algorise's picture
download
raw
52.9 kB
{
"datasets": {
"moons-hard": {
"acc": {
"linear-svm": {
"mean": 0.8481200000000001,
"ci_hw": 0.003945448596207932,
"lo": 0.8441745514037922,
"hi": 0.852065448596208,
"n": 25
},
"rbf-svm": {
"mean": 0.9086799999999999,
"ci_hw": 0.002745114400871819,
"lo": 0.9059348855991282,
"hi": 0.9114251144008717,
"n": 25
},
"deep-ce": {
"mean": 0.9127999997138977,
"ci_hw": 0.003334329477459666,
"lo": 0.909465670236438,
"hi": 0.9161343291913574,
"n": 25
},
"deep-svm": {
"mean": 0.9111600017547608,
"ci_hw": 0.0029058246494307115,
"lo": 0.9082541771053301,
"hi": 0.9140658264041914,
"n": 25
},
"ddsvm": {
"mean": 0.911639997959137,
"ci_hw": 0.0030679297061277726,
"lo": 0.9085720682530092,
"hi": 0.9147079276652648,
"n": 25
},
"ddsvm-rand": {
"mean": 0.9123600029945373,
"ci_hw": 0.0029330633222432166,
"lo": 0.9094269396722942,
"hi": 0.9152930663167805,
"n": 25
}
},
"paired": {
"ddsvm_vs_deep-ce": {
"mean": -0.001160001754760742,
"ci_hw": 0.0017047676723188042,
"lo": -0.0028647694270795463,
"hi": 0.0005447659175580621,
"p_ttest": 0.1730183666374289,
"p_wilcoxon": 0.18436571086917108,
"n": 25,
"ci_excludes_zero": false
},
"ddsvm_vs_deep-svm": {
"mean": 0.0004799962043762207,
"ci_hw": 0.0012217184969882384,
"lo": -0.0007417222926120177,
"hi": 0.0017017147013644591,
"p_ttest": 0.42540485271054074,
"p_wilcoxon": 0.5240452276574604,
"n": 25,
"ci_excludes_zero": false
},
"ddsvm_vs_rbf-svm": {
"mean": 0.002959997959136933,
"ci_hw": 0.0018011587199507691,
"lo": 0.0011588392391861638,
"hi": 0.004761156679087702,
"p_ttest": 0.0024056929968216253,
"p_wilcoxon": 0.008822321891784668,
"n": 25,
"ci_excludes_zero": true
},
"ddsvm_vs_linear-svm": {
"mean": 0.06351999795913699,
"ci_hw": 0.0030892395954081673,
"lo": 0.06043075836372882,
"hi": 0.06660923755454515,
"p_ttest": 4.340828738073182e-24,
"p_wilcoxon": 5.960464477539063e-08,
"n": 25,
"ci_excludes_zero": true
},
"ddsvm_vs_ddsvm-rand": {
"mean": -0.0007200050354003906,
"ci_hw": 0.001021715372869316,
"lo": -0.0017417204082697067,
"hi": 0.00030171033746892537,
"p_ttest": 0.15878046786905217,
"p_wilcoxon": 0.13426663796245403,
"n": 25,
"ci_excludes_zero": false
}
},
"test_norm_margin": {
"deep-svm": {
"mean": 0.6956362819671631,
"ci_hw": 0.010435007105020025,
"n": 25
},
"ddsvm": {
"mean": 0.7277236294746399,
"ci_hw": 0.007886950178183841,
"n": 25
},
"ddsvm-rand": {
"mean": 0.732604386806488,
"ci_hw": 0.008616664020138023,
"n": 25
}
},
"margin_paired": {
"ddsvm_vs_deep-svm": {
"mean": 0.032087347507476806,
"ci_hw": 0.011500168816271637,
"lo": 0.020587178691205167,
"hi": 0.043587516323748444,
"p_ttest": 6.186256101005496e-06,
"p_wilcoxon": 1.0073184967041016e-05,
"n": 25,
"ci_excludes_zero": true
},
"ddsvm_vs_ddsvm-rand": {
"mean": -0.004880757331848145,
"ci_hw": 0.009274110445744348,
"lo": -0.014154867777592492,
"hi": 0.004393353113896203,
"p_ttest": 0.2881873176419185,
"p_wilcoxon": 0.312333345413208,
"n": 25,
"ci_excludes_zero": false
}
}
},
"rings": {
"acc": {
"linear-svm": {
"mean": 0.5072000000000001,
"ci_hw": 0.024109068061267357,
"lo": 0.48309093193873276,
"hi": 0.5313090680612674,
"n": 25
},
"rbf-svm": {
"mean": 0.86652,
"ci_hw": 0.004256704265518667,
"lo": 0.8622632957344812,
"hi": 0.8707767042655187,
"n": 25
},
"deep-ce": {
"mean": 0.8637200045585632,
"ci_hw": 0.0048042313574395284,
"lo": 0.8589157732011237,
"hi": 0.8685242359160028,
"n": 25
},
"deep-svm": {
"mean": 0.8661200022697448,
"ci_hw": 0.004451070866054706,
"lo": 0.8616689314036902,
"hi": 0.8705710731357995,
"n": 25
},
"ddsvm": {
"mean": 0.8655599999427795,
"ci_hw": 0.004668671303447162,
"lo": 0.8608913286393324,
"hi": 0.8702286712462267,
"n": 25
},
"ddsvm-rand": {
"mean": 0.8660799980163574,
"ci_hw": 0.004716838975361723,
"lo": 0.8613631590409957,
"hi": 0.8707968369917191,
"n": 25
}
},
"paired": {
"ddsvm_vs_deep-ce": {
"mean": 0.0018399953842163086,
"ci_hw": 0.0014723768942708152,
"lo": 0.00036761848994549336,
"hi": 0.003312372278487124,
"p_ttest": 0.016459030485568106,
"p_wilcoxon": 0.031602850238570936,
"n": 25,
"ci_excludes_zero": true
},
"ddsvm_vs_deep-svm": {
"mean": -0.0005600023269653321,
"ci_hw": 0.0010861153325947592,
"lo": -0.0016461176595600913,
"hi": 0.0005261130056294271,
"p_ttest": 0.29785143344846177,
