Create tasks.md

tasks.md

@@ -0,0 +1,444 @@
+- 0 babi_nli/counting
+- 1 babi_nli/indefinite-knowledge
+- 2 babi_nli/simple-negation
+- 3 babi_nli/three-arg-relations
+- 4 babi_nli/basic-induction
+- 5 babi_nli/time-reasoning
+- 6 babi_nli/compound-coreference
+- 7 babi_nli/path-finding
+- 8 babi_nli/positional-reasoning
+- 9 babi_nli/conjunction
+- 10 babi_nli/size-reasoning
+- 11 babi_nli/yes-no-questions
+- 12 babi_nli/basic-coreference
+- 13 babi_nli/two-supporting-facts
+- 14 babi_nli/lists-sets
+- 15 babi_nli/two-arg-relations
+- 16 babi_nli/three-supporting-facts
+- 17 babi_nli/basic-deduction
+- 18 babi_nli/single-supporting-fact
+- 19 anli/a1
+- 20 anli/a2
+- 21 anli/a3
+- 22 sick/label
+- 23 sick/relatedness
+- 24 sick/entailment_AB
+- 25 sick/entailment_BA
+- 26 snli
+- 27 scitail/snli_format
+- 28 hans
+- 29 WANLI
+- 30 recast/recast_kg_relations
+- 31 recast/recast_puns
+- 32 recast/recast_factuality
+- 33 recast/recast_megaveridicality
+- 34 recast/recast_verbcorner
+- 35 recast/recast_verbnet
+- 36 recast/recast_ner
+- 37 recast/recast_sentiment
+- 38 probability_words_nli/usnli
+- 39 probability_words_nli/reasoning_1hop
+- 40 probability_words_nli/reasoning_2hop
+- 41 nan-nli/joey234--nan-nli
+- 42 nli_fever
+- 43 breaking_nli
+- 44 conj_nli
+- 45 fracas
+- 46 dialogue_nli
+- 47 mpe
+- 48 dnc
+- 49 gpt3_nli
+- 50 recast_white/fnplus
+- 51 recast_white/sprl
+- 52 recast_white/dpr
+- 53 joci
+- 54 contrast_nli
+- 55 robust_nli/IS_CS
+- 56 robust_nli/LI_LI
+- 57 robust_nli/ST_WO
+- 58 robust_nli/PI_SP
+- 59 robust_nli/PI_CD
+- 60 robust_nli/ST_SE
+- 61 robust_nli/ST_NE
+- 62 robust_nli/ST_LM
+- 63 robust_nli_is_sd
+- 64 robust_nli_li_ts
+- 65 gen_debiased_nli/snli_seq_z
+- 66 gen_debiased_nli/snli_z_aug
+- 67 gen_debiased_nli/snli_par_z
+- 68 gen_debiased_nli/mnli_par_z
+- 69 gen_debiased_nli/mnli_z_aug
+- 70 gen_debiased_nli/mnli_seq_z
+- 71 add_one_rte
+- 72 imppres/presupposition_cleft_uniqueness/presupposition
+- 73 imppres/presupposition_possessed_definites_uniqueness/presupposition
+- 74 imppres/presupposition_possessed_definites_existence/presupposition
+- 75 imppres/presupposition_only_presupposition/presupposition
+- 76 imppres/presupposition_all_n_presupposition/presupposition
+- 77 imppres/presupposition_both_presupposition/presupposition
+- 78 imppres/presupposition_change_of_state/presupposition
+- 79 imppres/presupposition_cleft_existence/presupposition
+- 80 imppres/presupposition_question_presupposition/presupposition
+- 81 imppres/implicature_modals/prag
+- 82 imppres/implicature_numerals_10_100/prag
+- 83 imppres/implicature_numerals_2_3/prag
+- 84 imppres/implicature_gradable_adjective/prag
+- 85 imppres/implicature_quantifiers/prag
+- 86 imppres/implicature_gradable_verb/prag
+- 87 imppres/implicature_connectives/prag
+- 88 imppres/implicature_gradable_adjective/log
+- 89 imppres/implicature_gradable_verb/log
