+@item local
+@cindex local variables
+The value of this entry should be a list of @code{(@var{var}
+@var{value})} pairs. Each @var{var} will be made buffer-local to the
+current summary buffer, and set to the value specified. This is a
+convenient, if somewhat strange, way of setting variables in some
+groups if you don't like hooks much. Note that the @var{value} won't
+be evaluated.
+@end table
+
+
+@node Score File Editing
+@section Score File Editing
+
+You normally enter all scoring commands from the summary buffer, but you
+might feel the urge to edit them by hand as well, so we've supplied you
+with a mode for that.
+
+It's simply a slightly customized @code{emacs-lisp} mode, with these
+additional commands:
+
+@table @kbd
+
+@item C-c C-c
+@kindex C-c C-c (Score)
+@findex gnus-score-edit-done
+Save the changes you have made and return to the summary buffer
+(@code{gnus-score-edit-done}).
+
+@item C-c C-d
+@kindex C-c C-d (Score)
+@findex gnus-score-edit-insert-date
+Insert the current date in numerical format
+(@code{gnus-score-edit-insert-date}). This is really the day number, if
+you were wondering.
+
+@item C-c C-p
+@kindex C-c C-p (Score)
+@findex gnus-score-pretty-print
+The adaptive score files are saved in an unformatted fashion. If you
+intend to read one of these files, you want to @dfn{pretty print} it
+first. This command (@code{gnus-score-pretty-print}) does that for
+you.
+
+@end table
+
+Type @kbd{M-x gnus-score-mode} to use this mode.
+
+@vindex gnus-score-mode-hook
+@code{gnus-score-menu-hook} is run in score mode buffers.
+
+In the summary buffer you can use commands like @kbd{V f}, @kbd{V e} and
+@kbd{V t} to begin editing score files.
+
+
+@node Adaptive Scoring
+@section Adaptive Scoring
+@cindex adaptive scoring
+
+If all this scoring is getting you down, Gnus has a way of making it all
+happen automatically---as if by magic. Or rather, as if by artificial
+stupidity, to be precise.
+
+@vindex gnus-use-adaptive-scoring
+When you read an article, or mark an article as read, or kill an
+article, you leave marks behind. On exit from the group, Gnus can sniff
+these marks and add score elements depending on what marks it finds.
+You turn on this ability by setting @code{gnus-use-adaptive-scoring} to
+@code{t} or @code{(line)}. If you want score adaptively on separate
+words appearing in the subjects, you should set this variable to
+@code{(word)}. If you want to use both adaptive methods, set this
+variable to @code{(word line)}.
+
+@vindex gnus-default-adaptive-score-alist
+To give you complete control over the scoring process, you can customize
+the @code{gnus-default-adaptive-score-alist} variable. For instance, it
+might look something like this:
+
+@lisp
+(setq gnus-default-adaptive-score-alist
+ '((gnus-unread-mark)
+ (gnus-ticked-mark (from 4))
+ (gnus-dormant-mark (from 5))
+ (gnus-del-mark (from -4) (subject -1))
+ (gnus-read-mark (from 4) (subject 2))
+ (gnus-expirable-mark (from -1) (subject -1))
+ (gnus-killed-mark (from -1) (subject -3))
+ (gnus-kill-file-mark)
+ (gnus-ancient-mark)
+ (gnus-low-score-mark)
+ (gnus-catchup-mark (from -1) (subject -1))))
+@end lisp
+
+As you see, each element in this alist has a mark as a key (either a
+variable name or a ``real'' mark---a character). Following this key is
+a arbitrary number of header/score pairs. If there are no header/score
+pairs following the key, no adaptive scoring will be done on articles
+that have that key as the article mark. For instance, articles with
+@code{gnus-unread-mark} in the example above will not get adaptive score
+entries.
+
+Each article can have only one mark, so just a single of these rules
+will be applied to each article.
+
+To take @code{gnus-del-mark} as an example---this alist says that all
+articles that have that mark (i.e., are marked with @samp{e}) will have a
+score entry added to lower based on the @code{From} header by -4, and
+lowered by @code{Subject} by -1. Change this to fit your prejudices.
+
+If you have marked 10 articles with the same subject with
+@code{gnus-del-mark}, the rule for that mark will be applied ten times.
+That means that that subject will get a score of ten times -1, which
+should be, unless I'm much mistaken, -10.
+
+If you have auto-expirable (mail) groups (@pxref{Expiring Mail}), all
+the read articles will be marked with the @samp{E} mark. This'll
+probably make adaptive scoring slightly impossible, so auto-expiring and
+adaptive scoring doesn't really mix very well.