"p_wilcoxon": 0.3149534488128901,
"n": 25,
"ci_excludes_zero": false
},
"ddsvm_vs_rbf-svm": {
"mean": -0.0009600000572204515,
"ci_hw": 0.001518896128816546,
"lo": -0.0024788961860369974,
"hi": 0.0005588960715960945,
"p_ttest": 0.2044474423673455,
"p_wilcoxon": 0.2996123433113098,
"n": 25,
"ci_excludes_zero": false
},
"ddsvm_vs_linear-svm": {
"mean": 0.3583599999427795,
"ci_hw": 0.024755568610761967,
"lo": 0.33360443133201756,
"hi": 0.38311556855354145,
"p_ttest": 1.6937495116201298e-20,
"p_wilcoxon": 5.960464477539063e-08,
"n": 25,
"ci_excludes_zero": true
},
"ddsvm_vs_ddsvm-rand": {
"mean": -0.0005199980735778809,
"ci_hw": 0.0008351362952119806,
"lo": -0.0013551343687898615,
"hi": 0.0003151382216340997,
"p_ttest": 0.21102573235776625,
"p_wilcoxon": 0.25376969576785324,
"n": 25,
"ci_excludes_zero": false
}
},
"test_norm_margin": {
"deep-svm": {
"mean": 0.7331007409095764,
"ci_hw": 0.004302176888475539,
"n": 25
},
"ddsvm": {
"mean": 0.7134105753898621,
"ci_hw": 0.007618533848000743,
"n": 25
},
"ddsvm-rand": {
"mean": 0.7146120357513428,
"ci_hw": 0.007377401813985203,
"n": 25
}
},
"margin_paired": {
"ddsvm_vs_deep-svm": {
"mean": -0.019690165519714354,
"ci_hw": 0.007624218315193087,
"lo": -0.02731438383490744,
"hi": -0.012065947204521267,
"p_ttest": 1.8053990287322344e-05,
"p_wilcoxon": 1.233816146850586e-05,
"n": 25,
"ci_excludes_zero": true
},
"ddsvm_vs_ddsvm-rand": {
"mean": -0.0012014603614807129,
"ci_hw": 0.007362390600183422,
"lo": -0.008563850961664135,
"hi": 0.006160930238702709,
"p_ttest": 0.7391911418413584,
"p_wilcoxon": 0.978915274143219,
"n": 25,
"ci_excludes_zero": false
}
}
},
"gauss-xor": {
"acc": {
"linear-svm": {
"mean": 0.49796,
"ci_hw": 0.007836910286049405,
"lo": 0.49012308971395063,
"hi": 0.5057969102860495,
"n": 25
},
"rbf-svm": {
"mean": 0.7982,
"ci_hw": 0.004141533590917648,
"lo": 0.7940584664090824,
"hi": 0.8023415335909176,
"n": 25
},
"deep-ce": {
"mean": 0.7459599924087524,
"ci_hw": 0.007280893020853958,
"lo": 0.7386790993878984,
"hi": 0.7532408854296064,
"n": 25
},
"deep-svm": {
"mean": 0.759799997806549,
"ci_hw": 0.005352888576084247,
"lo": 0.7544471092304648,
"hi": 0.7651528863826333,
"n": 25
},
"ddsvm": {
"mean": 0.7898399996757507,
"ci_hw": 0.004925587751820648,
"lo": 0.7849144119239301,
"hi": 0.7947655874275713,
"n": 25
},
"ddsvm-rand": {
"mean": 0.7912400007247925,
"ci_hw": 0.0044254162338886625,
"lo": 0.7868145844909038,
"hi": 0.7956654169586812,
"n": 25
}
},
"paired": {
"ddsvm_vs_deep-ce": {
"mean": 0.04388000726699829,
"ci_hw": 0.00607632496434152,
"lo": 0.03780368230265677,
"hi": 0.04995633223133981,
"p_ttest": 1.247773809214336e-13,
"p_wilcoxon": 5.960464477539063e-08,
"n": 25,
"ci_excludes_zero": true
},
"ddsvm_vs_deep-svm": {
"mean": 0.03004000186920166,
"ci_hw": 0.005892636432511468,
"lo": 0.02414736543669019,
"hi": 0.03593263830171313,
"p_ttest": 1.8046564108423801e-10,
"p_wilcoxon": 5.960464477539063e-08,
"n": 25,
"ci_excludes_zero": true
},
"ddsvm_vs_rbf-svm": {
"mean": -0.008360000324249302,
"ci_hw": 0.004677482094520435,
"lo": -0.013037482418769737,
"hi": -0.003682518229728867,
"p_ttest": 0.0011521672973715095,
"p_wilcoxon": 0.0009118914604187012,
"n": 25,
"ci_excludes_zero": true
},
"ddsvm_vs_linear-svm": {
"mean": 0.29187999967575073,
"ci_hw": 0.008549056406231539,
"lo": 0.2833309432695192,
"hi": 0.3004290560819823,
"p_ttest": 2.4791096255720396e-29,
"p_wilcoxon": 5.960464477539063e-08,
"n": 25,
"ci_excludes_zero": true
},
"ddsvm_vs_ddsvm-rand": {
"mean": -0.001400001049041748,
"ci_hw": 0.004373321860544831,
"lo": -0.005773322909586579,
"hi": 0.0029733208115030833,
"p_ttest": 0.5150962016238037,
"p_wilcoxon": 0.5249125957489014,
"n": 25,
"ci_excludes_zero": false
}
},
"test_norm_margin": {
"deep-svm": {
"mean": 0.5224483251571655,
"ci_hw": 0.008971926031335477,
"n": 25
},
"ddsvm": {
"mean": 0.593403959274292,
"ci_hw": 0.006738479685316939,
"n": 25
},
"ddsvm-rand": {
"mean": 0.5940263319015503,
"ci_hw": 0.007336890898395862,
"n": 25
}
},
"margin_paired": {
"ddsvm_vs_deep-svm": {
"mean": 0.07095563411712646,
"ci_hw": 0.0067108743578957065,
"lo": 0.06424475975923076,
"hi": 0.07766650847502217,
"p_ttest": 2.4543062412886753e-17,
"p_wilcoxon": 5.960464477539063e-08,
"n": 25,
