%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : PUZ082_8 : TPTP v9.3.1. Released v8.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% Computer : n005.cluster.edu
% Model : x86_64 x86_64
% CPU : Intel(R) Xeon(R) CPU E5-2620 v4 2.10GHz
% Memory : 8046.5625MB
% OS : Linux 6.8.0-71-generic
% CPULimit : 300s
% WCLimit : 300s
% DateTime : Tue Sep 29 12:31:32 PM UTC 2026
% Result : Theorem 3.57s 1.43s
% Output : Refutation 3.57s
% Verified :
% SZS Type : Refutation
% Derivation depth : 15
% Number of leaves : 8
% Syntax : Number of formulae : 52 ( 17 unt; 0 typ; 6 def)
% Number of atoms : 246 ( 47 equ)
% Maximal formula atoms : 6 ( 4 avg)
% Number of connectives : 119 ( 57 ~; 37 |; 8 &)
% ( 8 <=>; 9 =>; 0 <=; 0 <~>)
% Maximal formula depth : 6 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of FOOLs : 187 ( 137 fml; 50 var)
% Number of types : 2 ( 0 usr)
% Number of type conns : 0 ( 0 >; 0 *; 0 +; 0 <<)
% Number of predicates : 12 ( 9 usr; 8 prp; 0-2 aty)
% Number of functors : 0 ( 0 usr; 0 con; --- aty)
% Number of variables : 23 ( 0 sgn 21 !; 2 ?; 23 :)
% Comments :
%------------------------------------------------------------------------------
tff(func_def_3,type,
bG0: $o > $o ).
tff(func_def_4,type,
bG1: $o ).
tff(func_def_5,type,
bG2: $o > $o ).
tff(func_def_6,type,
sK3: $o ).
tff(pred_def_1,type,
says: ( $i * $o ) > $o ).
tff(f1,axiom,
says(peter,
! [X0: $o] :
( says(peter,(X0))
=> ~ (X0) )),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',ax1) ).
tff(f2,conjecture,
~ ! [X0: $o] :
( says(peter,(X0))
=> ~ (X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',thm) ).
tff(f3,negated_conjecture,
~ ~ ! [X0: $o] :
( says(peter,(X0))
=> ~ (X0) ),
inference(negated_conjecture,[status(cth)],[f2]) ).
tff(f4,plain,
says(peter,
! [X0: $o] :
( says(peter,(X0))
=> ~ (X0) )),
inference(rectify,[],[f1]) ).
tff(f5,definition,
! [X0: $o] :
( ( $true = (X0) )
<=> ( $true = bG0((X0)) ) ),
introduced(definition,[new_symbols(definition,[bG0])],[fool_formula_definition]) ).
tff(f6,definition,
( ! [X0: $o] :
( says(peter,bG0((X0)))
=> ( $true != (X0) ) )
<=> ( $true = bG1 ) ),
introduced(definition,[new_symbols(definition,[bG1])],[fool_formula_definition]) ).
tff(f7,plain,
says(peter,bG1),
inference(fool_elimination,[],[f4,f6,f5]) ).
tff(f8,plain,
~ ~ ! [X0: $o] :
( says(peter,(X0))
=> ~ (X0) ),
inference(rectify,[],[f3]) ).
tff(f9,definition,
! [X0: $o] :
( ( $true = (X0) )
<=> ( $true = bG2((X0)) ) ),
introduced(definition,[new_symbols(definition,[bG2])],[fool_formula_definition]) ).
tff(f10,plain,
~ ~ ! [X0: $o] :
( says(peter,bG2((X0)))
=> ( $true != (X0) ) ),
inference(fool_elimination,[],[f8,f9]) ).
tff(f11,plain,
( ! [X0: $o] :
( says(peter,bG0((X0)))
=> ( $true != (X0) ) )
<=> ( $true = bG1 ) ),
inference(flattening,[],[f6]) ).
tff(f12,plain,
! [X0: $o] :
( says(peter,bG2((X0)))
=> ( $true != (X0) ) ),
inference(flattening,[],[f10]) ).
tff(f13,plain,
( ! [X0: $o] :
( ( $true != (X0) )
| ~ says(peter,bG0((X0))) )
<=> ( $true = bG1 ) ),
inference(ennf_transformation,[],[f11]) ).
tff(f14,plain,
! [X0: $o] :
( ( $true != (X0) )
| ~ says(peter,bG2((X0))) ),
inference(ennf_transformation,[],[f12]) ).
tff(f15,plain,
! [X0: $o] :
( ( ( $true = (X0) )
| ( $true != bG2((X0)) ) )
& ( ( $true = bG2((X0)) )
| ( $true != (X0) ) ) ),
inference(nnf_transformation,[],[f9]) ).