+
+The headers you can score on are @code{from}, @code{subject},
+@code{message-id}, @code{references}, @code{xref}, @code{lines},
+@code{chars} and @code{date}. In addition, you can score on
+@code{followup}, which will create an adaptive score entry that matches
+on the @code{References} header using the @code{Message-ID} of the
+current article, thereby matching the following thread.
+
+If you use this scheme, you should set the score file atom @code{mark}
+to something small---like -300, perhaps, to avoid having small random
+changes result in articles getting marked as read.
+
+After using adaptive scoring for a week or so, Gnus should start to
+become properly trained and enhance the authors you like best, and kill
+the authors you like least, without you having to say so explicitly.
+
+You can control what groups the adaptive scoring is to be performed on
+by using the score files (@pxref{Score File Format}). This will also
+let you use different rules in different groups.
+
+@vindex gnus-adaptive-file-suffix
+The adaptive score entries will be put into a file where the name is the
+group name with @code{gnus-adaptive-file-suffix} appended. The default
+is @file{ADAPT}.
+
+@vindex gnus-score-exact-adapt-limit
+When doing adaptive scoring, substring or fuzzy matching would probably
+give you the best results in most cases. However, if the header one
+matches is short, the possibility for false positives is great, so if
+the length of the match is less than
+@code{gnus-score-exact-adapt-limit}, exact matching will be used. If
+this variable is @code{nil}, exact matching will always be used to avoid
+this problem.
+
+@vindex gnus-default-adaptive-word-score-alist
+As mentioned above, you can adapt either on individual words or entire
+headers. If you adapt on words, the
+@code{gnus-default-adaptive-word-score-alist} variable says what score
+each instance of a word should add given a mark.
+
+@lisp
+(setq gnus-default-adaptive-word-score-alist
+ `((,gnus-read-mark . 30)
+ (,gnus-catchup-mark . -10)
+ (,gnus-killed-mark . -20)
+ (,gnus-del-mark . -15)))
+@end lisp
+
+This is the default value. If you have adaption on words enabled, every
+word that appears in subjects of articles marked with
+@code{gnus-read-mark} will result in a score rule that increase the
+score with 30 points.
+
+@vindex gnus-default-ignored-adaptive-words
+@vindex gnus-ignored-adaptive-words
+Words that appear in the @code{gnus-default-ignored-adaptive-words} list
+will be ignored. If you wish to add more words to be ignored, use the
+@code{gnus-ignored-adaptive-words} list instead.
+
+@vindex gnus-adaptive-word-length-limit
+Some may feel that short words shouldn't count when doing adaptive
+scoring. If so, you may set @code{gnus-adaptive-word-length-limit} to
+an integer. Words shorter than this number will be ignored. This
+variable defaults to @code{nil}.
+
+@vindex gnus-adaptive-word-syntax-table
+When the scoring is done, @code{gnus-adaptive-word-syntax-table} is the
+syntax table in effect. It is similar to the standard syntax table, but
+it considers numbers to be non-word-constituent characters.
+
+@vindex gnus-adaptive-word-minimum
+If @code{gnus-adaptive-word-minimum} is set to a number, the adaptive
+word scoring process will never bring down the score of an article to
+below this number. The default is @code{nil}.
+
+@vindex gnus-adaptive-word-no-group-words
+If @code{gnus-adaptive-word-no-group-words} is set to @code{t}, gnus
+won't adaptively word score any of the words in the group name. Useful
+for groups like @samp{comp.editors.emacs}, where most of the subject
+lines contain the word @samp{emacs}.
+
+After using this scheme for a while, it might be nice to write a
+@code{gnus-psychoanalyze-user} command to go through the rules and see
+what words you like and what words you don't like. Or perhaps not.
+
+Note that the adaptive word scoring thing is highly experimental and is
+likely to change in the future. Initial impressions seem to indicate
+that it's totally useless as it stands. Some more work (involving more
+rigorous statistical methods) will have to be done to make this useful.
+
+
+@node Home Score File
+@section Home Score File
+
+The score file where new score file entries will go is called the
+@dfn{home score file}. This is normally (and by default) the score file
+for the group itself. For instance, the home score file for
+@samp{gnu.emacs.gnus} is @file{gnu.emacs.gnus.SCORE}.
+
+However, this may not be what you want. It is often convenient to share
+a common home score file among many groups---all @samp{emacs} groups
+could perhaps use the same home score file.
+
+@vindex gnus-home-score-file
+The variable that controls this is @code{gnus-home-score-file}. It can
+be:
+
+@enumerate
+@item
+A string. Then this file will be used as the home score file for all
+groups.