"ci_excludes_zero": true
},
"ddsvm_vs_ddsvm-rand": {
"mean": -0.0006223726272583008,
"ci_hw": 0.006491479664124042,
"lo": -0.007113852291382342,
"hi": 0.0058691070368657415,
"p_ttest": 0.8448078303605421,
"p_wilcoxon": 0.936802864074707,
"n": 25,
"ci_excludes_zero": false
}
}
},
"digits-3v8": {
"acc": {
"linear-svm": {
"mean": 0.9824472573839662,
"ci_hw": 0.003884130224745206,
"lo": 0.978563127159221,
"hi": 0.9863313876087114,
"n": 25
},
"rbf-svm": {
"mean": 0.9743459915611814,
"ci_hw": 0.006762739589912673,
"lo": 0.9675832519712687,
"hi": 0.9811087311510941,
"n": 25
},
"deep-ce": {
"mean": 0.969957799911499,
"ci_hw": 0.003937130480755224,
"lo": 0.9660206694307438,
"hi": 0.9738949303922542,
"n": 25
},
"deep-svm": {
"mean": 0.9795780467987061,
"ci_hw": 0.004166721840499094,
"lo": 0.975411324958207,
"hi": 0.9837447686392051,
"n": 25
},
"ddsvm": {
"mean": 0.9755274152755737,
"ci_hw": 0.005415121537744637,
"lo": 0.9701122937378291,
"hi": 0.9809425368133183,
"n": 25
},
"ddsvm-rand": {
"mean": 0.9772151756286621,
"ci_hw": 0.0046896338252034545,
"lo": 0.9725255418034586,
"hi": 0.9819048094538656,
"n": 25
}
},
"paired": {
"ddsvm_vs_deep-ce": {
"mean": 0.005569615364074707,
"ci_hw": 0.005070867446741569,
"lo": 0.0004987479173331382,
"hi": 0.010640482810816275,
"p_ttest": 0.032688882721537534,
"p_wilcoxon": 0.015095338331720862,
"n": 25,
"ci_excludes_zero": true
},
"ddsvm_vs_deep-svm": {
"mean": -0.004050631523132325,
"ci_hw": 0.006408836062118553,
"lo": -0.010459467585250877,
"hi": 0.002358204538986228,
"p_ttest": 0.2044470474639032,
"p_wilcoxon": 0.2540411333248247,
"n": 25,
"ci_excludes_zero": false
},
"ddsvm_vs_rbf-svm": {
"mean": 0.001181423714392289,
"ci_hw": 0.0067739425822590914,
"lo": -0.005592518867866802,
"hi": 0.00795536629665138,
"p_ttest": 0.7220264221290003,
"p_wilcoxon": 0.5249125957489014,
"n": 25,
"ci_excludes_zero": false
},
"ddsvm_vs_linear-svm": {
"mean": -0.0069198421083925335,
"ci_hw": 0.005596025773433344,
"lo": -0.012515867881825878,
"hi": -0.001323816334959189,
"p_ttest": 0.017491942582098536,
"p_wilcoxon": 0.007370948791503906,
"n": 25,
"ci_excludes_zero": true
},
"ddsvm_vs_ddsvm-rand": {
"mean": -0.0016877603530883788,
"ci_hw": 0.0034833707782946565,
"lo": -0.005171131131383035,
"hi": 0.0017956104252062777,
"p_ttest": 0.3272875090621661,
"p_wilcoxon": 0.3785411580145357,
"n": 25,
"ci_excludes_zero": false
}
},
"test_norm_margin": {
"deep-svm": {
"mean": 0.8812785816192626,
"ci_hw": 0.006614158598180567,
"n": 25
},
"ddsvm": {
"mean": 0.09920460628494766,
"ci_hw": 0.12626112874911202,
"n": 25
},
"ddsvm-rand": {
"mean": 0.11813999707963375,
"ci_hw": 0.1229362366623902,
"n": 25
}
},
"margin_paired": {
"ddsvm_vs_deep-svm": {
"mean": -0.782073975334315,
"ci_hw": 0.12527927769116892,
"lo": -0.907353253025484,
"hi": -0.656794697643146,
"p_ttest": 2.8293078673129235e-12,
"p_wilcoxon": 8.344650268554688e-07,
"n": 25,
"ci_excludes_zero": true
},
"ddsvm_vs_ddsvm-rand": {
"mean": -0.0189353907946861,
"ci_hw": 0.02474033604964284,
"lo": -0.04367572684432894,
"hi": 0.005804945254956739,
"p_ttest": 0.12728107366233818,
"p_wilcoxon": 0.09031611680984497,
"n": 25,
"ci_excludes_zero": false
}
}
}
},
"integrity": {
"moons-hard": {
"n_seeds": 25,
"unique_data_hashes": 25,
"all_hashes_distinct": true,
"acc_std_by_method": {
"linear-svm": 0.009365126801063621,
"rbf-svm": 0.006515949662175121,
"deep-ce": 0.007914541931415978,
"deep-svm": 0.006897420062633777,
"ddsvm": 0.007282201253933723,
"ddsvm-rand": 0.006962075226314523
},
"unique_cycle1_hinge": 25,
"wall_time_sec": 145.51979088783264,
"n_train": 2000,
"n_test": 1000,
"d": 2
},
"rings": {
"n_seeds": 25,
"unique_data_hashes": 25,
"all_hashes_distinct": true,
"acc_std_by_method": {
"linear-svm": 0.05722656725682574,
"rbf-svm": 0.010103939825632385,
"deep-ce": 0.011403579275449273,
"deep-svm": 0.01056529873464496,
"ddsvm": 0.011081806715538666,
"ddsvm-rand": 0.0111961400655221
},
"unique_cycle1_hinge": 25,
"wall_time_sec": 333.60646629333496,
"n_train": 2000,
"n_test": 1000,
"d": 2
},
"gauss-xor": {
"n_seeds": 25,
"unique_data_hashes": 25,
"all_hashes_distinct": true,
"acc_std_by_method": {
"linear-svm": 0.018602107407495544,
"rbf-svm": 0.009830564581955598,
"deep-ce": 0.0172823152304689,
