43 lines
1.2 KiB
JSON
43 lines
1.2 KiB
JSON
{
|
|
"dataset_version": "a8a99545d77a236e3c7aa1f5d0ccfd94d4bcc5c2d5adbd19f938aba844586c56",
|
|
"instance_count": 500,
|
|
"variant": "s",
|
|
"built_at": "2026-06-04T17:25:36.563Z",
|
|
"source": "https://huggingface.co/datasets/xiaowu0162/longmemeval-cleaned/resolve/main/longmemeval_s_cleaned.json",
|
|
"source_reference": "Wu et al. 2024, \"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory\" (arXiv:2410.10813)",
|
|
"hf_repo": "xiaowu0162/longmemeval-cleaned",
|
|
"canonicalisation": {
|
|
"abstention_included": true,
|
|
"no_sessions_excluded": true,
|
|
"sort_order": "instance_id ascending",
|
|
"field_order": [
|
|
"instance_id",
|
|
"conversation_id",
|
|
"question",
|
|
"expected",
|
|
"context",
|
|
"question_type",
|
|
"is_abstention"
|
|
],
|
|
"line_terminator": "\\n",
|
|
"trailing_newline": true,
|
|
"encoding": "utf-8",
|
|
"no_bom": true
|
|
},
|
|
"distribution_by_question_type": {
|
|
"single-session-user": 70,
|
|
"single-session-assistant": 56,
|
|
"single-session-preference": 30,
|
|
"temporal-reasoning": 133,
|
|
"knowledge-update": 78,
|
|
"multi-session": 133
|
|
},
|
|
"abstention_count": 30,
|
|
"skip_stats": {
|
|
"missingFields": 0,
|
|
"noSessions": 0
|
|
},
|
|
"expected_count": 500,
|
|
"count_matches_expected": true
|
|
}
|