+
+@item
+A function. The result of this function will be used as the home score
+file. The function will be called with the name of the group as the
+parameter.
+
+@item
+A list. The elements in this list can be:
+
+@enumerate
+@item
+@code{(@var{regexp} @var{file-name})}. If the @var{regexp} matches the
+group name, the @var{file-name} will be used as the home score file.
+
+@item
+A function. If the function returns non-@code{nil}, the result will
+be used as the home score file.
+
+@item
+A string. Use the string as the home score file.
+@end enumerate
+
+The list will be traversed from the beginning towards the end looking
+for matches.
+
+@end enumerate
+
+So, if you want to use just a single score file, you could say:
+
+@lisp
+(setq gnus-home-score-file
+ "my-total-score-file.SCORE")
+@end lisp
+
+If you want to use @file{gnu.SCORE} for all @samp{gnu} groups and
+@file{rec.SCORE} for all @samp{rec} groups (and so on), you can say:
+
+@findex gnus-hierarchial-home-score-file
+@lisp
+(setq gnus-home-score-file
+ 'gnus-hierarchial-home-score-file)
+@end lisp
+
+This is a ready-made function provided for your convenience.
+Other functions include
+
+@table @code
+@item gnus-current-home-score-file
+@findex gnus-current-home-score-file
+Return the ``current'' regular score file. This will make scoring
+commands add entry to the ``innermost'' matching score file.
+
+@end table
+
+If you want to have one score file for the @samp{emacs} groups and
+another for the @samp{comp} groups, while letting all other groups use
+their own home score files:
+
+@lisp
+(setq gnus-home-score-file
+ ;; @r{All groups that match the regexp @code{"\\.emacs"}}
+ '(("\\.emacs" "emacs.SCORE")
+ ;; @r{All the comp groups in one score file}
+ ("^comp" "comp.SCORE")))
+@end lisp
+
+@vindex gnus-home-adapt-file
+@code{gnus-home-adapt-file} works exactly the same way as
+@code{gnus-home-score-file}, but says what the home adaptive score file
+is instead. All new adaptive file entries will go into the file
+specified by this variable, and the same syntax is allowed.
+
+In addition to using @code{gnus-home-score-file} and
+@code{gnus-home-adapt-file}, you can also use group parameters
+(@pxref{Group Parameters}) and topic parameters (@pxref{Topic
+Parameters}) to achieve much the same. Group and topic parameters take
+precedence over this variable.
+
+
+@node Followups To Yourself
+@section Followups To Yourself
+
+Gnus offers two commands for picking out the @code{Message-ID} header in
+the current buffer. Gnus will then add a score rule that scores using
+this @code{Message-ID} on the @code{References} header of other
+articles. This will, in effect, increase the score of all articles that
+respond to the article in the current buffer. Quite useful if you want
+to easily note when people answer what you've said.
+
+@table @code
+
+@item gnus-score-followup-article
+@findex gnus-score-followup-article
+This will add a score to articles that directly follow up your own
+article.
+
+@item gnus-score-followup-thread
+@findex gnus-score-followup-thread
+This will add a score to all articles that appear in a thread ``below''
+your own article.
+@end table
+
+@vindex message-sent-hook
+These two functions are both primarily meant to be used in hooks like
+@code{message-sent-hook}, like this:
+@lisp
+(add-hook 'message-sent-hook 'gnus-score-followup-thread)
+@end lisp
+
+
+If you look closely at your own @code{Message-ID}, you'll notice that
+the first two or three characters are always the same. Here's two of
+mine:
+
+@example
+<x6u3u47icf.fsf@@eyesore.no>
+<x6sp9o7ibw.fsf@@eyesore.no>
+@end example
+
+So ``my'' ident on this machine is @samp{x6}. This can be
+exploited---the following rule will raise the score on all followups to
+myself:
+
+@lisp
+("references"
+ ("<x6[0-9a-z]+\\.fsf\\(_-_\\)?@@.*eyesore\\.no>"
+ 1000 nil r))
+@end lisp
+
+Whether it's the first two or first three characters that are ``yours''
+is system-dependent.
+
+
+@node Scoring On Other Headers
+@section Scoring On Other Headers
+@cindex scoring on other headers
+
+Gnus is quite fast when scoring the ``traditional''
+headers---@samp{From}, @samp{Subject} and so on. However, scoring
+other headers requires writing a @code{head} scoring rule, which means
+that Gnus has to request every single article from the back end to find
+matches. This takes a long time in big groups.