"deep-svm": 0.012705901254213657,
"ddsvm": 0.011691637272857072,
"ddsvm-rand": 0.010504403534159885
},
"unique_cycle1_hinge": 25,
"wall_time_sec": 316.4452886581421,
"n_train": 2000,
"n_test": 1000,
"d": 10
},
"digits-3v8": {
"n_seeds": 25,
"unique_data_hashes": 25,
"all_hashes_distinct": true,
"acc_std_by_method": {
"linear-svm": 0.009219578250631341,
"rbf-svm": 0.01605239866588985,
"deep-ce": 0.009345382479458377,
"deep-svm": 0.009890352751912697,
"ddsvm": 0.012853620724622027,
"ddsvm-rand": 0.011131564472997832
},
"unique_cycle1_hinge": 25,
"wall_time_sec": 144.27879452705383,
"n_train": 120,
"n_test": 237,
"d": 64
}
},
"claims": {
"claim1": {
"per_dataset": {
"moons-hard": {
"P1a": {
"max_head_drift_in_phaseA": 0.0,
"max_feat_drift_in_phaseB": 0.0,
"min_feat_move_in_phaseA": 0.14985588192939758,
"min_head_move_in_phaseB": 0.0009283832041546702,
"min_mean_disp_phaseC": 0.017343591898679733,
"n_cycle_observations": 375,
"pass": true
},
"P1b": {
"ratio_mean": 0.4880829667409371,
"ratio_ci_hw": 0.017181249820765014,
"ratio_lo": 0.4709017169201721,
"ratio_hi": 0.5052642165617021,
"final_hinge_mean": 0.19524386167526245,
"final_hinge_ci_hw": 0.004367793713028987,
"n": 25,
"pass": false
},
"P1c": {
"slope": -0.04864119324058819,
"intercept": -1.0557090363454482,
"r2": 0.7793733710548759,
"p_value": 1.3081056231329123e-05,
"degenerate_exact_zero_hinge": false,
"n_exact_zero_observations": 0,
"n_observations": 375,
"first_zero_cycle": null,
"slope_is_floor_artifact": false,
"mean_curve": [
0.4024544131755829,
0.3567036700248718,
0.3193225836753845,
0.29160435318946837,
0.2525572592020035,
0.223736235499382,
0.21039841532707215,
0.20442886114120484,
0.20168400108814238,
0.1998068779706955,
0.19847841918468476,
0.19757314145565033,
0.1968925702571869,
0.19609209418296814,
0.19524386167526245
],
"curve_ci_hw": [
0.015355650374362099,
0.005899713614441445,
0.005944581290708907,
0.008622228190812745,
0.008658079512256195,
0.005625915543979901,
0.004291343473786574,
0.004114122300092711,
0.00423850731497631,
0.0042378920480964245,
0.004277842473866503,
0.0042249287075005635,
0.004290230153521946,
0.004270185441228409,
0.004367793713028987
],
"pass": false
}
},
"rings": {
"P1a": {
"max_head_drift_in_phaseA": 0.0,
"max_feat_drift_in_phaseB": 0.0,
"min_feat_move_in_phaseA": 0.04617142677307129,
"min_head_move_in_phaseB": 0.003242947394028306,
"min_mean_disp_phaseC": 0.005049500614404678,
"n_cycle_observations": 375,
"pass": true
},
"P1b": {
"ratio_mean": 0.42558267076259226,
"ratio_ci_hw": 0.00999983076570627,
"ratio_lo": 0.415582839996886,
"ratio_hi": 0.4355825015282985,
"final_hinge_mean": 0.3189803946018219,
"final_hinge_ci_hw": 0.006330482851472424,
"n": 25,
"pass": true
},
"P1c": {
"slope": -0.024420673875078038,
"intercept": -0.8768704128022116,
"r2": 0.2501125635610935,
"p_value": 0.05763359213414906,
"degenerate_exact_zero_hinge": false,
"n_exact_zero_observations": 0,
"n_observations": 375,
"first_zero_cycle": null,
"slope_is_floor_artifact": false,
"mean_curve": [
0.7506220555305481,
0.34399707198143004,
0.33706104040145873,
0.32638504266738894,
0.3228618597984314,
0.32188896656036375,
0.3211166775226593,
0.320678573846817,
0.3203085553646088,
0.32001298666000366,
0.319764711856842,
0.3195491933822632,
0.31934455513954163,
0.3191612708568573,
0.3189803946018219
],
"curve_ci_hw": [
0.014722522905498123,
0.010099370042641598,
0.006142783373472556,
0.005980568800729116,
0.0061667441202198975,
0.006138104064010285,
0.006182514173793395,
0.006202527915552578,
0.006228400429342432,
0.006250098476669709,
0.006273583254424381,
0.006287892303951095,
0.006305687676590434,
0.006319359162038347,
0.006330482851472424
],
"pass": false
}
},
"gauss-xor": {
"P1a": {
"max_head_drift_in_phaseA": 0.0,
"max_feat_drift_in_phaseB": 0.0,
"min_feat_move_in_phaseA": 0.45711153745651245,
"min_head_move_in_phaseB": 0.00375084369443357,
"min_mean_disp_phaseC": 0.05407912656664848,
"n_cycle_observations": 375,
"pass": true
},
"P1b": {
"ratio_mean": 0.25466056140506416,
"ratio_ci_hw": 0.005992832865213845,
"ratio_lo": 0.2486677285398503,
"ratio_hi": 0.260653394270278,
"final_hinge_mean": 0.2272236728668213,
"final_hinge_ci_hw": 0.006161896122254704,
"n": 25,
