massive false negatives
Dan Stromberg
strombrg at dcs.nac.uci.edu
Mon May 5 18:53:12 CEST 2003
Ever since I upgraded to 0.11.1.3, I've been getting a Lot of false
negatives. In fact, I'm not sure Anything is getting filtered out.
I recently recreated my db from known spam and ham, but that didn't
appear to help.
I did:
/dcs/packages/bogofilter/bin/bogofilter -v < /tmp/bad
X-Bogosity: No, tests=bogofilter, spamicity=0.000001, version=0.11.1.3
...with what I consider fairly obvious spam (the "banned cd" thing). Is
that a strange spamicity. The man page didn't appear to say.
I'm attaching -vvv output, which I'm not sure what to do with.
--
Dan Stromberg DCS/NACS/UCI <strombrg at dcs.nac.uci.edu>
-------------- next part --------------
X-Bogosity: No, tests=bogofilter, spamicity=0.000001, version=0.11.1.3
n pgood pbad fw invfwlog fwlog U
"dcs.nac.uci.edu" 14985 1.000000 0.000000 0.000000 -0.00000 -17.40204 +
"128.200.34.32" 1075 0.071738 0.000000 0.000000 -0.00000 -14.76731 +
"imap" 492 0.032833 0.000000 0.000001 -0.00000 -13.98571 +
"x-evolution-source" 174 0.011612 0.000000 0.000002 -0.00000 -12.94629 +
"hang" 100 0.006673 0.000000 0.000004 -0.00000 -12.39241 +
"society" 89 0.005939 0.000000 0.000005 -0.00000 -12.27588 +
"fake" 64 0.004271 0.000000 0.000006 -0.00001 -11.94613 +
"sam" 60 0.004004 0.000000 0.000007 -0.00001 -11.88159 +
"contributing" 54 0.003604 0.000000 0.000008 -0.00001 -11.77623 +
"dig" 32 0.002135 0.000000 0.000013 -0.00001 -11.25300 +
"moral" 30 0.002002 0.000000 0.000014 -0.00001 -11.18846 +
"flames" 28 0.001869 0.000000 0.000015 -0.00001 -11.11947 +
"upset" 28 0.001869 0.000000 0.000015 -0.00001 -11.11947 +
"fines" 27 0.001802 0.000000 0.000015 -0.00002 -11.08311 +
"collectors" 21 0.001401 0.000000 0.000020 -0.00002 -10.83180 +
"constitutional" 19 0.001268 0.000000 0.000022 -0.00002 -10.73172 +
"threatened" 19 0.001268 0.000000 0.000022 -0.00002 -10.73172 +
"dirt" 18 0.001201 0.000000 0.000023 -0.00002 -10.67766 +
"banned" 17 0.001134 0.000000 0.000024 -0.00002 -10.62050 +
"uncle" 13 0.000868 0.000000 0.000032 -0.00003 -10.35226 +
"bedroom" 11 0.000734 0.000000 0.000038 -0.00004 -10.18522 +
"diploma" 11 0.000734 0.000000 0.000038 -0.00004 -10.18522 +
"diplomas" 11 0.000734 0.000000 0.000038 -0.00004 -10.18522 +
"imprisonment" 11 0.000734 0.000000 0.000038 -0.00004 -10.18522 +
"walmart" 11 0.000734 0.000000 0.000038 -0.00004 -10.18522 +
"hard-to-find" 9 0.000601 0.000000 0.000046 -0.00005 -9.98457 +
"intimidated" 9 0.000601 0.000000 0.000046 -0.00005 -9.98457 +
"decay" 8 0.000534 0.000000 0.000052 -0.00005 -9.86680 +
"ex-husband" 8 0.000534 0.000000 0.000052 -0.00005 -9.86680 +
"ex-wife" 8 0.000534 0.000000 0.000052 -0.00005 -9.86680 +
"horrified" 8 0.000534 0.000000 0.000052 -0.00005 -9.86680 +
"indictments" 8 0.000534 0.000000 0.000052 -0.00005 -9.86680 +
"218.246.127.132" 6 0.000400 0.000000 0.000069 -0.00007 -9.57916 +
"larson" 3 0.000200 0.000000 0.000138 -0.00014 -8.88618 +
