Spaces:
Running
Running
| { | |
| "3": { | |
| "industry": "Games/recreation", | |
| "decision": "keep" | |
| }, | |
| "6": { | |
| "industry": "Other", | |
| "tags": "OCR", | |
| "decision": "keep" | |
| }, | |
| "11": { | |
| "industry": "Healthcare", | |
| "decision": "keep" | |
| }, | |
| "12": { | |
| "industry": "Other", | |
| "tags": "OCR", | |
| "decision": "keep" | |
| }, | |
| "14": { | |
| "tags": "OCR", | |
| "industry": "Other", | |
| "decision": "keep" | |
| }, | |
| "15": { | |
| "decision": "keep" | |
| }, | |
| "16": { | |
| "industry": "Other", | |
| "decision": "keep", | |
| "tags": "OCR" | |
| }, | |
| "18": { | |
| "industry": "Other", | |
| "decision": "keep", | |
| "tags": "OCR" | |
| }, | |
| "20": { | |
| "decision": "keep", | |
| "industry": "Other", | |
| "tags": "OCR" | |
| }, | |
| "22": { | |
| "industry": "Other", | |
| "decision": "keep", | |
| "tags": "OCR" | |
| }, | |
| "23": { | |
| "industry": "Other", | |
| "decision": "keep", | |
| "tags": "demographics" | |
| }, | |
| "28": { | |
| "industry": "Other", | |
| "decision": "keep", | |
| "tags": "OCR" | |
| }, | |
| "30": { | |
| "industry": "Other", | |
| "tags": "OCR", | |
| "decision": "keep" | |
| }, | |
| "31": { | |
| "decision": "keep" | |
| }, | |
| "32": { | |
| "decision": "", | |
| "industry": "Image/audio", | |
| "tags": "needs-review", | |
| "notes": "gpt: Data collected from multiple writers; requires group-aware splits.", | |
| "needs_strat": true, | |
| "strat_col": "writer" | |
| }, | |
| "36": { | |
| "industry": "Image/audio", | |
| "decision": "keep" | |
| }, | |
| "37": { | |
| "decision": "keep" | |
| }, | |
| "46": { | |
| "industry": "Biology/genomics", | |
| "decision": "keep" | |
| }, | |
| "50": { | |
| "industry": "Games/recreation", | |
| "decision": "keep" | |
| }, | |
| "60": { | |
| "industry": "Other", | |
| "decision": "keep", | |
| "tags": "synthetic" | |
| }, | |
| "137": { | |
| "industry": "Games/recreation", | |
| "decision": "keep" | |
| }, | |
| "151": { | |
| "decision": "drop", | |
| "industry": "Energy/utilities", | |
| "tags": "non-IID,time-aware", | |
| "notes": "electricity \u2014 time-aware", | |
| "needs_strat": true, | |
| "strat_col": "date" | |
| }, | |
| "179": { | |
| "industry": "Other", | |
| "tags": "demographics", | |
| "decision": "keep" | |
| }, | |
| "181": { | |
| "industry": "Biology/genomics", | |
| "decision": "keep" | |
| }, | |
| "182": { | |
| "industry": "Other", | |
| "tags": "satellite", | |
| "decision": "keep" | |
| }, | |
| "184": { | |
| "decision": "keep" | |
| }, | |
| "185": { | |
| "decision": "keep", | |
| "industry": "Sport", | |
| "tags": "needs-review", | |
| "notes": "gpt: Players may have multiple entries affecting the split.", | |
| "needs_strat": false, | |
| "strat_col": "Player" | |
| }, | |
| "301": { | |
| "decision": "keep", | |
| "industry": "Other", | |
| "tags": "climate", | |
| "notes": "Idnetify potential confounding vars", | |
| "needs_strat": true, | |
| "strat_col": "suspiciously low" | |
| }, | |
| "333": { | |
| "industry": "Other", | |
| "decision": "keep", | |
| "tags": "synthetic" | |
| }, | |
| "334": { | |
| "industry": "Other", | |
| "decision": "keep", | |
| "tags": "synthetic" | |
| }, | |
| "335": { | |
| "industry": "Other", | |
| "decision": "keep", | |
| "tags": "synthetic" | |
| }, | |
| "375": { | |
| "decision": "drop", | |
| "industry": "Image/audio", | |
| "tags": "non-IID,speech", | |
| "notes": "JapaneseVowels \u2014 needs per-speaker split", | |
| "needs_strat": true, | |
| "strat_col": "speaker" | |
| }, | |
| "930": { | |
| "industry": "Text/NLP", | |
