lukekim / demo

main

/demo/spicepods/Jeadie/evals/spicepod.yaml

1datasets: 2 - from: spice.ai/Jeadie/evals/datasets/cube_pack__dev__v0 3 name: cube_pack__dev__v0 4 - from: spice.ai/Jeadie/evals/datasets/historical_kana_orthography_reading__dev__v0 5 name: historical_kana_orthography_reading__dev__v0 6 - from: spice.ai/Jeadie/evals/datasets/canto_wu_pronunciation_fewshot__dev__v0 7 name: canto_wu_pronunciation_fewshot__dev__v0 8 - from: spice.ai/Jeadie/evals/datasets/accounting_audit__dev__v0 9 name: accounting_audit__dev__v0 10 - from: spice.ai/Jeadie/evals/datasets/brazilian_lexicon__dev__v0 11 name: brazilian_lexicon__dev__v0 12 - from: spice.ai/Jeadie/evals/datasets/naughty_strings__test__v1 13 name: naughty_strings__test__v1 14 - from: spice.ai/Jeadie/evals/datasets/korean_phonetics__dev__v0 15 name: korean_phonetics__dev__v0 16 - from: spice.ai/Jeadie/evals/datasets/chinese_homophonic__dev__v0 17 name: chinese_homophonic__dev__v0 18 - from: spice.ai/Jeadie/evals/datasets/count_intersections_polynomial__dev__v0 19 name: count_intersections_polynomial__dev__v0 20 - from: spice.ai/Jeadie/evals/datasets/coqa_match__dev__v0 21 name: coqa_match__dev__v0 22 - from: spice.ai/Jeadie/evals/datasets/latin_grammar__dev__v0 23 name: latin_grammar__dev__v0 24 - from: spice.ai/Jeadie/evals/datasets/bitwise__dev__v0 25 name: bitwise__dev__v0 26 - from: spice.ai/Jeadie/evals/datasets/shared_borders__dev__v0 27 name: shared_borders__dev__v0 28 - from: spice.ai/Jeadie/evals/datasets/japanese_station__dev__v0 29 name: japanese_station__dev__v0 30 - from: spice.ai/Jeadie/evals/datasets/atpl_exams__dev__v0 31 name: atpl_exams__dev__v0 32 - from: spice.ai/Jeadie/evals/datasets/invoice_due_date_leap_day_adjustment__dev__v0 33 name: invoice_due_date_leap_day_adjustment__dev__v0 34 - from: spice.ai/Jeadie/evals/datasets/romanian_homonyms__dev__v0 35 name: romanian_homonyms__dev__v0 36 - from: spice.ai/Jeadie/evals/datasets/infiniteloop_match__s1__simple_v0 37 name: infiniteloop_match__s1__simple_v0 38 - from: spice.ai/Jeadie/evals/datasets/russian_nlp_tasks__dev__v0 39 name: russian_nlp_tasks__dev__v0 40 - from: spice.ai/Jeadie/evals/datasets/chinese_chu_ci__dev__v0 41 name: chinese_chu_ci__dev__v0 42 - from: spice.ai/Jeadie/evals/datasets/polish_syllable_count__val__v0 43 name: polish_syllable_count__val__v0 44 - from: spice.ai/Jeadie/evals/datasets/korean_postposition__dev__v0 45 name: korean_postposition__dev__v0 46 - from: spice.ai/Jeadie/evals/datasets/bulgarian_lexicon__dev__v0 47 name: bulgarian_lexicon__dev__v0 48 - from: spice.ai/Jeadie/evals/datasets/compare_countries_area__dev__v0 49 name: compare_countries_area__dev__v0 50 - from: spice.ai/Jeadie/evals/datasets/pattern_identification__dev__v0 51 name: pattern_identification__dev__v0 52 - from: spice.ai/Jeadie/evals/datasets/belarusian_synonyms__dev__v0 53 name: belarusian_synonyms__dev__v0 54 - from: spice.ai/Jeadie/evals/datasets/spanish_feminine_noun_masculine_article__dev__v0 55 name: spanish_feminine_noun_masculine_article__dev__v0 56 - from: spice.ai/Jeadie/evals/datasets/sarcasm__test__v1 57 name: sarcasm__test__v1 58 - from: spice.ai/Jeadie/evals/datasets/chinese_tang_poetries__dev__match_v1 59 name: chinese_tang_poetries__dev__match_v1 60 - from: spice.ai/Jeadie/evals/datasets/japanese_number_reading__dev__v0 61 name: japanese_number_reading__dev__v0 62 - from: spice.ai/Jeadie/evals/datasets/korean_honorific__dev__v0 63 name: korean_honorific__dev__v0 64 - from: spice.ai/Jeadie/evals/datasets/complex_replace_characters__dev__v0 65 name: complex_replace_characters__dev__v0 66 - from: spice.ai/Jeadie/evals/datasets/dice_rotation_sequence__dev__v0 67 name: dice_rotation_sequence__dev__v0 68 - from: spice.ai/Jeadie/evals/datasets/utah_real_estate__dev__v0 69 name: utah_real_estate__dev__v0 70 - from: spice.ai/Jeadie/evals/datasets/formal_logic__dev__v0 71 name: formal_logic__dev__v0 72 - from: spice.ai/Jeadie/evals/datasets/resistor_ohm_calculator__dev__simple_v0 73 name: resistor_ohm_calculator__dev__simple_v0 74 - from: spice.ai/Jeadie/evals/datasets/gol__dev__v1 75 name: gol__dev__v1 76 - from: spice.ai/Jeadie/evals/datasets/icelandic_sentences_gec__dev__v0 77 name: icelandic_sentences_gec__dev__v0 78 - from: spice.ai/Jeadie/evals/datasets/chinese_modern_poem_identification__test__v1 79 name: chinese_modern_poem_identification__test__v1 80 - from: spice.ai/Jeadie/evals/datasets/reverse_string__s1__simple_v0 81 name: reverse_string__s1__simple_v0 82 - from: spice.ai/Jeadie/evals/datasets/complex_analogies_en_ru__dev__v0 83 name: complex_analogies_en_ru__dev__v0 84 - from: spice.ai/Jeadie/evals/datasets/positive_binary_operations__test__v1 85 name: positive_binary_operations__test__v1 86 - from: spice.ai/Jeadie/evals/datasets/hindi_shuddha__dev__v0 87 name: hindi_shuddha__dev__v0 88 - from: spice.ai/Jeadie/evals/datasets/tokyo_station_number__dev__v0 89 name: tokyo_station_number__dev__v0 90 - from: spice.ai/Jeadie/evals/datasets/chinese_famous_novel__dev__v0 91 name: chinese_famous_novel__dev__v0 92 - from: spice.ai/Jeadie/evals/datasets/diagrammatic_logic__dev__v2 93 name: diagrammatic_logic__dev__v2 94 - from: spice.ai/Jeadie/evals/datasets/polish_lexicon__dev__v0 95 name: polish_lexicon__dev__v0 96 - from: spice.ai/Jeadie/evals/datasets/wkt_understanding__dev__v0 97 name: wkt_understanding__dev__v0 98 - from: spice.ai/Jeadie/evals/datasets/japanese_national_medical_exam02__dev__v0 99 name: japanese_national_medical_exam02__dev__v0 100 - from: spice.ai/Jeadie/evals/datasets/cardinal_directions__dev__v0 101 name: cardinal_directions__dev__v0 102 - from: spice.ai/Jeadie/evals/datasets/rectangles__dev__v0 103 name: rectangles__dev__v0 104 - from: spice.ai/Jeadie/evals/datasets/hindi_upsc__dev__v0 105 name: hindi_upsc__dev__v0 106 - from: spice.ai/Jeadie/evals/datasets/three_pt_mapping__dev__v0 107 name: three_pt_mapping__dev__v0 108 - from: spice.ai/Jeadie/evals/datasets/polish_proverbs__dev__v0 109 name: polish_proverbs__dev__v0 110 - from: spice.ai/Jeadie/evals/datasets/indonesian_numbers__dev__v0 111 name: indonesian_numbers__dev__v0 112 - from: spice.ai/Jeadie/evals/datasets/chinese_song_ci__dev__v0 113 name: chinese_song_ci__dev__v0 114 - from: spice.ai/Jeadie/evals/datasets/cybersecurity_filepaths__dev__v0 115 name: cybersecurity_filepaths__dev__v0 