{ "protocol": "btzsc22-ext-v1", "missing_predictions": { "A": { "ines": 0, "julia": 0, "laya": 0, "gliner": 0, "gemma": 0 }, "B": { "ines": 0, "julia": 0, "laya": 0, "gliner": 0, "gemma": "not run (Track B was not run for Gemma)" } }, "per_dataset": { "agnews": { "labels": 4, "in_ines_ft_mixture": false, "A": { "ines": { "accuracy": 0.59, "macro_f1": 0.5843451916892106 }, "julia": { "accuracy": 0.94, "macro_f1": 0.9399173646545361 }, "laya": { "accuracy": 0.94, "macro_f1": 0.939271525304066 }, "gliner": { "accuracy": 0.7, "macro_f1": 0.6588522320524076 }, "gemma": { "accuracy": 0.89, "macro_f1": 0.8797325209206743 } }, "B": { "ines": { "accuracy": 0.42, "macro_f1": 0.32652938961350175 }, "julia": { "accuracy": 0.42, "macro_f1": 0.399474348626891 }, "laya": { "accuracy": 0.89, "macro_f1": 0.8889659795261577 }, "gliner": { "accuracy": 0.45, "macro_f1": 0.39861358684888093 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "single request", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "emotiondair": { "labels": 6, "in_ines_ft_mixture": false, "A": { "ines": { "accuracy": 0.43, "macro_f1": 0.39042230395613853 }, "julia": { "accuracy": 0.86, "macro_f1": 0.8556934538891329 }, "laya": { "accuracy": 0.37, "macro_f1": 0.35268000920174836 }, "gliner": { "accuracy": 0.44, "macro_f1": 0.4070167592505414 }, "gemma": { "accuracy": 0.4, "macro_f1": 0.37637917637917634 } }, "B": { "ines": { "accuracy": 0.34, "macro_f1": 0.29478472669962036 }, "julia": { "accuracy": 0.26, "macro_f1": 0.25425384800384804 }, "laya": { "accuracy": 0.43, "macro_f1": 0.4279340742423987 }, "gliner": { "accuracy": 0.35, "macro_f1": 0.3193197964297709 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "single request", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "banking77": { "labels": 72, "in_ines_ft_mixture": true, "A": { "ines": { "accuracy": 0.39, "macro_f1": 0.34265873015873016 }, "julia": { "accuracy": 0.63, "macro_f1": 0.5703703703703703 }, "laya": { "accuracy": 0.02, "macro_f1": 0.0005611672278338945 }, "gliner": { "accuracy": 0.61, "macro_f1": 0.569268077601411 }, "gemma": { "accuracy": 0.8, "macro_f1": 0.7773148148148148 } }, "B": { "ines": { "accuracy": 0.29, "macro_f1": 0.2234898589065256 }, "julia": { "accuracy": 0.09, "macro_f1": 0.04716343327454439 }, "laya": { "accuracy": 0.22, "macro_f1": 0.18796296296296294 }, "gliner": { "accuracy": 0.41, "macro_f1": 0.3787818662818662 }, "gemma": null }, "trackA_strategy": { "ines": "knockout-20 (no native > 26 interface)", "julia": "Router(width=20, survivors=2)", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "amazonpolarity": { "labels": 2, "in_ines_ft_mixture": true, "A": { "ines": { "accuracy": 0.78, "macro_f1": 0.7756017951856384 }, "julia": { "accuracy": 0.62, "macro_f1": 0.6161616161616161 }, "laya": { "accuracy": 0.84, "macro_f1": 0.8368013055895553 }, "gliner": { "accuracy": 0.88, "macro_f1": 0.8799519807923168 }, "gemma": { "accuracy": 0.98, "macro_f1": 0.98 } }, "B": { "ines": { "accuracy": 0.65, "macro_f1": 0.6178622120318812 }, "julia": { "accuracy": 0.58, "macro_f1": 0.5716034271725826 }, "laya": { "accuracy": 0.91, "macro_f1": 0.9097744360902256 }, "gliner": { "accuracy": 0.83, "macro_f1": 0.8249407887962105 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "single request", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "imdb": { "labels": 2, "in_ines_ft_mixture": false, "A": { "ines": { "accuracy": 0.75, "macro_f1": 0.74997499749975 }, "julia": { "accuracy": 0.68, "macro_f1": 0.6798719487795117 }, "laya": { "accuracy": 0.73, "macro_f1": 0.7149192271143491 }, "gliner": { "accuracy": 0.8, "macro_f1": 0.7947454844006567 }, "gemma": { "accuracy": 0.97, "macro_f1": 0.96999699969997 } }, "B": { "ines": { "accuracy": 0.69, "macro_f1": 0.6807743795695603 }, "julia": { "accuracy": 0.54, "macro_f1": 0.5353535353535354 }, "laya": { "accuracy": 0.81, "macro_f1": 0.8090644156366193 }, "gliner": { "accuracy": 0.73, "macro_f1": 0.7175436761167486 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "single request", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "appreviews": { "labels": 2, "in_ines_ft_mixture": false, "A": { "ines": { "accuracy": 