+- 90 imppres/implicature_numerals_2_3/log
+- 91 imppres/implicature_numerals_10_100/log
+- 92 imppres/implicature_modals/log
+- 93 imppres/implicature_quantifiers/log
+- 94 imppres/implicature_connectives/log
+- 95 glue_diagnostics/diagnostics
+- 96 hlgd
+- 97 paws/labeled_final
+- 98 paws/labeled_swap
+- 99 quora
+- 100 medical_questions_pairs
+- 101 conll2003/pos_tags
+- 102 conll2003/chunk_tags
+- 103 conll2003/ner_tags
+- 104 hh-rlhf
+- 105 model-written-evals
+- 106 truthful_qa/multiple_choice
+- 107 fig-qa
+- 108 bigbench/fantasy_reasoning
+- 109 bigbench/nonsense_words_grammar
+- 110 bigbench/analytic_entailment
+- 111 bigbench/logic_grid_puzzle
+- 112 bigbench/geometric_shapes
+- 113 bigbench/key_value_maps
+- 114 bigbench/analogical_similarity
+- 115 bigbench/metaphor_understanding
+- 116 bigbench/metaphor_boolean
+- 117 bigbench/ruin_names
+- 118 bigbench/cs_algorithms
+- 119 bigbench/physical_intuition
+- 120 bigbench/mnist_ascii
+- 121 bigbench/moral_permissibility
+- 122 bigbench/emoji_movie
+- 123 bigbench/snarks
+- 124 bigbench/timedial
+- 125 bigbench/dark_humor_detection
+- 126 bigbench/gre_reading_comprehension
+- 127 bigbench/empirical_judgments
+- 128 bigbench/causal_judgment
+- 129 bigbench/fact_checker
+- 130 bigbench/logical_fallacy_detection
+- 131 bigbench/identify_math_theorems
+- 132 bigbench/dyck_languages
+- 133 bigbench/winowhy
+- 134 bigbench/logical_sequence
+- 135 bigbench/strategyqa
+- 136 bigbench/unit_interpretation
+- 137 bigbench/authorship_verification
+- 138 bigbench/undo_permutation
+- 139 bigbench/epistemic_reasoning
+- 140 bigbench/human_organs_senses
+- 141 bigbench/misconceptions
+- 142 bigbench/international_phonetic_alphabet_nli
+- 143 bigbench/identify_odd_metaphor
+- 144 bigbench/mathematical_induction
+- 145 bigbench/odd_one_out
+- 146 bigbench/reasoning_about_colored_objects
+- 147 bigbench/strange_stories
+- 148 bigbench/evaluating_information_essentiality
+- 149 bigbench/figure_of_speech_detection
+- 150 bigbench/english_proverbs
+- 151 bigbench/general_knowledge
+- 152 bigbench/tracking_shuffled_objects
+- 153 bigbench/physics
+- 154 bigbench/anachronisms
+- 155 bigbench/simple_ethical_questions
+- 156 bigbench/logical_args
+- 157 bigbench/suicide_risk
+- 158 bigbench/sentence_ambiguity
+- 159 bigbench/temporal_sequences
+- 160 bigbench/penguins_in_a_table
+- 161 bigbench/sports_understanding
+- 162 bigbench/hyperbaton
+- 163 bigbench/code_line_description
+- 164 bigbench/question_selection
+- 165 bigbench/disambiguation_qa
+- 166 bigbench/date_understanding
+- 167 bigbench/play_dialog_same_or_different
+- 168 bigbench/salient_translation_error_detection
+- 169 bigbench/irony_identification
+- 170 bigbench/emojis_emotion_prediction
+- 171 bigbench/hindu_knowledge
+- 172 bigbench/conceptual_combinations
+- 173 bigbench/implicatures
+- 174 bigbench/movie_dialog_same_or_different
