hyungi
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;3873;3863;3876;3871;3859 | 158.2 | 0.333 | 1.000 | 0.469 | 1 | |
| 3 | single | kw_002 | exact_keyword | fact_lookup | document | 중대재해 처벌 등에 관한 법률 제2장 중대산업재해 | 3917;3921 | 3917;3921;3919;3923;3916;3918;3920;3922;3995;4002 | 172.5 | 1.000 | 1.000 | 1.000 | 1 | |
| 4 | single | kw_003 | exact_keyword | fact_lookup | document | 화학물질관리법 유해화학물질 영업자 | 3981 | 3981;3980;3985;3979;3978;3983;3857;3903;3904;3984 | 137.3 | 1.000 | 1.000 | 1.000 | 1 | |
| 5 | single | kw_004 | exact_keyword | fact_lookup | document | 근로기준법 안전과 보건 | 4041 | 4041;3851;4042;3852;4044;3905;4043;4040;3853;4038 | 118.6 | 1.000 | 1.000 | 1.000 | 1 | |
| 6 | single | kw_005 | exact_keyword | fact_lookup | document | 산업안전보건기준에 관한 규칙 보호구 | 3888 | 3901;3910;3898;3891;3908;3911;3909;3888;3885;3892 | 145.5 | 1.000 | 0.125 | 0.315 | 0 | |
| 7 | single | nl_001 | natural_language_ko | semantic_search | document | 기계로 인한 산업재해 관련 법령 | 3856;3868;3879;3854 | 3895;3855;3863;3782;3785;3922;3985;3791;3880;3805 | 115.6 | 0.000 | 0.000 | 0.000 | 0 | |
| 8 | single | nl_002 | natural_language_ko | semantic_search | document | 사업주가 도급을 줄 때 산업재해를 예방하기 위해 해야 할 일 | 3855;3867;3878 | 3855;3896;3903;3898;3863;3902;3895;3890;3904;3886 | 134.3 | 0.333 | 1.000 | 0.469 | 1 | |
| 9 | single | nl_003 | natural_language_ko | semantic_search | document | 유해화학물질을 다루는 회사가 지켜야 할 안전 의무 | 3980;3981;3982 | 3896;3903;3909;3895;3904;3879;3851;3985;3857;3855 | 119.7 | 0.000 | 0.000 | 0.000 | 1 | |
| 10 | single | nl_004 | natural_language_ko | semantic_search | document | 중대재해가 발생했을 때 경영책임자가 처벌받는 기준 | 3916;3917;3920;3921 | 3773;4025;3802;3810;3797;3815;3968;3875;3793;4061 | 119.3 | 0.000 | 0.000 | 0.000 | 0 | |
| 11 | single | nl_005 | natural_language_ko | semantic_search | document | 안전보건교육은 누가 받아야 하고 어떤 내용을 다루는가 | 3853;3865 | 3787;3863;3817;3811;3767;3815;3793;3757;3792;3814 | 121.3 | 0.000 | 0.000 | 0.000 | 0 | |
| 12 | single | cl_001 | crosslingual_ko_en | semantic_search | document | 기계 안전 가드 설계 원리 | 3770;3856 | 3770;3791;3762;3773;3789;3855;3895;3793;3763;3856 | 107.7 | 1.000 | 1.000 | 0.790 | 1 | |
| 13 | single | cl_002 | crosslingual_ko_en | semantic_search | document | 산업 안전 입문서 | 3755;3775;3776;3777 | 3911;4025;3851;4026;3912;3886;3906;3985;4040;4060 | 109.7 | 0.000 | 0.000 | 0.000 | 1 | |
| 14 | single | cl_003 | crosslingual_ko_en | semantic_search | document | 전기 안전 위험 | 3772;3790 | 3790;3897;3772;3775;3778;3794;4019;3774;3795;3816 | 129.0 | 1.000 | 1.000 | 0.920 | 1 | |
| 15 | single | news_001 | news_ko | semantic_search | news | 이란과 미국의 군사 충돌 | 4303;4304;4307;4316;4322;4323;4327;4335 | 4321;4307;4744;4642;4333;4304;4447;4769;4647;4318 | 103.9 | 0.250 | 0.500 | 0.250 | 1 | |
| 16 | single | news_002 | news_ko | semantic_search | news | 호르무즈 해협 봉쇄 | 4316;4320;4322;4327 | 4320;4346;4349;4762;4767;4761;4322;4457;4340;4316 | 108.8 | 0.750 | 1.000 | 0.633 | 0 | |
| 17 | single | news_003 | news_en | semantic_search | news | Trump Iran ultimatum | 4258;4260;4262 | 4776;4691;4519;4688;4258;4361;4679;4347;4775;4665 | 106.2 | 0.333 | 0.200 | 0.182 | 1 | |
| 18 | single | news_004 | news_fr | semantic_search | news | guerre en Iran | 4199;4202;4210;4361;4363;4507;4519;4521 | 4776;4199;4507;4321;4688;4769;4363;4202;4521;4642 | 108.2 | 0.625 | 0.500 | 0.526 | 1 | |
| 19 | single | news_005 | news_crosslingual | semantic_search | news | 이란 미국 전쟁 글로벌 반응 | 4202;4258;4262;4536;4303;4304;4316 | 4765;4129;4452;4343;4457;4344;4307;4355;4569;4587 | 108.5 | 0.000 | 0.000 | 0.000 | 1 | |
| 20 | single | misc_001 | other_domain | fact_lookup | document | 강체의 평면 운동학 | 4063;4065 | 4064;4063;4060;4071;4059;4058;3795;4066;3758;4065 | 186.2 | 1.000 | 0.500 | 0.564 | 1 | |
| 21 | single | misc_002 | other_domain | semantic_search | document | 질점의 운동역학 | 4060;4061;4062 | 4060;4064;4059;4062;4058;4061;3758;4070;3783;3795 | 240.8 | 1.000 | 1.000 | 0.839 | 1 | |
| 22 | single | fail_001 | failure_expected | semantic_search | document | Rust async runtime tokio scheduler 내부 구조 | 3810;4546;3767;4547;3793;3779;3819;3802;4062;3817 | 116.3 | 0.000 | 0.000 | 0.000 | 1 | ||
| 23 | single | fail_002 | failure_expected | semantic_search | document | 양자컴퓨터 큐비트 디코히어런스 | 4058;4068;3802;4065;4059;4057;4545;4026;4025;4587 | 108.5 | 0.000 | 0.000 | 0.000 | 1 | ||
| 24 | single | fail_003 | failure_expected | semantic_search | news | 재즈 보컬리스트 빌리 홀리데이 | 4634;4057;3757;3764;4749;3785;3799;4316;3789;3815 | 106.9 | 0.000 | 0.000 | 0.000 | 1 |