0.77, "macro_f1": 0.7660461804495982 }, "julia": { "accuracy": 0.65, "macro_f1": 0.6395839769333744 }, "laya": { "accuracy": 0.78, "macro_f1": 0.7756017951856384 }, "gliner": { "accuracy": 0.89, "macro_f1": 0.8894583458948849 }, "gemma": { "accuracy": 0.94, "macro_f1": 0.9399038461538461 } }, "B": { "ines": { "accuracy": 0.81, "macro_f1": 0.8095238095238095 }, "julia": { "accuracy": 0.51, "macro_f1": 0.49541756770672435 }, "laya": { "accuracy": 0.89, "macro_f1": 0.8897243107769424 }, "gliner": { "accuracy": 0.8, "macro_f1": 0.7960016319869441 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "single request", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "yelpreviews": { "labels": 2, "in_ines_ft_mixture": false, "A": { "ines": { "accuracy": 0.72, "macro_f1": 0.6996996996996997 }, "julia": { "accuracy": 0.73, "macro_f1": 0.7277951406391774 }, "laya": { "accuracy": 0.9, "macro_f1": 0.8996386993175431 }, "gliner": { "accuracy": 0.9, "macro_f1": 0.8993558776167472 }, "gemma": { "accuracy": 0.96, "macro_f1": 0.9599358974358975 } }, "B": { "ines": { "accuracy": 0.68, "macro_f1": 0.64349376114082 }, "julia": { "accuracy": 0.51, "macro_f1": 0.5087719298245614 }, "laya": { "accuracy": 0.93, "macro_f1": 0.9298245614035088 }, "gliner": { "accuracy": 0.74, "macro_f1": 0.7211497211497211 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "single request", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "rottentomatoes": { "labels": 2, "in_ines_ft_mixture": false, "A": { "ines": { "accuracy": 0.59, "macro_f1": 0.5670995670995671 }, "julia": { "accuracy": 0.66, "macro_f1": 0.6263736263736264 }, "laya": { "accuracy": 0.69, "macro_f1": 0.6807743795695603 }, "gliner": { "accuracy": 0.71, "macro_f1": 0.7064480210547626 }, "gemma": { "accuracy": 0.91, "macro_f1": 0.90999099909991 } }, "B": { "ines": { "accuracy": 0.64, "macro_f1": 0.6347402597402598 }, "julia": { "accuracy": 0.46, "macro_f1": 0.43253467843631777 }, "laya": { "accuracy": 0.74, "macro_f1": 0.74 }, "gliner": { "accuracy": 0.67, "macro_f1": 0.6547756041426928 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "single request", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "financialphrasebank": { "labels": 3, "in_ines_ft_mixture": false, "A": { "ines": { "accuracy": 0.51, "macro_f1": 0.48911853494169083 }, "julia": { "accuracy": 0.45, "macro_f1": 0.37110209601081806 }, "laya": { "accuracy": 0.81, "macro_f1": 0.8084906388321863 }, "gliner": { "accuracy": 0.69, "macro_f1": 0.6821411017203141 }, "gemma": { "accuracy": 0.8, "macro_f1": 0.8029584462511292 } }, "B": { "ines": { "accuracy": 0.45, "macro_f1": 0.388558378810103 }, "julia": { "accuracy": 0.25, "macro_f1": 0.17441737846672992 }, "laya": { "accuracy": 0.91, "macro_f1": 0.9096611274030629 }, "gliner": { "accuracy": 0.55, "macro_f1": 0.47845237675746155 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "single request", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "empathetic": { "labels": 32, "in_ines_ft_mixture": false, "A": { "ines": { "accuracy": 0.25, "macro_f1": 0.1909003551273288 }, "julia": { "accuracy": 0.17, "macro_f1": 0.15942460317460316 }, "laya": { "accuracy": 0.06, "macro_f1": 0.02546768707482993 }, "gliner": { "accuracy": 0.33, "macro_f1": 0.2807043650793651 }, "gemma": { "accuracy": 0.51, "macro_f1": 0.46972402597402596 } }, "B": { "ines": { "accuracy": 0.18, "macro_f1": 0.14416745535166586 }, "julia": { "accuracy": 0.05, "macro_f1": 0.039042207792207795 }, "laya": { "accuracy": 0.33, "macro_f1": 0.2872519841269841 }, "gliner": { "accuracy": 0.14, "macro_f1": 0.13043154761904763 }, "gemma": null }, "trackA_strategy": { "ines": "knockout-20 (no native > 26 interface)", "julia": "Router(width=20, survivors=2)", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "biasframes_intent": { "labels": 2, "in_ines_ft_mixture": false, "A": { "ines": { "accuracy": 0.6, "macro_f1": 0.5998399359743898 }, "julia": { "accuracy": 0.57, "macro_f1": 0.5664885573142454 }, "laya": { "accuracy": 0.61, "macro_f1": 0.5920075321686369 }, "gliner": { "accuracy": 0.58, "macro_f1": 0.5738636363636364 }, "gemma": { "accuracy": 0.83, "macro_f1": 0.8299829982998299 } }, "B": { "ines": { "accuracy": 