Fallacy Detection 2026 — Results

Rankings per track (base / enhanced)
Combined rankings (base + enhanced merged)
Per-class details

This page lists the official results of the Fallacy Detection task at Touché 2026. Runs are ranked by macro F1-score; precision and recall are macro-averaged as well. For Sub-Task 3, the two label dimensions (argument goal and argument basis) are scored separately; the macro average runs over the four dimension classes. The Tag column indicates whether a system used only the original (base) fields or also the enhanced fields; base and enhanced runs are ranked separately per sub-task, followed by a combined ranking. The Repaired column marks broken runs: entries for which the run submitted no prediction or an invalid label were counted as incorrect (the column states how many predictions were affected). Runs marked as “not ranked (informational)” exceeded the submission limit or were submitted by organizers and are reported for reference only.

Rankings per track (base / enhanced)

Task 1 — base

Rank	Team	Run	Tag	Precision	Recall	F1
1	grtsh	llm-court-01	base	0.807	0.807	0.807
2	uzhcl-for-the-win	st1-base	base	0.770	0.754	0.751
3	veritas	RoBERTa-large-base	base	0.742	0.737	0.737
4	helium	Gem4-31B-no-desc	base	0.745	0.737	0.736
5	helium	Gemma4-31TrueRawCtx	base	0.745	0.737	0.736
6	helium	gemma-4-31b-it-context	base	0.745	0.737	0.736
7	napiernlp	CVB-Base	base	0.736	0.734	0.734
8	ooooooo	base-2	base	0.730	0.718	0.713
9	nit-agartala-nlp-team	fine tune deroberta	base	0.727	0.706	0.697
10	ooooooo	base	base	0.737	0.685	0.665
11	nit-agartala-nlp-team	nli-deberta	base	0.685	0.667	0.658
12	organizer	Organizer-LLM-Baseline-base	base	0.502	0.501	0.460

Not ranked (informational):

Team	Run	Tag	Precision	Recall	F1	Repaired
webis (organizer)	Webis-CourtroomTrial-base	base	0.705	0.704	0.704

Task 1 — enhanced

Rank	Team	Run	Tag	Precision	Recall	F1
1	seals-nlp	Seals-NLP	enhanced	0.957	0.957	0.957
2	uzhcl-for-the-win	st1-first-run	enhanced	0.946	0.945	0.944
3	ooooooo	enhanced	enhanced	0.940	0.940	0.940
4	veritas	RoBERTa-large-enhnc	enhanced	0.927	0.927	0.927
5	sevitha	multitask-deberta	enhanced	0.931	0.926	0.927
6	clef26-sophisma	RoBERTa-BF16	enhanced	0.914	0.914	0.914
7	napiernlp	CVB-Enhanced	enhanced	0.910	0.910	0.910
8	uzh-tt	cascaded-run-1	enhanced	0.894	0.892	0.893
9	uzh-tt	cascaded-v2	enhanced	0.894	0.892	0.893
10	napiernlp	MVB-Enhanced	enhanced	0.888	0.889	0.888
11	uzh-tt	Roberta-Run	enhanced	0.887	0.884	0.884
12	nit-agartala-nlp-team	Logistic-Reg-Tf-idf	enhanced	0.881	0.876	0.875
13	organizer	Organizer-LLM-Baseline-enhanced	enhanced	0.597	0.533	0.438

Not ranked (informational):

Team	Run	Tag	Precision	Recall	F1	Repaired
sevitha	tfidf-linearsvc	enhanced	0.884	0.884	0.884
webis (organizer)	Webis-CourtroomTrial-enhanced	enhanced	0.848	0.842	0.841

Task 2 — base

Rank	Team	Run	Tag	Precision	Recall	F1	Repaired
1	uzhcl-for-the-win	st2-base	base	0.876	0.860	0.859
2	grtsh	llm-court-02	base	0.807	0.607	0.671	25 preds
3	grtsh	llm-court-01	base	0.780	0.574	0.638	27 preds
4	organizer	Organizer-LLM-Baseline-base	base	0.143	0.127	0.050