tff(f16,plain,
( ( ! [X0: $o] :
( ( $true != (X0) )
| ~ says(peter,bG0((X0))) )
| ( $true != bG1 ) )
& ( ( $true = bG1 )
| ? [X0: $o] :
( ( $true = (X0) )
& says(peter,bG0((X0))) ) ) ),
inference(nnf_transformation,[],[f13]) ).
tff(f17,plain,
( ( ! [X0: $o] :
( ( $true != (X0) )
| ~ says(peter,bG0((X0))) )
| ( $true != bG1 ) )
& ( ( $true = bG1 )
| ? [X1: $o] :
( ( $true = (X1) )
& says(peter,bG0((X1))) ) ) ),
inference(rectify,[],[f16]) ).
tff(f18,plain,
( ( ! [X0: $o] :
( ( $true != (X0) )
| ~ says(peter,bG0((X0))) )
| ( $true != bG1 ) )
& ( ( $true = bG1 )
| ( ( $true = sK3 )
& says(peter,bG0(sK3)) ) ) ),
inference(skolemize,[status(esa),new_symbols(skolem,[sK3]),skolemize(X1,sK3)],[f17]) ).
tff(f19,plain,
! [X0: $o] :
( ( ( $true = (X0) )
| ( $true != bG0((X0)) ) )
& ( ( $true = bG0((X0)) )
| ( $true != (X0) ) ) ),
inference(nnf_transformation,[],[f5]) ).
tff(f20,plain,
! [X0: $o] :
( ( $true = bG2((X0)) )
| ( $true != (X0) ) ),
inference(cnf_transformation,[],[f15]) ).
tff(f22,plain,
( ( $true = bG1 )
| says(peter,bG0(sK3)) ),
inference(cnf_transformation,[],[f18]) ).
tff(f23,plain,
( ( $true = bG1 )
| ( $true = sK3 ) ),
inference(cnf_transformation,[],[f18]) ).
tff(f25,plain,
! [X0: $o] :
( ( $true = bG0((X0)) )
| ( $true != (X0) ) ),
inference(cnf_transformation,[],[f19]) ).
tff(f27,plain,
says(peter,bG1),
inference(cnf_transformation,[],[f7]) ).
tff(f28,plain,
! [X0: $o] :
( ( $true != (X0) )
| ~ says(peter,bG2((X0))) ),
inference(cnf_transformation,[],[f14]) ).
tff(f31,plain,
$true = bG2($true),
inference(equality_resolution,[],[f20]) ).
tff(f33,plain,
$true = bG0($true),
inference(equality_resolution,[],[f25]) ).
tff(f34,plain,
~ says(peter,bG2($true)),
inference(equality_resolution,[],[f28]) ).
tff(f36,definition,
( spl4_1
<=> says(peter,bG0(sK3)) ),
introduced(definition,[new_symbols(definition,[spl4_1])],[avatar_definition]) ).
tff(f38,plain,
( says(peter,bG0(sK3))
| ~ spl4_1 ),
inference(avatar_component_clause,[],[f36]) ).
tff(f40,definition,
( spl4_2
<=> ( $true = bG1 ) ),
introduced(definition,[new_symbols(definition,[spl4_2])],[avatar_definition]) ).
tff(f42,plain,
( ( $true = bG1 )
| ~ spl4_2 ),
inference(avatar_component_clause,[],[f40]) ).
tff(f43,plain,
( spl4_1
| spl4_2 ),
inference(avatar_split_clause,[],[f22,f40,f36]) ).
tff(f45,definition,
( spl4_3
<=> ( $true = sK3 ) ),
introduced(definition,[new_symbols(definition,[spl4_3])],[avatar_definition]) ).
tff(f47,plain,
( ( $true = sK3 )
| ~ spl4_3 ),
inference(avatar_component_clause,[],[f45]) ).
tff(f48,plain,
( spl4_3
| spl4_2 ),
inference(avatar_split_clause,[],[f23,f40,f45]) ).
tff(f54,plain,
( says(peter,$true)
| ~ spl4_2 ),
inference(superposition,[],[f27,f42]) ).
tff(f55,plain,
~ says(peter,$true),
inference(superposition,[],[f34,f31]) ).
tff(f56,plain,
( $false
| ~ spl4_2 ),
inference(forward_subsumption_resolution,[],[f54,f55]) ).
tff(f57,plain,
~ spl4_2,
inference(avatar_contradiction_clause,[],[f56]) ).
tff(f58,plain,
( says(peter,bG0($true))
| ~ spl4_1
| ~ spl4_3 ),
inference(forward_demodulation,[],[f38,f47]) ).
tff(f59,plain,
( says(peter,$true)
| ~ spl4_1
| ~ spl4_3 ),
inference(forward_demodulation,[],[f58,f33]) ).
tff(f60,plain,
( $false
| ~ spl4_1
| ~ spl4_3 ),
inference(forward_subsumption_resolution,[],[f59,f55]) ).
tff(f61,plain,
( ~ spl4_1
| ~ spl4_3 ),
inference(avatar_contradiction_clause,[],[f60]) ).
