{"id":"beam-published-2026-04-24","dataset":{"name":"Mohammadta/BEAM","conversations":10,"questions":100,"turns":500},"run":{"started_at":null,"ended_at":"2026-04-24T00:00:00.000Z","model":null,"strategy":null,"context_mode":null},"metrics":{"memcone_prompt_tokens_avg":473.9,"replay_prompt_tokens_avg":23886.5,"memcone_memory_tokens_avg":449.4,"replay_memory_tokens_avg":26750.1,"memcone_context_latency_ms_avg":614,"memcone_model_latency_ms_avg":1458,"replay_model_latency_ms_avg":3011,"remember_latency_ms_avg":4798,"memcone_units_delta":null,"memcone_cache_hits":null,"memcone_cache_misses":null,"judge":{"judge_model":"BEAM-aligned rubric","predictions_judged":100,"by_strategy":{"memcone":{"overall_accuracy":0.39,"questions_judged":100,"categories":{"abstention":0.85,"contradiction_resolution":0.2,"event_ordering":0.189,"information_extraction":0.425,"instruction_following":0.287}},"replay":{"overall_accuracy":0.53,"questions_judged":100,"categories":{"abstention":0.8,"contradiction_resolution":0.175,"event_ordering":0.191,"information_extraction":0.858,"instruction_following":0.625}}}}},"artifacts":{"summary_json":null,"predictions_jsonl":null,"remember_stats_jsonl":null}}