+- 175 bigbench/social_support
+- 176 bigbench/presuppositions_as_nli
+- 177 bigbench/vitaminc_fact_verification
+- 178 bigbench/hhh_alignment
+- 179 bigbench/implicit_relations
+- 180 bigbench/bbq_lite_json
+- 181 bigbench/phrase_relatedness
+- 182 bigbench/logical_deduction
+- 183 bigbench/discourse_marker_prediction
+- 184 bigbench/movie_recommendation
+- 185 bigbench/real_or_fake_text
+- 186 bigbench/formal_fallacies_syllogisms_negation
+- 187 bigbench/crass_ai
+- 188 blimp/inchoative
+- 189 blimp/principle_A_c_command
+- 190 blimp/matrix_question_npi_licensor_present
+- 191 blimp/wh_questions_subject_gap_long_distance
+- 192 blimp/sentential_subject_island
+- 193 blimp/existential_there_quantifiers_2
+- 194 blimp/sentential_negation_npi_scope
+- 195 blimp/complex_NP_island
+- 196 blimp/principle_A_reconstruction
+- 197 blimp/animate_subject_passive
+- 198 blimp/tough_vs_raising_1
+- 199 blimp/wh_vs_that_with_gap
+- 200 blimp/principle_A_domain_2
+- 201 blimp/npi_present_1
+- 202 blimp/wh_vs_that_with_gap_long_distance
+- 203 blimp/superlative_quantifiers_1
+- 204 blimp/npi_present_2
+- 205 blimp/wh_questions_object_gap
+- 206 blimp/coordinate_structure_constraint_complex_left_branch
+- 207 blimp/coordinate_structure_constraint_object_extraction
+- 208 blimp/left_branch_island_echo_question
+- 209 blimp/drop_argument
+- 210 cos_e/v1.0
+- 211 cosmos_qa
+- 212 dream
+- 213 openbookqa
+- 214 qasc
+- 215 quartz
+- 216 quail
+- 217 head_qa/en
+- 218 sciq
+- 219 social_i_qa
+- 220 wiki_hop
+- 221 wiqa
+- 222 piqa
+- 223 hellaswag
+- 224 super_glue/copa
+- 225 art
+- 226 hendrycks_test/moral_disputes
+- 227 hendrycks_test/moral_scenarios
+- 228 hendrycks_test/nutrition
+- 229 hendrycks_test/philosophy
+- 230 hendrycks_test/prehistory
+- 231 hendrycks_test/professional_accounting
+- 232 hendrycks_test/professional_law
+- 233 hendrycks_test/world_religions
+- 234 hendrycks_test/professional_psychology
+- 235 hendrycks_test/public_relations
+- 236 hendrycks_test/security_studies
+- 237 hendrycks_test/sociology
+- 238 hendrycks_test/us_foreign_policy
+- 239 hendrycks_test/virology
+- 240 hendrycks_test/miscellaneous
+- 241 hendrycks_test/professional_medicine
+- 242 hendrycks_test/medical_genetics
+- 243 hendrycks_test/college_mathematics
+- 244 hendrycks_test/management
+- 245 hendrycks_test/high_school_computer_science
+- 246 hendrycks_test/astronomy
+- 247 hendrycks_test/high_school_chemistry
+- 248 hendrycks_test/high_school_biology
+- 249 hendrycks_test/global_facts
+- 250 hendrycks_test/formal_logic
+- 251 hendrycks_test/elementary_mathematics
+- 252 hendrycks_test/high_school_european_history
+- 253 hendrycks_test/electrical_engineering
+- 254 hendrycks_test/conceptual_physics
+- 255 hendrycks_test/computer_security
+- 256 hendrycks_test/college_physics
+- 257 hendrycks_test/college_medicine
+- 258 hendrycks_test/college_computer_science