0.59, "macro_f1": 0.5523528769516323 }, "julia": { "accuracy": 0.59, "macro_f1": 0.5805626598465473 }, "laya": { "accuracy": 0.66, "macro_f1": 0.6550324675324675 }, "gliner": { "accuracy": 0.52, "macro_f1": 0.39117199391172 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "single request", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "massive": { "labels": 59, "in_ines_ft_mixture": true, "A": { "ines": { "accuracy": 0.35, "macro_f1": 0.2502433536331841 }, "julia": { "accuracy": 0.27, "macro_f1": 0.1801721818670971 }, "laya": { "accuracy": 0.01, "macro_f1": 0.0009685230024213075 }, "gliner": { "accuracy": 0.44, "macro_f1": 0.38272522334474407 }, "gemma": { "accuracy": 0.78, "macro_f1": 0.7265536723163842 } }, "B": { "ines": { "accuracy": 0.2, "macro_f1": 0.15282852740479855 }, "julia": { "accuracy": 0.02, "macro_f1": 0.01224105461393597 }, "laya": { "accuracy": 0.35, "macro_f1": 0.3254640839386602 }, "gliner": { "accuracy": 0.3, "macro_f1": 0.2353510895883777 }, "gemma": null }, "trackA_strategy": { "ines": "knockout-20 (no native > 26 interface)", "julia": "Router(width=20, survivors=2)", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "yahootopics": { "labels": 10, "in_ines_ft_mixture": false, "A": { "ines": { "accuracy": 0.5, "macro_f1": 0.4915120854091442 }, "julia": { "accuracy": 0.39, "macro_f1": 0.3675051008447593 }, "laya": { "accuracy": 0.15, "macro_f1": 0.13690074545337702 }, "gliner": { "accuracy": 0.41, "macro_f1": 0.4169864449276214 }, "gemma": { "accuracy": 0.73, "macro_f1": 0.7217792466130062 } }, "B": { "ines": { "accuracy": 0.18, "macro_f1": 0.12307189542483658 }, "julia": { "accuracy": 0.12, "macro_f1": 0.11272908345326083 }, "laya": { "accuracy": 0.37, "macro_f1": 0.36499120762278653 }, "gliner": { "accuracy": 0.32, "macro_f1": 0.31750090466808734 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "single request", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "trueteacher": { "labels": 2, "in_ines_ft_mixture": false, "A": { "ines": { "accuracy": 0.56, "macro_f1": 0.537620849096259 }, "julia": { "accuracy": 0.52, "macro_f1": 0.5151515151515151 }, "laya": { "accuracy": 0.56, "macro_f1": 0.46576007770762506 }, "gliner": { "accuracy": 0.53, "macro_f1": 0.5242433444680635 }, "gemma": { "accuracy": 0.71, "macro_f1": 0.69662098545873 } }, "B": { "ines": { "accuracy": 0.5, "macro_f1": 0.3333333333333333 }, "julia": { "accuracy": 0.5, "macro_f1": 0.43464495703301675 }, "laya": { "accuracy": 0.48, "macro_f1": 0.4206773618538324 }, "gliner": { "accuracy": 0.54, "macro_f1": 0.45238095238095233 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "single request", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "manifesto": { "labels": 56, "in_ines_ft_mixture": false, "A": { "ines": { "accuracy": 0.11, "macro_f1": 0.07504578754578754 }, "julia": { "accuracy": 0.1, "macro_f1": 0.0788690476190476 }, "laya": { "accuracy": 0.03, "macro_f1": 0.007711038961038961 }, "gliner": { "accuracy": 0.02, "macro_f1": 0.0007072135785007072 }, "gemma": { "accuracy": 0.44, "macro_f1": 0.37665816326530605 } }, "B": { "ines": { "accuracy": 0.05, "macro_f1": 0.032902735562310034 }, "julia": { "accuracy": 0.02, "macro_f1": 0.01488095238095238 }, "laya": { "accuracy": 0.11, "macro_f1": 0.09031507339778015 }, "gliner": { "accuracy": 0.06, "macro_f1": 0.013575543120473996 }, "gemma": null }, "trackA_strategy": { "ines": "knockout-20 (no native > 26 interface)", "julia": "Router(width=20, survivors=2)", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "capsotu": { "labels": 21, "in_ines_ft_mixture": false, "A": { "ines": { "accuracy": 0.36, "macro_f1": 0.3120540695728665 }, "julia": { "accuracy": 0.45, "macro_f1": 0.4451588094445238 }, "laya": { "accuracy": 0.05, "macro_f1": 0.005012531328320802 }, "gliner": { "accuracy": 0.3, "macro_f1": 0.2524050024050024 }, "gemma": { "accuracy": 0.79, "macro_f1": 0.7912510769653627 } }, "B": { "ines": { "accuracy": 0.21, "macro_f1": 0.17844985702128557 }, "julia": { "accuracy": 0.1, "macro_f1": 0.0798883656026513 }, "laya": { "accuracy": 0.27, "macro_f1": 0.2799847801788137 }, "gliner": { "accuracy": 0.17, "macro_f1": 0.18369192344347623 