Not ranked (informational):

Team	Run	Tag	Precision	Recall	F1	Repaired
veritas	RoBERTa-large-base	base	0.685	0.656	0.661
veritas	ModernBERT-lg-base	base	0.576	0.523	0.523

Task 2 — enhanced

Rank	Team	Run	Tag	Precision	Recall	F1
1	uzh-tt	cascaded-V22	enhanced	0.992	0.991	0.991
2	uzh-tt	cascaded-run2-2	enhanced	0.992	0.991	0.991
3	clef26-sophisma	RoBERTa-BF16-Class	enhanced	0.974	0.972	0.972
4	seals-nlp	Seals-NLP	enhanced	0.965	0.963	0.963
5	sevitha	multitask-deberta	enhanced	0.960	0.955	0.956
6	uzhcl-for-the-win	st2	enhanced	0.958	0.954	0.954
7	veritas	RoBERTa-large-enhnc	enhanced	0.950	0.947	0.947
8	uzh-tt	roberta-task2-run	enhanced	0.941	0.930	0.931
9	veritas	Ensembl	enhanced	0.936	0.925	0.927
10	veritas	ModernBERT	enhanced	0.936	0.925	0.927
11	nit-agartala-nlp-team	Reg-Lr	enhanced	0.733	0.821	0.773
12	nit-agartala-nlp-team	Bagging-LR	enhanced	0.730	0.812	0.766
13	organizer	Organizer-LLM-Baseline-enhanced	enhanced	0.142	0.133	0.045

Not ranked (informational):

Team	Run	Tag	Precision	Recall	F1	Repaired
sevitha	tfidf-linearsvc	enhanced	0.957	0.953	0.954

Task 3 — base

Rank	Team	Run	Tag	Precision	Recall	F1
1	uzhcl-for-the-win	st3-base	base	0.710	0.724	0.716
2	grtsh	llm-court-01	base	0.705	0.812	0.700
3	organizer	Organizer-LLM-Baseline-base	base	0.701	0.511	0.498

Task 3 — enhanced

Rank	Team	Run	Tag	Precision	Recall	F1
1	sevitha	multitask-deberta	enhanced	0.958	0.998	0.976
2	sevitha	TFIDF-LinearSVC	enhanced	0.880	0.880	0.880
3	uzh-tt	Roberta-run-task3	enhanced	0.837	0.897	0.858
4	seals-nlp	Seals-NLP	enhanced	0.866	0.798	0.816
5	uzhcl-for-the-win	st3	enhanced	0.716	0.933	0.748
6	organizer	Organizer-LLM-Baseline-enhanced	enhanced	0.701	0.513	0.499

Combined rankings (base + enhanced merged)

Task 1 — ranking (base + enhanced)