| "decision": "keep" | |
| }, | |
| "1037": { | |
| "industry": "Other", | |
| "decision": "keep", | |
| "tags": "demographics" | |
| }, | |
| "1038": { | |
| "decision": "keep", | |
| "industry": "Other" | |
| }, | |
| "1043": { | |
| "industry": "Other", | |
| "tags": "demographics", | |
| "decision": "keep" | |
| }, | |
| "1044": { | |
| "decision": "drop", | |
| "industry": "Biology/ecology", | |
| "tags": "needs-review", | |
| "notes": "rule: eye-tracking sequences \u2014 likely per-subject | gpt: No indication of group entities in the dataset.", | |
| "needs_strat": false, | |
| "strat_col": "" | |
| }, | |
| "1049": { | |
| "industry": "Manufacturing/quality", | |
| "decision": "keep" | |
| }, | |
| "1050": { | |
| "industry": "Manufacturing/quality", | |
| "decision": "keep" | |
| }, | |
| "1063": { | |
| "industry": "Manufacturing/quality", | |
| "decision": "keep" | |
| }, | |
| "1067": { | |
| "industry": "Manufacturing/quality", | |
| "decision": "keep" | |
| }, | |
| "1120": { | |
| "decision": "keep", | |
| "industry": "Physical sciences", | |
| "tags": "synthetic", | |
| "notes": "rule: may have per-event grouping | gpt: No group entities present in the dataset.", | |
| "needs_strat": false, | |
| "strat_col": "" | |
| }, | |
| "1444": { | |
| "decision": "keep" | |
| }, | |
| "1453": { | |
| "decision": "keep" | |
| }, | |
| "1459": { | |
| "industry": "Other", | |
| "tags": "OCR", | |
| "decision": "keep" | |
| }, | |
| "1471": { | |
| "decision": "keep", | |
| "industry": "", | |
| "tags": "not-sure,", | |
| "notes": "rule: EEG recording sessions | gpt: Data is from a continuous EEG measurement, likely from the same subjects.", | |
| "needs_strat": true, | |
| "strat_col": "time" | |
| }, | |
| "1475": { | |
| "decision": "keep", | |
| "industry": "Other", | |
| "tags": "mathematics" | |
| }, | |
| "1476": { | |
| "industry": "Energy/utilities", | |
| "decision": "keep" | |
| }, | |
| "1479": { | |
| "decision": "keep", | |
| "industry": "Other", | |
| "tags": "synthetic" | |
| }, | |
| "1481": { | |
| "industry": "Games/recreation", | |
| "decision": "keep" | |
| }, | |
| "1487": { | |
| "decision": "keep", | |
| "industry": "", | |
| "tags": "needs-review", | |
| "notes": "gpt: Data collected over time; potential for temporal correlation.", | |
| "needs_strat": false, | |
| "strat_col": "" | |
| }, | |
| "1489": { | |
| "decision": "keep", | |
| "industry": "Image/audio", | |
| "tags": "", | |
| "notes": "rule: description mentions: 'speaker independent' | gpt: Phoneme data likely comes from the same speakers, creating groups.", | |
| "needs_strat": false, | |
| "strat_col": "Class" | |
| }, | |
| "1491": { | |
| "industry": "Biology/ecology", | |
| "decision": "keep" | |
| }, | |
| "1492": { | |
| "industry": "Biology/ecology", | |
| "decision": "keep" | |
| }, | |
| "1493": { | |
| "industry": "Biology/ecology", | |
| "decision": "keep" | |
| }, | |
| "1494": { | |
| "industry": "Physics/chemistry/energy", | |
| "decision": "keep" | |
| }, | |
| "1496": { | |
| "industry": "Other", | |
| "tags": "synthetic", | |
| "decision": "keep" | |
| }, | |
| "1497": { | |
| "decision": "keep", | |
| "industry": "Tech/Web", | |
| "tags": "needs-review", | |
| "notes": "gpt: Data collected from a robot navigating, likely has temporal dependencies.", | |
| "needs_strat": false, | |
| "strat_col": "" | |
| }, | |
| "1501": { | |
| "decision": "keep", | |
| "industry": "Other", | |
| "tags": "OCR", | |
| "notes": "gpt: Data from multiple individuals; likely to have group dependencies.", | |
| "needs_strat": false, | |
| "strat_col": "" | |
| }, | |
| "1507": { | |