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "Router(width=20, survivors=2)", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "biasframes_offensive": { "labels": 2, "in_ines_ft_mixture": false, "A": { "ines": { "accuracy": 0.52, "macro_f1": 0.49558638083228246 }, "julia": { "accuracy": 0.54, "macro_f1": 0.5118845500848896 }, "laya": { "accuracy": 0.62, "macro_f1": 0.6193910256410255 }, "gliner": { "accuracy": 0.46, "macro_f1": 0.4375 }, "gemma": { "accuracy": 0.82, "macro_f1": 0.8199279711884754 } }, "B": { "ines": { "accuracy": 0.48, "macro_f1": 0.48 }, "julia": { "accuracy": 0.45, "macro_f1": 0.40675223816201056 }, "laya": { "accuracy": 0.69, "macro_f1": 0.6884735202492211 }, "gliner": { "accuracy": 0.52, "macro_f1": 0.37629937629937626 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "single request", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "biasframes_sex": { "labels": 2, "in_ines_ft_mixture": false, "A": { "ines": { "accuracy": 0.34, "macro_f1": 0.3389423076923077 }, "julia": { "accuracy": 0.56, "macro_f1": 0.5555555555555556 }, "laya": { "accuracy": 0.72, "macro_f1": 0.7083333333333334 }, "gliner": { "accuracy": 0.53, "macro_f1": 0.39673982800667434 }, "gemma": { "accuracy": 0.93, "macro_f1": 0.9298245614035088 } }, "B": { "ines": { "accuracy": 0.53, "macro_f1": 0.5191815856777494 }, "julia": { "accuracy": 0.56, "macro_f1": 0.5098039215686274 }, "laya": { "accuracy": 0.79, "macro_f1": 0.78997899789979 }, "gliner": { "accuracy": 0.56, "macro_f1": 0.47619047619047616 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "single request", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "wikitoxic_insult": { "labels": 2, "in_ines_ft_mixture": true, "A": { "ines": { "accuracy": 0.77, "macro_f1": 0.7694235588972431 }, "julia": { "accuracy": 0.56, "macro_f1": 0.5592948717948718 }, "laya": { "accuracy": 0.85, "macro_f1": 0.8481627695110842 }, "gliner": { "accuracy": 0.7, "macro_f1": 0.6899545266639107 }, "gemma": { "accuracy": 0.93, "macro_f1": 0.9299929992999301 } }, "B": { "ines": { "accuracy": 0.69, "macro_f1": 0.6899689968996899 }, "julia": { "accuracy": 0.54, "macro_f1": 0.5308037535699714 }, "laya": { "accuracy": 0.8, "macro_f1": 0.7960016319869441 }, "gliner": { "accuracy": 0.58, "macro_f1": 0.5 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "single request", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "wikitoxic_obscene": { "labels": 2, "in_ines_ft_mixture": true, "A": { "ines": { "accuracy": 0.44, "macro_f1": 0.34548854604955587 }, "julia": { "accuracy": 0.56, "macro_f1": 0.5571658615136876 }, "laya": { "accuracy": 0.65, "macro_f1": 0.6419437340153453 }, "gliner": { "accuracy": 0.52, "macro_f1": 0.39117199391172 }, "gemma": { "accuracy": 0.88, "macro_f1": 0.8798076923076923 } }, "B": { "ines": { "accuracy": 0.73, "macro_f1": 0.72997299729973 }, "julia": { "accuracy": 0.63, "macro_f1": 0.6189887756152817 }, "laya": { "accuracy": 0.83, "macro_f1": 0.8279178054458953 }, "gliner": { "accuracy": 0.62, "macro_f1": 0.5703301673450927 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "single request", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "wikitoxic_threat": { "labels": 2, "in_ines_ft_mixture": true, "A": { "ines": { "accuracy": 0.47, "macro_f1": 0.3497730339835603 }, "julia": { "accuracy": 0.47, "macro_f1": 0.467390212038991 }, "laya": { "accuracy": 0.91, "macro_f1": 0.90999099909991 }, "gliner": { "accuracy": 0.53, "macro_f1": 0.39673982800667434 }, "gemma": { "accuracy": 0.97, "macro_f1": 0.96999699969997 } }, "B": { "ines": { "accuracy": 0.73, "macro_f1": 0.7253585596582239 }, "julia": { "accuracy": 0.55, "macro_f1": 0.54226426609704 }, "laya": { "accuracy": 0.77, "macro_f1": 0.7613860358958398 }, "gliner": { "accuracy": 0.52, "macro_f1": 0.37629937629937626 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "single request", "laya": "single request", "gliner": "single request", "gemma": "single request" } }, "wikitoxic_toxicaggregated": { "labels": 2, "in_ines_ft_mixture": true, "A": { "ines": { "accuracy": 0.33, "macro_f1": 0.30490714804440294 }, "julia": { "accuracy": 0.57, "macro_f1": 0.5501621508525996 }, "laya": { "accuracy": 0.7, "macro_f1": 