You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spamassassin.apache.org by sp...@apache.org on 2023/07/24 02:45:45 UTC

svn commit: r1911219 [2/2] - in /spamassassin/trunk/rulesrc/scores: 72_scores.cf scores-set0 scores-set1 scores-set2 scores-set3 stats-set0 stats-set1

Modified: spamassassin/trunk/rulesrc/scores/scores-set3
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rulesrc/scores/scores-set3?rev=1911219&r1=1911218&r2=1911219&view=diff
==============================================================================
--- spamassassin/trunk/rulesrc/scores/scores-set3 (original)
+++ spamassassin/trunk/rulesrc/scores/scores-set3 Mon Jul 24 02:45:45 2023
@@ -1,40 +1,40 @@
 # Using score set 1 logs for revision 1911193 from:
 # ham-net-ena-week0.r1911193.log ham-net-ena-week1.r1911193.log ham-net-ena-week2.r1911193.log ham-net-ena-week3.r1911193.log ham-net-ena-week4.r1911193.log ham-net-giovanni-ham.r1911193.log ham-net-giovanni-spammy.r1911193.log ham-net-giovanni-spam.r1911193.log ham-net-grenier.r1911193.log ham-net-hege.r1911193.log ham-net-jhardin.r1911193.log ham-net-llanga.r1911193.log ham-net-mmiroslaw-mails-ham.r1911193.log ham-net-mmiroslaw-mails-spam.r1911193.log ham-net-spamsponge.r1911193.log ham-net-thendrikx.r1911193.log ham-net-whyscream.r1911193.log spam-net-ena-week0.r1911193.log spam-net-ena-week1.r1911193.log spam-net-ena-week2.r1911193.log spam-net-ena-week3.r1911193.log spam-net-ena-week4.r1911193.log spam-net-giovanni-ham.r1911193.log spam-net-giovanni-spammy.r1911193.log spam-net-giovanni-spam.r1911193.log spam-net-grenier.r1911193.log spam-net-hege.r1911193.log spam-net-jhardin.r1911193.log spam-net-llanga.r1911193.log spam-net-mmiroslaw-mails-ham.r1911193.log spam-net-mmiroslaw
 -mails-spam.r1911193.log spam-net-spamsponge.r1911193.log spam-net-thendrikx.r1911193.log spam-net-whyscream.r1911193.log
 