116 - from: spice.ai/Jeadie/evals/datasets/taxes__dev__v0 117 name: taxes__dev__v0 118 - from: spice.ai/Jeadie/evals/datasets/crontab__dev__v0 119 name: crontab__dev__v0 120 - from: spice.ai/Jeadie/evals/datasets/integer_sequence_predictions_misc__dev__v0 121 name: integer_sequence_predictions_misc__dev__v0 122 - from: spice.ai/Jeadie/evals/datasets/integer_sequence_predictions_obscure__dev__v0 123 name: integer_sequence_predictions_obscure__dev__v0 124 - from: spice.ai/Jeadie/evals/datasets/integer_sequence_predictions_notable__dev__v0 125 name: integer_sequence_predictions_notable__dev__v0 126 - from: spice.ai/Jeadie/evals/datasets/integer_sequence_predictions__dev__v0 127 name: integer_sequence_predictions__dev__v0 128 - from: spice.ai/Jeadie/evals/datasets/belarusian_orthography__dev__v0 129 name: belarusian_orthography__dev__v0 130 - from: spice.ai/Jeadie/evals/datasets/date_booking__dev__v0 131 name: date_booking__dev__v0 132 - from: spice.ai/Jeadie/evals/datasets/interlingual_homograph__dev__v0 133 name: interlingual_homograph__dev__v0 134 - from: spice.ai/Jeadie/evals/datasets/stats_tests__dev__v0 135 name: stats_tests__dev__v0 136 - from: spice.ai/Jeadie/evals/datasets/belarusian_russian_translation__dev__v0 137 name: belarusian_russian_translation__dev__v0 138 - from: spice.ai/Jeadie/evals/datasets/date_calculator__test__v1 139 name: date_calculator__test__v1 140 - from: spice.ai/Jeadie/evals/datasets/chinese_poem__dev__v0 141 name: chinese_poem__dev__v0 142 - from: spice.ai/Jeadie/evals/datasets/belarusian_lexicon__dev__v0 143 name: belarusian_lexicon__dev__v0 144 - from: spice.ai/Jeadie/evals/datasets/test_english_pronunciations__dev__v0 145 name: test_english_pronunciations__dev__v0 146 - from: spice.ai/Jeadie/evals/datasets/anagrams__test__v1 147 name: anagrams__test__v1 148 - from: spice.ai/Jeadie/evals/datasets/guess_the_singer__dev__v0 149 name: guess_the_singer__dev__v0 150 - from: spice.ai/Jeadie/evals/datasets/illinois_law__v0 151 name: illinois_law__v0 152 - from: spice.ai/Jeadie/evals/datasets/russian_medical__dev__v0 153 name: russian_medical__dev__v0 154 - from: spice.ai/Jeadie/evals/datasets/bigrams__dev__v0 155 name: bigrams__dev__v0 156 - from: spice.ai/Jeadie/evals/datasets/probability_questions__dev__v0 157 name: probability_questions__dev__v0 158 - from: spice.ai/Jeadie/evals/datasets/vintage_phone_keyboard_decode__dev__v0 159 name: vintage_phone_keyboard_decode__dev__v0 160 - from: spice.ai/Jeadie/evals/datasets/connect4__s1__v1 161 name: connect4__s1__v1 162 - from: spice.ai/Jeadie/evals/datasets/stock_options_bull_call_spread__dev__v0 163 name: stock_options_bull_call_spread__dev__v0 164 - from: spice.ai/Jeadie/evals/datasets/stock_options_bear_call_spread__dev__v0 165 name: stock_options_bear_call_spread__dev__v0 166 - from: spice.ai/Jeadie/evals/datasets/stock_option_terms_bear_call_spread__dev__v0 167 name: stock_option_terms_bear_call_spread__dev__v0 168 - from: spice.ai/Jeadie/evals/datasets/stock_option_terms_iron_butterfly_spread__dev__v0 169 name: stock_option_terms_iron_butterfly_spread__dev__v0 170 - from: spice.ai/Jeadie/evals/datasets/stock_option_terms_bull_call_spread__dev__v0 