Rank	Team	Run	Tag	Precision	Recall	F1
1	seals-nlp	Seals-NLP	enhanced	0.957	0.957	0.957
2	uzhcl-for-the-win	st1-first-run	enhanced	0.946	0.945	0.944
3	ooooooo	enhanced	enhanced	0.940	0.940	0.940
4	veritas	RoBERTa-large-enhnc	enhanced	0.927	0.927	0.927
5	sevitha	multitask-deberta	enhanced	0.931	0.926	0.927
6	clef26-sophisma	RoBERTa-BF16	enhanced	0.914	0.914	0.914
7	napiernlp	CVB-Enhanced	enhanced	0.910	0.910	0.910
8	uzh-tt	cascaded-run-1	enhanced	0.894	0.892	0.893
9	uzh-tt	cascaded-v2	enhanced	0.894	0.892	0.893
10	napiernlp	MVB-Enhanced	enhanced	0.888	0.889	0.888
11	uzh-tt	Roberta-Run	enhanced	0.887	0.884	0.884
12	nit-agartala-nlp-team	Logistic-Reg-Tf-idf	enhanced	0.881	0.876	0.875
13	grtsh	llm-court-01	base	0.807	0.807	0.807
14	uzhcl-for-the-win	st1-base	base	0.770	0.754	0.751
15	veritas	RoBERTa-large-base	base	0.742	0.737	0.737
16	helium	Gem4-31B-no-desc	base	0.745	0.737	0.736
17	helium	Gemma4-31TrueRawCtx	base	0.745	0.737	0.736
18	helium	gemma-4-31b-it-context	base	0.745	0.737	0.736
19	napiernlp	CVB-Base	base	0.736	0.734	0.734
20	ooooooo	base-2	base	0.730	0.718	0.713
21	nit-agartala-nlp-team	fine tune deroberta	base	0.727	0.706	0.697
22	ooooooo	base	base	0.737	0.685	0.665
23	nit-agartala-nlp-team	nli-deberta	base	0.685	0.667	0.658
24	organizer	Organizer-LLM-Baseline-base	base	0.502	0.501	0.460
25	organizer	Organizer-LLM-Baseline-enhanced	enhanced	0.597	0.533	0.438

Task 1 — not ranked (informational)

Team	Run	Tag	Precision	Recall	F1
sevitha	tfidf-linearsvc	enhanced	0.884	0.884	0.884
webis (organizer)	Webis-CourtroomTrial-enhanced	enhanced	0.848	0.842	0.841
webis (organizer)	Webis-CourtroomTrial-base	base	0.705	0.704	0.704

Task 2 — ranking (base + enhanced)

Rank	Team	Run	Tag	Precision	Recall	F1	Repaired
1	uzh-tt	cascaded-V22	enhanced	0.992	0.991	0.991
2	uzh-tt	cascaded-run2-2	enhanced	0.992	0.991	0.991
3	clef26-sophisma	RoBERTa-BF16-Class	enhanced	0.974	0.972	0.972
4	seals-nlp	Seals-NLP	enhanced	0.965	0.963	0.963
5	sevitha	multitask-deberta	enhanced	0.960	0.955	0.956
6	uzhcl-for-the-win	st2	enhanced	0.958	0.954	0.954
7	veritas	RoBERTa-large-enhnc	enhanced	0.950	0.947	0.947
8	uzh-tt	roberta-task2-run	enhanced	0.941	0.930	0.931
9	veritas	Ensembl	enhanced	0.936	0.925	0.927
10	veritas	ModernBERT	enhanced	0.936	0.925	0.927
11	uzhcl-for-the-win	st2-base	base	0.876	0.860	0.859
12	nit-agartala-nlp-team	Reg-Lr	enhanced	0.733	0.821	0.773
13	nit-agartala-nlp-team	Bagging-LR	enhanced	0.730	0.812	0.766
14	grtsh	llm-court-02	base	0.807	0.607	0.671	25 preds
15	grtsh	llm-court-01	base	0.780	0.574	0.638	27 preds
16	organizer	Organizer-LLM-Baseline-base	base	0.143	0.127	0.050
17	organizer	Organizer-LLM-Baseline-enhanced	enhanced	0.142	0.133	0.045

Task 2 — not ranked (informational)

Team	Run	Tag	Precision	Recall	F1
sevitha	tfidf-linearsvc	enhanced	0.957	0.953	0.954
veritas	RoBERTa-large-base	base	0.685	0.656	0.661
veritas	ModernBERT-lg-base	base	0.576	0.523	0.523

Task 3 — ranking (base + enhanced)

