更新 math Q1 Q2 实验与特征

This commit is contained in:
gloamxun committed 2026-09-25 08:58:10 +08:00
1 parent ca5be95757
commit 83ec3d1a83
168 files changed
+150303 -2874

No files matched your search

+31
View File
@@ -0,0 +1,31 @@
case_id,source_file,text_visible_steps,audio_visible_steps,vision_visible_steps,audio_missing_fraction,vision_missing_fraction,unknown_quality_flag,labels_available,input_note,source_sha256,visible_text_steps,visible_audio_steps,visible_vision_steps,low_information_prior_fallback,calibration_temperature,interval_90_lower,interval_90_upper,predictive_variance_mean_uncalibrated,predictive_variance_calibrated
附件3_01,附件3_01.pkl,8,6,6,0.88,0.88,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,b45b89a7eea55278abb130d44a6ee21128df5aa3239e68c968f9ac7743cfa0ea,8,6,6,False,1.212728800581531,-2.0970382690429688,2.056648015975952,1.7335734367370605,1.7042454481124878
附件3_02,附件3_02.pkl,30,23,23,0.54,0.54,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,6a628897c4b8c5e94e37f23bce680aad500fa8545414234f3564a58577c1023b,30,23,23,False,1.212728800581531,-0.9996623396873474,1.3429561853408813,0.42073488235473633,0.4336998462677002
附件3_03,附件3_03.pkl,34,27,23,0.45999999999999996,0.54,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,52bb6e11f4bba301e1bd90916dc9ad3a0d2d0885fec4598e3e737e2c4d100b6f,34,27,23,False,1.212728800581531,-0.45678868889808655,1.5853729248046875,0.3916955590248108,0.40991201996803284
附件3_04,附件3_04.pkl,33,29,29,0.42000000000000004,0.42000000000000004,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,ee1f4781ee7b7bc37e71a13e4bc53eedc8327d96a69c246964d0e84a8aa99f72,33,29,29,False,1.212728800581531,-0.3432163894176483,1.6048578023910522,0.3745034337043762,0.39313918352127075
附件3_05,附件3_05.pkl,14,12,12,0.76,0.76,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,9f8e5bae8488d8ee1576b1686864b7d8fc9970cfa720758fb040b9293b7e3619,14,12,12,False,1.212728800581531,-2.163356304168701,1.5903369188308716,1.2121071815490723,1.2855738401412964
附件3_06,附件3_06.pkl,27,22,22,0.56,0.56,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,9e973621f141b1af24fc3686ac329a10b66ba2b84d18c21918e86bf0429f790d,27,22,22,False,1.212728800581531,-0.36223649978637695,2.1398749351501465,0.6031956672668457,0.6750403046607971
附件3_07,附件3_07.pkl,23,18,18,0.64,0.64,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,62dd394e23c80af2898e039d7eb6f47556d747887331fa2853dad72e13bb223b,23,18,18,False,1.212728800581531,-0.3932100832462311,1.769598126411438,0.44835442304611206,0.47891828417778015
附件3_08,附件3_08.pkl,17,13,13,0.74,0.74,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,e668faea97f9a338051c19ee66383df799b2e461d6d079df8c5f92b32bd6437e,17,13,13,False,1.212728800581531,-0.9790695905685425,1.6200528144836426,0.5541559457778931,0.5690155625343323
附件3_09,附件3_09.pkl,16,12,12,0.76,0.76,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,ef57769eaa05f53a7d588948d565876356898658d9945202058ca763e53748b2,16,12,12,False,1.212728800581531,-0.27194494009017944,2.0130302906036377,0.5201191902160645,0.5757794380187988
附件3_10,附件3_10.pkl,8,6,6,0.88,0.88,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,7c87d84d69e0e68b9252c9839747558d07a91fd2d079a9a0850683d0d197241e,8,6,6,False,1.212728800581531,-0.9529624581336975,1.640604019165039,0.5439862012863159,0.5653517842292786
附件3_11,附件3_11.pkl,16,10,10,0.8,0.8,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,10e9d5443cecf2de9170deaa56995de0cf9c52580a74cd334de8fea0e4a735f2,16,10,10,False,1.212728800581531,-0.5261767506599426,1.6935460567474365,0.450601726770401,0.4752480089664459
