03a37c4b01
Phase 1.1a~1.3 / Phase 2.1~2.3 평가셋 측정 결과 + regression baseline + D9 STT 후속 VRAM 피크 관측 데이터. project_search_v2 메모리에 Phase 2 평가셋 v0.2 baseline용 보존 명시.
4.4 KiB
4.4 KiB
| 1 | label | id | category | intent | domain_hint | query | relevant_ids | returned_ids_top10 | latency_ms | recall_at_10 | mrr_at_10 | ndcg_at_10 | top3_hit | error |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | single | kw_001 | exact_keyword | fact_lookup | document | 산업안전보건법 제6장 | 3856;3868;3879 | 3856;3851;3862;3853;3861;3868;3879;3873;3876;3871 | 207.7 | 1.000 | 1.000 | 0.793 | 1 | |
| 3 | single | kw_002 | exact_keyword | fact_lookup | document | 중대재해 처벌 등에 관한 법률 제2장 중대산업재해 | 3917;3921 | 3917;3921;3923;3922;3918;3916;3919;3920;3874;3854 | 323.1 | 1.000 | 1.000 | 1.000 | 1 | |
| 4 | single | kw_003 | exact_keyword | fact_lookup | document | 화학물질관리법 유해화학물질 영업자 | 3981 | 3981;3980;3985;3978;3983;3984;3979;3857;3880;3993 | 155.9 | 1.000 | 1.000 | 1.000 | 1 | |
| 5 | single | kw_004 | exact_keyword | fact_lookup | document | 근로기준법 안전과 보건 | 4041 | 4041;3851;4042;3858;4044;3852;4043;4040;3881;4038 | 188.8 | 1.000 | 1.000 | 1.000 | 1 | |
| 6 | single | kw_005 | exact_keyword | fact_lookup | document | 산업안전보건기준에 관한 규칙 보호구 | 3888 | 3888;3885;3910;3897;3890;3894;3908;3909;3892;3901 | 260.7 | 1.000 | 1.000 | 1.000 | 1 | |
| 7 | single | nl_001 | natural_language_ko | semantic_search | document | 기계로 인한 산업재해 관련 법령 | 3856;3868;3879;3854 | 3897;3878;3856;3879;5249;3868;3851;3895;5244;3874 | 207.9 | 0.750 | 0.333 | 0.502 | 1 | |
| 8 | single | nl_002 | natural_language_ko | semantic_search | document | 사업주가 도급을 줄 때 산업재해를 예방하기 위해 해야 할 일 | 3855;3867;3878 | 3855;3917;3867;3878;5227;3854;5244;3896;3903;3895 | 315.7 | 1.000 | 1.000 | 0.906 | 1 | |
| 9 | single | nl_003 | natural_language_ko | semantic_search | document | 유해화학물질을 다루는 회사가 지켜야 할 안전 의무 | 3980;3981;3982 | 3980;3985;5253;3917;5227;3903;3855;3760;3904;3880 | 313.3 | 0.333 | 1.000 | 0.469 | 1 | |
| 10 | single | nl_004 | natural_language_ko | semantic_search | document | 중대재해가 발생했을 때 경영책임자가 처벌받는 기준 | 3916;3917;3920;3921 | 3917;3918;3854;3916;3877;3921;5244;3919;3923;3922 | 317.5 | 0.750 | 1.000 | 0.698 | 1 | |
| 11 | single | nl_005 | natural_language_ko | semantic_search | document | 안전보건교육은 누가 받아야 하고 어떤 내용을 다루는가 | 3853;3865 | 3853;3876;5249;3811;4025;3778;3810;3757;3787;5234 | 310.8 | 0.500 | 1.000 | 0.613 | 1 | |
| 12 | single | cl_001 | crosslingual_ko_en | semantic_search | document | 기계 안전 가드 설계 원리 | 3770;3856 | 5253;5244;3817;3791;3770;4540;3758;4548;3774;3787 | 205.5 | 0.500 | 0.200 | 0.237 | 0 | |
| 13 | single | cl_002 | crosslingual_ko_en | semantic_search | document | 산업 안전 입문서 | 3755;3775;3776;3777 | 5249;3755;5230;3817;3802;3807;3819;3774;3787;3815 | 178.6 | 0.250 | 0.500 | 0.246 | 1 | |
| 14 | single | cl_003 | crosslingual_ko_en | semantic_search | document | 전기 안전 위험 | 3772;3790 | 3790;3897;5260;3772;3775;5233;5248;5230;3771;5236 | 342.5 | 1.000 | 1.000 | 0.877 | 1 | |
| 15 | single | news_001 | news_ko | semantic_search | news | 이란과 미국의 군사 충돌 | 4303;4304;4307;4316;4322;4323;4327;4335 | 6660;4307;7809;4452;4317;4331;4339;4321;4650;4418 | 187.6 | 0.125 | 0.500 | 0.160 | 1 | |
| 16 | single | news_002 | news_ko | semantic_search | news | 호르무즈 해협 봉쇄 | 4316;4320;4322;4327 | 4346;4320;7808;4349;4767;6774;6802;4759;6067;6796 | 173.1 | 0.250 | 0.500 | 0.246 | 0 | |
| 17 | single | news_003 | news_en | semantic_search | news | Trump Iran ultimatum | 4258;4260;4262 | 4776;4519;4679;4258;4775;8777;7444;4202;4668;7417 | 324.5 | 0.333 | 0.250 | 0.202 | 1 | |
| 18 | single | news_004 | news_fr | semantic_search | news | guerre en Iran | 4199;4202;4210;4361;4363;4507;4519;4521 | 4776;4199;4507;4688;5840;8404;6945;4519;5398;6996 | 175.7 | 0.375 | 0.500 | 0.366 | 1 | |
| 19 | single | news_005 | news_crosslingual | semantic_search | news | 이란 미국 전쟁 글로벌 반응 | 4202;4258;4262;4536;4303;4304;4316 | 4457;4452;4307;4765;5307;4329;7780;4324;6789;4345 | 218.9 | 0.000 | 0.000 | 0.000 | 1 | |
| 20 | single | misc_001 | other_domain | fact_lookup | document | 강체의 평면 운동학 | 4063;4065 | 4063;4071;4065;4064;4066;4058;4067;4069;4068;5105 | 244.8 | 1.000 | 1.000 | 0.920 | 1 | |
| 21 | single | misc_002 | other_domain | semantic_search | document | 질점의 운동역학 | 4060;4061;4062 | 4062;4060;4061;4070;4059;4058;4064;4068;4065;4066 | 284.3 | 1.000 | 1.000 | 1.000 | 1 | |
| 22 | single | fail_001 | failure_expected | semantic_search | document | Rust async runtime tokio scheduler 내부 구조 | 3810;3774;5262;4547;5161;5174;5180;4546;5206;5186 | 343.8 | 0.000 | 0.000 | 0.000 | 1 | ||
| 23 | single | fail_002 | failure_expected | semantic_search | document | 양자컴퓨터 큐비트 디코히어런스 | 5092;5173;5118;5066;5091;5070;5115;3795;5250;5168 | 145.5 | 0.000 | 0.000 | 0.000 | 1 | ||
| 24 | single | fail_003 | failure_expected | semantic_search | news | 재즈 보컬리스트 빌리 홀리데이 | 4675;4634;4281;4289;4205;4116;4697;4100;5152;5738 | 147.4 | 0.000 | 0.000 | 0.000 | 1 |