-score ACCT_PHISHING_MANY             2.999
+score ACCT_PHISHING_MANY             3.000
 score AC_BR_BONANZA                  0.001
 score AC_DIV_BONANZA                 0.001
 score AC_FROM_MANY_DOTS              2.999
 score AC_HTML_NONSENSE_TAGS          1.999
-score ADMITS_SPAM                    0.001
-score ADVANCE_FEE_2_NEW_MONEY        2.000
-score ADVANCE_FEE_3_NEW              3.266
+score ADMITS_SPAM                    0.001 # force non-zero
+score ADVANCE_FEE_2_NEW_MONEY        1.999
+score ADVANCE_FEE_3_NEW              3.272
 score ADVANCE_FEE_3_NEW_MONEY        0.001
 score ADVANCE_FEE_4_NEW_MONEY        0.001
-score ADVANCE_FEE_5_NEW_FRM_MNY      1.496
-score ADVANCE_FEE_5_NEW_MONEY        0.281
-score AD_PREFS                       0.001
+score ADVANCE_FEE_5_NEW_FRM_MNY      2.028
+score ADVANCE_FEE_5_NEW_MONEY        0.540
+score AD_PREFS                       0.369
 score AMAZON_IMG_NOT_RCVD_AMZN       0.001
-score AXB_XMAILER_MIMEOLE_OL_024C2   0.001
-score BIGNUM_EMAILS_MANY             3.000
-score BITCOIN_DEADLINE               2.999
-score BITCOIN_EXTORT_01              4.245
-score BITCOIN_MALF_HTML              3.429
-score BITCOIN_MALWARE                0.474
-score BITCOIN_SPAM_02                0.001
-score BITCOIN_SPAM_05                0.001
+score AXB_XMAILER_MIMEOLE_OL_024C2   0.001 # force non-zero
+score BIGNUM_EMAILS_MANY             2.999
+score BITCOIN_DEADLINE               1.818
+score BITCOIN_EXTORT_01              4.396
+score BITCOIN_MALF_HTML              3.311
+score BITCOIN_MALWARE                0.576
+score BITCOIN_SPAM_02                0.004
+score BITCOIN_SPAM_05                0.166
 score BITCOIN_SPAM_07                0.001
 score BITCOIN_XPRIO                  0.001
-score BITCOIN_YOUR_INFO              2.793
+score BITCOIN_YOUR_INFO              2.733
 score BODY_SINGLE_URI                2.499
-score BODY_SINGLE_WORD               0.001
-score BODY_URI_ONLY                  2.049
-score CK_HELO_GENERIC                0.249
+score BODY_SINGLE_WORD               0.001 # force non-zero
+score BODY_URI_ONLY                  2.044
+score CK_HELO_GENERIC                0.250
 score CTE_8BIT_MISMATCH              0.001
-score DEAR_BENEFICIARY               0.001 # force non-zero
+score DEAR_BENEFICIARY               0.001
 score DKIMWL_BL                      2.669
 score DKIMWL_WL_HIGH                 -0.001
-score DKIMWL_WL_MED                  -0.001 # force non-zero
+score DKIMWL_WL_MED                  -0.001
 score DKIMWL_WL_MEDHI                -0.001
 score DOS_BODY_HIGH_NO_MID           0.001
 score DX_TEXT_03                     1.299
@@ -42,71 +42,71 @@ score END_FUTURE_EMAILS              2.4
 score FILL_THIS_FORM                 0.899
 score FONT_INVIS_DIRECT              0.001 # force non-zero
 score FONT_INVIS_LONG_LINE           2.999
-score FONT_INVIS_MSGID               0.001 # force non-zero
-score FONT_INVIS_POSTEXTRAS          3.083
-score FORGED_SPF_HELO                0.024
+score FONT_INVIS_MSGID               0.001
+score FONT_INVIS_POSTEXTRAS          3.084
+score FORGED_SPF_HELO                0.029
 score FORM_FRAUD                     0.999
-score FORM_FRAUD_5                   0.608
+score FORM_FRAUD_5                   0.350
 score FREEMAIL_FORGED_FROMDOMAIN     0.249
-score FROM_2_EMAILS_SHORT            0.621
-score FROM_ADDR_WS                   1.644
+score FROM_2_EMAILS_SHORT            0.614
+score FROM_ADDR_WS                   1.643
 score FROM_FMBLA_NEWDOM28            0.799
 score FROM_GOV_DKIM_AU               -0.999
-score FROM_IN_TO_AND_SUBJ            1.797
+score FROM_IN_TO_AND_SUBJ            1.691
 score FROM_MISSPACED                 0.001
-score FROM_MISSP_EH_MATCH            0.567
-score FROM_MISSP_FREEMAIL            0.096
-score FROM_MISSP_MSFT                0.001
+score FROM_MISSP_EH_MATCH            0.561
+score FROM_MISSP_FREEMAIL            0.092
+score FROM_MISSP_MSFT                0.001 # force non-zero
 score FROM_MISSP_REPLYTO             0.001
 score FROM_MISSP_SPF_FAIL            0.001
 score FROM_MISSP_USER                0.001
-score FROM_PAYPAL_SPOOF              1.599
-score FROM_SUSPICIOUS_NTLD           0.001 # force non-zero
+score FROM_PAYPAL_SPOOF              1.498
+score FROM_SUSPICIOUS_NTLD           0.001
 score FROM_SUSPICIOUS_NTLD_FP        1.999
