chore: capture semantic pipeline baseline
This commit is contained in:
@@ -0,0 +1,322 @@
|
||||
{
|
||||
"artifact": "NCM_RETRIEVAL_EVALUATION_V2",
|
||||
"eval_total": 200,
|
||||
"quality_counts": {
|
||||
"GOLD": 65,
|
||||
"SILVER": 118,
|
||||
"NOISY": 17
|
||||
},
|
||||
"lexicon_size": 644,
|
||||
"lexicon_sample": {
|
||||
"100M": "100MT",
|
||||
"10A": "10AM",
|
||||
"10M": "10MT",
|
||||
"20A": "20AM",
|
||||
"20M": "20MT",
|
||||
"220V": "220VX4600W",
|
||||
"30M": "30MT",
|
||||
"32M": "32MM",
|
||||
"32X25": "32X25MM",
|
||||
"40M": "40MM",
|
||||
"4E0V": "4E0V4",
|
||||
"4PC": "4PCA",
|
||||
"50M": "50MT",
|
||||
"5X100": "5X100MM",
|
||||
"60M": "60MT",
|
||||
"ACES": "ACESSORIO",
|
||||
"ACHOC": "ACHOCOLATADO",
|
||||
"ACO": "ACOPLADO",
|
||||
"ACOPL": "ACOPLADA",
|
||||
"ACQUA": "ACQUAMARINE",
|
||||
"ACR": "ACRILICA",
|
||||
"ACRIL": "ACRILICA",
|
||||
"ADM": "ADMISSAO",
|
||||
"ADVAN": "ADVANC",
|
||||
"AERO": "AEROSOL",
|
||||
"AFRIC": "AFRICANO",
|
||||
"ALAV": "ALAVANCA",
|
||||
"ALAVA": "ALAVANCA",
|
||||
"ALC": "ALCOOL",
|
||||
"ALE": "ALEJANDRA",
|
||||
"ALF": "ALFAIATARIA",
|
||||
"ALFA": "ALFAIATARIA",
|
||||
"ALI": "ALINE",
|
||||
"ALIC": "ALICATE",
|
||||
"ALL": "ALLELA",
|
||||
"ALMOF": "ALMOFADADO",
|
||||
"ALUM": "ALUMASA",
|
||||
"ALUMI": "ALUMINIO",
|
||||
"AMEND": "AMENDOA",
|
||||
"AMOR": "AMORI"
|
||||
},
|
||||
"overall": {
|
||||
"OFFICIAL_ONLY": {
|
||||
"total": 200,
|
||||
"recall_at_1": 0.015,
|
||||
"recall_at_5": 0.08,
|
||||
"recall_at_10": 0.11,
|
||||
"recall_at_20": 0.14,
|
||||
"recall_at_50": 0.195,
|
||||
"mrr": 0.0456
|
||||
},
|
||||
"KB_ONLY": {
|
||||
"total": 200,
|
||||
"recall_at_1": 0.665,
|
||||
"recall_at_5": 0.85,
|
||||
"recall_at_10": 0.895,
|
||||
"recall_at_20": 0.925,
|
||||
"recall_at_50": 0.935,
|
||||
"mrr": 0.7499
|
||||
},
|
||||
"HYBRID": {
|
||||
"total": 200,
|
||||
"recall_at_1": 0.635,
|
||||
"recall_at_5": 0.855,
|
||||
"recall_at_10": 0.9,
|
||||
"recall_at_20": 0.92,
|
||||
"recall_at_50": 0.935,
|
||||
"mrr": 0.7325
|
||||
}
|
||||
},
|
||||
"by_quality": {
|
||||
"GOLD": {
|
||||
"OFFICIAL_ONLY": {
|
||||
"total": 65,
|
||||
"recall_at_1": 0.0308,
|
||||
"recall_at_5": 0.1077,
|
||||
"recall_at_10": 0.1231,
|
||||
"recall_at_20": 0.1538,
|
||||
"recall_at_50": 0.1692,
|
||||
"mrr": 0.0681
|
||||
},
|
||||
"KB_ONLY": {
|
||||
"total": 65,
|
||||
"recall_at_1": 0.7692,
|
||||
"recall_at_5": 0.9077,
|
||||
"recall_at_10": 0.9385,
|
||||
"recall_at_20": 0.9538,
|
||||
"recall_at_50": 0.9538,
|
||||
"mrr": 0.8276
|
||||
},
|
||||
"HYBRID": {
|
||||
"total": 65,
|
||||
"recall_at_1": 0.7846,