| "industry": "Other", | |
| "tags": "synthetic", | |
| "decision": "keep" | |
| }, | |
| "1509": { | |
| "decision": "keep", | |
| "industry": "Other", | |
| "tags": "har", | |
| "notes": "gpt: Multiple rows from the same participants may lead to information leakage.", | |
| "needs_strat": true, | |
| "strat_col": "Class" | |
| }, | |
| "1510": { | |
| "decision": "keep" | |
| }, | |
| "1548": { | |
| "tags": "synthetic", | |
| "industry": "Other", | |
| "decision": "keep" | |
| }, | |
| "1552": { | |
| "decision": "keep", | |
| "industry": "Other", | |
| "tags": "synthetic" | |
| }, | |
| "4538": { | |
| "decision": "keep", | |
| "industry": "Other", | |
| "tags": "human-action-recognition", | |
| "notes": "GesturePhase Processed \u2014 NOT time-aware", | |
| "needs_strat": true, | |
| "strat_col": "" | |
| }, | |
| "6332": { | |
| "decision": "keep", | |
| "industry": "Manufacturing/quality", | |
| "tags": "needs-review", | |
| "notes": "gpt: Multiple rows may come from the same customer.", | |
| "needs_strat": true, | |
| "strat_col": "timestamp" | |
| }, | |
| "40478": { | |
| "decision": "keep" | |
| }, | |
| "40497": { | |
| "decision": "keep" | |
| }, | |
| "40498": { | |
| "industry": "Retail", | |
| "decision": "drop", | |
| "notes": "duplicate" | |
| }, | |
| "40499": { | |
| "industry": "Image/audio", | |
| "decision": "keep" | |
| }, | |
| "40646": { | |
| "industry": "Biology/genomics", | |
| "decision": "keep" | |
| }, | |
| "40649": { | |
| "industry": "Biology/genomics", | |
| "decision": "keep" | |
| }, | |
| "40668": { | |
| "industry": "Games/recreation", | |
| "decision": "keep" | |
| }, | |
| "40670": { | |
| "industry": "Biology/genomics", | |
| "decision": "keep" | |
| }, | |
| "40677": { | |
| "decision": "keep", | |
| "tags": "OCR" | |
| }, | |
| "40678": { | |
| "decision": "keep", | |
| "tags": "OCR" | |
| }, | |
| "40707": { | |
| "decision": "keep", | |
| "industry": "", | |
| "tags": "needs-review", | |
| "notes": "gpt: Potentially multiple rows per patient based on medical features.", | |
| "needs_strat": true, | |
| "strat_col": "referral-ID?" | |
| }, | |
| "40708": { | |
| "decision": "keep", | |
| "industry": "", | |
| "tags": "needs-review", | |
| "notes": "gpt: Similar to allbp, likely multiple rows per patient.", | |
| "needs_strat": false, | |
| "strat_col": "age" | |
| }, | |
| "40713": { | |
| "decision": "drop", | |
| "industry": "", | |
| "tags": "needs-review", | |
| "notes": "Duplicate of allrep", | |
| "needs_strat": true, | |
| "strat_col": "age" | |
| }, | |
| "40900": { | |
| "decision": "keep", | |
| "industry": "Other", | |
| "tags": "satellite" | |
| }, | |
| "40966": { | |
| "decision": "keep", | |
| "industry": "Biology/genomics", | |
| "tags": "needs-review", | |
| "notes": "gpt: Multiple rows per mouse in the dataset.", | |
| "needs_strat": true, | |
| "strat_col": "MouseID" | |
| }, | |
| "40975": { | |
| "decision": "keep" | |
| }, | |
| "40982": { | |
| "industry": "Manufacturing/quality", | |
| "decision": "keep" | |
| }, | |
| "40983": { | |
| "industry": "Other", | |
| "tags": "satellite", | |
| "decision": "keep" | |
| }, | |
| "40984": { | |
| "decision": "drop", | |
| "notes": "duplicate" | |
| }, | |
| "40994": { | |
| "industry": "Physical sciences", | |
| "tags": "climate" | |
| }, | |
| "41027": { | |
| "decision": "keep" | |
| }, | |
| "41143": { | |
| "decision": "keep", | |
| "industry": "Other", | |
| "tags": "OCR" | |
| }, | |
| "41144": { | |
| "industry": "Other", | |
| "decision": "keep" | |
| }, | |
| "41145": { | |
| "industry": "Biology/genomics", | |
| "decision": "keep" | |
| }, | |
