Slayer1B-Benchmarks / contamination_field_roles.json
Maggio33's picture
Benchmarks: first results bench50-v0.3.1 (results 1cf2b8bb, page b71d0c71)
2d3d73f verified
Raw History Blame Contribute Delete
18.2 kB
{
"release": "bench50-v0.3.1",
"kind": "contamination_field_roles",
"scan": {
"receipt_sha256": "bc6c168cf6ef35bce80b70f3bf582853526b558cb7f37e30101e35f3c2342de7",
"benchmarks_section_sha256_prefix": "8be608af",
"scanner_sha256": "685fa9ef1fbd6e9a680be53da7fd7d943e3c1f2cde6ef69b24271027df74dad2"
},
"rule": {
"context": "a supporting document shown to the model but separate from the question and the answer (passage, context, story, article, support)",
"answer_bearing": "the question, the options, the gold answer or its explanation, or the scored text itself (items with no separate document: minimal pairs, sentence classification, continuation, perplexity pages)",
"metadata": "annotation tags that are not shown to the model as text; hits are ignored in every variant and listed with counts",
"variant_a": "items with no hit in any context or answer_bearing field",
"variant_b": "items with no hit in any answer_bearing field",
"extractive_qa": "answer span fields are answer_bearing even where the span is copied from the passage (SQuAD2, PoQuAD, CoQA, DROP): variant (b) is strict there and the report says so",
"assigned": "from the meaning of each field in the pinned task definition, before any variant value was computed"
},
"justification": {
"extractive_qa": "An answer span copied from the passage is still the gold answer; one rule for every task type is preferred to a type-dependent exception, so variant (b) is stricter for extractive QA and the report says so.",
"scored_text": "Where a benchmark has no separate document, the scored text is the item itself, so a hit there is a hit on the answer.",
"metadata": "Morphological tags are not shown to the model as text; their hits are exact-short matches of tag strings and do not indicate exposure."
},
"counts": {
"context": 12,
"answer_bearing": 93,
"metadata": 2
},
"roles": [
{
"task_id": "T44",
"benchmark_id": "pubmedqa",
"field": "CONTEXTS[]",
"hit_items": 4,
"role": "context"
},
{
"task_id": "T44",
"benchmark_id": "pubmedqa",
"field": "LONG_ANSWER",
"hit_items": 1,
"role": "answer_bearing"
},
{
"task_id": "T19",
"benchmark_id": "mathqa",
"field": "Problem",
"hit_items": 74,
"role": "answer_bearing"
},
{
"task_id": "T44",
"benchmark_id": "pubmedqa",
"field": "QUESTION",
"hit_items": 2,
"role": "answer_bearing"
},
{
"task_id": "T19",
"benchmark_id": "mathqa",
"field": "Rationale",
"hit_items": 14,
"role": "answer_bearing"
},
{
"task_id": "T28",
"benchmark_id": "cbd",
"field": "TEXT",
"hit_items": 26,
"role": "answer_bearing"
},
{
"task_id": "T41",
"benchmark_id": "coqa",
"field": "additional_answers.0.input_text[]",
"hit_items": 10,
"role": "answer_bearing"
},
{
"task_id": "T41",
"benchmark_id": "coqa",
"field": "additional_answers.0.span_text[]",
"hit_items": 39,
"role": "answer_bearing"
},
{
"task_id": "T41",
"benchmark_id": "coqa",
"field": "additional_answers.1.input_text[]",
"hit_items": 7,
"role": "answer_bearing"
},
{
"task_id": "T41",
"benchmark_id": "coqa",
"field": "additional_answers.1.span_text[]",
"hit_items": 28,
"role": "answer_bearing"
},
{
"task_id": "T41",
"benchmark_id": "coqa",
"field": "additional_answers.2.input_text[]",
"hit_items": 6,
"role": "answer_bearing"
},
{
"task_id": "T41",
"benchmark_id": "coqa",
"field": "additional_answers.2.span_text[]",
"hit_items": 22,
"role": "answer_bearing"
},
{
"task_id": "T25",
