data/processed/filter_stats.json

{
 "stats": {
  "ibo": {
   "total": 8091,
   "kept": 7436,
   "dropped": 655,
   "by_rule": {
    "R2_loop": 6,
    "R3_copy": 250,
    "R4_length": 7,
    "R5_semantic": 392
   },
   "semantic_threshold": 0.7416,
   "labse_sim_pctiles_all": {
    "1": 0.639,
    "5": 0.742,
    "25": 0.83,
    "50": 0.871
   },
   "agreement_with_afrimm_filtered": {
    "afrimm_kept": 8078,
    "both_kept": 7436,
    "we_drop_afrimm_keeps": 642,
    "we_keep_afrimm_drops": 0
   }
  },
  "hau": {
   "total": 8091,
   "kept": 7655,
   "dropped": 436,
   "by_rule": {
    "R2_loop": 12,
    "R3_copy": 11,
    "R4_length": 10,
    "R5_semantic": 403
   },
   "semantic_threshold": 0.6025,
   "labse_sim_pctiles_all": {
    "1": 0.489,
    "5": 0.601,
    "25": 0.726,
    "50": 0.796
   },
   "agreement_with_afrimm_filtered": {
    "afrimm_kept": 7943,
    "both_kept": 7655,
    "we_drop_afrimm_keeps": 288,
    "we_keep_afrimm_drops": 0
   }
  },
  "yor": {
   "total": 8091,
   "kept": 7611,
   "dropped": 480,
   "by_rule": {
    "R2_loop": 24,
    "R3_copy": 16,
    "R4_length": 39,
    "R5_semantic": 401
   },
   "semantic_threshold": 0.5099,
   "labse_sim_pctiles_all": {
    "1": 0.33,
    "5": 0.501,
    "25": 0.658,
    "50": 0.737
   },
   "agreement_with_afrimm_filtered": {
    "afrimm_kept": 7526,
    "both_kept": 7490,
    "we_drop_afrimm_keeps": 36,
    "we_keep_afrimm_drops": 121
   }
  },
  "params": {
   "LEN_LO": 0.45,
   "LEN_HI": 2.2,
   "ABS_FLOOR": 0.5,
   "PCT": 5,
   "scorer": "sentence-transformers/LaBSE"
  }
 },
 "examples": {
  "ibo": {
   "R2_loop": [
    [
     "A little girl is carefully coloring in the pictures of a coloring book .",
     "Nwatakịrị nwanyị na-eji nlezianya agba agba agba"
    ],
    [
     "A little girl with blonde hair and a blue shirt is blowing bubbles outside with someone .",
     "Nwatakịrị nwanyị nwere ntutu isi na-acha odo odo na uwe elu na-acha anụnụ anụnụ na-afụ afụ afụ n'èzí na mmadụ ."
    ],
    [
     "A blue car drives down a mostly dirt road .",
     "A-acha anụnụ anụnụ ụgbọala ụgbọala ụgbọala ụgbọala ala a ukwuu n'ime unyi ụzọ ."
    ]
   ],
   "R3_copy": [
    [
     "A man is rock climbing .",
     "Otu nwoke bụ rock climbing ."
    ],
    [
     "A snowboarder sits on a slope with skiers and boarders nearby .",
     "A snowboarder na-anọdụ na a mkpọda na skiers na boarders nso ."
    ],
    [
     "Young boy with a black \" ADHD \" t-shirt nodding off",
     "Nwa okorobịa nwere \"ADHD\" t-shirt nodding off"
    ]
   ],
   "R4_length": [
    [
     "A child in a swing .",
     "Nwatakịrị nọ n'ebe a na-agbagharị agbagharị ."
    ],
    [
     "a team of rowers rowing in a green and red boat",
     "Otu ìgwè ndị na-agba ụgbọ mmiri na-agba ụgbọ mmiri na-acha akwụkwọ ndụ akwụkwọ ndụ na nke na-acha uhie uhie"
    ],
    [
     "A surfer is riding a wave .",
     "Onye na - eme njem n' ime mmiri na - agbagharị n' ebili mmiri."
    ]
   ],
   "R5_semantic": [
    [
     "a man is standing in front of a skyscraper",
     "Otu nwoke na-eguzo n'ihu ụlọ elu."
    ],
    [
     "Woman with three children fishing over boardwalk in the evening .",
     "Otu nwaanyị nwere ụmụ atọ na - akụ azụ̀ n' elu osimiri n' anyasị."
    ],
    [
     "A boy jumping in a fountain .",
     "Otu nwata nwoke na-awụlikwa elu n'isi iyi ."
