| cru-ablR-PlaidX- (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
HLTCOE |
0.6425349568731922 |
0.6425349568731923 |
0.8981279341573459 |
| cru-ablR-LSR- (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
HLTCOE |
0.5955677492442198 |
0.5955677492442196 |
0.9175862536156653 |
| cru-ansR-PlaidX- (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
HLTCOE |
0.5718871814460049 |
0.5718871814460048 |
0.832282423458894 |
| cru-ablR- (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
HLTCOE |
0.5589891365842923 |
0.5589891365842922 |
0.9009728593206102 |
| extractive-rag (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
coordinators |
0.5499999999999999 |
0.5499999999999999 |
0.8606060606060606 |
| cru-ansR- (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
HLTCOE |
0.5491125512319284 |
0.5491125512319284 |
0.8315601929788781 |
| cru-ablR-conf- (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
HLTCOE |
0.5467673690208292 |
0.5467673690208291 |
0.859863845785126 |
| cru-ansR-conf- (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
HLTCOE |
0.5410091710480982 |
0.5410091710480982 |
0.8162233599733599 |
| WueRAG_2025_08_22 (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
WueRAG |
0.5297211206302116 |
0.5297211206302116 |
0.772145363054454 |
| cru-ansR-LSR- (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
HLTCOE |
0.5244099038216685 |
0.5244099038216686 |
0.8250195882548823 |
| gptr_nt_q3d3_mt (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-multiagt |
0.5235362676539147 |
0.5235362676539147 |
0.8208493304081539 |
| genaius-cluster (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
GenAIus |
0.5214224472845163 |
0.5214224472845163 |
0.8113910993221336 |
| auto_swarm_mt (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-multiagt |
0.5109185940933345 |
0.5109185940933344 |
0.8673531426433903 |
| gptr_nt_q4d4_mt (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-multiagt |
0.5094725535902007 |
0.5094725535902007 |
0.7833590429178664 |
| gptr_e2_q3d3_mt (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-multiagt |
0.4987745098039215 |
0.49877450980392174 |
0.8179738562091503 |
| AMU1ML (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
AMU |
0.4905927405927406 |
0.504679307620484 |
0.8217285981991864 |
| AMU1ENG (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
AMU |
0.4898512435277142 |
0.4960603938545114 |
0.8129010695187167 |
| cru-ansR-bareconf- (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
HLTCOE |
0.4869381195505763 |
0.4869381195505763 |
0.7601053358406299 |
| lg_nt_4q12r3l_mt_c (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-multiagt |
0.48678935633156173 |
0.48678935633156184 |
0.8026351562296745 |
| lg_nt_4q12r3l_natv_c (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-multiagt |
0.4757411735000061 |
0.4757411735000061 |
0.7972738221884553 |
| pybm25 (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
DUTH |
0.47478991596638653 |
0.47478991596638664 |
0.8193277310924368 |
| IDACCS_extract_4.1 (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
IDACCS |
0.46690601224354084 |
0.4690095356452387 |
0.7022001298905997 |
| lg_e2_3q5r3l (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-multiagt |
0.45599975840141566 |
0.4559997584014157 |
0.8950127667563016 |
| hltime-lg.crux (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-rerank |
0.44080069334235245 |
0.44080069334235233 |
0.7431895952395405 |
| IDACCS_hybrid_4.1 (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
IDACCS |
0.43858745815930694 |
0.438587458159307 |
0.6738815758063658 |
| IDACCS_hybridtb_4.1 (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
IDACCS |
0.4314906227092077 |
0.4324393893126232 |
0.6667847403562664 |
| hltime-lg.fsrrfprf (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-rerank |
0.4219098951797914 |
0.4219098951797914 |
0.7099258368505774 |
| gptr_ka_q3d3_natv (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-multiagt |
0.41736694677871156 |
0.41736694677871156 |
0.7304621848739495 |
| hltime-lg.fsrrf (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-rerank |
0.40561115946519327 |
0.4056111594651934 |
0.6974520289399182 |
| gptr_ka_q3d3_mt (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-multiagt |
0.39391074611662846 |
0.39391074611662846 |