| "41146": { | |
| "industry": "Other", | |
| "decision": "keep" | |
| }, | |
| "41156": { | |
| "industry": "Other", | |
| "decision": "keep", | |
| "tags": "demographics" | |
| }, | |
| "41169": { | |
| "decision": "keep", | |
| "industry": "Other" | |
| }, | |
| "41671": { | |
| "tags": "synthetic", | |
| "decision": "keep" | |
| }, | |
| "41705": { | |
| "industry": "Other", | |
| "decision": "keep", | |
| "tags": "synthetic" | |
| }, | |
| "41718": { | |
| "decision": "drop", | |
| "industry": "", | |
| "tags": "needs-review", | |
| "notes": "gpt: Time-series data; rows are dependent on time.", | |
| "needs_strat": true, | |
| "strat_col": "Timestamp" | |
| }, | |
| "41763": { | |
| "decision": "drop", | |
| "industry": "", | |
| "tags": "needs-review", | |
| "notes": "gpt: Time-series data; rows are dependent on time.", | |
| "needs_strat": true, | |
| "strat_col": "Timestamp" | |
| }, | |
| "41833": { | |
| "decision": "drop", | |
| "industry": "Finance/insurance", | |
| "tags": "non-IID,time-aware", | |
| "notes": "FOREX cadjpy hour \u2014 time-aware", | |
| "needs_strat": true, | |
| "strat_col": "Timestamp" | |
| }, | |
| "41839": { | |
| "decision": "drop", | |
| "industry": "Finance/insurance", | |
| "tags": "non-IID,time-aware", | |
| "notes": "FOREX cadjpy day \u2014 time-aware", | |
| "needs_strat": true, | |
| "strat_col": "Timestamp" | |
| }, | |
| "41843": { | |
| "decision": "drop", | |
| "industry": "", | |
| "tags": "needs-review", | |
| "notes": "gpt: Time-series data; rows are dependent on time.", | |
| "needs_strat": true, | |
| "strat_col": "Timestamp" | |
| }, | |
| "41972": { | |
| "industry": "Image/audio", | |
| "decision": "keep", | |
| "tags": "satellite" | |
| }, | |
| "42464": { | |
| "industry": "Agriculture", | |
| "decision": "keep" | |
| }, | |
| "43582": { | |
| "decision": "keep", | |
| "industry": "", | |
| "tags": "needs-review", | |
| "notes": "gpt: Medical dataset; likely multiple rows per patient.", | |
| "needs_strat": false, | |
| "strat_col": "" | |
| }, | |
| "43892": { | |
| "industry": "Other", | |
| "tags": "demographics", | |
| "decision": "keep" | |
| }, | |
| "44122": { | |
| "decision": "keep" | |
| }, | |
| "44123": { | |
| "decision": "keep", | |
| "tags": "real estate" | |
| }, | |
| "44124": { | |
| "decision": "keep", | |
| "industry": "Other", | |
| "tags": "demographics" | |
| }, | |
| "44130": { | |
| "decision": "keep", | |
| "industry": "Biology/genomics", | |
| "tags": "needs-review", | |
| "notes": "rule: eye-tracking sequences \u2014 likely per-subject | gpt: Multiple rows likely correspond to the same assignment or subject.", | |
| "needs_strat": false, | |
| "strat_col": "assgNo" | |
| }, | |
| "44160": { | |
| "decision": "keep", | |
| "industry": "Retail" | |
| }, | |
| "44162": { | |
| "industry": "Government/public", | |
| "decision": "keep" | |
| }, | |
| "44186": { | |
| "decision": "keep" | |
| }, | |
| "44489": { | |
| "industry": "Other", | |
| "decision": "keep", | |
| "tags": "Satellite" | |
| }, | |
| "44971": { | |
| "decision": "keep", | |
| "industry": "Industry & Science" | |
| }, | |
| "45040": { | |
| "decision": "keep", | |
| "industry": "", | |
| "tags": "synthetic", | |
| "notes": "gpt: Multiple rows likely correspond to the same patient or subject.", | |
| "needs_strat": false, | |
| "strat_col": "Diagnosis" | |
| }, | |
| "45052": { | |
| "industry": "Healthcare", | |
| "decision": "keep" | |
| }, | |
| "45067": { | |
| "decision": "keep", | |
| "industry": "Other", | |
| "tags": "demographics", | |
| "notes": "gpt: Users may have multiple entries, indicating potential group entities.", | |