+
+Now, there's not much you can do about this for news groups, but for
+mail groups, you have greater control. In @ref{To From Newsgroups},
+it's explained in greater detail what this mechanism does, but here's
+a cookbook example for @code{nnml} on how to allow scoring on the
+@samp{To} and @samp{Cc} headers.
+
+Put the following in your @file{~/.gnus.el} file.
+
+@lisp
+(setq gnus-extra-headers '(To Cc Newsgroups Keywords)
+ nnmail-extra-headers gnus-extra-headers)
+@end lisp
+
+Restart Gnus and rebuild your @code{nnml} overview files with the
+@kbd{M-x nnml-generate-nov-databases} command. This will take a long
+time if you have much mail.
+
+Now you can score on @samp{To} and @samp{Cc} as ``extra headers'' like
+so: @kbd{I e s p To RET <your name> RET}.
+
+See? Simple.
+
+
+@node Scoring Tips
+@section Scoring Tips
+@cindex scoring tips
+
+@table @dfn
+
+@item Crossposts
+@cindex crossposts
+@cindex scoring crossposts
+If you want to lower the score of crossposts, the line to match on is
+the @code{Xref} header.
+@lisp
+("xref" (" talk.politics.misc:" -1000))
+@end lisp
+
+@item Multiple crossposts
+If you want to lower the score of articles that have been crossposted to
+more than, say, 3 groups:
+@lisp
+("xref"
+ ("[^:\n]+:[0-9]+ +[^:\n]+:[0-9]+ +[^:\n]+:[0-9]+"
+ -1000 nil r))
+@end lisp
+
+@item Matching on the body
+This is generally not a very good idea---it takes a very long time.
+Gnus actually has to fetch each individual article from the server. But
+you might want to anyway, I guess. Even though there are three match
+keys (@code{Head}, @code{Body} and @code{All}), you should choose one
+and stick with it in each score file. If you use any two, each article
+will be fetched @emph{twice}. If you want to match a bit on the
+@code{Head} and a bit on the @code{Body}, just use @code{All} for all
+the matches.
+
+@item Marking as read
+You will probably want to mark articles that have scores below a certain
+number as read. This is most easily achieved by putting the following
+in your @file{all.SCORE} file:
+@lisp
+((mark -100))
+@end lisp
+You may also consider doing something similar with @code{expunge}.
+
+@item Negated character classes
+If you say stuff like @code{[^abcd]*}, you may get unexpected results.
+That will match newlines, which might lead to, well, The Unknown. Say
+@code{[^abcd\n]*} instead.
+@end table
+
+
+@node Reverse Scoring
+@section Reverse Scoring
+@cindex reverse scoring
+
+If you want to keep just articles that have @samp{Sex with Emacs} in the
+subject header, and expunge all other articles, you could put something
+like this in your score file:
+
+@lisp
+(("subject"
+ ("Sex with Emacs" 2))
+ (mark 1)
+ (expunge 1))
+@end lisp
+
+So, you raise all articles that match @samp{Sex with Emacs} and mark the
+rest as read, and expunge them to boot.
+
+
+@node Global Score Files
+@section Global Score Files
+@cindex global score files
+
+Sure, other newsreaders have ``global kill files''. These are usually
+nothing more than a single kill file that applies to all groups, stored
+in the user's home directory. Bah! Puny, weak newsreaders!
+
+What I'm talking about here are Global Score Files. Score files from
+all over the world, from users everywhere, uniting all nations in one
+big, happy score file union! Ange-score! New and untested!
+
+@vindex gnus-global-score-files
+All you have to do to use other people's score files is to set the
+@code{gnus-global-score-files} variable. One entry for each score file,
+or each score file directory. Gnus will decide by itself what score
+files are applicable to which group.
+
+To use the score file
+@file{/ftp@@ftp.gnus.org:/pub/larsi/ding/score/soc.motss.SCORE} and
+all score files in the @file{/ftp@@ftp.some-where:/pub/score} directory,
+say this:
+
+@lisp
+(setq gnus-global-score-files
+ '("/ftp@@ftp.gnus.org:/pub/larsi/ding/score/soc.motss.SCORE"
+ "/ftp@@ftp.some-where:/pub/score/"))
+@end lisp
+
+@findex gnus-score-search-global-directories
+@noindent
+Simple, eh? Directory names must end with a @samp{/}. These
+directories are typically scanned only once during each Gnus session.
+If you feel the need to manually re-scan the remote directories, you can
+use the @code{gnus-score-search-global-directories} command.
+
+Note that, at present, using this option will slow down group entry
+somewhat. (That is---a lot.)
