Classification Report for GPT-4o-mini

Consolidated Classification Report

Test	Total Samples	True Violations	Predicted Violations	Accuracy	Precision (macro)	Recall (macro)	F1-score (macro)	Precision (weighted)	Recall (weighted)	F1-score (weighted)
base	411	248	312	0.815	0.858	0.773	0.787	0.841	0.815	0.803
0%_64	411	248	310	0.791	0.821	0.749	0.76	0.809	0.791	0.778
0%_128	411	248	337	0.764	0.835	0.707	0.712	0.812	0.764	0.738
0%_256	411	248	338	0.752	0.817	0.693	0.697	0.796	0.752	0.724
0%_512	411	248	332	0.752	0.803	0.697	0.701	0.786	0.752	0.727
0%_1024	411	248	325	0.779	0.83	0.728	0.738	0.812	0.779	0.759
0%_2048	411	248	340	0.718	0.763	0.657	0.653	0.748	0.718	0.684
0%_4096	411	248	385	0.662	0.802	0.575	0.522	0.768	0.662	0.576
0%_8192	411	248	392	0.645	0.789	0.553	0.485	0.756	0.645	0.544
0%_16384	411	248	399	0.628	0.768	0.532	0.445	0.737	0.628	0.511
0%_32768	411	248	400	0.625	0.763	0.529	0.439	0.733	0.625	0.506
25%_64	411	248	341	0.735	0.795	0.674	0.674	0.776	0.735	0.703
25%_128	411	248	352	0.723	0.803	0.656	0.648	0.78	0.723	0.682
25%_256	411	248	360	0.708	0.8	0.636	0.621	0.774	0.708	0.659
25%_512	411	248	343	0.72	0.773	0.658	0.654	0.757	0.72	0.685
25%_1024	411	248	365	0.686	0.766	0.611	0.586	0.745	0.686	0.628
25%_2048	411	248	350	0.713	0.777	0.646	0.638	0.758	0.713	0.672
25%_4096	411	248	393	0.642	0.786	0.55	0.479	0.754	0.642	0.54
25%_8192	411	248	402	0.62	0.752	0.523	0.427	0.723	0.62	0.495
25%_16384	411	248	402	0.611	0.638	0.512	0.412	0.632	0.611	0.483
25%_32768	411	248	377	0.594	0.524	0.508	0.443	0.541	0.594	0.503
50%_64	411	248	343	0.725	0.782	0.663	0.66	0.765	0.725	0.691
50%_128	411	248	346	0.742	0.822	0.679	0.678	0.798	0.742	0.708
50%_256	411	248	332	0.723	0.756	0.666	0.666	0.745	0.723	0.695
50%_512	411	248	340	0.713	0.754	0.652	0.648	0.741	0.713	0.679
50%_1024	411	248	354	0.713	0.789	0.644	0.634	0.767	0.713	0.669
50%_2048	411	248	372	0.674	0.763	0.594	0.56	0.74	0.674	0.606
50%_4096	411	248	399	0.628	0.768	0.532	0.445	0.737	0.628	0.511
50%_8192	411	248	401	0.628	0.809	0.531	0.44	0.77	0.628	0.507
50%_16384	411	248	382	0.601	0.546	0.513	0.443	0.56	0.601	0.504
50%_32768	411	248	371	0.574	0.474	0.491	0.428	0.5	0.574	0.488
75%_64	411	248	339	0.73	0.782	0.67	0.669	0.765	0.73	0.699
75%_128	411	248	357	0.715	0.805	0.645	0.634	0.78	0.715	0.669
75%_256	411	248	339	0.701	0.731	0.64	0.634	0.721	0.701	0.666
75%_512	411	248	331	0.725	0.758	0.669	0.67	0.747	0.725	0.698
75%_1024	411	248	371	0.681	0.779	0.602	0.572	0.754	0.681	0.616
75%_2048	411	248	364	0.674	0.733	0.598	0.571	0.717	0.674	0.615
75%_4096	411	248	397	0.618	0.664	0.523	0.435	0.654	0.618	0.501
75%_8192	411	248	396	0.601	0.536	0.505	0.412	0.551	0.601	0.481
75%_16384	411	248	379	0.594	0.522	0.507	0.439	0.54	0.594	0.5
75%_32768	411	248	385	0.569	0.411	0.478	0.392	0.449	0.569	0.46
100%_64	411	248	334	0.747	0.799	0.69	0.694	0.782	0.747	0.72
100%_128	411	248	342	0.713	0.758	0.651	0.646	0.744	0.713	0.678
100%_256	411	248	341	0.706	0.743	0.644	0.638	0.731	0.706	0.67
100%_512	411	248	343	0.696	0.729	0.632	0.624	0.719	0.696	0.658
100%_1024	411	248	365	0.676	0.742	0.6	0.573	0.724	0.676	0.617
100%_2048	411	248	382	0.655	0.75	0.569	0.518	0.727	0.655	0.571
100%_4096	411	248	397	0.633	0.775	0.538	0.456	0.744	0.633	0.52
100%_8192	411	248	376	0.635	0.658	0.551	0.501	0.652	0.635	0.555
100%_16384	411	248	383	0.584	0.479	0.494	0.417	0.504	0.584	0.481
100%_32768	411	248	385	0.589	0.494	0.498	0.419	0.516	0.589	0.484