"benchmark_id": "dyk",
"field": "answer",
"hit_items": 799,
"role": "answer_bearing"
},
{
"task_id": "T43",
"benchmark_id": "triviaqa",
"field": "answer.aliases[]",
"hit_items": 1137,
"role": "answer_bearing"
},
{
"task_id": "T43",
"benchmark_id": "triviaqa",
"field": "answer.normalized_aliases[]",
"hit_items": 776,
"role": "answer_bearing"
},
{
"task_id": "T43",
"benchmark_id": "triviaqa",
"field": "answer.normalized_value",
"hit_items": 28,
"role": "answer_bearing"
},
{
"task_id": "T43",
"benchmark_id": "triviaqa",
"field": "answer.value",
"hit_items": 62,
"role": "answer_bearing"
},
{
"task_id": "T46",
"benchmark_id": "social_iqa",
"field": "answerA",
"hit_items": 2,
"role": "answer_bearing"
},
{
"task_id": "T46",
"benchmark_id": "social_iqa",
"field": "answerB",
"hit_items": 4,
"role": "answer_bearing"
},
{
"task_id": "T42",
"benchmark_id": "nq_open",
"field": "answer[]",
"hit_items": 64,
"role": "answer_bearing"
},
{
"task_id": "T41",
"benchmark_id": "coqa",
"field": "answers.input_text[]",
"hit_items": 4,
"role": "answer_bearing"
},
{
"task_id": "T41",
"benchmark_id": "coqa",
"field": "answers.span_text[]",
"hit_items": 36,
"role": "answer_bearing"
},
{
"task_id": "T31",
"benchmark_id": "poquad",
"field": "answers.text[]",
"hit_items": 731,
"role": "answer_bearing"
},
{
"task_id": "T38",
"benchmark_id": "squad2",
"field": "answers.text[]",
"hit_items": 34,
"role": "answer_bearing"
},
{
"task_id": "T30",
"benchmark_id": "polqa",
"field": "answers[]",
"hit_items": 2,
"role": "answer_bearing"
},
{
"task_id": "T37",
"benchmark_id": "llmzszl",
"field": "answers[]",
"hit_items": 555,
"role": "answer_bearing"
},
{
"task_id": "T40",
"benchmark_id": "race",
"field": "article",
"hit_items": 75,
"role": "context"
},
{
"task_id": "T04",
"benchmark_id": "multiblimp",
"field": "attractors[].xpos",
"hit_items": 3,
"role": "metadata"
},
{
"task_id": "T11",
"benchmark_id": "copa",
"field": "choice1",
"hit_items": 6,
"role": "answer_bearing"
},
{
"task_id": "T11",
"benchmark_id": "copa",
"field": "choice2",
"hit_items": 11,
"role": "answer_bearing"
},
{
"task_id": "T02",
"benchmark_id": "arc",
"field": "choices.text[]",
"hit_items": 33,
"role": "answer_bearing"
},
{
"task_id": "T08",
"benchmark_id": "openbookqa",
"field": "choices.text[]",
"hit_items": 48,
"role": "answer_bearing"
},
{
"task_id": "T32",
"benchmark_id": "mmlu",
"field": "choices[]",
"hit_items": 257,
"role": "answer_bearing"
},
{
"task_id": "T04",
"benchmark_id": "multiblimp",
"field": "congruent_attractors[].xpos",
"hit_items": 3,
"role": "metadata"
},
{
"task_id": "T31",
"benchmark_id": "poquad",
"field": "context",
"hit_items": 5764,
"role": "context"
},
{
"task_id": "T38",
"benchmark_id": "squad2",
"field": "context",
"hit_items": 3097,
"role": "context"
},
{
"task_id": "T05",
"benchmark_id": "hellaswag",
"field": "ctx",
"hit_items": 21,
"role": "answer_bearing"
},
{
"task_id": "T05",
"benchmark_id": "hellaswag",
"field": "ctx_a",
"hit_items": 22,
"role": "answer_bearing"
},
{
"task_id": "T05",
"benchmark_id": "hellaswag",
"field": "endings[]",
"hit_items": 28,
"role": "answer_bearing"
},
{
"task_id": "T45",
"benchmark_id": "medmcqa",
"field": "exp",
"hit_items": 33,
"role": "answer_bearing"
},
{
"task_id": "T27",
"benchmark_id": "psc",
"field": "extract_text",
"hit_items": 2,
"role": "answer_bearing"
},
{
"task_id": "T06",
"benchmark_id": "piqa",
"field": "goal",
"hit_items": 11,
"role": "answer_bearing"
},
{
"task_id": "T15",
"benchmark_id": "rte",
"field": "hypothesis",
"hit_items": 1,
"role": "answer_bearing"
},
{
"task_id": "T47",
"benchmark_id": "bbh",