+
+If you want to start maintaining score files for other people to use,
+just put your score file up for anonymous ftp and announce it to the
+world. Become a retro-moderator! Participate in the retro-moderator
+wars sure to ensue, where retro-moderators battle it out for the
+sympathy of the people, luring them to use their score files on false
+premises! Yay! The net is saved!
+
+Here are some tips for the would-be retro-moderator, off the top of my
+head:
+
+@itemize @bullet
+
+@item
+Articles heavily crossposted are probably junk.
+@item
+To lower a single inappropriate article, lower by @code{Message-ID}.
+@item
+Particularly brilliant authors can be raised on a permanent basis.
+@item
+Authors that repeatedly post off-charter for the group can safely be
+lowered out of existence.
+@item
+Set the @code{mark} and @code{expunge} atoms to obliterate the nastiest
+articles completely.
+
+@item
+Use expiring score entries to keep the size of the file down. You
+should probably have a long expiry period, though, as some sites keep
+old articles for a long time.
+@end itemize
+
+@dots{} I wonder whether other newsreaders will support global score files
+in the future. @emph{Snicker}. Yup, any day now, newsreaders like Blue
+Wave, xrn and 1stReader are bound to implement scoring. Should we start
+holding our breath yet?
+
+
+@node Kill Files
+@section Kill Files
+@cindex kill files
+
+Gnus still supports those pesky old kill files. In fact, the kill file
+entries can now be expiring, which is something I wrote before Daniel
+Quinlan thought of doing score files, so I've left the code in there.
+
+In short, kill processing is a lot slower (and I do mean @emph{a lot})
+than score processing, so it might be a good idea to rewrite your kill
+files into score files.
+
+Anyway, a kill file is a normal @code{emacs-lisp} file. You can put any
+forms into this file, which means that you can use kill files as some
+sort of primitive hook function to be run on group entry, even though
+that isn't a very good idea.
+
+Normal kill files look like this:
+
+@lisp
+(gnus-kill "From" "Lars Ingebrigtsen")
+(gnus-kill "Subject" "ding")
+(gnus-expunge "X")
+@end lisp
+
+This will mark every article written by me as read, and remove the
+marked articles from the summary buffer. Very useful, you'll agree.
+
+Other programs use a totally different kill file syntax. If Gnus
+encounters what looks like a @code{rn} kill file, it will take a stab at
+interpreting it.
+
+Two summary functions for editing a @sc{gnus} kill file:
+
+@table @kbd
+
+@item M-k
+@kindex M-k (Summary)
+@findex gnus-summary-edit-local-kill
+Edit this group's kill file (@code{gnus-summary-edit-local-kill}).
+
+@item M-K
+@kindex M-K (Summary)
+@findex gnus-summary-edit-global-kill
+Edit the general kill file (@code{gnus-summary-edit-global-kill}).
+@end table
+
+Two group mode functions for editing the kill files:
+
+@table @kbd
+
+@item M-k
+@kindex M-k (Group)
+@findex gnus-group-edit-local-kill
+Edit this group's kill file (@code{gnus-group-edit-local-kill}).
+
+@item M-K
+@kindex M-K (Group)
+@findex gnus-group-edit-global-kill
+Edit the general kill file (@code{gnus-group-edit-global-kill}).
+@end table
+
+Kill file variables:
+
+@table @code
+@item gnus-kill-file-name
+@vindex gnus-kill-file-name
+A kill file for the group @samp{soc.motss} is normally called
+@file{soc.motss.KILL}. The suffix appended to the group name to get
+this file name is detailed by the @code{gnus-kill-file-name} variable.
+The ``global'' kill file (not in the score file sense of ``global'', of
+course) is just called @file{KILL}.
+
+@vindex gnus-kill-save-kill-file
+@item gnus-kill-save-kill-file
+If this variable is non-@code{nil}, Gnus will save the
+kill file after processing, which is necessary if you use expiring
+kills.
+
+@item gnus-apply-kill-hook
+@vindex gnus-apply-kill-hook
+@findex gnus-apply-kill-file-unless-scored
+@findex gnus-apply-kill-file
+A hook called to apply kill files to a group. It is
+@code{(gnus-apply-kill-file)} by default. If you want to ignore the
+kill file if you have a score file for the same group, you can set this
+hook to @code{(gnus-apply-kill-file-unless-scored)}. If you don't want
+kill files to be processed, you should set this variable to @code{nil}.
+
+@item gnus-kill-file-mode-hook
+@vindex gnus-kill-file-mode-hook
+A hook called in kill-file mode buffers.
