC",
"SMILES:CCCCCC(=O)OC",
"SMILES:CCCCCC(=O)OCC(C)C",
"SMILES:CCCCCC(C)=O",
"SMILES:CCCCCC1CCC(=O)O1",
"SMILES:CCCCCCC#CC(=O)OC",
"SMILES:CCCCCCC(=O)O",
"SMILES:CCCCCCC(=O)OC",
"SMILES:CCCCCCC(=O)OCC",
"SMILES:CCCCCCC(C)=O",
"SMILES:CCCCCCC(C=O)=Cc1ccccc1",
"SMILES:CCCCCCC=CC(=O)OC",
"SMILES:CCCCCCCC(=O)O",
"SMILES:CCCCCCCC(=O)OC",
"SMILES:CCCCCCCC(=O)OCC",
"SMILES:CCCCCCCCC(=O)NCc1ccc(O)c(OC)c1",
"SMILES:CCCCCCCCC(=O)O",
"SMILES:CCCCCCCCCC(=O)O",
"SMILES:CCCCCCCCCC(=O)OC",
"SMILES:CCCCCCCCCC(=O)OCC",
"SMILES:CCCCCCCCCC(C)=O",
"SMILES:CCCCCCCCCCC(=O)O",
"SMILES:CCCCCCCCCCCC(=O)N(C)CC(=O)O",
"SMILES:CCCCCCCCCCCC(=O)O",
"SMILES:CCCCCCCCCCCC(=O)OC",
"SMILES:CCCCCCCCCCCC(=O)OCC",
"SMILES:CCCCCCCCCCCCCC(=O)OC(C)C",
"SMILES:CCCCCCCCCCCCCC(=O)OCCCC",
"SMILES:CCCCCCCCCCCCCCCC(=O)O",
"SMILES:CCCCCCCCCCCCCCCCCC(=O)O",
"SMILES:CCCCCCCCCCCCCCCCCC(=O)OCC",
"SMILES:CCCCCCCCCCCCCCCCCC(=O)OCCOCCO",
"SMILES:CCCCCCCCCCCCCCCCO",
"SMILES:CCCCCCCCCCO",
"SMILES:CCCCCCCCCCOC(C)=O",
"SMILES:CCCCCCCCO",
"SMILES:CCCCCCCCOC(C)=O",
"SMILES:CCCCCCCCOC=O",
"SMILES:CCCCCCCCS",
"SMILES:CCCCCCCOC(C)=O",
"SMILES:CCCCCCCOC=O",
"SMILES:CCCCCCN",
"SMILES:CCCCCCO",
"SMILES:CCCCCCS",
"SMILES:CCCCCN",
"SMILES:CCCCCO",
"SMILES:CCCCCS",
"SMILES:CCCCN",
"SMILES:CCCCO",
"SMILES:CCCCOC(=O)C(C)C",
"SMILES:CCCCOC(=O)CC(C)C",
"SMILES:CCCCOC(=O)CC(CC(=O)OCCCC)(OC(C)=O)C(=O)OCCCC",
"SMILES:CCCCOC(=O)CC(O)(CC(=O)OCCCC)C(=O)OCCCC",
"SMILES:CCCCOC(=O)CCC",
"SMILES:CCCCOC(=O)CCCCCCCCC(=O)OCCCC",
"SMILES:CCCCOC(=O)COC(=O)c1ccccc1C(=O)OCCCC",
"SMILES:CCCCOC(=O)c1ccc(O)cc1",
"SMILES:CCCCOC(=O)c1ccccc1C(=O)OCCCC",
"SMILES:CCCCS",
"SMILES:CCCN",
"SMILES:CCCN(CCC)CCC",
"SMILES:CCCO",
"SMILES:CCCOC(=O)CC",
"SMILES:CCCOC(=O)CCC",
"SMILES:CCCOC(=O)CCCCC(=O)OCCC",
"SMILES:CCCOC(=O)c1cc(O)c(O)c(O)c1",
"SMILES:CCCOC(=O)c1ccc(O)cc1",
"SMILES:CCCOC(C)=O",
"SMILES:CCCOC=O",
"SMILES:CCCS",
"SMILES:CCCSCCC",
"SMILES:CCCc1ccc(OC)cc1",
"SMILES:CCNCC",
"SMILES:CCOC(=O)C(C)C",
"SMILES:CCOC(=O)C(C)O",
"SMILES:CCOC(=O)C1OC1(C)c1ccccc1",
"SMILES:CCOC(=O)C=Cc1ccccc1",
"SMILES:CCOC(=O)CC",
"SMILES:CCOC(=O)CC(=O)OCC",
"SMILES:CCOC(=O)CC(=O)c1ccccc1",
"SMILES:CCOC(=O)CC(C)C",
"SMILES:CCOC(=O)CC(CC(=O)OCC)(OC(C)=O)C(=O)OCC",
"SMILES:CCOC(=O)CC(O)(CC(=O)OCC)C(=O)OCC",
"SMILES:CCOC(=O)CCCCCCCCC(=O)OCC",
"SMILES:CCOC(=O)c1ccccc1",