Rank	Team	Run	Tag	Precision	Recall	F1
1	sevitha	multitask-deberta	enhanced	0.958	0.998	0.976
2	sevitha	TFIDF-LinearSVC	enhanced	0.880	0.880	0.880
3	uzh-tt	Roberta-run-task3	enhanced	0.837	0.897	0.858
4	seals-nlp	Seals-NLP	enhanced	0.866	0.798	0.816
5	uzhcl-for-the-win	st3	enhanced	0.716	0.933	0.748
6	uzhcl-for-the-win	st3-base	base	0.710	0.724	0.716
7	grtsh	llm-court-01	base	0.705	0.812	0.700
8	organizer	Organizer-LLM-Baseline-enhanced	enhanced	0.701	0.513	0.499
9	organizer	Organizer-LLM-Baseline-base	base	0.701	0.511	0.498

Per-class details

Task 1 — base

#1 llm-court-01 (team: grtsh)

Class	Precision	Recall	F1
fallacy	0.818	0.783	0.800
non-fallacy	0.797	0.831	0.813
MACRO	0.807	0.807	0.807

#2 st1-base (team: uzhcl-for-the-win)

Class	Precision	Recall	F1
fallacy	0.830	0.635	0.719
non-fallacy	0.710	0.873	0.783
MACRO	0.770	0.754	0.751

#3 RoBERTa-large-base (team: veritas)

Class	Precision	Recall	F1
fallacy	0.770	0.670	0.716
non-fallacy	0.714	0.805	0.757
MACRO	0.742	0.737	0.737

#4 Gem4-31B-no-desc (team: helium)

Class	Precision	Recall	F1
fallacy	0.781	0.652	0.711
non-fallacy	0.708	0.822	0.761
MACRO	0.745	0.737	0.736

#5 Gemma4-31TrueRawCtx (team: helium)

Class	Precision	Recall	F1
fallacy	0.781	0.652	0.711
non-fallacy	0.708	0.822	0.761
MACRO	0.745	0.737	0.736

#6 gemma-4-31b-it-context (team: helium)

Class	Precision	Recall	F1
fallacy	0.781	0.652	0.711
non-fallacy	0.708	0.822	0.761
MACRO	0.745	0.737	0.736

#7 CVB-Base (team: napiernlp)

Class	Precision	Recall	F1
fallacy	0.712	0.774	0.742
non-fallacy	0.759	0.695	0.726
MACRO	0.736	0.734	0.734

#8 base-2 (team: ooooooo)

Class	Precision	Recall	F1
fallacy	0.671	0.835	0.744
non-fallacy	0.789	0.602	0.683
MACRO	0.730	0.718	0.713

#9 fine tune deroberta (team: nit-agartala-nlp-team)

Class	Precision	Recall	F1
fallacy	0.651	0.861	0.742
non-fallacy	0.802	0.551	0.653
MACRO	0.727	0.706	0.697

#10 base (team: ooooooo)

Class	Precision	Recall	F1
fallacy	0.620	0.922	0.741
non-fallacy	0.855	0.449	0.589
MACRO	0.737	0.685	0.665

#11 nli-deberta (team: nit-agartala-nlp-team)

Class	Precision	Recall	F1
fallacy	0.621	0.826	0.709
non-fallacy	0.750	0.508	0.606
MACRO	0.685	0.667	0.658

#12 Organizer-LLM-Baseline-base (team: organizer)

Class	Precision	Recall	F1
fallacy	0.494	0.774	0.603
non-fallacy	0.509	0.229	0.316
MACRO	0.502	0.501	0.460

[info] Webis-CourtroomTrial-base (team: webis (organizer))

Class	Precision	Recall	F1
fallacy	0.685	0.739	0.711
non-fallacy	0.725	0.669	0.696
MACRO	0.705	0.704	0.704

Task 1 — enhanced

#1 Seals-NLP (team: seals-nlp)

Class	Precision	Recall	F1
fallacy	0.949	0.965	0.957
non-fallacy	0.966	0.949	0.957
MACRO	0.957	0.957	0.957

#2 st1-first-run (team: uzhcl-for-the-win)