"pass": true
},
"P1c": {
"slope": -0.06970394212342047,
"intercept": -0.4942110531230731,
"r2": 0.8110862801145821,
"p_value": 4.691081089276253e-06,
"degenerate_exact_zero_hinge": false,
"n_exact_zero_observations": 0,
"n_observations": 375,
"first_zero_cycle": null,
"slope_is_floor_artifact": false,
"mean_curve": [
0.8918926334381103,
0.5612753820419312,
0.41771032571792605,
0.3870406246185303,
0.3716553771495819,
0.35994244933128355,
0.34778363585472105,
0.3349344849586487,
0.32063512325286864,
0.30562763690948486,
0.2902171468734741,
0.27442299962043765,
0.2585348755121231,
0.24309480249881743,
0.2272236728668213
],
"curve_ci_hw": [
0.005311006696482533,
0.014532500338628965,
0.007696370826948051,
0.006083750135142318,
0.006030195099285395,
0.0061906190562797765,
0.0065358735502344025,
0.0067778841584598334,
0.006927103742273247,
0.006863921638514571,
0.006587979552395042,
0.006319214290251313,
0.005899510755454413,
0.005808439701513146,
0.006161896122254704
],
"pass": true
}
},
"digits-3v8": {
"P1a": {
"max_head_drift_in_phaseA": 0.0,
"max_feat_drift_in_phaseB": 0.0,
"min_feat_move_in_phaseA": 1.666782765141761e-07,
"min_head_move_in_phaseB": 0.0005479278042912483,
"min_mean_disp_phaseC": 8.93519214173466e-08,
"n_cycle_observations": 375,
"pass": true
},
"P1b": {
"ratio_mean": 0.0,
"ratio_ci_hw": 0.0,
"ratio_lo": 0.0,
"ratio_hi": 0.0,
"final_hinge_mean": 0.0,
"final_hinge_ci_hw": 0.0,
"n": 25,
"pass": false
},
"P1c": {
"slope": -44.15372339119516,
"intercept": -200.23525764492024,
"r2": 0.4825352439644267,
"p_value": 0.004053583465018846,
"degenerate_exact_zero_hinge": true,
"n_exact_zero_observations": 310,
"n_observations": 375,
"first_zero_cycle": 4,
"slope_is_floor_artifact": true,
"mean_curve": [
0.16881915628910066,
0.018089673947542906,
0.0010302069064346143,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"curve_ci_hw": [
0.011235980297331877,
0.004723074115750731,
0.0005092544485731841,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"pass": false
}
}
},
"checks": [
true,
false,
false,
true,
true,
false,
true,
true,
true,
true,
false,
false
],
"n_pass": 7,
"n_checks": 12,
"verdict": "PARTIAL"
},
"claim2": {
"per_dataset": {
"moons-hard": {
"P2a": {
"mean": 0.09472618928584658,
"ci_hw": 0.011178990213416102,
"lo": 0.08354719907243048,
"hi": 0.10590517949926269,
"n": 25,
"pass": false,
"control_random_push_cos_mean": 0.020378823895240202,
"control_random_push_cos_ci_hw": 0.00706374781729617,
"posthoc_cos_vs_random_paired": {
"mean": 0.07434736539060638,
"ci_hw": 0.013342153430633556,
"lo": 0.06100521195997283,
"hi": 0.08768951882123993,
"p_ttest": 2.9965216174176984e-11,
"p_wilcoxon": 5.960464477539063e-08,
"n": 25,
"ci_excludes_zero": true
}
},
"P2b": {
"mean": 0.02327192480045293,
"ci_hw": 0.0014909770897416272,
"lo": 0.0217809477107113,
"hi": 0.024762901890194557,
"n": 25,
"pass": true
},
"P2c": {
"growth_mean": 0.27473395824432373,
"growth_ci_hw": 0.23249424400957325,
"growth_lo": 0.04223971423475048,
"growth_hi": 0.507228202253897,
"frac_seeds_violators_down": 1.0,
"n": 25,
"pass": true
},
"P2d": {
"mean": -0.004880757331848145,
"ci_hw": 0.009274110445744348,
"lo": -0.014154867777592492,
"hi": 0.004393353113896203,
"p_ttest": 0.2881873176419185,
"p_wilcoxon": 0.312333345413208,
"n": 25,
"ci_excludes_zero": false,
"pass": false
},
"active_frac_curve": [
0.24652000069618224,
0.19904000103473662,
0.22295999944210051,
0.21057999968528748,
0.20047999799251556,
0.17561999917030335,
0.16178000032901763,
0.1538400012254715,
0.15058000028133392,
0.14777999937534333,
0.14557999849319458,
0.14431999802589415,
0.14262000054121018,
0.14153999894857405,
0.1399199992418289
],
"active_frac_ci": [
0.008968954992797632,
0.003641147857329583,
0.003703495715973862,
0.0036131399358019373,
0.0054934481780890675,
0.005399202493323466,
0.0033412853497618855,
0.002840342357769159,
0.0027745689483292704,
0.0028318067051777353,
0.003154166122225843,
0.0031800563211225354,
0.003030535449994512,
0.003233762498204213,
0.0034641743610007054
],
"violators_curve": [
502.48,
385.4,
460.6,
409.56,
395.4,
349.04,
322.52,
305.96,
297.12,
293.16,
288.72,
286.88,
284.04,
282.32,
279.8
],
"margin_pre_curve": [
2.490618929862976,
3.5498769760131834,