+- 259 hendrycks_test/college_chemistry
+- 260 hendrycks_test/college_biology
+- 261 hendrycks_test/econometrics
+- 262 hendrycks_test/clinical_knowledge
+- 263 hendrycks_test/anatomy
+- 264 hendrycks_test/marketing
+- 265 hendrycks_test/machine_learning
+- 266 hendrycks_test/logical_fallacies
+- 267 hendrycks_test/jurisprudence
+- 268 hendrycks_test/international_law
+- 269 hendrycks_test/human_sexuality
+- 270 hendrycks_test/human_aging
+- 271 hendrycks_test/high_school_world_history
+- 272 hendrycks_test/abstract_algebra
+- 273 hendrycks_test/high_school_us_history
+- 274 hendrycks_test/high_school_psychology
+- 275 hendrycks_test/high_school_physics
+- 276 hendrycks_test/high_school_microeconomics
+- 277 hendrycks_test/high_school_mathematics
+- 278 hendrycks_test/high_school_macroeconomics
+- 279 hendrycks_test/high_school_government_and_politics
+- 280 hendrycks_test/high_school_geography
+- 281 hendrycks_test/high_school_statistics
+- 282 hendrycks_test/business_ethics
+- 283 winogrande/winogrande_xl
+- 284 codah/codah
+- 285 ai2_arc/ARC-Challenge/challenge
+- 286 ai2_arc/ARC-Easy/challenge
+- 287 definite_pronoun_resolution
+- 288 swag
+- 289 math_qa
+- 290 utilitarianism
+- 291 TuringBench
+- 292 trec
+- 293 vitaminc/tals--vitaminc
+- 294 hope_edi/english
+- 295 rumoureval_2019/RumourEval2019
+- 296 ethos/binary
+- 297 ethos/multilabel
+- 298 glue/cola
+- 299 glue/sst2
+- 300 glue/mrpc
+- 301 glue/qqp
+- 302 glue/stsb
+- 303 glue/mnli
+- 304 glue/qnli
+- 305 glue/rte
+- 306 glue/wnli
+- 307 super_glue/boolq
+- 308 super_glue/cb
+- 309 super_glue/multirc
+- 310 super_glue/wic
+- 311 super_glue/axg
+- 312 tweet_eval/stance_feminist
+- 313 tweet_eval/stance_atheism
+- 314 tweet_eval/stance_hillary
+- 315 tweet_eval/stance_abortion
+- 316 tweet_eval/sentiment
+- 317 tweet_eval/offensive
+- 318 tweet_eval/stance_climate
+- 319 tweet_eval/irony
+- 320 tweet_eval/emotion
+- 321 tweet_eval/emoji
+- 322 tweet_eval/hate
+- 323 discovery/discovery
+- 324 pragmeval/switchboard
+- 325 pragmeval/squinky-informativeness
+- 326 pragmeval/emobank-arousal
+- 327 pragmeval/emobank-dominance
+- 328 pragmeval/emobank-valence
+- 329 pragmeval/mrda
+- 330 pragmeval/verifiability
+- 331 pragmeval/squinky-implicature
+- 332 pragmeval/squinky-formality
+- 333 pragmeval/gum
+- 334 pragmeval/emergent
+- 335 pragmeval/persuasiveness-premisetype
+- 336 pragmeval/pdtb
+- 337 pragmeval/persuasiveness-eloquence
+- 338 pragmeval/persuasiveness-specificity
+- 339 pragmeval/persuasiveness-strength
+- 340 pragmeval/sarcasm
+- 341 pragmeval/stac
+- 342 pragmeval/persuasiveness-claimtype
+- 343 pragmeval/persuasiveness-relevance
+- 344 lex_glue/eurlex
+- 345 lex_glue/scotus
+- 346 lex_glue/ledgar
+- 347 lex_glue/unfair_tos
+- 348 lex_glue/case_hold
+- 349 imdb
+- 350 rotten_tomatoes
+- 351 ag_news
+- 352 yelp_review_full/yelp_review_full
+- 353 financial_phrasebank/sentences_allagree