 score FROM_WSP_TRAIL                 2.499
 score FSL_BULK_SIG                   0.001
 score FSL_CTYPE_WIN1251              0.001
 score FSL_HELO_FAKE                  0.001
 score FSL_NEW_HELO_USER              0.001
-score FUZZY_AMAZON                   0.001 # force non-zero
+score FUZZY_AMAZON                   0.001
 score GB_CUSTOM_HTM_URI              1.499
 score GB_FAKE_RF_SHORT               1.999
 score GB_FREEMAIL_DISPTO             0.001
-score GB_HASHBL_BTC                  0.159
+score GB_HASHBL_BTC                  0.001
 score GOOG_REDIR_HTML_ONLY           1.999
 score GOOG_REDIR_NORDNS              3.099
-score GOOG_STO_NOIMG_HTML            2.710
-score HAS_X_OUTGOING_SPAM_STAT       1.254
+score GOOG_STO_NOIMG_HTML            2.713
+score HAS_X_OUTGOING_SPAM_STAT       1.009
 score HDRS_MISSP                     0.001
 score HDR_ORDER_FTSDMCXX_DIRECT      0.001
 score HDR_ORDER_FTSDMCXX_NORDNS      0.001
-score HEADER_FROM_DIFFERENT_DOMAINS  0.249
+score HEADER_FROM_DIFFERENT_DOMAINS  0.250
 score HELO_NO_DOMAIN                 0.001
-score HK_LOTTO                       0.001 # force non-zero
+score HK_LOTTO                       0.001
 score HK_NAME_MR_MRS                 0.999
-score HK_RANDOM_ENVFROM              0.001 # force non-zero
+score HK_RANDOM_ENVFROM              0.001
 score HK_RANDOM_FROM                 0.001
 score HK_RANDOM_REPLYTO              0.999
 score HK_SCAM                        1.999
 score HOSTED_IMG_DIRECT_MX           0.001
-score HOSTED_IMG_FREEM               3.217
+score HOSTED_IMG_FREEM               3.214
 score HOSTED_IMG_MULTI_PUB_01        2.999
 score HTML_ENTITY_ASCII              2.999
 score HTML_FONT_TINY_NORDNS          0.001
-score HTML_OFF_PAGE                  0.001 # force non-zero
+score HTML_OFF_PAGE                  0.001
 score HTML_SINGLET_MANY              2.499
 score HTML_TAG_BALANCE_CENTER        2.699
-score HTML_TEXT_INVISIBLE_FONT       1.751
-score HTML_TEXT_INVISIBLE_STYLE      0.001 # force non-zero
+score HTML_TEXT_INVISIBLE_FONT       1.748
+score HTML_TEXT_INVISIBLE_STYLE      0.001
 score KHOP_HELO_FCRDNS               0.001
 score LONGLN_LOW_CONTRAST            0.001
-score LONG_HEX_URI                   3.000
+score LONG_HEX_URI                   2.999
 score LONG_IMG_URI                   0.001
-score LONG_INVISIBLE_TEXT            0.969
+score LONG_INVISIBLE_TEXT            0.976
 score LOTS_OF_MONEY                  0.010
 score LOTTO_DEPT                     1.999
-score MALWARE_NORDNS                 0.002
-score MALWARE_PASSWORD               1.486
+score MALWARE_NORDNS                 0.001
+score MALWARE_PASSWORD               1.437
 score MANY_SPAN_IN_TEXT              2.099
 score MILLION_HUNDRED                0.001
 score MILLION_USD                    1.999
@@ -116,87 +116,87 @@ score MONEY_ATM_CARD                 0.0
 score MONEY_FORM                     0.001
 score MONEY_FORM_SHORT               0.001
 score MONEY_FRAUD_3                  0.001
-score MONEY_FRAUD_5                  0.807
+score MONEY_FRAUD_5                  0.805
 score MONEY_FRAUD_8                  0.001
-score MONEY_FREEMAIL_REPTO           1.240
+score MONEY_FREEMAIL_REPTO           1.239
 score MONEY_FROM_MISSP               0.001
-score MSMAIL_PRI_ABNORMAL            0.001
+score MSMAIL_PRI_ABNORMAL            0.158
 score NA_DOLLARS                     1.499
-score NICE_REPLY_A                   -0.093
+score NICE_REPLY_A                   -0.091
 score NO_FM_NAME_IP_HOSTN            0.001
 score NSL_RCVD_FROM_USER             0.001
-score NSL_RCVD_HELO_USER             0.001 # force non-zero
-score OBFU_TEXT_ATTACH               0.348
-score ODD_FREEM_REPTO                2.549
-score PDS_BAD_THREAD_QP_64           0.999
-score PDS_BTC_ID                     0.298
+score NSL_RCVD_HELO_USER             0.001
+score OBFU_TEXT_ATTACH               0.346
+score ODD_FREEM_REPTO                2.552
+score PDS_BAD_THREAD_QP_64           1.000
+score PDS_BTC_ID                     0.410
 score PDS_BTC_MSGID                  0.001
 score PDS_EMPTYSUBJ_URISHRT          1.499
 score PDS_FRNOM_TODOM_DBL_URL        1.499
-score PDS_FRNOM_TODOM_NAKED_TO       1.499
-score PDS_FROM_2_EMAILS              2.999
+score PDS_FRNOM_TODOM_NAKED_TO       1.500