    ]
   ]
  },
  "hau": {
   "R2_loop": [
    [
     "Hockey goalie boy in red jacket crouches by goal , with stick .",
     "Wani dan wasan Hockey mai tsaron gida a cikin jacket ja ja ja da kullun da ƙofa, tare da sanda."
    ],
    [
     "A young boy plays on a swing .",
     "Yaro yana wasa a kan ɗan ɗan ɗan ɗan"
    ],
    [
     "A person swinging on a swing",
     "Wani mutum yana ɗaukan ɗaukan ɗaukan"
    ]
   ],
   "R3_copy": [
    [
     "a man dressed as Jack Sparrow from Pirates of the Caribbean",
     "Wani mutumin da ya saka tufafin Jack Sparrow daga Pirates of the Caribbean"
    ],
    [
     "A child sleds .",
     "Yaro ya yi sleds ."
    ],
    [
     "Woman in a blue and white striped shirt with a straw cowboy hat on .",
     "Wata mace a cikin blue da fari striped shirt da straw cowboy hat a kan."
    ]
   ],
   "R4_length": [
    [
     "Young man with a nose ring and a hat .",
     "Matashi mai ɗan"
    ],
    [
     "Child with striped shirt , red shorts and orange cap standing on pavement near cars .",
     "Yaro da shiti mai launin"
    ],
    [
     "The two children swinging together on a swing .",
     "Yara biyu suna ɗaukan"
    ]
   ],
   "R5_semantic": [
    [
     "A dog leaps to catch a ball in a field .",
     "Karnuka suna tsallake don su kama ƙwallo a fili ."
    ],
    [
     "A child jumps off a high diving board into the pool .",
     "Yaro ya tsallake daga tafiyar ruwan da ke cikin ruwan da ke da tsaye ."
    ],
    [
     "A boy jumping in a fountain .",
     "Yaro yana tsallake cikin ruwan marar ruwa ."
    ]
   ]
  },
  "yor": {
   "R2_loop": [
    [
     "A woman is riding a three wheeler bicycle behind a pack of dogs .",
     "Obìnrin kan ń gun kẹ̀kẹ́ kẹ̀kẹ́ mẹ́ta lẹ́yìn àwọn ajá kan ."
    ],
    [
     "Two little kids in strollers have face makeup on like the band \" Kiss \" .",
     "Àwọn ọmọ kéékèèké méjì tí wọ́n wọ kẹ̀kẹ́ kẹ̀kẹ́ máa ń dojú kọ bí ẹgbẹ́ náà \" Kiss \" ."
    ],
    [
     "Two women riding a tandem bicycle go by a wall painting .",
     "Àwọn obìnrin méjì tí wọ́n ń gun kẹ̀kẹ́ kẹ̀kẹ́ alágbèéká máa ń lọ lẹ́gbẹ̀ẹ́ ògiri ."
    ]
   ],
   "R3_copy": [
    [
     "a man dressed as Jack Sparrow from Pirates of the Caribbean",
     "Ọkùnrin kan tí ó múra gẹ́gẹ́ bíi Jack Sparrow láti Pirates of the Caribbean"
    ],
    [
     "A motocross biker about to descend",
     "Motocross biker fẹ́ sọ̀kalẹ̀"
    ],
    [
     "person on a wakeboard in the air",
     "eniyan lori a wakeboard ni air"
    ]
   ],
   "R4_length": [
    [
     "A thin brown horse standing and a small black horse sitting on sand .",
     "Ẹṣin aláwọ̀"
    ],
    [
     "A black and brown dog is laying on a white shaggy carpet .",
     "Ajá aláwọ̀ dúdú àti aláwọ̀"
    ],
    [
     "The skinny brown dog is walking on a fallen tree .",
     "Ajá aláwọ̀ aláwọ"
    ]
   ],
   "R5_semantic": [
    [
     "Two dogs playing together on a beach .",
     "Àwọn ajá méjì ń ṣeré pa pọ̀ ní etíkun ."
    ],
    [
     "an ice climber in a blue jacket and black pants is scaling a frozen ice wall .",
     "Ẹni tó ń gun yìnyín nínú jákẹ́ẹ̀tì aláwọ̀ búlúù àti ṣòkòtò dúdú ń gbé ògiri yìnyín dídì ."
    ],
    [
     "A light-colored dog runs on the beach .",
     "Ajá aláwọ̀ fẹ́lẹ́fẹ́lẹ́ máa ń ṣiṣẹ́ ní etí òkun."
    ]
   ]
  }
 }
}