Class	Precision	Recall	F1
fallacy	0.918	0.974	0.945
non-fallacy	0.973	0.915	0.943
MACRO	0.946	0.945	0.944

#3 enhanced (team: ooooooo)

Class	Precision	Recall	F1
fallacy	0.939	0.939	0.939
non-fallacy	0.941	0.941	0.941
MACRO	0.940	0.940	0.940

#4 RoBERTa-large-enhnc (team: veritas)

Class	Precision	Recall	F1
fallacy	0.930	0.922	0.926
non-fallacy	0.924	0.932	0.928
MACRO	0.927	0.927	0.927

#5 multitask-deberta (team: sevitha)

Class	Precision	Recall	F1
fallacy	0.971	0.878	0.922
non-fallacy	0.891	0.975	0.931
MACRO	0.931	0.926	0.927

#6 RoBERTa-BF16 (team: clef26-sophisma)

Class	Precision	Recall	F1
fallacy	0.899	0.930	0.915
non-fallacy	0.930	0.898	0.914
MACRO	0.914	0.914	0.914

#7 CVB-Enhanced (team: napiernlp)

Class	Precision	Recall	F1
fallacy	0.898	0.922	0.910
non-fallacy	0.922	0.898	0.910
MACRO	0.910	0.910	0.910

#8 cascaded-run-1 (team: uzh-tt)

Class	Precision	Recall	F1
fallacy	0.909	0.870	0.889
non-fallacy	0.878	0.915	0.896
MACRO	0.894	0.892	0.893

#9 cascaded-v2 (team: uzh-tt)

Class	Precision	Recall	F1
fallacy	0.909	0.870	0.889
non-fallacy	0.878	0.915	0.896
MACRO	0.894	0.892	0.893

#10 MVB-Enhanced (team: napiernlp)

Class	Precision	Recall	F1
fallacy	0.880	0.896	0.888
non-fallacy	0.897	0.881	0.889
MACRO	0.888	0.889	0.888

#11 Roberta-Run (team: uzh-tt)

Class	Precision	Recall	F1
fallacy	0.915	0.843	0.878
non-fallacy	0.858	0.924	0.890
MACRO	0.887	0.884	0.884

#12 Logistic-Reg-Tf-idf (team: nit-agartala-nlp-team)

Class	Precision	Recall	F1
fallacy	0.831	0.939	0.882
non-fallacy	0.932	0.814	0.869
MACRO	0.881	0.876	0.875

#13 Organizer-LLM-Baseline-enhanced (team: organizer)

Class	Precision	Recall	F1
fallacy	0.512	0.939	0.663
non-fallacy	0.682	0.127	0.214
MACRO	0.597	0.533	0.438

[info] tfidf-linearsvc (team: sevitha)

Class	Precision	Recall	F1
fallacy	0.879	0.887	0.883
non-fallacy	0.889	0.881	0.885
MACRO	0.884	0.884	0.884

[info] Webis-CourtroomTrial-enhanced (team: webis (organizer))

Class	Precision	Recall	F1
fallacy	0.795	0.913	0.850
non-fallacy	0.901	0.771	0.831
MACRO	0.848	0.842	0.841

Task 2 — base

#1 st2-base (team: uzhcl-for-the-win)

Class	Precision	Recall	F1
authority	0.882	1.000	0.938
black-white	0.647	0.846	0.733
hasty_generalization	1.000	0.929	0.963
natural	0.875	0.933	0.903
population	0.900	0.750	0.818
slippery_slope	0.778	0.933	0.848
tradition	1.000	0.688	0.815
worse_problems	0.923	0.800	0.857
MACRO	0.876	0.860	0.859

#2 llm-court-02 (team: grtsh) [repaired: 25 preds]

Class	Precision	Recall	F1
authority	0.846	0.733	0.786
black-white	0.583	0.538	0.560
hasty_generalization	0.909	0.714	0.800
natural	0.750	0.800	0.774
population	1.000	0.250	0.400
slippery_slope	0.917	0.733	0.815
tradition	0.786	0.688	0.733
worse_problems	0.667	0.400	0.500
MACRO	0.807	0.607	0.671