"218.76.63.192" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"aips" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"alonzo" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"cxe" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"dfg" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"emphysema" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"g8vu.kzyqea.com" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"krt" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"ogumxbrasxehspucekmeqa" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"rfjovsb" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"rpacyw" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"tbbdqbjmzf" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"tbdx" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"tzulccbxqp" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"wiiqdcixwycloggingjp" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"xemz" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"zn8gs040fk" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"zonwvxoalheibw" 2 0.000133 0.000000 0.000207 -0.00021 -8.48088 +
"i'm" 2659 0.176176 0.015768 0.082147 -0.08572 -2.49924 +
"problem" 3262 0.215349 0.029046 0.118848 -0.12652 -2.12991 +
"maybe" 947 0.062462 0.009129 0.127511 -0.13641 -2.05955 +
"identity" 82 0.005405 0.000830 0.133097 -0.14283 -2.01668 +
"access" 1487 0.097364 0.023237 0.192674 -0.21403 -1.64676 +
"using" 3531 0.230163 0.068050 0.228192 -0.25902 -1.47757 +
"obviously" 164 0.010677 0.003320 0.237162 -0.27071 -1.43901 +
"can't" 1207 0.078545 0.024896 0.240680 -0.27533 -1.42429 +
"unless" 554 0.035969 0.012448 0.257100 -0.29719 -1.35829 +
"but" 5823 0.377978 0.131950 0.258762 -0.29943 -1.35185 +
"local" 1686 0.109176 0.041494 0.275396 -0.32213 -1.28955 +
"list" 8520 0.550617 0.223237 0.288474 -0.34034 -1.24315 +
"sure" 1931 0.124658 0.052282 0.295479 -0.35024 -1.21916 +
"two" 1680 0.108041 0.050622 0.319055 -0.38427 -1.14239 +
"some" 3549 0.226960 0.122822 0.351138 -0.43253 -1.04658 +
"old" 894 0.057124 0.031535 0.355692 -0.43958 -1.03369 +
"cacheflowserver" 47 0.003003 0.001660 0.355961 -0.44000 -1.03294 +
"avoid" 302 0.019286 0.010788 0.358724 -0.44430 -1.02520 +
"gives" 324 0.020687 0.011618 0.359636 -0.44572 -1.02266 +
"that" 8815 0.562563 0.319502 0.362221 -0.44976 -1.01550 +
"still" 1638 0.104505 0.059751 0.363769 -0.45219 -1.01124 +
"been" 3521 0.224024 0.136100 0.377925 -0.47469 -0.97306 +
"build" 1005 0.063864 0.039834 0.384135 -0.48473 -0.95676 +
"bit" 5489 0.348549 0.220747 0.387755 -0.49062 -0.94738 +
"look" 1279 0.081148 0.052282 0.391832 -0.49730 -0.93692 +
"message" 6639 0.420354 0.282158 0.401641 -0.51357 -0.91220 -
"there" 4286 0.271138 0.185062 0.405660 -0.52030 -0.90224 -
"x-mailer" 7067 0.446246 0.315353 0.414067 -0.53455 -0.88173 -
"saying" 295 0.018619 0.013278 0.416283 -0.53834 -0.87639 -
"have" 7838 0.494361 0.356846 0.419224 -0.54339 -0.86935 -
"the" 12810 0.807541 0.588382 0.421500 -0.54732 -0.86393 -
"these" 2768 0.174374 0.128631 0.424517 -0.55254 -0.85680 -
"don't" 2974 0.187254 0.139419 0.426785 -0.55649 -0.85148 -
"how" 3142 0.197531 0.151037 0.433308 -0.56794 -0.83631 -
"and" 11330 0.711044 0.560166 0.440656 -0.58099 -0.81949 -
"powers" 33 0.002069 0.001660 0.445153 -0.58906 -0.80934 -
"can" 6397 0.400267 0.331120 0.452729 -0.60281 -0.79246 -
"completely" 327 0.020420 0.017427 0.460459 -0.61704 -0.77553 -
"giving" 261 0.016283 0.014108 0.464215 -0.62402 -0.76741 -
"need" 2706 0.168769 0.146888 0.465341 -0.62613 -0.76499 -
"may" 4392 0.273807 0.239834 0.466929 -0.62910 -0.76158 -