|
||||
"recall_at_5": 0.9231,
|
||||
"recall_at_10": 0.9538,
|
||||
"recall_at_20": 0.9538,
|
||||
"recall_at_50": 0.9538,
|
||||
"mrr": 0.8392
|
||||
}
|
||||
},
|
||||
"SILVER": {
|
||||
"OFFICIAL_ONLY": {
|
||||
"total": 118,
|
||||
"recall_at_1": 0.0085,
|
||||
"recall_at_5": 0.0763,
|
||||
"recall_at_10": 0.1186,
|
||||
"recall_at_20": 0.1525,
|
||||
"recall_at_50": 0.2373,
|
||||
"mrr": 0.0398
|
||||
},
|
||||
"KB_ONLY": {
|
||||
"total": 118,
|
||||
"recall_at_1": 0.661,
|
||||
"recall_at_5": 0.8814,
|
||||
"recall_at_10": 0.9237,
|
||||
"recall_at_20": 0.9661,
|
||||
"recall_at_50": 0.9831,
|
||||
"mrr": 0.7656
|
||||
},
|
||||
"HYBRID": {
|
||||
"total": 118,
|
||||
"recall_at_1": 0.6271,
|
||||
"recall_at_5": 0.8898,
|
||||
"recall_at_10": 0.9322,
|
||||
"recall_at_20": 0.9576,
|
||||
"recall_at_50": 0.9831,
|
||||
"mrr": 0.7471
|
||||
}
|
||||
},
|
||||
"NOISY": {
|
||||
"OFFICIAL_ONLY": {
|
||||
"total": 17,
|
||||
"recall_at_1": 0.0,
|
||||
"recall_at_5": 0.0,
|
||||
"recall_at_10": 0.0,
|
||||
"recall_at_20": 0.0,
|
||||
"recall_at_50": 0.0,
|
||||
"mrr": 0.0
|
||||
},
|
||||
"KB_ONLY": {
|
||||
"total": 17,
|
||||
"recall_at_1": 0.2941,
|
||||
"recall_at_5": 0.4118,
|
||||
"recall_at_10": 0.5294,
|
||||
"recall_at_20": 0.5294,
|
||||
"recall_at_50": 0.5294,
|
||||
"mrr": 0.3442
|
||||
},
|
||||
"HYBRID": {
|
||||
"total": 17,
|
||||
"recall_at_1": 0.1176,
|
||||
"recall_at_5": 0.3529,
|
||||
"recall_at_10": 0.4706,
|
||||
"recall_at_20": 0.5294,
|
||||
"recall_at_50": 0.5294,
|
||||
"mrr": 0.2235
|
||||
}
|
||||
}
|
||||
},
|
||||
"by_segment": {
|
||||
"base_testes": {
|
||||
"OFFICIAL_ONLY": {
|
||||
"total": 40,
|
||||
"recall_at_1": 0.0,
|
||||
"recall_at_5": 0.05,
|
||||
"recall_at_10": 0.075,
|
||||
"recall_at_20": 0.075,
|
||||
"recall_at_50": 0.1,
|
||||
"mrr": 0.0254
|
||||
},
|
||||
"KB_ONLY": {
|
||||
"total": 40,
|
||||
"recall_at_1": 0.5,
|
||||
"recall_at_5": 0.75,
|
||||
"recall_at_10": 0.825,
|
||||
"recall_at_20": 0.85,
|
||||
"recall_at_50": 0.85,
|
||||
"mrr": 0.6171
|
||||
},
|
||||
"HYBRID": {
|
||||
"total": 40,
|
||||
"recall_at_1": 0.375,
|
||||
"recall_at_5": 0.7,
|
||||
"recall_at_10": 0.775,
|
||||
"recall_at_20": 0.85,
|
||||
"recall_at_50": 0.85,
|
||||
"mrr": 0.5297
|
||||
}
|
||||
},
|
||||
"construcao": {
|
||||
"OFFICIAL_ONLY": {
|
||||
"total": 40,
|
||||
"recall_at_1": 0.025,
|
||||
"recall_at_5": 0.075,
|
||||
"recall_at_10": 0.1,
|
||||
"recall_at_20": 0.175,
|
||||
"recall_at_50": 0.2,
|
||||
"mrr": 0.0578
|
||||
},
|
||||
"KB_ONLY": {
|
||||
"total": 40,
|
||||
"recall_at_1": 0.875,
|
||||
"recall_at_5": 0.95,