"field": "input",
"hit_items": 22,
"role": "answer_bearing"
},
{
"task_id": "T35",
"benchmark_id": "truthfulqa",
"field": "mc1_targets.choices[]",
"hit_items": 35,
"role": "answer_bearing"
},
{
"task_id": "T35",
"benchmark_id": "truthfulqa",
"field": "mc2_targets.choices[]",
"hit_items": 48,
"role": "answer_bearing"
},
{
"task_id": "T04",
"benchmark_id": "multiblimp",
"field": "metadata.text",
"hit_items": 164,
"role": "answer_bearing"
},
{
"task_id": "T45",
"benchmark_id": "medmcqa",
"field": "opa",
"hit_items": 46,
"role": "answer_bearing"
},
{
"task_id": "T45",
"benchmark_id": "medmcqa",
"field": "opb",
"hit_items": 41,
"role": "answer_bearing"
},
{
"task_id": "T45",
"benchmark_id": "medmcqa",
"field": "opc",
"hit_items": 38,
"role": "answer_bearing"
},
{
"task_id": "T45",
"benchmark_id": "medmcqa",
"field": "opd",
"hit_items": 85,
"role": "answer_bearing"
},
{
"task_id": "T19",
"benchmark_id": "mathqa",
"field": "options",
"hit_items": 5,
"role": "answer_bearing"
},
{
"task_id": "T03",
"benchmark_id": "wikitext2",
"field": "page",
"hit_items": 21,
"role": "answer_bearing"
},
{
"task_id": "T10",
"benchmark_id": "boolq",
"field": "passage",
"hit_items": 637,
"role": "context"
},
{
"task_id": "T39",
"benchmark_id": "drop",
"field": "passage",
"hit_items": 2327,
"role": "context"
},
{
"task_id": "T50",
"benchmark_id": "record",
"field": "passage",
"hit_items": 189,
"role": "context"
},
{
"task_id": "T30",
"benchmark_id": "polqa",
"field": "passage_text",
"hit_items": 12667,
"role": "context"
},
{
"task_id": "T30",
"benchmark_id": "polqa",
"field": "passage_title",
"hit_items": 19,
"role": "context"
},
{
"task_id": "T30",
"benchmark_id": "polqa",
"field": "passage_wiki",
"hit_items": 13050,
"role": "context"
},
{
"task_id": "T04",
"benchmark_id": "multiblimp",
"field": "prefix",
"hit_items": 41,
"role": "answer_bearing"
},
{
"task_id": "T11",
"benchmark_id": "copa",
"field": "premise",
"hit_items": 9,
"role": "answer_bearing"
},
{
"task_id": "T15",
"benchmark_id": "rte",
"field": "premise",
"hit_items": 9,
"role": "answer_bearing"
},
{
"task_id": "T16",
"benchmark_id": "anli",
"field": "premise",
"hit_items": 19,
"role": "answer_bearing"
},
{
"task_id": "T34",
"benchmark_id": "math",
"field": "problem",
"hit_items": 34,
"role": "answer_bearing"
},
{
"task_id": "T40",
"benchmark_id": "race",
"field": "problems[].question",
"hit_items": 1,
"role": "answer_bearing"
},
{
"task_id": "T36",
"benchmark_id": "ifeval",
"field": "prompt",
"hit_items": 2,
"role": "answer_bearing"
},
{
"task_id": "T50",
"benchmark_id": "record",
"field": "query",
"hit_items": 36,
"role": "answer_bearing"
},
{
"task_id": "T02",
"benchmark_id": "arc",
"field": "question",
"hit_items": 15,
"role": "answer_bearing"
},
{
"task_id": "T09",
"benchmark_id": "sciq",
"field": "question",
"hit_items": 15,
"role": "answer_bearing"
},
{
"task_id": "T10",
"benchmark_id": "boolq",
"field": "question",
"hit_items": 1,
"role": "answer_bearing"
},
{
"task_id": "T30",
"benchmark_id": "polqa",
"field": "question",
"hit_items": 20,
"role": "answer_bearing"
},
{
"task_id": "T31",
"benchmark_id": "poquad",
"field": "question",
"hit_items": 563,
"role": "answer_bearing"
},
{
"task_id": "T32",
"benchmark_id": "mmlu",
"field": "question",
"hit_items": 405,
"role": "answer_bearing"
},
{
"task_id": "T35",
"benchmark_id": "truthfulqa",
"field": "question",
"hit_items": 16,
"role": "answer_bearing"
},
{
"task_id": "T37",
"benchmark_id": "llmzszl",
"field": "question",
"hit_items": 235,
"role": "answer_bearing"
},
{
"task_id": "T38",