附件3_12,附件3_12.pkl,15,11,11,0.78,0.78,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,d0342f4931a05e40fb0a3220010f1ac801a2f06d123bc4d9a7dc5355794347ba,15,11,11,False,1.212728800581531,-0.9405485391616821,1.926857590675354,0.7031970620155334,0.7392448782920837
附件3_13,附件3_13.pkl,21,17,17,0.6599999999999999,0.6599999999999999,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,9e2144ab4385636b259d9e358c7e511be5242c89340f894473317b7757f218b7,21,17,17,False,1.212728800581531,-0.9272081851959229,1.7548140287399292,0.6093371510505676,0.6293941736221313
附件3_14,附件3_14.pkl,25,21,21,0.5800000000000001,0.5800000000000001,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,f6d45e8fa882062f70fd48ee1f7584b0a75ea0ed1c85a9eb218684e954dc1b82,25,21,21,False,1.212728800581531,-1.5893217325210571,1.5921794176101685,0.8739535212516785,0.8658839464187622
附件3_15,附件3_15.pkl,29,24,24,0.52,0.52,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,263b960d4d66b25a3db447fb7a16aee7b7d735e8bee3fe55c7869ad3103bf9d4,29,24,24,False,1.212728800581531,-0.087561696767807,1.8981196880340576,0.43900278210639954,0.4791504144668579
附件3_16,附件3_16.pkl,36,30,30,0.4,0.4,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,df8b4c881e3fc971d532988bbd161d8d9bf8c5d16c3e7a559bb7a4045e96547f,36,30,30,False,1.212728800581531,-0.3259946405887604,2.3747494220733643,0.6431438326835632,0.7642990946769714
附件3_17,附件3_17.pkl,24,14,14,0.72,0.72,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,b6c64a55fb8050cb9fda15b0245df8f16b20d2a25d9368485dd1229e213fdba5,24,14,14,False,1.212728800581531,-0.6764342784881592,1.3940967321395874,0.3571646213531494,0.36965644359588623
附件3_18,附件3_18.pkl,19,14,14,0.72,0.72,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,dc8eb37586b93bdd4debe895041275fdabb94c3392bde667b4e0ccdc6429fab1,19,14,14,False,1.212728800581531,-0.38681817054748535,1.673882246017456,0.41236546635627747,0.43565449118614197
附件3_19,附件3_19.pkl,26,17,17,0.6599999999999999,0.6599999999999999,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,d3a912bc3c70b60c1021babc521f28a6a34f9e916c164ad0191182e587c2385a,26,17,17,False,1.212728800581531,-1.0595200061798096,1.3693560361862183,0.45944827795028687,0.4690973460674286
附件3_20,附件3_20.pkl,50,34,34,0.31999999999999995,0.31999999999999995,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,bf24c7189bba3904e911dd452266078d8ff15768438a9069e6596ff73a4b925e,50,34,34,False,1.212728800581531,-0.37013763189315796,1.301245093345642,0.26743096113204956,0.2766386568546295
附件3_21,附件3_21.pkl,11,6,6,0.88,0.88,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,c0605bd5757ff0c5dea345c96236ed7168ff976d37843572143efe11d6454600,11,6,6,False,1.212728800581531,-0.33592545986175537,1.722812533378601,0.42267656326293945,0.4489213228225708
附件3_22,附件3_22.pkl,19,13,13,0.74,0.74,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,6f9dc33f9d3e5680ee3a3b2b0c53b1bac51fb98f1d75375a2cb1224cd7bd4d43,19,13,13,False,1.212728800581531,-0.5156432390213013,1.6332861185073853,0.42243894934654236,0.4429676830768585
附件3_23,附件3_23.pkl,15,9,9,0.8200000000000001,0.8200000000000001,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,5200bd05e2611777875eb1d88826bb56bb71dee4c708fec9d9f851222d243aae,15,9,9,False,1.212728800581531,-0.49955275654792786,1.6659469604492188,0.43331629037857056,0.4561525285243988
附件3_24,附件3_24.pkl,10,6,6,0.88,0.88,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,76b1c126e2043f90afd5af00d51299bc8f5bf1bee8148f5ff904ccbeb931a5e5,10,6,6,False,1.212728800581531,-1.0213178396224976,1.8038268089294434,0.6638259291648865,0.6895806193351746
附件3_25,附件3_25.pkl,11,7,7,0.86,0.86,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,88d52e2d0b0229ad6ec638e6e7463f6852f127ae9308fbee1cbc2405d8ebc4c8,11,7,7,False,1.212728800581531,-1.013203501701355,1.9055728912353516,0.7159426808357239,0.7510258555412292