+
+@end table
+
+
+@node Converting Kill Files
+@section Converting Kill Files
+@cindex kill files
+@cindex converting kill files
+
+If you have loads of old kill files, you may want to convert them into
+score files. If they are ``regular'', you can use
+the @file{gnus-kill-to-score.el} package; if not, you'll have to do it
+by hand.
+
+The kill to score conversion package isn't included in Gnus by default.
+You can fetch it from
+@uref{http://www.stud.ifi.uio.no/~larsi/ding-various/gnus-kill-to-score.el}.
+
+If your old kill files are very complex---if they contain more
+non-@code{gnus-kill} forms than not, you'll have to convert them by
+hand. Or just let them be as they are. Gnus will still use them as
+before.
+
+
+@node GroupLens
+@section GroupLens
+@cindex GroupLens
+
+@sc{Note:} Unfortunately the GroupLens system seems to have shut down,
+so this section is mostly of historical interest.
+
+@uref{http://www.cs.umn.edu/Research/GroupLens/, GroupLens} is a
+collaborative filtering system that helps you work together with other
+people to find the quality news articles out of the huge volume of
+news articles generated every day.
+
+To accomplish this the GroupLens system combines your opinions about
+articles you have already read with the opinions of others who have done
+likewise and gives you a personalized prediction for each unread news
+article. Think of GroupLens as a matchmaker. GroupLens watches how you
+rate articles, and finds other people that rate articles the same way.
+Once it has found some people you agree with it tells you, in the form
+of a prediction, what they thought of the article. You can use this
+prediction to help you decide whether or not you want to read the
+article.
+
+@menu
+* Using GroupLens:: How to make Gnus use GroupLens.
+* Rating Articles:: Letting GroupLens know how you rate articles.
+* Displaying Predictions:: Displaying predictions given by GroupLens.
+* GroupLens Variables:: Customizing GroupLens.
+@end menu
+
+
+@node Using GroupLens
+@subsection Using GroupLens
+
+To use GroupLens you must register a pseudonym with your local
+@uref{http://www.cs.umn.edu/Research/GroupLens/bbb.html, Better Bit
+Bureau (BBB)} is the only better bit in town at the moment.
+
+Once you have registered you'll need to set a couple of variables.
+
+@table @code
+
+@item gnus-use-grouplens
+@vindex gnus-use-grouplens
+Setting this variable to a non-@code{nil} value will make Gnus hook into
+all the relevant GroupLens functions.
+
+@item grouplens-pseudonym
+@vindex grouplens-pseudonym
+This variable should be set to the pseudonym you got when registering
+with the Better Bit Bureau.
+
+@item grouplens-newsgroups
+@vindex grouplens-newsgroups
+A list of groups that you want to get GroupLens predictions for.
+
+@end table
+
+That's the minimum of what you need to get up and running with GroupLens.
+Once you've registered, GroupLens will start giving you scores for
+articles based on the average of what other people think. But, to get
+the real benefit of GroupLens you need to start rating articles
+yourself. Then the scores GroupLens gives you will be personalized for
+you, based on how the people you usually agree with have already rated.
+
+
+@node Rating Articles
+@subsection Rating Articles
+
+In GroupLens, an article is rated on a scale from 1 to 5, inclusive.
+Where 1 means something like this article is a waste of bandwidth and 5
+means that the article was really good. The basic question to ask
+yourself is, ``on a scale from 1 to 5 would I like to see more articles
+like this one?''
+
+There are four ways to enter a rating for an article in GroupLens.
+
+@table @kbd
+
+@item r
+@kindex r (GroupLens)
+@findex bbb-summary-rate-article
+This function will prompt you for a rating on a scale of one to five.
+
+@item k
+@kindex k (GroupLens)
+@findex grouplens-score-thread
+This function will prompt you for a rating, and rate all the articles in
+the thread. This is really useful for some of those long running giant
+threads in rec.humor.
+
+@end table
+
+The next two commands, @kbd{n} and @kbd{,} take a numerical prefix to be
+the score of the article you're reading.
+
+@table @kbd
+
+@item 1-5 n
+@kindex n (GroupLens)
+@findex grouplens-next-unread-article
+Rate the article and go to the next unread article.
+
+@item 1-5 ,
+@kindex , (GroupLens)
+@findex grouplens-best-unread-article
+Rate the article and go to the next unread article with the highest score.
+
+@end table
+
+If you want to give the current article a score of 4 and then go to the
+next article, just type @kbd{4 n}.