"benchmark_id": "squad2",
"field": "question",
"hit_items": 9,
"role": "answer_bearing"
},
{
"task_id": "T39",
"benchmark_id": "drop",
"field": "question",
"hit_items": 4,
"role": "answer_bearing"
},
{
"task_id": "T42",
"benchmark_id": "nq_open",
"field": "question",
"hit_items": 13,
"role": "answer_bearing"
},
{
"task_id": "T43",
"benchmark_id": "triviaqa",
"field": "question",
"hit_items": 161,
"role": "answer_bearing"
},
{
"task_id": "T45",
"benchmark_id": "medmcqa",
"field": "question",
"hit_items": 34,
"role": "answer_bearing"
},
{
"task_id": "T46",
"benchmark_id": "social_iqa",
"field": "question",
"hit_items": 3,
"role": "answer_bearing"
},
{
"task_id": "T08",
"benchmark_id": "openbookqa",
"field": "question_stem",
"hit_items": 26,
"role": "answer_bearing"
},
{
"task_id": "T41",
"benchmark_id": "coqa",
"field": "questions.input_text[]",
"hit_items": 1,
"role": "answer_bearing"
},
{
"task_id": "T04",
"benchmark_id": "multiblimp",
"field": "sen",
"hit_items": 162,
"role": "answer_bearing"
},
{
"task_id": "T21",
"benchmark_id": "sst2",
"field": "sentence",
"hit_items": 6,
"role": "answer_bearing"
},
{
"task_id": "T22",
"benchmark_id": "polemo2",
"field": "sentence",
"hit_items": 27,
"role": "answer_bearing"
},
{
"task_id": "T23",
"benchmark_id": "8tags",
"field": "sentence",
"hit_items": 243,
"role": "answer_bearing"
},
{
"task_id": "T29",
"benchmark_id": "klej_ner",
"field": "sentence",
"hit_items": 138,
"role": "answer_bearing"
},
{
"task_id": "T49",
"benchmark_id": "cola",
"field": "sentence",
"hit_items": 44,
"role": "answer_bearing"
},
{
"task_id": "T13",
"benchmark_id": "wic",
"field": "sentence1",
"hit_items": 156,
"role": "answer_bearing"
},
{
"task_id": "T48",
"benchmark_id": "paws",
"field": "sentence1",
"hit_items": 14,
"role": "answer_bearing"
},
{
"task_id": "T13",
"benchmark_id": "wic",
"field": "sentence2",
"hit_items": 168,
"role": "answer_bearing"
},
{
"task_id": "T48",
"benchmark_id": "paws",
"field": "sentence2",
"hit_items": 16,
"role": "answer_bearing"
},
{
"task_id": "T26",
"benchmark_id": "ppc",
"field": "sentence_A",
"hit_items": 223,
"role": "answer_bearing"
},
{
"task_id": "T26",
"benchmark_id": "ppc",
"field": "sentence_B",
"hit_items": 185,
"role": "answer_bearing"
},
{
"task_id": "T01",
"benchmark_id": "blimp",
"field": "sentence_bad",
"hit_items": 138,
"role": "answer_bearing"
},
{
"task_id": "T01",
"benchmark_id": "blimp",
"field": "sentence_good",
"hit_items": 226,
"role": "answer_bearing"
},
{
"task_id": "T06",
"benchmark_id": "piqa",
"field": "sol1",
"hit_items": 48,
"role": "answer_bearing"
},
{
"task_id": "T06",
"benchmark_id": "piqa",
"field": "sol2",
"hit_items": 40,
"role": "answer_bearing"
},
{
"task_id": "T34",
"benchmark_id": "math",
"field": "solution",
"hit_items": 42,
"role": "answer_bearing"
},
{
"task_id": "T41",
"benchmark_id": "coqa",
"field": "story",
"hit_items": 67,
"role": "context"
},
{
"task_id": "T27",
"benchmark_id": "psc",
"field": "summary_text",
"hit_items": 5,
"role": "answer_bearing"
},
{
"task_id": "T09",
"benchmark_id": "sciq",
"field": "support",
"hit_items": 79,
"role": "context"
},
{
"task_id": "T14",
"benchmark_id": "wsc273",
"field": "text",
"hit_items": 4,
"role": "answer_bearing"
},
{
"task_id": "T17",
"benchmark_id": "lambada",
"field": "text",
"hit_items": 1,
"role": "answer_bearing"
},
{
"task_id": "T39",
"benchmark_id": "drop",
"field": "validated_answers.spans[][]",
"hit_items": 3,
"role": "answer_bearing"
},
{
"task_id": "T04",
"benchmark_id": "multiblimp",
"field": "wrong_sen",
"hit_items": 58,
"role": "answer_bearing"
}
]
}