|
||||
"recall_at_10": 0.95,
|
||||
"recall_at_20": 0.975,
|
||||
"recall_at_50": 0.975,
|
||||
"mrr": 0.9106
|
||||
},
|
||||
"HYBRID": {
|
||||
"total": 40,
|
||||
"recall_at_1": 0.85,
|
||||
"recall_at_5": 0.975,
|
||||
"recall_at_10": 0.975,
|
||||
"recall_at_20": 0.975,
|
||||
"recall_at_50": 0.975,
|
||||
"mrr": 0.9008
|
||||
}
|
||||
},
|
||||
"mercado": {
|
||||
"OFFICIAL_ONLY": {
|
||||
"total": 40,
|
||||
"recall_at_1": 0.025,
|
||||
"recall_at_5": 0.125,
|
||||
"recall_at_10": 0.15,
|
||||
"recall_at_20": 0.15,
|
||||
"recall_at_50": 0.175,
|
||||
"mrr": 0.0637
|
||||
},
|
||||
"KB_ONLY": {
|
||||
"total": 40,
|
||||
"recall_at_1": 0.825,
|
||||
"recall_at_5": 0.95,
|
||||
"recall_at_10": 0.975,
|
||||
"recall_at_20": 0.975,
|
||||
"recall_at_50": 0.975,
|
||||
"mrr": 0.8807
|
||||
},
|
||||
"HYBRID": {
|
||||
"total": 40,
|
||||
"recall_at_1": 0.85,
|
||||
"recall_at_5": 0.95,
|
||||
"recall_at_10": 0.975,
|
||||
"recall_at_20": 0.975,
|
||||
"recall_at_50": 0.975,
|
||||
"mrr": 0.8932
|
||||
}
|
||||
},
|
||||
"moda": {
|
||||
"OFFICIAL_ONLY": {
|
||||
"total": 40,
|
||||
"recall_at_1": 0.025,
|
||||
"recall_at_5": 0.15,
|
||||
"recall_at_10": 0.225,
|
||||
"recall_at_20": 0.25,
|
||||
"recall_at_50": 0.425,
|
||||
"mrr": 0.0773
|
||||
},
|
||||
"KB_ONLY": {
|
||||
"total": 40,
|
||||
"recall_at_1": 0.425,
|
||||
"recall_at_5": 0.725,
|
||||
"recall_at_10": 0.85,
|
||||
"recall_at_20": 0.95,
|
||||
"recall_at_50": 1.0,
|
||||
"mrr": 0.5758
|
||||
},
|
||||
"HYBRID": {
|
||||
"total": 40,
|
||||
"recall_at_1": 0.475,
|
||||
"recall_at_5": 0.775,
|
||||
"recall_at_10": 0.9,
|
||||
"recall_at_20": 0.925,
|
||||
"recall_at_50": 1.0,
|
||||
"mrr": 0.6194
|
||||
}
|
||||
},
|
||||
"restaurante": {
|
||||
"OFFICIAL_ONLY": {
|
||||
"total": 40,
|
||||
"recall_at_1": 0.0,
|
||||
"recall_at_5": 0.0,
|
||||
"recall_at_10": 0.0,
|
||||
"recall_at_20": 0.05,
|
||||
"recall_at_50": 0.075,
|
||||
"mrr": 0.0039
|
||||
},
|
||||
"KB_ONLY": {
|
||||
"total": 40,
|
||||
"recall_at_1": 0.7,
|
||||
"recall_at_5": 0.875,
|
||||
"recall_at_10": 0.875,
|
||||
"recall_at_20": 0.875,
|
||||
"recall_at_50": 0.875,
|
||||
"mrr": 0.7654
|
||||
},
|
||||
"HYBRID": {
|
||||
"total": 40,
|
||||
"recall_at_1": 0.625,
|
||||
"recall_at_5": 0.875,
|
||||
"recall_at_10": 0.875,
|
||||
"recall_at_20": 0.875,
|
||||
"recall_at_50": 0.875,
|
||||
"mrr": 0.7196
|
||||
}
|
||||
}
|
||||
},
|
||||
"llm_liberation_gate": {
|
||||
"gold_recall_at_20_min": 0.8,
|
||||
"gold_recall_at_50_preferred": 0.9
|
||||
},
|
||||
"cost_usd": 0.0
|
||||
}
|
||||
Reference in New Issue
Block a user