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;3853;3851;3862;3861;3868;3873;3879;3876;3871 | 163.4 | 1.000 | 1.000 | 0.784 | 1 | |
| 3 | single | kw_002 | exact_keyword | fact_lookup | document | 중대재해 처벌 등에 관한 법률 제2장 중대산업재해 | 3917;3921 | 3917;3921;3916;3919;3923;3922;3920;3918;4019;3987 | 188.1 | 1.000 | 1.000 | 1.000 | 1 | |
| 4 | single | kw_003 | exact_keyword | fact_lookup | document | 화학물질관리법 유해화학물질 영업자 | 3981 | 3981;3980;3978;3985;3979;3983;3984;3982;3857;3988 | 132.3 | 1.000 | 1.000 | 1.000 | 1 | |
| 5 | single | kw_004 | exact_keyword | fact_lookup | document | 근로기준법 안전과 보건 | 4041 | 4041;4036;3851;4042;3853;4044;3860;4043;3883;4040 | 123.7 | 1.000 | 1.000 | 1.000 | 1 | |
| 6 | single | kw_005 | exact_keyword | fact_lookup | document | 산업안전보건기준에 관한 규칙 보호구 | 3888 | 3888;3885;3901;3890;3886;3910;3893;3894;3908;3909 | 149.1 | 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 | 3868;3856;3879;3895;3915;3872;3851;3867;3897;3863 | 118.7 | 0.750 | 1.000 | 0.832 | 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;3867;3878;3863;3917;3872;3854;3896;3861;3886 | 136.7 | 1.000 | 1.000 | 1.000 | 1 | |
| 9 | single | nl_003 | natural_language_ko | semantic_search | document | 유해화학물질을 다루는 회사가 지켜야 할 안전 의무 | 3980;3981;3982 | 3857;3869;3980;3880;3896;3903;3854;3981;3909;3904 | 122.8 | 0.667 | 0.333 | 0.383 | 1 | |
| 10 | single | nl_004 | natural_language_ko | semantic_search | document | 중대재해가 발생했을 때 경영책임자가 처벌받는 기준 | 3916;3917;3920;3921 | 3918;3917;3919;3921;3916;3923;3867;3922;3877;3984 | 82.5 | 0.750 | 0.500 | 0.565 | 1 | |
| 11 | single | nl_005 | natural_language_ko | semantic_search | document | 안전보건교육은 누가 받아야 하고 어떤 내용을 다루는가 | 3853;3865 | 3853;3876;3965;3871;3958;3875;3861;3866;3877;3856 | 125.3 | 0.500 | 1.000 | 0.613 | 1 | |
| 12 | single | cl_001 | crosslingual_ko_en | semantic_search | document | 기계 안전 가드 설계 원리 | 3770;3856 | 4540;4548;3895;4550;3770;3762;3773;3879;3856;3767 | 90.3 | 1.000 | 0.200 | 0.422 | 0 | |
| 13 | single | cl_002 | crosslingual_ko_en | semantic_search | document | 산업 안전 입문서 | 3755;3775;3776;3777 | 3755;3816;3775;3851;3896;3853;3876;3871;3776;3863 | 89.2 | 0.750 | 1.000 | 0.703 | 1 | |
| 14 | single | cl_003 | crosslingual_ko_en | semantic_search | document | 전기 안전 위험 | 3772;3790 | 3897;3790;3775;3772;4024;4018;4020;4023;4022;4013 | 115.6 | 1.000 | 0.500 | 0.651 | 1 | |
| 15 | single | news_001 | news_ko | semantic_search | news | 이란과 미국의 군사 충돌 | 4303;4304;4307;4316;4322;4323;4327;4335 | 4452;4307;4317;4321;4339;4331;4650;4329;4418;4771 | 82.5 | 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;4349;4767;4322;4762;4340;4759;4642;4327 | 77.5 | 0.750 | 0.500 | 0.510 | 0 | |
| 17 | single | news_003 | news_en | semantic_search | news | Trump Iran ultimatum | 4258;4260;4262 | 4776;4775;4679;4519;4258;4199;4670;4202;4668;4321 | 76.2 | 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;4688;4519;4678;4211;4521;4363;4258 | 77.2 | 0.625 | 0.500 | 0.540 | 1 | |
| 19 | single | news_005 | news_crosslingual | semantic_search | news | 이란 미국 전쟁 글로벌 반응 | 4202;4258;4262;4536;4303;4304;4316 | 4457;4307;4452;4765;4329;4345;4324;4443;4761;4444 | 95.9 | 0.000 | 0.000 | 0.000 | 1 | |
| 20 | single | misc_001 | other_domain | fact_lookup | document | 강체의 평면 운동학 | 4063;4065 | 4063;4066;4071;4064;4065;4067;4069;4058;4068;4060 | 166.5 | 1.000 | 1.000 | 0.850 | 1 | |
| 21 | single | misc_002 | other_domain | semantic_search | document | 질점의 운동역학 | 4060;4061;4062 | 4062;4060;4061;4070;4059;4064;4066;4058;4068;4065 | 213.1 | 1.000 | 1.000 | 1.000 | 1 | |
| 22 | single | fail_001 | failure_expected | semantic_search | document | Rust async runtime tokio scheduler 내부 구조 | 4546;4069;4549;4550;4542;4539;3789;4067;4548;4070 | 81.1 | 0.000 | 0.000 | 0.000 | 1 | ||
| 23 | single | fail_002 | failure_expected | semantic_search | document | 양자컴퓨터 큐비트 디코히어런스 | 4068;4058;4064;4060;4065;4063;4061;3899;4067;4196 | 76.0 | 0.000 | 0.000 | 0.000 | 1 | ||
| 24 | single | fail_003 | failure_expected | semantic_search | news | 재즈 보컬리스트 빌리 홀리데이 | 4675;4634;4289;4281;4205;4116;4697;4100;4768;4077 | 75.7 | 0.000 | 0.000 | 0.000 | 1 |