#3 llm-court-01 (team: grtsh) [repaired: 27 preds]

Class	Precision	Recall	F1
authority	0.846	0.733	0.786
black-white	0.583	0.538	0.560
hasty_generalization	0.833	0.714	0.769
natural	0.750	0.800	0.774
population	1.000	0.250	0.400
slippery_slope	0.778	0.467	0.583
tradition	0.786	0.688	0.733
worse_problems	0.667	0.400	0.500
MACRO	0.780	0.574	0.638

#4 Organizer-LLM-Baseline-base (team: organizer)

Class	Precision	Recall	F1
authority	0.000	0.000	0.000
black-white	0.000	0.000	0.000
hasty_generalization	0.000	0.000	0.000
natural	0.000	0.000	0.000
population	1.000	0.083	0.154
slippery_slope	0.140	0.933	0.243
tradition	0.000	0.000	0.000
worse_problems	0.000	0.000	0.000
MACRO	0.143	0.127	0.050

[info] RoBERTa-large-base (team: veritas)

Class	Precision	Recall	F1
authority	0.909	0.667	0.769
black-white	0.350	0.538	0.424
hasty_generalization	0.571	0.571	0.571
natural	0.882	1.000	0.938
population	0.467	0.583	0.519
slippery_slope	0.714	0.667	0.690
tradition	0.917	0.688	0.786
worse_problems	0.667	0.533	0.593
MACRO	0.685	0.656	0.661

[info] ModernBERT-lg-base (team: veritas)

Class	Precision	Recall	F1
authority	0.385	0.333	0.357
black-white	0.368	0.538	0.438
hasty_generalization	0.700	0.500	0.583
natural	0.722	0.867	0.788
population	0.250	0.500	0.333
slippery_slope	0.714	0.667	0.690
tradition	0.833	0.312	0.455
worse_problems	0.636	0.467	0.538
MACRO	0.576	0.523	0.523

Task 2 — enhanced

#1 cascaded-V22 (team: uzh-tt)

Class	Precision	Recall	F1
authority	0.938	1.000	0.968
black-white	1.000	1.000	1.000
hasty_generalization	1.000	0.929	0.963
natural	1.000	1.000	1.000
population	1.000	1.000	1.000
slippery_slope	1.000	1.000	1.000
tradition	1.000	1.000	1.000
worse_problems	1.000	1.000	1.000
MACRO	0.992	0.991	0.991

#2 cascaded-run2-2 (team: uzh-tt)

Class	Precision	Recall	F1
authority	0.938	1.000	0.968
black-white	1.000	1.000	1.000
hasty_generalization	1.000	0.929	0.963
natural	1.000	1.000	1.000
population	1.000	1.000	1.000
slippery_slope	1.000	1.000	1.000
tradition	1.000	1.000	1.000
worse_problems	1.000	1.000	1.000
MACRO	0.992	0.991	0.991

#3 RoBERTa-BF16-Class (team: clef26-sophisma)

Class	Precision	Recall	F1
authority	1.000	1.000	1.000
black-white	1.000	0.923	0.960
hasty_generalization	0.933	1.000	0.966
natural	1.000	0.933	0.966
population	0.917	0.917	0.917
slippery_slope	1.000	1.000	1.000
tradition	0.941	1.000	0.970
worse_problems	1.000	1.000	1.000
MACRO	0.974	0.972	0.972

#4 Seals-NLP (team: seals-nlp)

Class	Precision	Recall	F1
authority	1.000	0.933	0.966
black-white	1.000	0.923	0.960
hasty_generalization	0.933	1.000	0.966
natural	1.000	0.933	0.966
population	0.846	0.917	0.880
slippery_slope	1.000	1.000	1.000
tradition	0.941	1.000	0.970
worse_problems	1.000	1.000	1.000
MACRO	0.965	0.963	0.963

