My PHP version is 4.4.6; that version wasn't in the drop-down list, so I put 4.4.5.

Here is my phpinfo:

http://www.prontonyc.com/phpinfo.php

Can you please provide a backtrace?
If possible, try to reproduce the segfault on the console.
Details on how to generate a backtrace can be found at http://bugs.php.net/bugs-generating-backtrace.php
Basically

gdb /path/to/php
run /path/to/script
<segfault>
bt full

Thanks; it was installed in a shared hosting environment, and I do not have access to the command line.  I have asked the hosting provider if they can generate a backtrace, but I do not know if they will have the time.

Here is the backtrace sent by my hosting provider:

(gdb) run gnupg_encryptsign.php
Starting program: /usr/local/bin/php gnupg_encryptsign.php
Reading symbols from shared object read from target memory...done.
Loaded system supplied DSO at 0xb7f89000
[Thread debugging using libthread_db enabled]
[New Thread 16384 (LWP 17942)]
Detaching after fork from child process 29694.
Detaching after fork from child process 22864.
Detaching after fork from child process 17081.
Detaching after fork from child process 28824.
*** glibc detected *** double free or corruption (!prev): 0x0856b288 ***

Program received signal SIGABRT, Aborted.
[Switching to Thread 16384 (LWP 17942)]
0x4f21fba1 in kill () from /lib/i686/libc.so.6
(gdb) bt
#0 0x4f21fba1 in kill () from /lib/i686/libc.so.6
#1 0x4f399271 in pthread_kill () from /lib/i686/libpthread.so.0
#2 0x4f3995db in raise () from /lib/i686/libpthread.so.0
#3 0x4f21f808 in raise () from /lib/i686/libc.so.6
#4 0x4f220f10 in abort () from /lib/i686/libc.so.6
#5 0x4f25377e in __libc_message () from /lib/i686/libc.so.6
#6 0x4f259e7f in _int_free () from /lib/i686/libc.so.6
#7 0x4f25a226 in free () from /lib/i686/libc.so.6
#8 0xb78e098f in zif_gnupg_encryptsign (ht=2, return_value=0x4f31e9c0, this_ptr=0x0, return_value_used=1)
at /root/gnupg-1.3/gnupg.c:1080
#9 0xb780648f in zend_optimizer_set_oe_ex () from /usr/local/Zend/lib/Optimizer-3.2.0/php-4.4.x/ZendOptimizer.so
#10 0x00000002 in ?? ()
#11 0x08561f5c in ?? ()
#12 0x00000000 in ?? ()
(gdb)

They also sent this, which may be useful to you:

pid 32365] <... read resumed> "-----BEGIN PGP MESSAGE-----\nVers"..., 4096) = 1014
[pid 32365] select(12, [4 11], [], NULL, {1, 0} <unfinished ...>
[pid 26388] open("/home/pronto/.gnupg/random_seed", O_WRONLY|O_CREAT|O_TRUNC|O_LARGEFILE, 0600 <unfinished ...>
[pid 32365] <... select resumed> ) = 1 (in [4], left {1, 0})
[pid 26388] <... open resumed> ) = 15
[pid 32365] select(5, [4], [], NULL, {0, 0} <unfinished ...>
[pid 26388] write(15, "\3479\0\263\323\3408Q\334\200\3244v\'\203.i\342+\335\225"..., 600 <unfinished ...>
[pid 32365] <... select resumed> ) = 1 (in [4], left {0, 0})
[pid 32365] read(4, <unfinished ...>
[pid 26388] <... write resumed> ) = 600
[pid 32365] <... read resumed> "[GNUPG:] END_ENCRYPTION\n", 1024) = 24
[pid 26388] close(15 <unfinished ...>
[pid 32365] select(12, [4 11], [], NULL, {1, 0} <unfinished ...>
[pid 26388] <... close resumed> ) = 0
[pid 26388] munmap(0xb7f98000, 32768) = 0
[pid 26388] unlink("/home/pronto/.gnupg/.#lk0x800af138.ocean.hostingzoom.com.26388") = 0
[pid 26388] exit_group(0) = ?
Process 26388 detached
<... select resumed> ) = 1 (in [11], left {0, 996000})
select(12, [11], [], NULL, {0, 0}) = 1 (in [11], left {0, 0})
read(11, "", 4096) = 0
close(11) = 0
select(5, [4], [], NULL, {1, 0}) = 1 (in [4], left {1, 0})
select(5, [4], [], NULL, {0, 0}) = 1 (in [4], left {0, 0})
read(4, "", 1024) = 0
close(4) = 0
open("/dev/tty", O_RDWR|O_NONBLOCK|O_NOCTTY) = 4
writev(4, [{"*** glibc detected *** ", 23}, {"double free or corruption (!prev"..., 33}, {": 0x", 4}, {"0856b7f8", 8}, {" ***\n", 5}], 5*** glibc detected *** double free or corruption (!prev): 0x0856b7f8 ***
) = 73
rt_sigprocmask(SIG_UNBLOCK, [ABRT], NULL, 8) = 0
kill(32365, SIGABRT) = 0
--- SIGABRT (Aborted) @ 0 (0) ---
+++ killed by SIGABRT (core dumped) +++

Thanks for the backtrace.
This issue occurs with recent gpgme-libs and is now fixed.