附件3_26,附件3_26.pkl,24,16,16,0.6799999999999999,0.6799999999999999,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,e483daa1391987552f9ee7f21bffec918dd61267af36885a9ae3073813193234,24,16,16,False,1.212728800581531,-0.42688244581222534,1.7250646352767944,0.4398258328437805,0.46607935428619385
附件3_27,附件3_27.pkl,23,13,13,0.74,0.74,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,27f16bbd4541196bb33f4caa36e038b2ff66fa72649f1b22f2328a5630de37ad,23,13,13,False,1.212728800581531,-0.5788680911064148,1.7725975513458252,0.5006299018859863,0.529201865196228
附件3_28,附件3_28.pkl,35,22,22,0.56,0.56,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,81def781fa8fa5aebb555631b59ce48ee71a10c9e4226f1a5b6d91a2078f8f32,35,22,22,False,1.212728800581531,-0.2326158583164215,1.5581943988800049,0.34371161460876465,0.35912466049194336
附件3_29,附件3_29.pkl,20,10,10,0.8,0.8,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,8caf12e71117bd7334be12aba5af6322fb02a2397f8e2402e75391f4f9ef3686,20,10,10,False,1.212728800581531,-0.4160189926624298,1.6209927797317505,0.3967360258102417,0.4166872203350067
附件3_30,附件3_30.pkl,26,12,12,0.76,0.76,True,False,official aligned_50 only; unaligned rows and raw transcript are not used,a6b272abb5d083804b6902054d4180d55d3c1d5822c483967e70e6a9657546d3,26,12,12,False,1.212728800581531,-0.5056151747703552,1.6129341125488281,0.41301825642585754,0.4326811134815216
1 case_id source_file text_visible_steps audio_visible_steps vision_visible_steps audio_missing_fraction vision_missing_fraction unknown_quality_flag labels_available input_note source_sha256 visible_text_steps visible_audio_steps visible_vision_steps low_information_prior_fallback calibration_temperature interval_90_lower interval_90_upper predictive_variance_mean_uncalibrated predictive_variance_calibrated
2 附件3_01 附件3_01.pkl 8 6 6 0.88 0.88 True False official aligned_50 only; unaligned rows and raw transcript are not used b45b89a7eea55278abb130d44a6ee21128df5aa3239e68c968f9ac7743cfa0ea 8 6 6 False 1.212728800581531 -2.0970382690429688 2.056648015975952 1.7335734367370605 1.7042454481124878
3 附件3_02 附件3_02.pkl 30 23 23 0.54 0.54 True False official aligned_50 only; unaligned rows and raw transcript are not used 6a628897c4b8c5e94e37f23bce680aad500fa8545414234f3564a58577c1023b 30 23 23 False 1.212728800581531 -0.9996623396873474 1.3429561853408813 0.42073488235473633 0.4336998462677002
4 附件3_03 附件3_03.pkl 34 27 23 0.45999999999999996 0.54 True False official aligned_50 only; unaligned rows and raw transcript are not used 52bb6e11f4bba301e1bd90916dc9ad3a0d2d0885fec4598e3e737e2c4d100b6f 34 27 23 False 1.212728800581531 -0.45678868889808655 1.5853729248046875 0.3916955590248108 0.40991201996803284
5 附件3_04 附件3_04.pkl 33 29 29 0.42000000000000004 0.42000000000000004 True False official aligned_50 only; unaligned rows and raw transcript are not used ee1f4781ee7b7bc37e71a13e4bc53eedc8327d96a69c246964d0e84a8aa99f72 33 29 29 False 1.212728800581531 -0.3432163894176483 1.6048578023910522 0.3745034337043762 0.39313918352127075
6 附件3_05 附件3_05.pkl 14 12 12 0.76 0.76 True False official aligned_50 only; unaligned rows and raw transcript are not used 9f8e5bae8488d8ee1576b1686864b7d8fc9970cfa720758fb040b9293b7e3619 14 12 12 False 1.212728800581531 -2.163356304168701 1.5903369188308716 1.2121071815490723 1.2855738401412964
7 附件3_06 附件3_06.pkl 27 22 22 0.56 0.56 True False official aligned_50 only; unaligned rows and raw transcript are not used 9e973621f141b1af24fc3686ac329a10b66ba2b84d18c21918e86bf0429f790d 27 22 22 False 1.212728800581531 -0.36223649978637695 2.1398749351501465 0.6031956672668457 0.6750403046607971