| "needs_strat": false, | |
| "strat_col": "location" | |
| }, | |
| "45068": { | |
| "decision": "drop" | |
| }, | |
| "45075": { | |
| "decision": "keep" | |
| }, | |
| "45536": { | |
| "decision": "keep", | |
| "industry": "Other", | |
| "tags": "alimentation" | |
| }, | |
| "45537": { | |
| "industry": "Other", | |
| "decision": "keep", | |
| "tags": "alimentation" | |
| }, | |
| "45538": { | |
| "industry": "Other", | |
| "tags": "alimentation", | |
| "decision": "keep" | |
| }, | |
| "45540": { | |
| "industry": "Other", | |
| "tags": "alimentation", | |
| "decision": "keep" | |
| }, | |
| "45558": { | |
| "industry": "Other", | |
| "decision": "keep", | |
| "tags": "astronomy" | |
| }, | |
| "45578": { | |
| "industry": "Other", | |
| "tags": "real estate", | |
| "decision": "keep" | |
| }, | |
| "46441": { | |
| "decision": "keep", | |
| "industry": "Finance/insurance", | |
| "tags": "", | |
| "notes": "Credit_Score \u2014 NOT time-aware (false positive)", | |
| "needs_strat": true, | |
| "strat_col": "customer_id" | |
| }, | |
| "46597": { | |
| "decision": "keep" | |
| }, | |
| "46906": { | |
| "decision": "keep", | |
| "industry": "Physical sciences" | |
| }, | |
| "46908": { | |
| "decision": "keep", | |
| "industry": "Transport" | |
| }, | |
| "46912": { | |
| "industry": "Biology/genomics", | |
| "decision": "keep" | |
| }, | |
| "46922": { | |
| "decision": "keep", | |
| "industry": "Healthcare", | |
| "tags": "needs-review", | |
| "notes": "rule: patients have multiple visits | gpt: No indication of group entities in the dataset.", | |
| "needs_strat": false, | |
| "strat_col": "" | |
| }, | |
| "46930": { | |
| "decision": "keep", | |
| "industry": "", | |
| "tags": "alimentation", | |
| "notes": "manually added; catboost miss is model-side" | |
| }, | |
| "46933": { | |
| "industry": "Healthcare", | |
| "decision": "keep" | |
| }, | |
| "46937": { | |
| "decision": "keep" | |
| }, | |
| "46939": { | |
| "decision": "keep" | |
| }, | |
| "46941": { | |
| "decision": "keep" | |
| }, | |
| "46955": { | |
| "tags": "astronomy", | |
| "decision": "keep" | |
| }, | |
| "46956": { | |
| "industry": "Physical sciences", | |
| "decision": "keep" | |
| }, | |
| "46958": { | |
| "industry": "Biology/genomics", | |
| "decision": "keep" | |
| }, | |
| "46960": { | |
| "decision": "keep", | |
| "industry": "Education", | |
| "tags": "TabArena", | |
| "notes": "students_dropout \u2014 Education, not Government", | |
| "needs_strat": true, | |
| "strat_col": "" | |
| }, | |
| "46969": { | |
| "industry": "Web/security", | |
| "needs_strat": false, | |
| "decision": "keep" | |
| }, | |
| "46979": { | |
| "industry": "Manufacturing/quality", | |
| "decision": "keep" | |
| }, | |
| "46980": { | |
| "decision": "keep" | |
| }, | |
| "44091": { | |
| "decision": "drop", | |
| "notes": "duplicate" | |
| }, | |
| "40691": { | |
| "decision": "drop", | |
| "notes": "duplicate" | |
| }, | |
| "44972": { | |
| "decision": "keep", | |
| "industry": "Industry & Science" | |
| }, | |
| "46905": { | |
| "decision": "keep", | |
| "notes": "manually added to mix; tabdpt+tabicl_v2 miss are model-side" | |
| }, | |
| "45539": { | |
| "decision": "keep", | |
| "notes": "manually added; catboost miss is model-side" | |
| }, | |
| "458": { | |
| "decision": "keep", | |
| "notes": "manually added; xgboost miss is model-side" | |
| }, | |
| "46356": { | |
| "decision": "keep", | |
| "notes": "manually added; lightgbm miss is model-side" | |
| }, | |
| "54": { | |
| "decision": "keep", | |
| "notes": "manually added; xgboost miss is model-side" | |
| } | |
| } |