0.6921182266009853 }, "gliner": { "accuracy": 0.62, "macro_f1": 0.5766488413547237 }, "gemma": { "accuracy": 0.85, "macro_f1": 0.84998499849985 } }, "B": { "ines": { "accuracy": 0.77, "macro_f1": 0.7681217864704104 }, "julia": { "accuracy": 0.57, "macro_f1": 0.557203171661003 }, "laya": { "accuracy": 0.87, "macro_f1": 0.8677652324280338 }, "gliner": { "accuracy": 0.62, "macro_f1": 0.5766488413547237 }, "gemma": null }, "trackA_strategy": { "ines": "single request", "julia": "single request", "laya": "single request", "gliner": "single request", "gemma": "single request" } } }, "global": { "all 22": { "A": { "ines": 0.4739229278426516, "julia": 0.5245951186849342, "laya": 0.5301139532382007, "gliner": 0.536710369477031, "gemma": 0.7994690041839767 }, "B": { "ines": 0.45679397195871585, "julia": 0.3572179797391928, "laya": 0.6294614568454058, "gliner": 0.44952051094233986, "gemma": null } }, "2 labels (13)": { "A": { "ines": 0.561538769269558, "julia": 0.5825291987072047, "laya": 0.7219571619118916, "gliner": 0.627447823733444, "gemma": 0.8973820729652007 }, "B": { "ines": 0.6295911198690077, "julia": 0.5172849909267092, "laya": 0.7758169828614861, "gliner": 0.5718255850749258, "gemma": null } }, "3-20 labels (4)": { "A": { "ines": 0.48884952899904605, "julia": 0.6335545038498116, "laya": 0.5593357296978444, "gliner": 0.5412491344877212, "gemma": 0.6952123475409966 }, "B": { "ines": 0.28323609763701546, "julia": 0.23521866463768246, "laya": 0.6478880971986014, "gliner": 0.3784716661760502, "gemma": null } }, "21-72 labels (5)": { "A": { "ines": 0.23418045920757943, "julia": 0.28679900249512835, "laya": 0.00794418951888898, "gliner": 0.29716197640180464, "gemma": 0.6283003506671788 }, "B": { "ines": 0.14636768684931714, "julia": 0.03864320273285837, "laya": 0.23419577692104018, "gliner": 0.18836639401064836, "gemma": null } }, "absent from Ines-1 decision FT mixture (15)": { "A": { "ines": 0.4858805497724014, "julia": 0.5360250230979545, "laya": 0.5154640164128853, "gliner": 0.5280778437879452, "gemma": 0.7649777943405899 }, "B": { "ines": 0.4094576296280325, "julia": 0.3319018448171922, "laya": 0.6114586574566909, "gliner": 0.4284732740710553, "gemma": null } }, "families in Ines-1 decision FT mixture (7)": { "A": { "ines": 0.44829945227890217, "julia": 0.500102466371319, "laya": 0.5615066750067336, "gliner": 0.5552086388107859, "gemma": 0.8733787395626631 }, "B": { "ines": 0.5582289912387514, "julia": 0.411466840286337, "laya": 0.6680388841069373, "gliner": 0.4946217328093781, "gemma": null } } }, "bootstrap": { "all 22": { "A:julia - A:ines": { "difference": 0.050672190842282465, "ci95": [ -0.026197789339992814, 0.12574349835362167 ] }, "A:laya - A:ines": { "difference": 0.05619102539554903, "ci95": [ -0.03957741468351192, 0.16332715413710902 ] }, "A:gliner - A:ines": { "difference": 0.06278744163437923, "ci95": [ 0.014208626140706566, 0.10706083324209556 ] }, "A:gemma - A:ines": { "difference": 0.32554607634132515, "ci95": [ 0.2531753321872848, 0.39198685847503467 ] }, "B:julia - B:ines": { "difference": -0.099575992219523, "ci95": [ -0.14637550498902815, -0.05017137416536893 ] }, "B:laya - B:ines": { "difference": 0.17266748488669, "ci95": [ 0.11284488099527132, 0.23744000375671462 ] }, "B:gliner - B:ines": { "difference": -0.007273461016375937, "ci95": [ -0.06982555475121606, 0.05100715361862577 ] }, "B:ines - A:ines": { "difference": -0.017128955883935842, "ci95": [ -0.09913170297625284, 0.07045906519324419 ] }, "B:julia - A:julia": { "difference": -0.16737713894574127, "ci95": [ -0.2550239493204071, -0.08802480974576297 ] }, "B:laya - A:laya": { "difference": 0.09934750360720516, "ci95": [ 0.0454206858231911, 0.14433272375703962 ] }, "B:gliner - A:gliner": { "difference": -0.087189858534691, "ci95": [ -0.13204415683257073, -0.0406803117967699 ] } }, "2 labels (13)": { "A:julia - A:ines": { "difference": 0.020990429437646712, "ci95": [ -0.06061145608979183, 0.10740818043124331 ] }, "A:laya - A:ines": { "difference": 0.16041839264233365, "ci95": [ 0.059458802921318936, 0.27206775011759543 ] }, "A:gliner - A:ines": { "difference": 0.0659090544638859, "ci95": [ 0.004675393764386895, 0.12582906809147268 ] }, "A:gemma - A:ines": { "difference": 0.33584330369564275, "ci95": [ 0.25214648887513785, 0.4349238101458538 ] }, "B:julia - B:ines": { "difference": -0.11230612894229851, "ci95": [ -0.18080307502401038, -0.042581067377537536 ] }, "B:laya - B:ines": { "difference": 0.14622586299247847, "ci95": [ 0.09520841847771228, 0.20567775456268422 ] }, "B:gliner - B:ines": { "difference": -0.057765534794081974, "ci95": [ -0.1428996478267053, 0.029876283921421498 ] }, "B:ines - A:ines": { "difference": 0.06805235059944967, "ci95": [ -0.04906521051519053, 0.19755199873107607 ] }, "B:julia - A:julia": { "difference": -0.06524420778049556, "ci95": [ -0.12548066475124145, -0.012510733064128867 ] }, "B:laya - A:laya": { "difference": 0.05385982094959447, "ci95": [ -0.0009695761275055773, 0.1065780484194153 ] }, "B:gliner - A:gliner": { "difference": -0.0556222386585182, "ci95": [ -0.11618959302529945, 0.007571405517821818 ] } }, "3-20 labels (4)": { "A:julia - A:ines": { "difference": 0.14470497485076556, "ci95": [ -0.12895039644581718, 0.42568245069405136 ] }, "A:laya - A:ines": { "difference": 0.07048620069879838, "ci95": [ -0.229964039114142, 0.3531563180395061 ] }, "A:gliner - A:ines": { "difference": 0.052399605488675075, "ci95": [ -0.05581876515491288, 0.1600753585487263 ] }, "A:gemma - A:ines": { "difference": 0.2063628185419505, "ci95": [ 0.06159339629875036, 0.3329951554044995 ] }, "B:julia - B:ines": { "difference": -0.048017432999332976, "ci95": [ -0.16164512046595278, 0.05754769356829411 ] }, "B:laya - B:ines": { "difference": 0.364651999561586, "ci95": [ 0.18329205393405798, 0.5540391760322673 ] }, "B:gliner - B:ines": { "difference": 0.09523556853903474, "ci95": [ 0.01900107622902177, 0.17430955225269407 ] }, "B:ines - A:ines": { "difference": -0.2056134313620306, "ci95": [ -0.3164880910714138, -0.09244502441135767 ] }, "B:julia - A:julia": { "difference": -0.3983358392121291, "ci95": [ -0.5756158997267588, -0.20827382157801752 ] }, "B:laya - A:laya": { "difference": 0.08855236750075707, "ci95": [ -0.008752159824462086, 0.1939655463264431 ] }, "B:gliner - A:gliner": { "difference": -0.16277746831167095, "ci95": [ -0.25637377988986315, -0.07162803351218687 ] } }, "21-72 labels (5)": { "A:julia - A:ines": { "difference": 0.05261854328754896, "ci95": [ -0.04301551177445001, 0.15765204279382006 ] }, "A:laya - A:ines": { "difference": -0.22623626968869046, "ci95": [ -0.30032025667320744, -0.12187817221877785 ] }, "A:gliner - A:ines": { "difference": 0.06298151719422522, "ci95": [ -0.039063579916225874, 0.1689149673736492 ] }, "A:gemma - A:ines": { "difference": 0.39411989145959925, "ci95": [ 0.3019916275555586, 0.473337812412976 ] }, "B:julia - B:ines": { "difference": -0.10772448411645877, "ci95": [ -0.15259487999276594, -0.04920310152464395 ] }, "B:laya - B:ines": { "difference": 0.0878280900717231, "ci95": [ 0.011100563313016499, 0.14839732102914302 ] }, "B:gliner - B:ines": { "difference": 0.041998707161331236, "ci95": [ -0.019529909671919345, 0.11057761360469363 ] }, "B:ines - A:ines": { "difference": -0.08781277235826232, "ci95": [ -0.12624266008952723, -0.04849955912024958 ] }, "B:julia - A:julia": { "difference": -0.24815579976227004, "ci95": [ -0.3988206525705068, -0.09861247338677506 ] }, "B:laya - A:laya": { "difference": 0.22625158740215126, "ci95": [ 0.12816497504348637, 0.286499258070288 ] }, "B:gliner - A:gliner": { "difference": -0.1087955823911563, "ci95": [ -0.1700071752364474, -0.032048604061386245 ] } }, "absent from Ines-1 decision FT mixture (15)": { "A:julia - A:ines": { "difference": 0.050144473325553045, "ci95": [ -0.028885054771255515, 0.1500566532935792 ] }, "A:laya - A:ines": { "difference": 0.029583466640483884, "ci95": [ -0.08075161791194013, 0.14421513826606108 ] }, "A:gliner - A:ines": { "difference": 0.04219729401554383, "ci95": [ -0.006600902674686908, 0.09437438464034366 ] }, "A:gemma - A:ines": { "difference": 0.2790972445681884, "ci95": [ 0.211381616754686, 0.3521485454260135 ] }, "B:julia - B:ines": { "difference": -0.0775557848108404, "ci95": [ -0.14064220126958463, -0.013517268561773333 ] }, "B:laya - B:ines": { "difference": 0.2020010278286585, "ci95": [ 0.1269579464717378, 