"SMILES:CCOC(=O)c1ccccc1N",
"SMILES:CCOC(C)OCC",
"SMILES:CCOC=O",
"SMILES:CCOCC",
"SMILES:CCOCCOCCO",
"SMILES:CCOc1ccc2ccccc2c1",
"SMILES:CCS",
"SMILES:CCSSCC",
"SMILES:CC[C@H](C)[C@H](N)C(=O)O",
"SMILES:CCc1ccc(C)nc1",
"SMILES:CCc1ccccn1",
"SMILES:CN(C)C",
"SMILES:CNCC(=O)O",
"SMILES:CNc1ccccc1C(=O)OC",
"SMILES:COC(=O)C=Cc1ccccc1",
"SMILES:COC(=O)CC(=O)OC",
"SMILES:COC(=O)CC(C)=O",
"SMILES:COC(=O)CCC(=O)OC",
"SMILES:COC(=O)CCc1ccccc1",
"SMILES:COC(=O)Cc1ccccc1",
"SMILES:COC(=O)c1ccc(C)cc1",
"SMILES:COC(=O)c1ccc(O)cc1",
"SMILES:COC(=O)c1ccccc1O",
"SMILES:COC(=O)c1cccnc1",
"SMILES:COC(C)=O",
"SMILES:COC=O",
"SMILES:COCOC",
"SMILES:COc1cc(C)ccc1O",
"SMILES:COc1ccc(C(=O)O)cc1",
"SMILES:COc1ccc(C(C)=O)cc1",
"SMILES:COc1ccc(C)cc1",
"SMILES:COc1ccc(CO)cc1",
"SMILES:COc1ccc(COC(=O)Cc2ccccc2)cc1",
"SMILES:COc1ccc(COC(C)=O)cc1",
"SMILES:COc1ccc2ccccc2c1",
"SMILES:COc1cccc(C)c1",
"SMILES:COc1cccc(OC)c1O",
"SMILES:COc1ccccc1",
"SMILES:COc1ccccc1-c1ccccc1",
"SMILES:COc1ccccc1OC",
"SMILES:CS(C)=O",
"SMILES:CSC",
"SMILES:CSCCC(=O)O",
"SMILES:CSCCC(N)C(=O)O",
"SMILES:CSc1ccccc1",
"SMILES:C[C@@H](O)[C@H](N)C(=O)O",
"SMILES:Cc1ccc(C(C)(C)C)c(O)c1",
"SMILES:Cc1ccc(C(C)C)c(O)c1",
"SMILES:Cc1ccc(C(C)C)cc1",
"SMILES:Cc1ccc(C)c(O)c1",
"SMILES:Cc1ccc(C=O)cc1",
"SMILES:Cc1ccc(O)c(C)c1",
"SMILES:Cc1ccc(O)cc1C",
"SMILES:Cc1ccc(OC(=O)C(C)C)cc1",
"SMILES:Cc1ccc2ccccc2c1",
"SMILES:Cc1ccc2ncccc2c1",
"SMILES:Cc1cccc(C)c1",
"SMILES:Cc1cccc(C)n1",
"SMILES:Cc1cccc(O)c1",
"SMILES:Cc1cccc2ccccc12",
"SMILES:Cc1ccccc1",
"SMILES:Cc1ccccc1C",
"SMILES:Cc1ccccc1O",
"SMILES:Cc1ccccn1",
"SMILES:Cc1ccnc(C)c1",
"SMILES:Cc1cncc(C)n1",
"SMILES:Cc1cnccn1",
"SMILES:Cn1cccc1",
"SMILES:NC(=O)CC[C@H](N)C(=O)O",
"SMILES:NC(=O)C[C@H](N)C(=O)O",
"SMILES:NC(CC(=O)O)C(=O)O",
"SMILES:NC(Cc1ccccc1)C(=O)O",
"SMILES:NCC(=O)O",
"SMILES:NCCCCC(N)C(=O)O",
"SMILES:NCCCCN",
"SMILES:NCCCC[C@H](N)C(=O)O",
"SMILES:NCCc1ccc(O)cc1",
"SMILES:NCCc1ccccc1",
"SMILES:N[C@@H](CC(=O)O)C(=O)O",
"SMILES:N[C@@H](CS)C(=O)O",
"SMILES:N[C@@H](Cc1ccc(O)c(O)c1)C(=O)O",
"SMILES:N[C@@H](Cc1ccc(O)cc1)C(=O)O",
"SMILES:N[C@@H](Cc1ccccc1)C(=O)O",
"SMILES:O=C(CCc1ccc(O)cc1)c1c(O)cc(O)cc1O",
"SMILES:O=C(CO)CO",
"SMILES:O=C(CO)[C@@H](O)[C@H](O)[C@H](O)CO",
"SMILES:O=C(Cc1ccccc1)Cc1ccccc1",
"SMILES:O=C(Cc1ccccc1)OCCc1ccccc1",
"SMILES:O=C(O)C(=O)CO",