2.295317039489746,
2.248809585571289,
2.1657674884796143,
2.554211301803589,
2.8857970905303953,
3.0232308292388916,
3.04231671333313,
2.9990116691589357,
2.944653434753418,
2.890003728866577,
2.8540428256988526,
2.8068303298950195,
2.772229290008545
],
"margin_post_curve": [
2.3216859483718872,
3.732334966659546,
2.0899335670471193,
2.275066947937012,
2.1864734935760497,
2.6082595348358155,
2.910491733551025,
3.0424036884307863,
3.053787040710449,
3.0072400093078615,
2.943138599395752,
2.8910654640197753,
2.856673631668091,
2.802239189147949,
2.7653528881072997
]
},
"rings": {
"P2a": {
"mean": 0.05803313966204102,
"ci_hw": 0.007994710570939437,
"lo": 0.05003842909110158,
"hi": 0.06602785023298045,
"n": 25,
"pass": false,
"control_random_push_cos_mean": 0.02336164625494954,
"control_random_push_cos_ci_hw": 0.006185585805695125,
"posthoc_cos_vs_random_paired": {
"mean": 0.034671493407091476,
"ci_hw": 0.008782882570825398,
"lo": 0.025888610836266077,
"hi": 0.043454375977916876,
"p_ttest": 2.2805818777064983e-08,
"p_wilcoxon": 1.1920928955078125e-07,
"n": 25,
"ci_excludes_zero": true
}
},
"P2b": {
"mean": 0.025213463317150547,
"ci_hw": 0.004688343838934804,
"lo": 0.020525119478215743,
"hi": 0.029901807156085352,
"n": 25,
"pass": true
},
"P2c": {
"growth_mean": 1.566041305065155,
"growth_ci_hw": 0.07182239356673907,
"growth_lo": 1.494218911498416,
"growth_hi": 1.637863698631894,
"frac_seeds_violators_down": 1.0,
"n": 25,
"pass": true
},
"P2d": {
"mean": -0.0012014603614807129,
"ci_hw": 0.007362390600183422,
"lo": -0.008563850961664135,
"hi": 0.006160930238702709,
"p_ttest": 0.7391911418413584,
"p_wilcoxon": 0.978915274143219,
"n": 25,
"ci_excludes_zero": false,
"pass": false
},
"active_frac_curve": [
0.5476800048351288,
0.309559999704361,
0.22551999986171722,
0.23934000134468078,
0.2619999969005585,
0.268560004234314,
0.2649199992418289,
0.26321999847888944,
0.2610600024461746,
0.2596000009775162,
0.25769999861717224,
0.25630000174045564,
0.2548200011253357,
0.25329999983310697,
0.2513400006294251
],
"active_frac_ci": [
0.026003545359228074,
0.019530060618557627,
0.005124359890426656,
0.005272619049025335,
0.006625939215144284,
0.0056059708526404,
0.0057695982421162315,
0.005826959711859393,
0.006141995888130577,
0.006182804410424134,
0.006087917466681355,
0.006244500919980637,
0.006120449090745142,
0.0060934540913653145,
0.006128805294607838
],
"violators_curve": [
1122.92,
498.96,
448.24,
494.68,
533.64,
536.56,
528.24,
525.72,
521.32,
518.28,
515.12,
512.64,
509.52,
506.36,
502.88
],
"margin_pre_curve": [
0.8000732064247131,
1.9002295351028442,
2.9574402713775636,
2.6278429889678954,
2.257837700843811,
2.1648268127441406,
2.1897586250305174,
2.2183564949035643,
2.23531418800354,
2.25612886428833,
2.2760759353637696,
2.296202940940857,
2.316986083984375,
2.3401871299743653,
2.364041233062744
],
"margin_post_curve": [
0.8887463617324829,
2.5994462394714355,
2.9936683273315428,
2.4987174797058107,
2.1925210905075074,
2.166409673690796,
2.1996525144577026,
2.2224074268341063,
2.2380447149276734,
2.2602160453796385,
2.2791364669799803,
2.2990901565551756,
2.319318370819092,
2.343340721130371,
2.3661145114898683
]
},
"gauss-xor": {
"P2a": {
"mean": 0.14653198755260868,
"ci_hw": 0.00877799166051373,
"lo": 0.13775399589209494,
"hi": 0.15530997921312242,
"n": 25,
"pass": false,
"control_random_push_cos_mean": 0.007081093376735226,
"control_random_push_cos_ci_hw": 0.005042828685971617,
"posthoc_cos_vs_random_paired": {
"mean": 0.13945089417587345,
"ci_hw": 0.009911076541129967,
"lo": 0.12953981763474348,
"hi": 0.1493619707170034,
"p_ttest": 3.2921990062539596e-20,
"p_wilcoxon": 5.960464477539063e-08,
"n": 25,
"ci_excludes_zero": true
}
},
"P2b": {
"mean": 0.04039233710314147,
"ci_hw": 0.0026244896695692835,
"lo": 0.037767847433572185,
"hi": 0.04301682677271075,
"n": 25,
"pass": true
},
"P2c": {
"growth_mean": 2.2112715047597886,
"growth_ci_hw": 0.07004637284349538,
"growth_lo": 2.1412251319162934,
"growth_hi": 2.281317877603284,
"frac_seeds_violators_down": 1.0,
"n": 25,
"pass": true
},
"P2d": {
"mean": -0.0006223726272583008,
"ci_hw": 0.006491479664124042,
"lo": -0.007113852291382342,
"hi": 0.0058691070368657415,
"p_ttest": 0.8448078303605421,