+
+
+@node Displaying Predictions
+@subsection Displaying Predictions
+
+GroupLens makes a prediction for you about how much you will like a
+news article. The predictions from GroupLens are on a scale from 1 to
+5, where 1 is the worst and 5 is the best. You can use the predictions
+from GroupLens in one of three ways controlled by the variable
+@code{gnus-grouplens-override-scoring}.
+
+@vindex gnus-grouplens-override-scoring
+There are three ways to display predictions in grouplens. You may
+choose to have the GroupLens scores contribute to, or override the
+regular Gnus scoring mechanism. override is the default; however, some
+people prefer to see the Gnus scores plus the grouplens scores. To get
+the separate scoring behavior you need to set
+@code{gnus-grouplens-override-scoring} to @code{'separate}. To have the
+GroupLens predictions combined with the grouplens scores set it to
+@code{'override} and to combine the scores set
+@code{gnus-grouplens-override-scoring} to @code{'combine}. When you use
+the combine option you will also want to set the values for
+@code{grouplens-prediction-offset} and
+@code{grouplens-score-scale-factor}.
+
+@vindex grouplens-prediction-display
+In either case, GroupLens gives you a few choices for how you would like
+to see your predictions displayed. The display of predictions is
+controlled by the @code{grouplens-prediction-display} variable.
+
+The following are valid values for that variable.
+
+@table @code
+@item prediction-spot
+The higher the prediction, the further to the right an @samp{*} is
+displayed.
+
+@item confidence-interval
+A numeric confidence interval.
+
+@item prediction-bar
+The higher the prediction, the longer the bar.
+
+@item confidence-bar
+Numerical confidence.
+
+@item confidence-spot
+The spot gets bigger with more confidence.
+
+@item prediction-num
+Plain-old numeric value.
+
+@item confidence-plus-minus
+Prediction +/- confidence.
+
+@end table
+
+
+@node GroupLens Variables
+@subsection GroupLens Variables
+
+@table @code
+
+@item gnus-summary-grouplens-line-format
+The summary line format used in GroupLens-enhanced summary buffers. It
+accepts the same specs as the normal summary line format (@pxref{Summary
+Buffer Lines}). The default is @samp{%U%R%z%l%I%(%[%4L: %-23,23n%]%)
+%s\n}.
+
+@item grouplens-bbb-host
+Host running the bbbd server. @samp{grouplens.cs.umn.edu} is the
+default.
+
+@item grouplens-bbb-port
+Port of the host running the bbbd server. The default is 9000.
+
+@item grouplens-score-offset
+Offset the prediction by this value. In other words, subtract the
+prediction value by this number to arrive at the effective score. The
+default is 0.
+
+@item grouplens-score-scale-factor
+This variable allows the user to magnify the effect of GroupLens scores.
+The scale factor is applied after the offset. The default is 1.
+
+@end table
+
+
+@node Advanced Scoring
+@section Advanced Scoring
+
+Scoring on Subjects and From headers is nice enough, but what if you're
+really interested in what a person has to say only when she's talking
+about a particular subject? Or what if you really don't want to
+read what person A has to say when she's following up to person B, but
+want to read what she says when she's following up to person C?
+
+By using advanced scoring rules you may create arbitrarily complex
+scoring patterns.
+
+@menu
+* Advanced Scoring Syntax:: A definition.
+* Advanced Scoring Examples:: What they look like.
+* Advanced Scoring Tips:: Getting the most out of it.
+@end menu
+
+
+@node Advanced Scoring Syntax
+@subsection Advanced Scoring Syntax
+
+Ordinary scoring rules have a string as the first element in the rule.
+Advanced scoring rules have a list as the first element. The second
+element is the score to be applied if the first element evaluated to a
+non-@code{nil} value.
+
+These lists may consist of three logical operators, one redirection
+operator, and various match operators.
+
+Logical operators:
+
+@table @code
+@item &
+@itemx and
+This logical operator will evaluate each of its arguments until it finds
+one that evaluates to @code{false}, and then it'll stop. If all arguments
+evaluate to @code{true} values, then this operator will return
+@code{true}.
+
+@item |
+@itemx or
+This logical operator will evaluate each of its arguments until it finds
+one that evaluates to @code{true}. If no arguments are @code{true},
+then this operator will return @code{false}.
+
+@item !
+@itemx not
+@itemx ¬
+This logical operator only takes a single argument. It returns the
+logical negation of the value of its argument.
+
+@end table
+
+There is an @dfn{indirection operator} that will make its arguments
+apply to the ancestors of the current article being scored. For
+instance, @code{1-} will make score rules apply to the parent of the
+current article. @code{2-} will make score rules apply to the
+grandparent of the current article. Alternatively, you can write
+@code{^^}, where the number of @code{^}s (carets) says how far back into
+the ancestry you want to go.