+- 354 poem_sentiment
+- 355 dbpedia_14/dbpedia_14
+- 356 amazon_polarity/amazon_polarity
+- 357 app_reviews
+- 358 hate_speech18
+- 359 sms_spam
+- 360 humicroedit/subtask-1
+- 361 humicroedit/subtask-2
+- 362 snips_built_in_intents
+- 363 banking77
+- 364 hate_speech_offensive
+- 365 hyperpartisan_news_detection/byarticle
+- 366 hyperpartisan_news_detection/bypublisher
+- 367 go_emotions/simplified
+- 368 scicite
+- 369 liar
+- 370 lexical_relation_classification/ROOT09
+- 371 lexical_relation_classification/EVALution
+- 372 lexical_relation_classification/CogALexV
+- 373 lexical_relation_classification/BLESS
+- 374 lexical_relation_classification/K&H+N
+- 375 linguisticprobing/coordination_inversion
+- 376 linguisticprobing/odd_man_out
+- 377 linguisticprobing/word_content
+- 378 linguisticprobing/obj_number
+- 379 linguisticprobing/past_present
+- 380 linguisticprobing/tree_depth
+- 381 linguisticprobing/sentence_length
+- 382 linguisticprobing/top_constituents
+- 383 linguisticprobing/bigram_shift
+- 384 linguisticprobing/subj_number
+- 385 crowdflower/sentiment_nuclear_power
+- 386 crowdflower/tweet_global_warming
+- 387 crowdflower/airline-sentiment
+- 388 crowdflower/economic-news
+- 389 crowdflower/political-media-audience
+- 390 crowdflower/political-media-bias
+- 391 crowdflower/political-media-message
+- 392 crowdflower/text_emotion
+- 393 crowdflower/corporate-messaging
+- 394 ethics/commonsense
+- 395 ethics/deontology
+- 396 ethics/justice
+- 397 ethics/virtue
+- 398 emo/emo2019
+- 399 google_wellformed_query
+- 400 tweets_hate_speech_detection
+- 401 adv_glue/adv_sst2
+- 402 adv_glue/adv_qqp
+- 403 adv_glue/adv_mnli
+- 404 adv_glue/adv_mnli_mismatched
+- 405 adv_glue/adv_qnli
+- 406 adv_glue/adv_rte
+- 407 has_part
+- 408 wnut_17/wnut_17
+- 409 ncbi_disease/ncbi_disease
+- 410 acronym_identification
+- 411 jnlpba/jnlpba
+- 412 species_800/species_800
+- 413 ontonotes_english/SpeedOfMagic--ontonotes_english
+- 414 blog_authorship_corpus/gender
+- 415 blog_authorship_corpus/age
+- 416 blog_authorship_corpus/horoscope
+- 417 blog_authorship_corpus/job
+- 418 open_question_type
+- 419 health_fact
+- 420 commonsense_qa
+- 421 mc_taco
+- 422 ade_corpus_v2/Ade_corpus_v2_classification
+- 423 discosense
+- 424 circa
+- 425 code_x_glue_cc_defect_detection
+- 426 code_x_glue_cc_clone_detection_big_clone_bench
+- 427 code_x_glue_cc_code_refinement/medium
+- 428 EffectiveFeedbackStudentWriting
+- 429 promptSentiment
+- 430 promptNLI
+- 431 promptSpoke
+- 432 promptProficiency
+- 433 promptGrammar
+- 434 promptCoherence
+- 435 phrase_similarity
+- 436 scientific-exaggeration-detection
+- 437 quarel
+- 438 fever-evidence-related/mwong--fever-related
+- 439 numer_sense
+- 440 dynasent/dynabench.dynasent.r1.all/r1
+- 441 dynasent/dynabench.dynasent.r2.all/r2
+- 442 Sarcasm_News_Headline
+- 443 sem_eval_2010_task_8