"p_wilcoxon": 0.936802864074707,
"n": 25,
"ci_excludes_zero": false,
"pass": false
},
"active_frac_curve": [
0.7092199969291687,
0.5001199984550476,
0.35553999900817873,
0.32656000018119813,
0.3244200003147125,
0.3148799991607666,
0.30335999965667726,
0.29218000173568726,
0.2803999990224838,
0.26921999990940093,
0.25906000077724456,
0.2505599993467331,
0.2431199997663498,
0.23387999951839447,
0.22953999876976014
],
"active_frac_ci": [
0.037296607253184996,
0.0077666961412310095,
0.007335293079001886,
0.004728730995401593,
0.005852975234051244,
0.006611266783483674,
0.006322327277278776,
0.0067256082209103145,
0.007189657301491052,
0.007336300122061339,
0.00718034979717018,
0.007551424591096476,
0.007748850810645695,
0.008106393083593367,
0.00804852485053251
],
"violators_curve": [
1422.48,
854.8,
666.16,
654.36,
649.96,
628.0,
602.8,
582.44,
558.44,
536.56,
516.44,
503.64,
495.04,
479.84,
473.48
],
"margin_pre_curve": [
0.2712486082315445,
1.1173741483688355,
2.0626373720169067,
2.325490264892578,
2.2459070014953615,
2.2617892360687257,
2.2888603353500367,
2.3204267597198487,
2.346876745223999,
2.3765122413635256,
2.397618751525879,
2.4168948554992675,
2.4316092681884767,
2.4586287212371825,
2.474308423995972
],
"margin_post_curve": [
0.3187326920032501,
1.593959550857544,
2.296677408218384,
2.3138804912567137,
2.234184465408325,
2.2672630453109743,
2.2971515130996703,
2.3274467992782593,
2.355773591995239,
2.386670541763306,
2.4068999004364016,
2.4244446659088137,
2.4394275379180907,
2.466071300506592,
2.482520112991333
]
},
"digits-3v8": {
"P2a": {
"mean": 0.7486074461539587,
"ci_hw": 0.07069765084286048,
"lo": 0.6779097953110982,
"hi": 0.8193050969968192,
"n": 25,
"pass": true,
"control_random_push_cos_mean": 0.01821102383856972,
"control_random_push_cos_ci_hw": 0.05633232200980966,
"posthoc_cos_vs_random_paired": {
"mean": 0.7303964223153889,
"ci_hw": 0.08224469052806435,
"lo": 0.6481517317873245,
"hi": 0.8126411128434533,
"p_ttest": 1.2843939158666783e-15,
"p_wilcoxon": 5.960464477539063e-08,
"n": 25,
"ci_excludes_zero": true
}
},
"P2b": {
"mean": 0.3922601452718179,
"ci_hw": 0.0469911630933622,
"lo": 0.3452689821784557,
"hi": 0.4392513083651801,
"n": 25,
"pass": true
},
"P2c": {
"growth_mean": 0.15234076499938964,
"growth_ci_hw": 0.13453612495163186,
"growth_lo": 0.01780464004775778,
"growth_hi": 0.2868768899510215,
"frac_seeds_violators_down": 1.0,
"n": 25,
"pass": true
},
"P2d": {
"mean": -0.0189353907946861,
"ci_hw": 0.02474033604964284,
"lo": -0.04367572684432894,
"hi": 0.005804945254956739,
"p_ttest": 0.12728107366233818,
"p_wilcoxon": 0.09031611680984497,
"n": 25,
"ci_excludes_zero": false,
"pass": false
},
"active_frac_curve": [
0.08933333471417428,
0.025000000819563866,
0.0003333333507180214,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"active_frac_ci": [
0.011300948171059835,
0.006040144696265541,
0.0006879662230895727,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"violators_curve": [
11.04,
1.68,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"margin_pre_curve": [
4.069617738723755,
4.468085489273071,
4.089049072265625,
4.222936019897461,
4.199183416366577,
4.210524959564209,
4.209090785980225,
4.211717624664306,
4.212894248962402,
4.214598808288574,
4.216084461212159,
4.217616920471191,
4.219087791442871,
4.220537624359131,
4.2219585609436034
],
"margin_post_curve": [
3.4680603885650636,
4.847200832366943,
4.053505935668945,
4.238560447692871,
4.19734040260315,
4.211173648834229,
4.209035568237304,
4.21174560546875,
4.21289514541626,
4.214598693847656,
4.216085453033447,
4.217616539001465,
4.219087886810303,
4.220537700653076,
4.221958503723145
]
}
},
"checks": [
false,
true,
true,
false,
false,
true,
true,
false,
false,
true,
true,
false,
true,
true,
true,
false
],
"n_pass": 9,
"n_checks": 16,
"verdict": "PARTIAL"
},
"claim3": {
"per_dataset": {
"moons-hard": {
"both_baselines_beaten": false,
"any_baseline_beaten": false,
"regression": false,
"vs_deep_ce": {
"mean": -0.001160001754760742,
"ci_hw": 0.0017047676723188042,
"lo": -0.0028647694270795463,
"hi": 0.0005447659175580621,
"p_ttest": 0.1730183666374289,
"p_wilcoxon": 0.18436571086917108,
"n": 25,
"ci_excludes_zero": false
},