+
+Finally, we have the match operators. These are the ones that do the
+real work. Match operators are header name strings followed by a match
+and a match type. A typical match operator looks like @samp{("from"
+"Lars Ingebrigtsen" s)}. The header names are the same as when using
+simple scoring, and the match types are also the same.
+
+
+@node Advanced Scoring Examples
+@subsection Advanced Scoring Examples
+
+Please note that the following examples are score file rules. To
+make a complete score file from them, surround them with another pair
+of parentheses.
+
+Let's say you want to increase the score of articles written by Lars
+when he's talking about Gnus:
+
+@example
+@group
+((&
+ ("from" "Lars Ingebrigtsen")
+ ("subject" "Gnus"))
+ 1000)
+@end group
+@end example
+
+Quite simple, huh?
+
+When he writes long articles, he sometimes has something nice to say:
+
+@example
+((&
+ ("from" "Lars Ingebrigtsen")
+ (|
+ ("subject" "Gnus")
+ ("lines" 100 >)))
+ 1000)
+@end example
+
+However, when he responds to things written by Reig Eigil Logge, you
+really don't want to read what he's written:
+
+@example
+((&
+ ("from" "Lars Ingebrigtsen")
+ (1- ("from" "Reig Eigir Logge")))
+ -100000)
+@end example
+
+Everybody that follows up Redmondo when he writes about disappearing
+socks should have their scores raised, but only when they talk about
+white socks. However, when Lars talks about socks, it's usually not
+very interesting:
+
+@example
+((&
+ (1-
+ (&
+ ("from" "redmondo@@.*no" r)
+ ("body" "disappearing.*socks" t)))
+ (! ("from" "Lars Ingebrigtsen"))
+ ("body" "white.*socks"))
+ 1000)
+@end example
+
+The possibilities are endless.
+
+
+@node Advanced Scoring Tips
+@subsection Advanced Scoring Tips
+
+The @code{&} and @code{|} logical operators do short-circuit logic.
+That is, they stop processing their arguments when it's clear what the
+result of the operation will be. For instance, if one of the arguments
+of an @code{&} evaluates to @code{false}, there's no point in evaluating
+the rest of the arguments. This means that you should put slow matches
+(@samp{body}, @samp{header}) last and quick matches (@samp{from},
+@samp{subject}) first.
+
+The indirection arguments (@code{1-} and so on) will make their
+arguments work on previous generations of the thread. If you say
+something like:
+
+@example
+...
+(1-
+ (1-
+ ("from" "lars")))
+...
+@end example
+
+Then that means "score on the from header of the grandparent of the
+current article". An indirection is quite fast, but it's better to say:
+
+@example
+(1-
+ (&
+ ("from" "Lars")
+ ("subject" "Gnus")))
+@end example
+
+than it is to say:
+
+@example
+(&
+ (1- ("from" "Lars"))
+ (1- ("subject" "Gnus")))
+@end example
+
+
+@node Score Decays
+@section Score Decays
+@cindex score decays
+@cindex decays
+
+You may find that your scores have a tendency to grow without
+bounds, especially if you're using adaptive scoring. If scores get too
+big, they lose all meaning---they simply max out and it's difficult to
+use them in any sensible way.
+
+@vindex gnus-decay-scores
+@findex gnus-decay-score
+@vindex gnus-decay-score-function
+Gnus provides a mechanism for decaying scores to help with this problem.
+When score files are loaded and @code{gnus-decay-scores} is
+non-@code{nil}, Gnus will run the score files through the decaying
+mechanism thereby lowering the scores of all non-permanent score rules.
+The decay itself if performed by the @code{gnus-decay-score-function}
+function, which is @code{gnus-decay-score} by default. Here's the
+definition of that function:
+
+@lisp
+(defun gnus-decay-score (score)
+ "Decay SCORE according to `gnus-score-decay-constant'
+and `gnus-score-decay-scale'."
+ (let ((n (- score
+ (* (if (< score 0) -1 1)
+ (min (abs score)
+ (max gnus-score-decay-constant
+ (* (abs score)
+ gnus-score-decay-scale)))))))
+ (if (and (featurep 'xemacs)
+ ;; XEmacs' floor can handle only the floating point
+ ;; number below the half of the maximum integer.
+ (> (abs n) (lsh -1 -2)))
+ (string-to-number
+ (car (split-string (number-to-string n) "\\.")))
+ (floor n))))