171 name: stock_option_terms_bull_call_spread__dev__v0 172 - from: spice.ai/Jeadie/evals/datasets/stock_options_inverse_iron_condor_spread__dev__v0 173 name: stock_options_inverse_iron_condor_spread__dev__v0 174 - from: spice.ai/Jeadie/evals/datasets/stock_options_iron_condor_spread__dev__v0 175 name: stock_options_iron_condor_spread__dev__v0 176 - from: spice.ai/Jeadie/evals/datasets/stock_option_terms_iron_condor_spread__dev__v0 177 name: stock_option_terms_iron_condor_spread__dev__v0 178 - from: spice.ai/Jeadie/evals/datasets/stock_options_inverse_iron_butterfly_spread__dev__v0 179 name: stock_options_inverse_iron_butterfly_spread__dev__v0 180 - from: spice.ai/Jeadie/evals/datasets/stock_option_terms_inverse_iron_condor_spread__dev__v0 181 name: stock_option_terms_inverse_iron_condor_spread__dev__v0 182 - from: spice.ai/Jeadie/evals/datasets/japanese_romantic_context__dev__v0 183 name: japanese_romantic_context__dev__v0 184 - from: spice.ai/Jeadie/evals/datasets/phonetics_identify_words_needing_missing_gpcs__s1__simple_v0 185 name: phonetics_identify_words_needing_missing_gpcs__s1__simple_v0 186 - from: spice.ai/Jeadie/evals/datasets/prompt_injection__dev__v0 187 name: prompt_injection__dev__v0 188 - from: spice.ai/Jeadie/evals/datasets/word_vector_over_reliance__dev__simple_v0 189 name: word_vector_over_reliance__dev__simple_v0 190 - from: spice.ai/Jeadie/evals/datasets/iso_to_lunar_calendar__dev__v0 191 name: iso_to_lunar_calendar__dev__v0 192 - from: spice.ai/Jeadie/evals/datasets/lunar_calendar_to_iso__dev__v0 193 name: lunar_calendar_to_iso__dev__v0 194 - from: spice.ai/Jeadie/evals/datasets/code_combination__dev__v0 195 name: code_combination__dev__v0 196 - from: spice.ai/Jeadie/evals/datasets/partially_solved_crossword_clues__dev__v0 197 name: partially_solved_crossword_clues__dev__v0 198 - from: spice.ai/Jeadie/evals/datasets/quartz__test__v1 199 name: quartz__test__v1 200 - from: spice.ai/Jeadie/evals/datasets/physics__interaction__dev__v0 201 name: physics__interaction__dev__v0 202 - from: spice.ai/Jeadie/evals/datasets/next_val_series__dev__simple_v0 203 name: next_val_series__dev__simple_v0 204evals: 205 - dataset: cube_pack__dev__v0 206 name: cube-pack 207 scorers: 208 - match 209 - dataset: historical_kana_orthography_reading__dev__v0 210 name: historical-kana-orthography-reading 211 scorers: 212 - match 213 - dataset: canto_wu_pronunciation_fewshot__dev__v0 214 name: canto_wu_pronunciation_fewshot 215 scorers: 216 - match 217 - dataset: accounting_audit__dev__v0 218 name: accounting_audit 219 scorers: 220 - match 221 - dataset: brazilian_lexicon__dev__v0 222 name: brazilian-lexicon 223 scorers: 224 - match 225 - dataset: naughty_strings__test__v1 226 name: naughty_strings 227 scorers: 228 - match 229 - dataset: korean_phonetics__dev__v0 230 name: korean-phonetics 231 scorers: 232 - match 233 - dataset: chinese_homophonic__dev__v0 234 name: chinese-homo 235 scorers: 236 - match 237 - dataset: count_intersections_polynomial__dev__v0 238 name: count_intersections_polynomial 239 scorers: 240 - match 241 - dataset: coqa_match__dev__v0 242 name: coqa-match 243 scorers: 244 - match 245 - dataset: latin_grammar__dev__v0 246 name: latin-grammar 247 scorers: 248 - match 249 - dataset: bitwise__dev__v0 250 name: bitwise 251 scorers: 252 - match 253 - dataset: shared_borders__dev__v0 254 name: shared-borders 255 scorers: 256 - match 257 - dataset: japanese_station__dev__v0 258 name: japanese-station 259 scorers: 260 - match 261 - dataset: atpl_exams__dev__v0 262 name: atpl_exams 263 scorers: 264 - match 265 - dataset: invoice_due_date_leap_day_adjustment__dev__v0 266 name: invoice_due_date_leap_day_adjustment 267 scorers: 268 - match 269 - dataset: romanian_homonyms__dev__v0 270 name: romanian_homonyms 271 scorers: 272 - match 273 - dataset: infiniteloop_match__s1__simple_v0 274 name: infiniteloop-match 275 scorers: 276 - match 277 - dataset: russian_nlp_tasks__dev__v0 278 name: russian-nlp-tasks 279 scorers: 280 - match 281 - dataset: chinese_chu_ci__dev__v0 282 name: chinese_chu_ci 283 scorers: 284 - match 285 - dataset: polish_syllable_count__val__v0 286 name: polish-syllable-count 287 scorers: 288 - match 289 - dataset: korean_postposition__dev__v0 290 name: korean-postposition 291 scorers: 292 - match 293 - dataset: bulgarian_lexicon__dev__v0 294 name: bulgarian-lexicon 295 scorers: 296 - match 297 - dataset: compare_countries_area__dev__v0 298 name: compare-countries-area 299 scorers: 300 - match 301 - dataset: pattern_identification__dev__v0 302 name: pattern_identification 303 scorers: 304 - match 305 - dataset: belarusian_synonyms__dev__v0 306 name: belarusian-synonyms 307 scorers: 308 - match 309 - dataset: spanish_feminine_noun_masculine_article__dev__v0 310 name: spanish_feminine_noun_masculine_article 311 scorers: 312 - match 313 - dataset: sarcasm__test__v1 314 name: sarcasm 315 scorers: 316 - match 317 - dataset: chinese_tang_poetries__dev__match_v1 318 name: chinese_tang_poetries 319 scorers: 320 - match 321 - dataset: japanese_number_reading__dev__v0 322 name: japanese-number-reading 323 scorers: 324 - match 325 - dataset: korean_honorific__dev__v0 326 name: korean-honorific 327 scorers: 328 - match 329 - dataset: complex_replace_characters__dev__v0 330 name: complex-replace-characters 331 scorers: 332 - match 333 - dataset: dice_rotation_sequence__dev__v0 334 name: dice-rotation-sequence 335 scorers: 336 - match 337 - dataset: utah_real_estate__dev__v0 338 name: utah_real_estateh 339 scorers: 340 - match 341 - dataset: formal_logic__dev__v0 342 name: formal-logic 343 scorers: 344 - match 345 - dataset: resistor_ohm_calculator__dev__simple_v0 346 name: resistor-ohm-calculator 347 scorers: 348 - match 349 - dataset: gol__dev__v1 350 name: gol 351 scorers: 352 - match 353 - dataset: icelandic_sentences_gec__dev__v0 354 name: icelandic-sentences-gec 355 scorers: 356 - match 357 - dataset: chinese_modern_poem_identification__test__v1 358 name: chinese_modern_poem_identification 359 scorers: 360 - match 361 - dataset: reverse_string__s1__simple_v0 362 name: reverse-string 363 scorers: 364 - match 365 - dataset: complex_analogies_en_ru__dev__v0 366 name: complex-analogies-en-ru 367 scorers: 368 - match 369 - dataset: positive_binary_operations__test__v1 370 name: positive-binary-operations 371 scorers: 372 - match 373 - dataset: hindi_shuddha__dev__v0 374 name: hindi_shuddha 375 scorers: 376 - match 377 - dataset: tokyo_station_number__dev__v0 378 name: tokyo-station-number 379 scorers: 380 - match 381 - dataset: chinese_famous_novel__dev__v0 382 name: chinese_famous_novel 383 scorers: 384 - match 385 - dataset: diagrammatic_logic__dev__v2 386 name: diagrammatic_logic 387 scorers: 388 - match 389 - dataset: polish_lexicon__dev__v0 390 name: polish-lexicon 391 scorers: 392 - match 393 - dataset: wkt_understanding__dev__v0 394 name: wkt_understanding 395 scorers: 396 - match 397 - dataset: japanese_national_medical_exam02__dev__v0 398 name: japanese-national-medical-exam02 399 scorers: 400 - match 401 - dataset: cardinal_directions__dev__v0 402 name: cardinal-directions 403 scorers: 404 - match 405 - dataset: rectangles__dev__v0 406 name: rectangles 407 scorers: 408 - match 409 - dataset: hindi_upsc__dev__v0 410 name: hindi_upsc 411 scorers: 412 - match 413 - dataset: three_pt_mapping__dev__v0 414 name: three-pt-mapping 415 scorers: 416 - match 417 - dataset: polish_proverbs__dev__v0 418 name: polish-proverbs 419 scorers: 420 - match 421 - dataset: indonesian_numbers__dev__v0 422 name: indonesian_numbers 423 scorers: 424 - match 425 - dataset: chinese_song_ci__dev__v0 426 name: chinese_song_ci 427 scorers: 428 - match 429 - dataset: cybersecurity_filepaths__dev__v0 430 name: cybersecurity-filepaths 431 scorers: 432 - match 433 - dataset: taxes__dev__v0 434 name: taxes 435 scorers: 436 - match 437 - dataset: crontab__dev__v0 438 name: crontab 439 scorers: 440 - match 441 - dataset: integer_sequence_predictions_misc__dev__v0 442 name: integer-sequence-predictions-misc 443 scorers: 444 - match 445 - dataset: integer_sequence_predictions_obscure__dev__v0 446 name: integer-sequence-predictions-obscure 447 scorers: 448 - match 449 - dataset: integer_sequence_predictions_notable__dev__v0 450 name: integer-sequence-predictions-notable 451 scorers: 452 - match 453 - dataset: integer_sequence_predictions__dev__v0 454 name: integer-sequence-predictions 455 scorers: 456 - match 457 - dataset: belarusian_orthography__dev__v0 458 name: belarusian-orthography 459 scorers: 460 - match 461 - dataset: date_booking__dev__v0 462 name: date-booking 463 scorers: 464 - match 465 - dataset: interlingual_homograph__dev__v0 466 name: interlingual-homograph 467 scorers: 468 - match 469 - dataset: stats_tests__dev__v0 470 name: stats-tests 471 scorers: 472 - match 473 - dataset: belarusian_russian_translation__dev__v0 474 name: belarusian-russian-translation 475 scorers: 476 - match 477 - dataset: date_calculator__test__v1 478 name: date-calculator 479 scorers: 480 - match 481 - dataset: chinese_poem__dev__v0 482 name: chinese_poem 483 scorers: 484 - match 485 - dataset: belarusian_lexicon__dev__v0 486 name: belarusian-lexicon 487 scorers: 488 - match 489 - dataset: test_english_pronunciations__dev__v0 490 name: test_english_pronunciations 491 scorers: 492 - match 493 - dataset: anagrams__test__v1 494 name: anagrams 495 scorers: 496 - match 497 - dataset: guess_the_singer__dev__v0 498 name: guess-the-singer 499 scorers: 500 - match 501 - dataset: illinois_law__v0 502 name: illinois-law 503 scorers: 504 - match 505 - dataset: russian_medical__dev__v0 506 name: russian_medical 507 scorers: 508 - match 509 - dataset: bigrams__dev__v0 510 name: bigrams 511 scorers: 512 - match 513 - dataset: probability_questions__dev__v0 514 name: probability-questions 515 scorers: 516 - match 517 - dataset: vintage_phone_keyboard_decode__dev__v0 518 name: vintage_phone_keyboard_decode 519 scorers: 520 - match 521 - dataset: connect4__s1__v1 522 name: connect4 523 scorers: 524 - match 525 - dataset: stock_options_bull_call_spread__dev__v0 526 name: stock-options-bull-call-spread 527 scorers: 528 - match 529 - dataset: stock_options_bear_call_spread__dev__v0 530 name: stock-options-bear-call-spread 531 scorers: 532 - match 533 - dataset: stock_option_terms_bear_call_spread__dev__v0 534 name: stock-option-terms-bear-call-spread 535 scorers: 536 - match 537 - dataset: stock_option_terms_iron_butterfly_spread__dev__v0 538 name: stock-option-terms-iron-butteryfly-spread 539 scorers: 540 - match 541 - dataset: stock_option_terms_bull_call_spread__dev__v0 542 name: stock-option-terms-bull-call-spread 543 scorers: 544 - match 545 - dataset: stock_options_inverse_iron_condor_spread__dev__v0 546 name: stock-options-inverse-iron-condor-spread 547 scorers: 548 - match 549 - dataset: stock_options_iron_condor_spread__dev__v0 550 name: stock-options-iron-condor-spread 551 scorers: 552 - match 553 - dataset: stock_option_terms_iron_condor_spread__dev__v0 554 name: stock-option-terms-iron-condor-spread 555 scorers: 556 - match 557 - dataset: stock_options_inverse_iron_butterfly_spread__dev__v0 558 name: stock-options-inverse-iron-butterfly-spread 559 scorers: 560 - match 561 - dataset: stock_option_terms_inverse_iron_condor_spread__dev__v0 562 name: stock-option-terms-inverse-iron-condor-spread 563 scorers: 564 - match 565 - dataset: japanese_romantic_context__dev__v0 566 name: japanese_romantic_context 567 scorers: 568 - match 569 - dataset: phonetics_identify_words_needing_missing_gpcs__s1__simple_v0 570 name: phonetics-identify-words-needing-missing-gpcs 571 scorers: 572 - match 573 - dataset: prompt_injection__dev__v0 574 name: prompt-injection 575 scorers: 576 - match 577 - dataset: word_vector_over_reliance__dev__simple_v0 578 name: word_vector_over_reliance 579 scorers: 580 - match 581 - dataset: iso_to_lunar_calendar__dev__v0 582 name: iso-to-lunar-calendar 583 scorers: 584 - match 585 - dataset: lunar_calendar_to_iso__dev__v0 586 name: lunar-calendar-to-iso 587 scorers: 588 - match 589 - dataset: code_combination__dev__v0 590 name: code_combination 591 scorers: 592 - match 593 - dataset: partially_solved_crossword_clues__dev__v0 594 name: partially_solved_crossword_clues 595 scorers: 596 - match 597 - dataset: quartz__test__v1 598 name: quartz 599 scorers: 600 - match 601 - dataset: physics__interaction__dev__v0 602 name: physics-interaction 603 scorers: 604 - match 605 - dataset: next_val_series__dev__simple_v0 606 name: next-val-series 607 scorers: 608 - match 609kind: Spicepod 610name: spicepod 611version: v1beta1 612