0.707703081232493 |
| hltime-lg.searcher (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-rerank |
0.3853952535101233 |
0.38539525351012327 |
0.6712067387376985 |
| hltime-lg.jina (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-rerank |
0.37529056249239673 |
0.37529056249239673 |
0.6783271164805078 |
| hltime-lg.listllama (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-rerank |
0.3676965058505306 |
0.3676965058505306 |
0.6475472214404104 |
| hltime-lg.qwen (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-rerank |
0.3610342286004733 |
0.36103422860047335 |
0.6558677020535062 |
| hltime-lg.jina.qwen (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-rerank |
0.33939588204749377 |
0.3393958820474938 |
0.6531485493047595 |
| hltime-gpt5.searcher (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-rerank |
0.3383255112172194 |
0.3383255112172194 |
0.6430407764082631 |
| las_ag_round_robin (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
ncsu-las |
0.3118750826210754 |
0.31187508262107544 |
0.6006003471966316 |
| las_ag_sel_28 (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
ncsu-las |
0.2776619985724806 |
0.2776619985724806 |
0.5725501243706529 |
| electra (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
DUTH |
0.2773109243697479 |
0.3876050420168067 |
0.9495798319327731 |
| xenc-report (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
DUTH |
0.2759103641456583 |
0.38620448179271705 |
0.9495798319327731 |
| eng_mlm6loc (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
DUTH |
0.2759103641456583 |
0.38620448179271705 |
0.9495798319327731 |
| las_ag_sel_29 (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
ncsu-las |
0.2758899225517327 |
0.27711541274781126 |
0.5227047162318516 |
| las_ag_sel_new_prompt (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
ncsu-las |
0.2736767581707028 |
0.27367675817070275 |
0.5525690668424231 |
| eng_fused (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
DUTH |
0.273109243697479 |
0.3834033613445378 |
0.9453781512605043 |
| tblocal (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
DUTH |
0.2724089635854342 |
0.38270308123249297 |
0.9453781512605043 |
| mlm12 (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
DUTH |
0.2689075630252101 |
0.38655462184873945 |
0.9411764705882353 |
| eng_mlm6 (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
DUTH |
0.26750700280112044 |
0.37780112044817926 |
0.9411764705882353 |
| genaius-question (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
GenAIus |
0.26486928104575164 |
0.26486928104575164 |
0.5383986928104576 |
| tb (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
DUTH |
0.25210084033613445 |
0.3623949579831932 |
0.9260504201680672 |
| mlir-rrf-report (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
DUTH |
0.2394957983193277 |
0.34978991596638653 |
0.9117647058823529 |
| las_ag_sel_all_4.1 (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
ncsu-las |
0.23942355513221472 |
0.23942355513221478 |
0.511539249920237 |
| IDACCS_nugget_4.1 (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
IDACCS |
0.23424122653566137 |
0.23424122653566137 |
0.4695353441827202 |
| IDACCS_nugget_tb4.1 (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
IDACCS |
0.2223238689645874 |
0.22337428913265456 |
0.45761798661164615 |
| cru-ansR-mostcommon- (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (paper) |
HLTCOE |
0.20627071482686457 |
0.20627071482686454 |
0.4042074705844759 |
| lg_e2_3q5r2l_mt_qw3 (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
hltcoe-multiagt |
0.14179175783847064 |
0.14546822842670593 |
0.6212141439672854 |
| v3_surround_glm4 (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
CSU |
0.12239424518836284 |
0.12729620597267657 |
0.36980179406649993 |
| v2_split_qwen (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
CSU |
0.09170168067226891 |
0.10150560224089634 |
0.3772408963585434 |
| v1_qwen (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) |
CSU |
0.038457049486461246 |
0.038457049486461246 |
0.3747570240217299 |
| zetaalpha (autoargue) (almost-human-judgments.tsv) (almost-human-scores.tsv) (autoargue-scores.tsv) (autoargue-judgments.jsonl) (paper) |
UvA |
0.0 |
0.0 |
1.0 |
| dfki-milp-base (autoargue) |
DFKI |
|
|
|
| milp-query-expanded (autoargue) |
DFKI |
|
|
|