8 附件3_07 附件3_07.pkl 23 18 18 0.64 0.64 True False official aligned_50 only; unaligned rows and raw transcript are not used 62dd394e23c80af2898e039d7eb6f47556d747887331fa2853dad72e13bb223b 23 18 18 False 1.212728800581531 -0.3932100832462311 1.769598126411438 0.44835442304611206 0.47891828417778015
9 附件3_08 附件3_08.pkl 17 13 13 0.74 0.74 True False official aligned_50 only; unaligned rows and raw transcript are not used e668faea97f9a338051c19ee66383df799b2e461d6d079df8c5f92b32bd6437e 17 13 13 False 1.212728800581531 -0.9790695905685425 1.6200528144836426 0.5541559457778931 0.5690155625343323
10 附件3_09 附件3_09.pkl 16 12 12 0.76 0.76 True False official aligned_50 only; unaligned rows and raw transcript are not used ef57769eaa05f53a7d588948d565876356898658d9945202058ca763e53748b2 16 12 12 False 1.212728800581531 -0.27194494009017944 2.0130302906036377 0.5201191902160645 0.5757794380187988
11 附件3_10 附件3_10.pkl 8 6 6 0.88 0.88 True False official aligned_50 only; unaligned rows and raw transcript are not used 7c87d84d69e0e68b9252c9839747558d07a91fd2d079a9a0850683d0d197241e 8 6 6 False 1.212728800581531 -0.9529624581336975 1.640604019165039 0.5439862012863159 0.5653517842292786
12 附件3_11 附件3_11.pkl 16 10 10 0.8 0.8 True False official aligned_50 only; unaligned rows and raw transcript are not used 10e9d5443cecf2de9170deaa56995de0cf9c52580a74cd334de8fea0e4a735f2 16 10 10 False 1.212728800581531 -0.5261767506599426 1.6935460567474365 0.450601726770401 0.4752480089664459
13 附件3_12 附件3_12.pkl 15 11 11 0.78 0.78 True False official aligned_50 only; unaligned rows and raw transcript are not used d0342f4931a05e40fb0a3220010f1ac801a2f06d123bc4d9a7dc5355794347ba 15 11 11 False 1.212728800581531 -0.9405485391616821 1.926857590675354 0.7031970620155334 0.7392448782920837
14 附件3_13 附件3_13.pkl 21 17 17 0.6599999999999999 0.6599999999999999 True False official aligned_50 only; unaligned rows and raw transcript are not used 9e2144ab4385636b259d9e358c7e511be5242c89340f894473317b7757f218b7 21 17 17 False 1.212728800581531 -0.9272081851959229 1.7548140287399292 0.6093371510505676 0.6293941736221313
15 附件3_14 附件3_14.pkl 25 21 21 0.5800000000000001 0.5800000000000001 True False official aligned_50 only; unaligned rows and raw transcript are not used f6d45e8fa882062f70fd48ee1f7584b0a75ea0ed1c85a9eb218684e954dc1b82 25 21 21 False 1.212728800581531 -1.5893217325210571 1.5921794176101685 0.8739535212516785 0.8658839464187622
16 附件3_15 附件3_15.pkl 29 24 24 0.52 0.52 True False official aligned_50 only; unaligned rows and raw transcript are not used 263b960d4d66b25a3db447fb7a16aee7b7d735e8bee3fe55c7869ad3103bf9d4 29 24 24 False 1.212728800581531 -0.087561696767807 1.8981196880340576 0.43900278210639954 0.4791504144668579
17 附件3_16 附件3_16.pkl 36 30 30 0.4 0.4 True False official aligned_50 only; unaligned rows and raw transcript are not used df8b4c881e3fc971d532988bbd161d8d9bf8c5d16c3e7a559bb7a4045e96547f 36 30 30 False 1.212728800581531 -0.3259946405887604 2.3747494220733643 0.6431438326835632 0.7642990946769714
18 附件3_17 附件3_17.pkl 24 14 14 0.72 0.72 True False official aligned_50 only; unaligned rows and raw transcript are not used b6c64a55fb8050cb9fda15b0245df8f16b20d2a25d9368485dd1229e213fdba5 24 14 14 False 1.212728800581531 -0.6764342784881592 1.3940967321395874 0.3571646213531494 0.36965644359588623
19 附件3_18 附件3_18.pkl 19 14 14 0.72 0.72 True False official aligned_50 only; unaligned rows and raw transcript are not used dc8eb37586b93bdd4debe895041275fdabb94c3392bde667b4e0ccdc6429fab1 19 14 14 False 1.212728800581531 -0.38681817054748535 1.673882246017456 0.41236546635627747 0.43565449118614197