"mime-version" 12700 0.791391 0.697925 0.468621 -0.63228 -0.75796 -
"because" 1869 0.116450 0.102905 0.469125 -0.63323 -0.75689 -
"they" 2521 0.157024 0.139419 0.470307 -0.63546 -0.75437 -
"are" 6970 0.434034 0.386722 0.471178 -0.63710 -0.75252 -
"able" 1314 0.081815 0.073029 0.471629 -0.63796 -0.75156 -
"format" 2400 0.149416 0.133610 0.472077 -0.63880 -0.75061 -
"minutes" 370 0.023023 0.020747 0.473999 -0.64245 -0.74655 -
"this" 10357 0.642442 0.605809 0.485326 -0.66422 -0.72293 -
"even" 1746 0.108242 0.102905 0.487362 -0.66818 -0.71875 -
"last" 1224 0.075742 0.073859 0.493705 -0.68064 -0.70582 -
"why" 1217 0.075275 0.073859 0.495251 -0.68369 -0.70269 -
"just" 4019 0.248582 0.243983 0.495332 -0.68385 -0.70253 -
"head" 287 0.017751 0.017427 0.495399 -0.68399 -0.70239 -
"you" 9223 0.570437 0.560166 0.495458 -0.68410 -0.70227 -
"strombrg" 15119 0.934735 0.922822 0.496793 -0.68675 -0.69958 -
"subject" 16171 0.998866 0.998340 0.499868 -0.69288 -0.69341 -
"from" 16190 1.000000 1.000000 0.500000 -0.69315 -0.69315 -
"received" 16190 1.000000 1.000000 0.500000 -0.69315 -0.69315 -
"with" 16183 0.999533 1.000000 0.500117 -0.69338 -0.69291 -
"outlook" 1254 0.077411 0.078008 0.501922 -0.69700 -0.68931 -
"down" 985 0.060794 0.061411 0.502523 -0.69821 -0.68811 -
"product" 1056 0.065132 0.066390 0.504783 -0.70276 -0.68363 -
"content-type" 13179 0.811879 0.840664 0.508709 -0.71072 -0.67588 -
"text" 13220 0.814348 0.843983 0.508935 -0.71118 -0.67543 -
"one" 3807 0.234501 0.243154 0.509057 -0.71143 -0.67520 -
"for" 15471 0.952886 0.989212 0.509352 -0.71203 -0.67462 -
"content-transfer-encoding" 8349 0.514047 0.536100 0.510500 -0.71437 -0.67237 -
"back" 1451 0.089289 0.093776 0.512254 -0.71796 -0.66893 -
"mon" 3389 0.208542 0.219087 0.512330 -0.71812 -0.66879 -
"get" 4001 0.246180 0.258921 0.512613 -0.71870 -0.66823 -
"next" 972 0.059793 0.063071 0.513337 -0.72018 -0.66682 -
"will" 5457 0.335469 0.356846 0.515439 -0.72451 -0.66274 -
"find" 2090 0.128395 0.137759 0.517592 -0.72896 -0.65857 -
"want" 2371 0.145612 0.156846 0.518571 -0.73100 -0.65668 -
"new" 3643 0.223357 0.245643 0.523760 -0.74183 -0.64672 -
"investigate" 61 0.003737 0.004149 0.526138 -0.74684 -0.64219 -
"more" 4843 0.296697 0.329461 0.526163 -0.74689 -0.64214 -
"multipart" 3500 0.214348 0.239004 0.527193 -0.74907 -0.64019 -
"right" 1353 0.082816 0.092946 0.528817 -0.75251 -0.63711 -
"make" 2659 0.162696 0.183402 0.529914 -0.75484 -0.63504 -
"much" 1463 0.089223 0.104564 0.539584 -0.77562 -0.61696 -
"three" 490 0.029496 0.039834 0.574555 -0.85462 -0.55416 -
"addresses" 673 0.040440 0.055602 0.578930 -0.86496 -0.54657 -
"must" 1033 0.061929 0.087137 0.584554 -0.87840 -0.53691 -
"sun" 1994 0.119453 0.169295 0.586307 -0.88263 -0.53391 -
"college" 221 0.013213 0.019087 0.590926 -0.89386 -0.52606 -
"immediately" 374 0.022356 0.032365 0.591459 -0.89516 -0.52516 -
"emails" 275 0.016416 0.024066 0.594484 -0.90259 -0.52006 -
"please" 4156 0.247114 0.375934 0.603379 -0.92477 -0.50521 +
"your" 5978 0.355088 0.545228 0.605596 -0.93038 -0.50154 +
"address" 2613 0.155022 0.240664 0.608220 -0.93705 -0.49722 +
"feel" 519 0.030764 0.048133 0.610072 -0.94179 -0.49418 +
"stop" 552 0.032699 0.051452 0.611423 -0.94526 -0.49197 +
"information" 2933 0.173640 0.274689 0.612694 -0.94854 -0.48989 +