+score PDS_FROM_2_EMAILS              3.000
 score PDS_FROM_NAME_TO_DOMAIN        1.999
-score PDS_HP_HELO_NORDNS             0.001 # force non-zero
-score PDS_OTHER_BAD_TLD              0.001 # force non-zero
+score PDS_HP_HELO_NORDNS             0.001
+score PDS_OTHER_BAD_TLD              0.001
 score PDS_TINYSUBJ_URISHRT           0.001
 score PDS_TO_EQ_FROM_NAME            0.001
 score PHP_ORIG_SCRIPT                0.001
-score PHP_SCRIPT                     2.043
+score PHP_SCRIPT                     2.285
 score PP_MIME_FAKE_ASCII_TEXT        0.001
-score RAND_MKTG_HEADER               1.500
+score RAND_MKTG_HEADER               1.497
 score RATWARE_NO_RDNS                0.001
 score RCVD_IN_MSPIKE_H2              -0.001
 score SCC_BODY_SINGLE_WORD           0.001
-score SCC_CANSPAM_2                  2.899
+score SCC_CANSPAM_2                  2.900
 score SCC_ISEMM_LID_1B               1.499
-score SENDGRID_REDIR                 1.042
-score SERGIO_SUBJECT_PORN014         1.147
-score SERGIO_SUBJECT_VIAGRA01        3.450
-score SHOPIFY_IMG_NOT_RCVD_SFY       1.478
+score SENDGRID_REDIR                 1.038
+score SERGIO_SUBJECT_PORN014         1.374
+score SERGIO_SUBJECT_VIAGRA01        3.203
+score SHOPIFY_IMG_NOT_RCVD_SFY       1.482
 score SHORT_SHORTNER                 1.999
-score SPOOFED_FREEMAIL               0.001 # force non-zero
+score SPOOFED_FREEMAIL               0.001
 score SPOOFED_FREEMAIL_NO_RDNS       0.001
 score SPOOFED_FREEM_REPTO            0.001
-score SPOOF_GMAIL_MID                0.001 # force non-zero
+score SPOOF_GMAIL_MID                0.001
 score STATIC_XPRIO_OLE               1.999
-score STOX_BOUND_090909_B            2.257
-score SUBJ_BROKEN_WORD               0.833
+score STOX_BOUND_090909_B            1.970
+score SUBJ_BROKEN_WORD               2.399
 score SUSP_UTF8_WORD_COMBO           2.999
-score SUSP_UTF8_WORD_FROM            1.999
+score SUSP_UTF8_WORD_FROM            2.000
 score THIS_AD                        1.599
-score TONOM_EQ_TOLOC_SHRT_SHRTNER    1.500
-score TO_EQ_FM_DIRECT_MX             1.225
-score TO_EQ_FM_DOM_HTML_IMG          2.400
+score TONOM_EQ_TOLOC_SHRT_SHRTNER    1.499
+score TO_EQ_FM_DIRECT_MX             1.222
+score TO_EQ_FM_DOM_HTML_IMG          2.399
 score TO_EQ_FM_DOM_SPF_FAIL          0.001
-score TO_EQ_FM_SPF_FAIL              0.001
-score TO_IN_SUBJ                     0.100
-score TO_NAME_SUBJ_NO_RDNS           2.929
+score TO_EQ_FM_SPF_FAIL              0.001 # force non-zero
+score TO_IN_SUBJ                     0.099
+score TO_NAME_SUBJ_NO_RDNS           2.956
 score TO_NO_BRKTS_FROM_MSSP          2.499
 score TO_NO_BRKTS_HTML_IMG           1.999
-score TO_NO_BRKTS_HTML_ONLY          1.999
-score TO_NO_BRKTS_MSFT               0.873
-score TO_NO_BRKTS_NORDNS_HTML        1.921
+score TO_NO_BRKTS_HTML_ONLY          2.000
+score TO_NO_BRKTS_MSFT               0.861
+score TO_NO_BRKTS_NORDNS_HTML        1.923
 score TO_NO_BRKTS_PCNT               2.499
-score TVD_IP_HEX                     2.348
+score TVD_IP_HEX                     2.358
 score TVD_SPACE_ENCODED              0.001
 score TVD_SPACE_RATIO_MINFP          0.001
 score UNDISC_FREEM                   2.599
 score UNDISC_MONEY                   2.899
 score UNICODE_OBFU_ASC               2.499
-score URI_GOOGLE_PROXY               2.399
-score URI_ONLY_MSGID_MALF            1.275
-score URI_PHISH                      3.672
+score URI_GOOGLE_PROXY               2.400
+score URI_ONLY_MSGID_MALF            0.001
+score URI_PHISH                      3.674
 score URI_TRY_3LD                    1.999
-score URI_WP_HACKED                  0.562
+score URI_WP_HACKED                  0.561
 score URI_WP_HACKED_2                2.499
 score VFY_ACCT_NORDNS                2.999
-score WORD_INVIS                     2.347
+score WORD_INVIS                     2.342
 score WORD_INVIS_MANY                2.999
-score XFER_LOTSA_MONEY               0.991
+score XFER_LOTSA_MONEY               0.988
 score XM_RANDOM                      0.001
 score XM_RECPTID                     2.999
 score XPRIO                          0.001
-score YOUR_PERMISSION                2.170
+score YOUR_PERMISSION                2.699
 score AC_POST_EXTRAS                 1.000
 score AC_SPAMMY_URI_PATTERNS1        1.000
 score AC_SPAMMY_URI_PATTERNS10       1.000