#5 multitask-deberta (team: sevitha)

Class	Precision	Recall	F1
authority	1.000	0.867	0.929
black-white	1.000	0.923	0.960
hasty_generalization	0.933	1.000	0.966
natural	1.000	1.000	1.000
population	0.917	0.917	0.917
slippery_slope	1.000	1.000	1.000
tradition	1.000	0.938	0.968
worse_problems	0.833	1.000	0.909
MACRO	0.960	0.955	0.956

#6 st2 (team: uzhcl-for-the-win)

Class	Precision	Recall	F1
authority	1.000	0.867	0.929
black-white	1.000	0.923	0.960
hasty_generalization	0.929	0.929	0.929
natural	1.000	1.000	1.000
population	0.733	0.917	0.815
slippery_slope	1.000	1.000	1.000
tradition	1.000	1.000	1.000
worse_problems	1.000	1.000	1.000
MACRO	0.958	0.954	0.954

#7 RoBERTa-large-enhnc (team: veritas)

Class	Precision	Recall	F1
authority	1.000	0.867	0.929
black-white	1.000	0.923	0.960
hasty_generalization	0.875	1.000	0.933
natural	1.000	0.933	0.966
population	0.846	0.917	0.880
slippery_slope	1.000	1.000	1.000
tradition	0.938	0.938	0.938
worse_problems	0.938	1.000	0.968
MACRO	0.950	0.947	0.947

#8 roberta-task2-run (team: uzh-tt)

Class	Precision	Recall	F1
authority	1.000	0.800	0.889
black-white	1.000	0.923	0.960
hasty_generalization	0.737	1.000	0.848
natural	1.000	0.933	0.966
population	0.917	0.917	0.917
slippery_slope	0.938	1.000	0.968
tradition	0.938	0.938	0.938
worse_problems	1.000	0.933	0.966
MACRO	0.941	0.930	0.931

#9 Ensembl (team: veritas)

Class	Precision	Recall	F1
authority	1.000	0.800	0.889
black-white	1.000	0.923	0.960
hasty_generalization	0.765	0.929	0.839
natural	1.000	1.000	1.000
population	0.900	0.750	0.818
slippery_slope	1.000	1.000	1.000
tradition	0.941	1.000	0.970
worse_problems	0.882	1.000	0.938
MACRO	0.936	0.925	0.927

#10 ModernBERT (team: veritas)

Class	Precision	Recall	F1
authority	1.000	0.800	0.889
black-white	1.000	0.923	0.960
hasty_generalization	0.765	0.929	0.839
natural	1.000	1.000	1.000
population	0.900	0.750	0.818
slippery_slope	1.000	1.000	1.000
tradition	0.941	1.000	0.970
worse_problems	0.882	1.000	0.938
MACRO	0.936	0.925	0.927

#11 Reg-Lr (team: nit-agartala-nlp-team)

Class	Precision	Recall	F1
authority	0.812	0.867	0.839
black-white	0.000	0.000	0.000
hasty_generalization	0.875	1.000	0.933
natural	1.000	0.933	0.966
population	0.714	0.833	0.769
slippery_slope	0.833	1.000	0.909
tradition	0.882	0.938	0.909
worse_problems	0.750	1.000	0.857
MACRO	0.733	0.821	0.773

#12 Bagging-LR (team: nit-agartala-nlp-team)

Class	Precision	Recall	F1
authority	0.824	0.933	0.875
black-white	0.000	0.000	0.000
hasty_generalization	0.812	0.929	0.867
natural	1.000	0.933	0.966
population	0.833	0.833	0.833
slippery_slope	0.833	1.000	0.909
tradition	0.833	0.938	0.882
worse_problems	0.700	0.933	0.800
MACRO	0.730	0.812	0.766

#13 Organizer-LLM-Baseline-enhanced (team: organizer)