"type" 1926 0.113981 0.180913 0.613485 -0.95059 -0.48860 +
"lawsuits" 33 0.001935 0.003320 0.631706 -0.99887 -0.45933 +
"fast" 302 0.017484 0.033195 0.655002 -1.06422 -0.42312 +
"chance" 356 0.020554 0.039834 0.659635 -1.07774 -0.41607 +
"learn" 442 0.025425 0.050622 0.665665 -1.09561 -0.40697 +
"you'll" 461 0.026493 0.053112 0.667193 -1.10019 -0.40468 +
"powerful" 158 0.009076 0.018257 0.667955 -1.10248 -0.40353 +
"buy" 328 0.018819 0.038174 0.669804 -1.10807 -0.40077 +
"lovers" 21 0.001201 0.002490 0.674532 -1.12249 -0.39374 +
"irs" 28 0.001602 0.003320 0.674535 -1.12250 -0.39373 +
"companies" 454 0.025959 0.053942 0.675107 -1.12426 -0.39288 +
"wall" 125 0.007140 0.014938 0.676581 -1.12881 -0.39070 +
"microsoft" 2372 0.134601 0.294606 0.686395 -1.15962 -0.37630 +
"here" 2496 0.141408 0.312863 0.688714 -1.16704 -0.37293 +
"promotion" 85 0.004805 0.010788 0.691862 -1.17721 -0.36837 +
"receiving" 434 0.024491 0.055602 0.694215 -1.18487 -0.36497 +
"track" 284 0.015949 0.037344 0.700727 -1.20640 -0.35564 +
"disappear" 41 0.002269 0.005809 0.719116 -1.26982 -0.32973 +
"our" 2957 0.163564 0.419917 0.719676 -1.27181 -0.32895 +
"benefit" 187 0.010344 0.026556 0.719680 -1.27182 -0.32895 +
"freedom" 171 0.009409 0.024896 0.725717 -1.29359 -0.32060 +
"price" 385 0.021154 0.056432 0.727341 -1.29953 -0.31836 +
"internet" 2185 0.119920 0.321992 0.728634 -1.30429 -0.31658 +
"strongly" 163 0.008942 0.024066 0.729091 -1.30597 -0.31596 +
"order" 877 0.048048 0.130290 0.730579 -1.31148 -0.31392 +
"never" 849 0.046446 0.126971 0.732169 -1.31740 -0.31174 +
"friends" 294 0.016016 0.044813 0.736704 -1.33448 -0.30557 +
"criminal" 58 0.003136 0.009129 0.744271 -1.36364 -0.29535 +
"boss" 67 0.003604 0.010788 0.749605 -1.38472 -0.28821 +
"normal" 1779 0.095095 0.293776 0.755458 -1.40837 -0.28043 +
"enemies" 15 0.000801 0.002490 0.756604 -1.41307 -0.27891 +
"mime" 848 0.045112 0.142739 0.759852 -1.42650 -0.27463 +
"selling" 94 0.004872 0.017427 0.781531 -1.52111 -0.24650 +
"alternative" 1140 0.058725 0.215768 0.786058 -1.54205 -0.24072 +
"nis.acs.uci.edu" 4866 0.244311 1.000000 0.803658 -1.62789 -0.21858 +
"html" 2670 0.133267 0.558506 0.807355 -1.64691 -0.21399 +
"x-msmail-priority" 1289 0.062930 0.287137 0.820235 -1.71610 -0.19816 +
"x-priority" 1556 0.075676 0.350207 0.822309 -1.72771 -0.19564 +
"click" 1298 0.062462 0.300415 0.827869 -1.75950 -0.18890 +
"tax" 128 0.006073 0.030705 0.834879 -1.80107 -0.18047 +
"yahoo.com" 579 0.026827 0.146888 0.845569 -1.86801 -0.16775 +
"multi-part" 416 0.018886 0.110373 0.853893 -1.92341 -0.15795 +
"removed" 749 0.033834 0.200830 0.855819 -1.93669 -0.15570 +
"remove" 1021 0.044978 0.287967 0.864907 -2.00179 -0.14513 +
"greedy" 29 0.001268 0.008299 0.867448 -2.02078 -0.14220 +
"quot" 218 0.008609 0.073859 0.895610 -2.25962 -0.11025 +
"judgments" 28 0.000734 0.014108 0.950522 -3.00623 -0.05074 +
"creditors" 42 0.000801 0.024896 0.968824 -3.46810 -0.03167 +
N_P_Q_S_s_x_md 131 1.00e-00 0.00e+00 1.05e-06 1.00e-03 4.15e-01 0.10
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 189 bytes
Desc: This is a digitally signed message part
URL: <http://www.bogofilter.org/pipermail/bogofilter/attachments/20030505/092cf13d/attachment.sig>
More information about the Bogofilter
mailing list