Modified: spamassassin/trunk/rulesrc/scores/stats-set0
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rulesrc/scores/stats-set0?rev=1911219&r1=1911218&r2=1911219&view=diff
==============================================================================
--- spamassassin/trunk/rulesrc/scores/stats-set0 (original)
+++ spamassassin/trunk/rulesrc/scores/stats-set0 Mon Jul 24 02:45:45 2023
@@ -1,40 +1,40 @@
 ##### WITH NEW RULES AND SCORES #####
 
 # SUMMARY for threshold 5.0:
-# Correctly non-spam: 397670  50.696%  (99.188% of non-spam corpus)
-# Correctly spam:     188724  24.059%  (49.212% of spam corpus)
-# False positives:      3256  0.415%  (0.812% of nonspam, 109832 weighted)
-# False negatives:    194766  24.829%  (50.788% of spam, 403237 weighted)
-# Average score for spam:  6.7    nonspam: 0.7
-# Average for false-pos:   7.1  false-neg: 2.1
-# TOTAL:              784416  100.00%
+# Correctly non-spam: 396883  51.219%  (99.172% of non-spam corpus)
+# Correctly spam:     183357  23.663%  (48.936% of spam corpus)
+# False positives:      3313  0.428%  (0.828% of nonspam, 110344 weighted)
+# False negatives:    191329  24.691%  (51.064% of spam, 392090 weighted)
+# Average score for spam:  6.5    nonspam: 0.7
+# Average for false-pos:   7.1  false-neg: 2.0
+# TOTAL:              774882  100.00%
 