"vs_deep_svm": {
"mean": 0.0004799962043762207,
"ci_hw": 0.0012217184969882384,
"lo": -0.0007417222926120177,
"hi": 0.0017017147013644591,
"p_ttest": 0.42540485271054074,
"p_wilcoxon": 0.5240452276574604,
"n": 25,
"ci_excludes_zero": false
},
"vs_rbf_svm": {
"mean": 0.002959997959136933,
"ci_hw": 0.0018011587199507691,
"lo": 0.0011588392391861638,
"hi": 0.004761156679087702,
"p_ttest": 0.0024056929968216253,
"p_wilcoxon": 0.008822321891784668,
"n": 25,
"ci_excludes_zero": true
},
"vs_linear_svm": {
"mean": 0.06351999795913699,
"ci_hw": 0.0030892395954081673,
"lo": 0.06043075836372882,
"hi": 0.06660923755454515,
"p_ttest": 4.340828738073182e-24,
"p_wilcoxon": 5.960464477539063e-08,
"n": 25,
"ci_excludes_zero": true
}
},
"rings": {
"both_baselines_beaten": false,
"any_baseline_beaten": true,
"regression": false,
"vs_deep_ce": {
"mean": 0.0018399953842163086,
"ci_hw": 0.0014723768942708152,
"lo": 0.00036761848994549336,
"hi": 0.003312372278487124,
"p_ttest": 0.016459030485568106,
"p_wilcoxon": 0.031602850238570936,
"n": 25,
"ci_excludes_zero": true
},
"vs_deep_svm": {
"mean": -0.0005600023269653321,
"ci_hw": 0.0010861153325947592,
"lo": -0.0016461176595600913,
"hi": 0.0005261130056294271,
"p_ttest": 0.29785143344846177,
"p_wilcoxon": 0.3149534488128901,
"n": 25,
"ci_excludes_zero": false
},
"vs_rbf_svm": {
"mean": -0.0009600000572204515,
"ci_hw": 0.001518896128816546,
"lo": -0.0024788961860369974,
"hi": 0.0005588960715960945,
"p_ttest": 0.2044474423673455,
"p_wilcoxon": 0.2996123433113098,
"n": 25,
"ci_excludes_zero": false
},
"vs_linear_svm": {
"mean": 0.3583599999427795,
"ci_hw": 0.024755568610761967,
"lo": 0.33360443133201756,
"hi": 0.38311556855354145,
"p_ttest": 1.6937495116201298e-20,
"p_wilcoxon": 5.960464477539063e-08,
"n": 25,
"ci_excludes_zero": true
}
},
"gauss-xor": {
"both_baselines_beaten": true,
"any_baseline_beaten": true,
"regression": false,
"vs_deep_ce": {
"mean": 0.04388000726699829,
"ci_hw": 0.00607632496434152,
"lo": 0.03780368230265677,
"hi": 0.04995633223133981,
"p_ttest": 1.247773809214336e-13,
"p_wilcoxon": 5.960464477539063e-08,
"n": 25,
"ci_excludes_zero": true
},
"vs_deep_svm": {
"mean": 0.03004000186920166,
"ci_hw": 0.005892636432511468,
"lo": 0.02414736543669019,
"hi": 0.03593263830171313,
"p_ttest": 1.8046564108423801e-10,
"p_wilcoxon": 5.960464477539063e-08,
"n": 25,
"ci_excludes_zero": true
},
"vs_rbf_svm": {
"mean": -0.008360000324249302,
"ci_hw": 0.004677482094520435,
"lo": -0.013037482418769737,
"hi": -0.003682518229728867,
"p_ttest": 0.0011521672973715095,
"p_wilcoxon": 0.0009118914604187012,
"n": 25,
"ci_excludes_zero": true
},
"vs_linear_svm": {
"mean": 0.29187999967575073,
"ci_hw": 0.008549056406231539,
"lo": 0.2833309432695192,
"hi": 0.3004290560819823,
"p_ttest": 2.4791096255720396e-29,
"p_wilcoxon": 5.960464477539063e-08,
"n": 25,
"ci_excludes_zero": true
}
},
"digits-3v8": {
"both_baselines_beaten": false,
"any_baseline_beaten": true,
"regression": false,
"vs_deep_ce": {
"mean": 0.005569615364074707,
"ci_hw": 0.005070867446741569,
"lo": 0.0004987479173331382,
"hi": 0.010640482810816275,
"p_ttest": 0.032688882721537534,
"p_wilcoxon": 0.015095338331720862,
"n": 25,
"ci_excludes_zero": true
},
"vs_deep_svm": {
"mean": -0.004050631523132325,
"ci_hw": 0.006408836062118553,
"lo": -0.010459467585250877,
"hi": 0.002358204538986228,
"p_ttest": 0.2044470474639032,
"p_wilcoxon": 0.2540411333248247,
"n": 25,
"ci_excludes_zero": false
},
"vs_rbf_svm": {
"mean": 0.001181423714392289,
"ci_hw": 0.0067739425822590914,
"lo": -0.005592518867866802,
"hi": 0.00795536629665138,
"p_ttest": 0.7220264221290003,
"p_wilcoxon": 0.5249125957489014,
"n": 25,
"ci_excludes_zero": false
},
"vs_linear_svm": {
"mean": -0.0069198421083925335,
"ci_hw": 0.005596025773433344,
"lo": -0.012515867881825878,
"hi": -0.001323816334959189,
"p_ttest": 0.017491942582098536,
"p_wilcoxon": 0.007370948791503906,
"n": 25,
"ci_excludes_zero": true
}
}
},
"n_datasets_both_baselines_beaten": 1,
"n_datasets_any_baseline_beaten": 3,
"n_datasets_regression": 0,
"verdict": "PARTIAL"
}
}
}

Xet Storage Details

Size:
52.9 kB
·
Xet hash:
b2381343c617140efcbac5f9f3b26fb33b5df33d59cdf7e2fde8a948535d83fb

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.