"SMILES:O=C(O)C(=O)Cc1ccccc1",
"SMILES:O=C(O)C(=O)O",
"SMILES:O=C(O)C(O)C(O)C(=O)O",
"SMILES:O=C(O)C1CCCCC1",
"SMILES:O=C(O)C=C(CC(=O)O)C(=O)O",
"SMILES:O=C(O)C=CC(=O)O",
"SMILES:O=C(O)CC(O)(CC(=O)O)C(=O)O",
"SMILES:O=C(O)CC(O)C(=O)O",
"SMILES:O=C(O)CCC(=O)O",
"SMILES:O=C(O)CCCC(=O)O",
"SMILES:O=C(O)CO",
"SMILES:O=C(O)c1ccc(O)cc1O",
"SMILES:O=C(O)c1ccccc1O",
"SMILES:O=C(OC1CCCCC1)c1ccccc1C(=O)OC1CCCCC1",
"SMILES:O=C(OCCc1ccccc1)c1ccccc1",
"SMILES:O=C(OOC(=O)c1ccccc1)c1ccccc1",
"SMILES:O=C(Oc1ccccc1)c1ccccc1",
"SMILES:O=C1CCCCC1C1CCCCC1",
"SMILES:O=C1CCCCCCCCCCCCCCCO1",
"SMILES:O=C1CCCCCN1",
"SMILES:O=C1CCCO1",
"SMILES:O=C1OCc2ccccc21",
"SMILES:O=C1O[C@H](CO)[C@@H](O)[C@H](O)[C@H]1O",
"SMILES:O=CC=O",
"SMILES:O=CCCCC=O",
"SMILES:O=CCCc1ccccc1",
"SMILES:O=CCc1ccccc1",
"SMILES:O=COCC=Cc1ccccc1",
"SMILES:O=COCCc1ccccc1",
"SMILES:O=COCc1ccccc1",
"SMILES:O=Cc1ccccc1O",
"SMILES:O=Cc1cccs1",
"SMILES:OC(c1ccccc1)c1ccccc1",
"SMILES:OCC(O)CO",
"SMILES:OCC1CCCO1",
"SMILES:OCCNCCO",
"SMILES:OCCOCCO",
"SMILES:OC[C@@H](O)C(O)[C@@H](O)CO",
"SMILES:OC[C@@H](O)[C@@H](O)[C@H](O)[C@@H](O)CO",
"SMILES:OC[C@@H](O)[C@@H](O)[C@H](O)[C@H](O)CO",
"SMILES:O[C@@H]1[C@@H](O)[C@@H](O)OC[C@H]1O",
"SMILES:Oc1ccccc1",
"SMILES:SCCCS",
"SMILES:SCc1ccccc1",
"SMILES:c1ccc(-c2ccccc2)cc1",
"SMILES:c1ccc(CC2OCCO2)cc1",
"SMILES:c1ccc(COCc2ccccc2)cc1",
"SMILES:c1ccc(Cc2ccccc2)cc1",
"SMILES:c1ccc2ccccc2c1",
"SMILES:c1ccc2ncccc2c1",
"SMILES:c1ccncc1",
"SMILES:c1ccsc1"
],
"material_universe": {
"definition": "unique CAS from empirical_dataset_v8 formula components plus model-ready Poucher substantivity targets plus resolved taxonomy anchors; solvent/carrier class reported separately",
"formula_visible_unique_materials": 629,
"model_ready_poucher_substantivity_targets": 170,
"unique_materials": 746
},
"per_class_counts_ge10": {
"F": 10,
"G": 17,
"H": 12,
"W": 17
},
"per_class_counts_ge5": {
"A": 6,
"B": 8,
"C": 5,
"F": 10,
"G": 17,
"H": 12,
"Q": 7,
"R": 7,
"S": 5,
"W": 17,
"X": 7
},
"per_class_sparsity_lt5_examples": {
"D": 2,
"E": 2,
"I": 3,
"J": 2,
"K": 2,
"L": 3,
"M": 3,
"N": 0,
"O": 0,
"P": 4,
"T": 0,
"U": 3,
"V": 3,
"Y": 1
},
"pimt_version": "v8",
"source_coverage_artifact": "artifacts/odour_character_source_coverage_v8_1.json",
"stop": "STOP_AFTER_CENSUS_NO_DATASET_ASSEMBLY_NO_TRAINING_NO_HF_UPLOAD"
}