0.2900629696566373 ] }, "B:gliner - B:ines": { "difference": 0.019015644443022794, "ci95": [ -0.03174972794352044, 0.07223435697834166 ] }, "B:ines - A:ines": { "difference": -0.0764229201443689, "ci95": [ -0.15017289217507543, -0.009184764537925973 ] }, "B:julia - A:julia": { "difference": -0.20412317828076224, "ci95": [ -0.2998785466263466, -0.11592881332069362 ] }, "B:laya - A:laya": { "difference": 0.09599464104380576, "ci95": [ 0.0459047217540702, 0.1442013728576654 ] }, "B:gliner - A:gliner": { "difference": -0.09960456971688988, "ci95": [ -0.14649500828750583, -0.04960181354566028 ] } }, "families in Ines-1 decision FT mixture (7)": { "A:julia - A:ines": { "difference": 0.051803014092416944, "ci95": [ -0.10019425716510703, 0.1778425425557031 ] }, "A:laya - A:ines": { "difference": 0.11320722272783149, "ci95": [ -0.12479087223953271, 0.3295312555301822 ] }, "A:gliner - A:ines": { "difference": 0.10690918653188367, "ci95": [ 0.019280206335977032, 0.19106643449909544 ] }, "A:gemma - A:ines": { "difference": 0.42507928728376093, "ci95": [ 0.28040693225491636, 0.5352594526522105 ] }, "B:julia - B:ines": { "difference": -0.14676215095241435, "ci95": [ -0.1986636251903599, -0.08740265140015356 ] }, "B:laya - B:ines": { "difference": 0.10980989286818602, "ci95": [ 0.03243625252632493, 0.19414880936010162 ] }, "B:gliner - B:ines": { "difference": -0.06360725842937322, "ci95": [ -0.21886027228587646, 0.08094216222892091 ] }, "B:ines - A:ines": { "difference": 0.10992953895984924, "ci95": [ -0.07562649281899102, 0.2927199100383737 ] }, "B:julia - A:julia": { "difference": -0.08863562608498207, "ci95": [ -0.24495270619294315, 0.033542744774361914 ] }, "B:laya - A:laya": { "difference": 0.10653220910020378, "ci95": [ -0.015590406007179902, 0.20797413933948058 ] }, "B:gliner - A:gliner": { "difference": -0.06058690600140765, "ci95": [ -0.14995189706107254, 0.032545729267887305 ] } } }, "calibration": { "native (Track A, full native distributions, <=20 labels, 17 datasets)": { "ines": { "brier": 0.5014338202978408, "nll": 0.8000206904458703, "ece": 0.1270706365126021, "coverage_at_error_budget": 0.08941176470588236, "mean_confidence": 0.6118652016888647, "datasets": 17 }, "julia": { "brier": 0.645280763707045, "nll": 1.6618435294062641, "ece": 0.2983721069531266, "coverage_at_error_budget": 0.1288235294117647, "mean_confidence": 0.8941619627630315, "datasets": 17 }, "laya": { "brier": 0.4006447652764705, "nll": 0.6925248427789752, "ece": 0.09332229411764704, "coverage_at_error_budget": 0.25588235294117645, "mean_confidence": 0.6874152352941176, "datasets": 17 }, "gliner": { "brier": 0.48542838104085484, "nll": 0.8599173300405782, "ece": 0.1585389382487745, "coverage_at_error_budget": 0.19705882352941173, "mean_confidence": 0.7310719386879542, "datasets": 17 }, "gemma": { "brier": 0.24999771502464618, "nll": 0.6128898920857043, "ece": 0.1156891273014901, "coverage_at_error_budget": 0.693529411764706, "mean_confidence": 0.9580137741914275, "datasets": 17 } }, "derived (Track B softmax of log-odds, same 17 datasets)": { "ines": { "brier": 0.5266089613872135, "nll": 0.8626628971730973, "ece": 0.11876053221277025, "coverage_at_error_budget": 0.1335294117647059, "mean_confidence": 0.4924301710578631, "datasets": 17 }, "julia": { "brier": 0.7685502933200778, "nll": 1.5719702226511314, "ece": 0.31343832319933446, "coverage_at_error_budget": 0.014117647058823528, "mean_confidence": 0.7770917395785171, "datasets": 17 }, "laya": { "brier": 0.35941673886508035, "nll": 0.6807608663005745, "ece": 0.12656927310814167, "coverage_at_error_budget": 0.38176470588235295, "mean_confidence": 0.7694262437653563, "datasets": 17 }, "gliner": { "brier": 0.5872442915941616, "nll": 1.0308428769681912, "ece": 0.2029575594285007, "coverage_at_error_budget": 0.03705882352941177, "mean_confidence": 0.7019368747032854, "datasets": 17 } }, "derived (Track B softmax of log-odds, all 22 datasets)": { "ines": { "brier": 0.6231953131399431, "nll": 1.4522999819886815, "ece": 0.12354853986128157, "coverage_at_error_budget": 0.10590909090909091, "mean_confidence": 0.39202771650296064, "datasets": 22 }, "julia": { "brier": 0.8554517402951244, "nll": 