Class	Precision	Recall	F1
authority	0.000	0.000	0.000
black-white	0.000	0.000	0.000
hasty_generalization	0.000	0.000	0.000
natural	0.000	0.000	0.000
population	0.000	0.000	0.000
slippery_slope	0.138	1.000	0.242
tradition	1.000	0.062	0.118
worse_problems	0.000	0.000	0.000
MACRO	0.142	0.133	0.045

[info] tfidf-linearsvc (team: sevitha)

Class	Precision	Recall	F1
authority	0.933	0.933	0.933
black-white	1.000	0.923	0.960
hasty_generalization	0.875	1.000	0.933
natural	1.000	0.933	0.966
population	0.909	0.833	0.870
slippery_slope	1.000	1.000	1.000
tradition	0.941	1.000	0.970
worse_problems	1.000	1.000	1.000
MACRO	0.957	0.953	0.954

Task 3 — base

#1 st3-base (team: uzhcl-for-the-win)

Class	Precision	Recall	F1
goal:epistemic	0.959	0.949	0.954
goal:practical	0.750	0.789	0.769
basis:external	0.167	0.200	0.182
basis:internal	0.964	0.956	0.960
MACRO	0.710	0.724	0.716

#2 llm-court-01 (team: grtsh)

Class	Precision	Recall	F1
goal:epistemic	1.000	0.939	0.969
goal:practical	0.760	1.000	0.864
basis:external	0.083	0.600	0.146
basis:internal	0.976	0.708	0.821
MACRO	0.705	0.812	0.700

#3 Organizer-LLM-Baseline-base (team: organizer)

Class	Precision	Recall	F1
goal:epistemic	0.846	1.000	0.917
goal:practical	1.000	0.053	0.100
basis:external	0.000	0.000	0.000
basis:internal	0.957	0.991	0.974
MACRO	0.701	0.511	0.498

Task 3 — enhanced

#1 multitask-deberta (team: sevitha)

Class	Precision	Recall	F1
goal:epistemic	1.000	1.000	1.000
goal:practical	1.000	1.000	1.000
basis:external	0.833	1.000	0.909
basis:internal	1.000	0.991	0.996
MACRO	0.958	0.998	0.976

#2 TFIDF-LinearSVC (team: sevitha)

Class	Precision	Recall	F1
goal:epistemic	0.990	0.990	0.990
goal:practical	0.947	0.947	0.947
basis:external	0.600	0.600	0.600
basis:internal	0.982	0.982	0.982
MACRO	0.880	0.880	0.880

#3 Roberta-run-task3 (team: uzh-tt)

Class	Precision	Recall	F1
goal:epistemic	0.970	0.980	0.975
goal:practical	0.889	0.842	0.865
basis:external	0.500	0.800	0.615
basis:internal	0.991	0.965	0.978
MACRO	0.837	0.897	0.858

#4 Seals-NLP (team: seals-nlp)

Class	Precision	Recall	F1
goal:epistemic	1.000	1.000	1.000
goal:practical	1.000	1.000	1.000
basis:external	0.500	0.200	0.286
basis:internal	0.966	0.991	0.978
MACRO	0.866	0.798	0.816

#5 st3 (team: uzhcl-for-the-win)

Class	Precision	Recall	F1
goal:epistemic	1.000	0.899	0.947
goal:practical	0.655	1.000	0.792
basis:external	0.208	1.000	0.345
basis:internal	1.000	0.832	0.908
MACRO	0.716	0.933	0.748

#6 Organizer-LLM-Baseline-enhanced (team: organizer)

Class	Precision	Recall	F1
goal:epistemic	0.846	1.000	0.917
goal:practical	1.000	0.053	0.100
basis:external	0.000	0.000	0.000
basis:internal	0.958	1.000	0.978
MACRO	0.701	0.513	0.499

If you have any questions, please do not hesitate to contact us.