 Reading scores from "tmprules"...
 Reading per-message hit stat logs and scores...
 
 # SUMMARY for threshold 5.0:
-# Correctly non-spam:  49603  99.19%
-# Correctly spam:      23623  49.41%
-# False positives:       405  0.81%
-# False negatives:     24183  50.59%
-# TCR(l=50): 1.075912  SpamRecall: 49.414%  SpamPrec: 98.314%
+# Correctly non-spam:  49538  99.21%
+# Correctly spam:      22609  48.43%
+# False positives:       395  0.79%
+# False negatives:     24078  51.57%
+# TCR(l=50): 1.065232  SpamRecall: 48.427%  SpamPrec: 98.283%
 
 ##### WITHOUT NEW RULES AND SCORES #####
 Reading scores from "../rules-base"...
 Reading per-message hit stat logs and scores...
 
 # SUMMARY for threshold 5.0:
-# Correctly non-spam: 392091  97.80%
-# Correctly spam:     122141  31.85%
-# False positives:      8835  2.20%
-# False negatives:    261349  68.15%
-# TCR(l=50): 0.545428  SpamRecall: 31.850%  SpamPrec: 93.254%
+# Correctly non-spam: 391224  97.76%
+# Correctly spam:     118598  31.65%
+# False positives:      8972  2.24%
+# False negatives:    256088  68.35%
+# TCR(l=50): 0.531705  SpamRecall: 31.653%  SpamPrec: 92.967%
 Reading scores from "../rules-base"...
 Reading per-message hit stat logs and scores...
 
 # SUMMARY for threshold 5.0:
-# Correctly non-spam:  48775  97.53%
-# Correctly spam:      15442  32.30%
-# False positives:      1233  2.47%
-# False negatives:     32364  67.70%
-# TCR(l=50): 0.508499  SpamRecall: 32.301%  SpamPrec: 92.606%
+# Correctly non-spam:  48826  97.78%
+# Correctly spam:      14852  31.81%
+# False positives:      1107  2.22%
+# False negatives:     31835  68.19%
+# TCR(l=50): 0.535493  SpamRecall: 31.812%  SpamPrec: 93.063%

Modified: spamassassin/trunk/rulesrc/scores/stats-set1
URL: http://svn.apache.org/viewvc/spamassassin/trunk/rulesrc/scores/stats-set1?rev=1911219&r1=1911218&r2=1911219&view=diff
==============================================================================
--- spamassassin/trunk/rulesrc/scores/stats-set1 (original)
+++ spamassassin/trunk/rulesrc/scores/stats-set1 Mon Jul 24 02:45:45 2023
@@ -1,12 +1,12 @@
 ##### WITH NEW RULES AND SCORES #####
 
 # SUMMARY for threshold 5.0:
-# Correctly non-spam: 373862  76.545%  (98.912% of non-spam corpus)
-# Correctly spam:      78780  16.130%  (71.331% of spam corpus)
-# False positives:      4114  0.842%  (1.088% of nonspam, 136738 weighted)
-# False negatives:     31663  6.483%  (28.669% of spam,  26875 weighted)
-# Average score for spam:  13.7    nonspam: -0.4
-# Average for false-pos:   11.4  false-neg: 0.8
+# Correctly non-spam: 373871  76.547%  (98.914% of non-spam corpus)
+# Correctly spam:      78742  16.122%  (71.297% of spam corpus)
+# False positives:      4105  0.840%  (1.086% of nonspam, 136612 weighted)
+# False negatives:     31701  6.491%  (28.703% of spam,  27075 weighted)
+# Average score for spam:  13.8    nonspam: -0.4
+# Average for false-pos:   11.4  false-neg: 0.9
 # TOTAL:              488419  100.00%
 
 Reading scores from "tmprules"...