2.468274766821923, "ece": 0.31679964418123413, "coverage_at_error_budget": 0.011363636363636364, "mean_confidence": 0.687741939307485, "datasets": 22 }, "laya": { "brier": 0.47884708479764443, "nll": 1.203588850522752, "ece": 0.12330875423821963, "coverage_at_error_budget": 0.29681818181818187, "mean_confidence": 0.6690071844208508, "datasets": 22 }, "gliner": { "brier": 0.6643794367941797, "nll": 1.5673671850720794, "ece": 0.18732672413963056, "coverage_at_error_budget": 0.031363636363636364, "mean_confidence": 0.5655688289154754, "datasets": 22 } } }, "ines_ablation": { "agnews": { "labels": 4, "accuracy": { "native(<=26)": 0.59, "knockout-20": null, "knockout-2": 0.64, "one-vs-rest": 0.42 }, "macro_f1": { "native(<=26)": 0.5843451916892106, "knockout-20": null, "knockout-2": 0.639691081949832, "one-vs-rest": 0.32652938961350175 } }, "emotiondair": { "labels": 6, "accuracy": { "native(<=26)": 0.43, "knockout-20": null, "knockout-2": 0.43, "one-vs-rest": 0.34 }, "macro_f1": { "native(<=26)": 0.39042230395613853, "knockout-20": null, "knockout-2": 0.39217171717171717, "one-vs-rest": 0.29478472669962036 } }, "banking77": { "labels": 72, "accuracy": { "native(<=26)": null, "knockout-20": 0.39, "knockout-2": 0.45, "one-vs-rest": 0.29 }, "macro_f1": { "native(<=26)": null, "knockout-20": 0.34265873015873016, "knockout-2": 0.4010912698412698, "one-vs-rest": 0.2234898589065256 } }, "financialphrasebank": { "labels": 3, "accuracy": { "native(<=26)": 0.51, "knockout-20": null, "knockout-2": 0.44, "one-vs-rest": 0.45 }, "macro_f1": { "native(<=26)": 0.48911853494169083, "knockout-20": null, "knockout-2": 0.3744570258331727, "one-vs-rest": 0.388558378810103 } }, "empathetic": { "labels": 32, "accuracy": { "native(<=26)": null, "knockout-20": 0.25, "knockout-2": 0.16, "one-vs-rest": 0.18 }, "macro_f1": { "native(<=26)": null, "knockout-20": 0.1909003551273288, "knockout-2": 0.10230728593731689, "one-vs-rest": 0.14416745535166586 } }, "massive": { "labels": 59, "accuracy": { "native(<=26)": null, "knockout-20": 0.35, "knockout-2": 0.41, "one-vs-rest": 0.2 }, "macro_f1": { "native(<=26)": null, "knockout-20": 0.2502433536331841, "knockout-2": 0.3015873015873015, "one-vs-rest": 0.15282852740479855 } }, "yahootopics": { "labels": 10, "accuracy": { "native(<=26)": 0.5, "knockout-20": null, "knockout-2": 0.57, "one-vs-rest": 0.18 }, "macro_f1": { "native(<=26)": 0.4915120854091442, "knockout-20": null, "knockout-2": 0.5584408865987813, "one-vs-rest": 0.12307189542483658 } }, "manifesto": { "labels": 56, "accuracy": { "native(<=26)": null, "knockout-20": 0.11, "knockout-2": 0.18, "one-vs-rest": 0.05 }, "macro_f1": { "native(<=26)": null, "knockout-20": 0.07504578754578754, "knockout-2": 0.14917929292929294, "one-vs-rest": 0.032902735562310034 } }, "capsotu": { "labels": 21, "accuracy": { "native(<=26)": 0.36, "knockout-20": 0.37, "knockout-2": 0.39, "one-vs-rest": 0.21 }, "macro_f1": { "native(<=26)": 0.3120540695728665, "knockout-20": 0.3317682178584434, "knockout-2": 0.3739835503810659, "one-vs-rest": 0.17844985702128557 } } }, "anchors": { "GLiNER2.5 Track A vs published pilot (accuracy)": { "agnews": { "ours": 0.7, "published": 0.7 }, "emotiondair": { "ours": 0.44, "published": 0.44 }, "banking77": { "ours": 0.61, "published": 0.61 } }, "Julia-1 Track A vs its model card (accuracy)": { "agnews": { "ours": 0.94, "card": 0.94, "ours_strategy": "single request" }, "emotiondair": { "ours": 0.86, "card": 0.86, "ours_strategy": "single request" }, "banking77": { "ours": 0.63, "card": 0.64, "ours_strategy": "Router(width=20, survivors=2)" } } }, "ovr_ties": { "ines": { "examples_with_tie_at_max": 268, "n": 2200 }, "julia": { "examples_with_tie_at_max": 4, "n": 2200 }, "laya": { "examples_with_tie_at_max": 11, "n": 2200 }, "gliner": { "examples_with_tie_at_max": 0, "n": 2200 } }, "addon": { "date": "2026-10-06", "model": "RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic (DiffusionGemma-26B-A4B-it, FP8) via razorback16/openjev:0.4.0, model openjev-0.1, think 0", "scope": "Track A (native) only; added after the btzsc22-ext-v1 freeze; the four original models are recomputed by the same code and match results.json exactly" } }