20 附件3_19 附件3_19.pkl 26 17 17 0.6599999999999999 0.6599999999999999 True False official aligned_50 only; unaligned rows and raw transcript are not used d3a912bc3c70b60c1021babc521f28a6a34f9e916c164ad0191182e587c2385a 26 17 17 False 1.212728800581531 -1.0595200061798096 1.3693560361862183 0.45944827795028687 0.4690973460674286
21 附件3_20 附件3_20.pkl 50 34 34 0.31999999999999995 0.31999999999999995 True False official aligned_50 only; unaligned rows and raw transcript are not used bf24c7189bba3904e911dd452266078d8ff15768438a9069e6596ff73a4b925e 50 34 34 False 1.212728800581531 -0.37013763189315796 1.301245093345642 0.26743096113204956 0.2766386568546295
22 附件3_21 附件3_21.pkl 11 6 6 0.88 0.88 True False official aligned_50 only; unaligned rows and raw transcript are not used c0605bd5757ff0c5dea345c96236ed7168ff976d37843572143efe11d6454600 11 6 6 False 1.212728800581531 -0.33592545986175537 1.722812533378601 0.42267656326293945 0.4489213228225708
23 附件3_22 附件3_22.pkl 19 13 13 0.74 0.74 True False official aligned_50 only; unaligned rows and raw transcript are not used 6f9dc33f9d3e5680ee3a3b2b0c53b1bac51fb98f1d75375a2cb1224cd7bd4d43 19 13 13 False 1.212728800581531 -0.5156432390213013 1.6332861185073853 0.42243894934654236 0.4429676830768585
24 附件3_23 附件3_23.pkl 15 9 9 0.8200000000000001 0.8200000000000001 True False official aligned_50 only; unaligned rows and raw transcript are not used 5200bd05e2611777875eb1d88826bb56bb71dee4c708fec9d9f851222d243aae 15 9 9 False 1.212728800581531 -0.49955275654792786 1.6659469604492188 0.43331629037857056 0.4561525285243988
25 附件3_24 附件3_24.pkl 10 6 6 0.88 0.88 True False official aligned_50 only; unaligned rows and raw transcript are not used 76b1c126e2043f90afd5af00d51299bc8f5bf1bee8148f5ff904ccbeb931a5e5 10 6 6 False 1.212728800581531 -1.0213178396224976 1.8038268089294434 0.6638259291648865 0.6895806193351746
26 附件3_25 附件3_25.pkl 11 7 7 0.86 0.86 True False official aligned_50 only; unaligned rows and raw transcript are not used 88d52e2d0b0229ad6ec638e6e7463f6852f127ae9308fbee1cbc2405d8ebc4c8 11 7 7 False 1.212728800581531 -1.013203501701355 1.9055728912353516 0.7159426808357239 0.7510258555412292
27 附件3_26 附件3_26.pkl 24 16 16 0.6799999999999999 0.6799999999999999 True False official aligned_50 only; unaligned rows and raw transcript are not used e483daa1391987552f9ee7f21bffec918dd61267af36885a9ae3073813193234 24 16 16 False 1.212728800581531 -0.42688244581222534 1.7250646352767944 0.4398258328437805 0.46607935428619385
28 附件3_27 附件3_27.pkl 23 13 13 0.74 0.74 True False official aligned_50 only; unaligned rows and raw transcript are not used 27f16bbd4541196bb33f4caa36e038b2ff66fa72649f1b22f2328a5630de37ad 23 13 13 False 1.212728800581531 -0.5788680911064148 1.7725975513458252 0.5006299018859863 0.529201865196228
29 附件3_28 附件3_28.pkl 35 22 22 0.56 0.56 True False official aligned_50 only; unaligned rows and raw transcript are not used 81def781fa8fa5aebb555631b59ce48ee71a10c9e4226f1a5b6d91a2078f8f32 35 22 22 False 1.212728800581531 -0.2326158583164215 1.5581943988800049 0.34371161460876465 0.35912466049194336
30 附件3_29 附件3_29.pkl 20 10 10 0.8 0.8 True False official aligned_50 only; unaligned rows and raw transcript are not used 8caf12e71117bd7334be12aba5af6322fb02a2397f8e2402e75391f4f9ef3686 20 10 10 False 1.212728800581531 -0.4160189926624298 1.6209927797317505 0.3967360258102417 0.4166872203350067
31 附件3_30 附件3_30.pkl 26 12 12 0.76 0.76 True False official aligned_50 only; unaligned rows and raw transcript are not used a6b272abb5d083804b6902054d4180d55d3c1d5822c483967e70e6a9657546d3 26 12 12 False 1.212728800581531 -0.5056151747703552 1.6129341125488281 0.41301825642585754 0.4326811134815216