cnf(s1,plain,
( spl4_1
| spl4_2 ),
inference(sat_conversion,[],[f43]) ).
cnf(s2,plain,
( spl4_2
| spl4_3 ),
inference(sat_conversion,[],[f48]) ).
cnf(s4,plain,
~ spl4_2,
inference(sat_conversion,[],[f57]) ).
cnf(s5,plain,
( ~ spl4_1
| ~ spl4_3 ),
inference(sat_conversion,[],[f61]) ).
cnf(s6,plain,
spl4_3,
inference(rat,[],[s2,s4]) ).
cnf(s7,plain,
~ spl4_1,
inference(rat,[],[s5,s6]) ).
cnf(s8,plain,
$false,
inference(rat,[],[s1,s4,s7]) ).
tff(f62,plain,
$false,
inference(avatar_sat_refutation,[],[s8]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ082_8 : TPTP v9.3.1. Released v8.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.11/0.37 % Computer : n005.cluster.edu
% 0.11/0.37 % Model : x86_64 x86_64
% 0.11/0.37 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.11/0.37 % Memory : 8046.5625MB
% 0.11/0.37 % OS : Linux 6.8.0-71-generic
% 0.11/0.37 % CPULimit : 300
% 0.11/0.37 % WCLimit : 300
% 0.11/0.37 % DateTime : Sun Sep 27 22:40:17 UTC 2026
% 0.11/0.37 % CPUTime :
% 0.11/0.37 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.11/0.41 Running first-order theorem proving
% 0.11/0.41 Running: /export/starexec/sandbox2/solver/bin/vampire --input_syntax tptp --output_axiom_names on --mode casc -m 16384 --cores 7 -t 300 /export/starexec/sandbox2/benchmark/theBenchmark.p
% 3.57/1.43 % (244003)Detected formulas, will run a generic FOF schedule.
% 3.57/1.43 % (244008)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=full:npcc=on:drc=off:sp=weighted_frequency:spb=goal:fd=preordered:foolp=on:random_seed=2569113479:i=141193_2999 on theBenchmark for (2999ds/141193Mi)
% 3.57/1.43 % (244012)dis-1010_2:3_sil=16000:sp=reverse_frequency:random_seed=1888189283:i=119:av=off:ss=axioms_2999 on theBenchmark for (2999ds/119Mi)
% 3.57/1.43 % (244011)lrs+1010_1_to=lpo:sil=32000:sos=on:spb=goal_then_units:bce=on:random_seed=4234095033:i=109:sd=1:ins=1:gsp=on:ss=axioms_2999 on theBenchmark for (2999ds/109Mi)
% 3.57/1.43 % (244009)lrs+11_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:lma=off:spb=units:urr=ec_only:bce=on:s2agt=64:updr=off:random_seed=173067329:i=134677:sd=20:aac=none:nm=16:ss=included:sgt=10_2999 on theBenchmark for (2999ds/134677Mi)
% 3.57/1.43 % (244010)lrs+1010_1_anc=all:sfv=off:to=kbo:ncem=casc2026/models/loop7.pt:sil=128000:npcc=on:prc=on:sos=all:bsr=unit_only:sac=on:random_seed=3051291068:i=141695:sd=1:nm=32:gsp=on:ss=included_2999 on theBenchmark for (2999ds/141695Mi)
% 3.57/1.43 % (244011)Refutation not found, incomplete strategy
% 3.57/1.43 % (244011)------------------------------
% 3.57/1.43 % (244011)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.57/1.43 % (244011)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.57/1.43 % (244011)CaDiCaL version: 2.1.3
% 3.57/1.43 % (244011)Termination reason: Refutation not found, incomplete strategy
% 3.57/1.43 % (244011)Time elapsed: 0.001 s
% 3.57/1.43 % (244011)Peak memory usage: 88 MB
% 3.57/1.43 % (244014)dis-21_1_sil=8000:lcm=predicate:random_seed=147303717:st=5:avsq=on:i=129:avsqr=1,16:sd=3:aac=none:ep=RS:fsr=off:ss=included_2999 on theBenchmark for (2999ds/129Mi)
% 3.57/1.43 % (244013)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=1691088510:s2a=on:i=139:gtg=position_2999 on theBenchmark for (2999ds/139Mi)
% 3.57/1.43 % (244014)Refutation not found, incomplete strategy
% 3.57/1.43 % (244014)------------------------------
% 3.57/1.43 % (244014)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.57/1.43 % (244014)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.57/1.43 % (244014)CaDiCaL version: 2.1.3
% 3.57/1.43 % (244014)Termination reason: Refutation not found, incomplete strategy
% 3.57/1.43 % (244014)Time elapsed: 0.002 s
% 3.57/1.43 % (244014)Peak memory usage: 88 MB
% 3.57/1.43 % (244014)Instructions burned: 1 (million)
% 3.57/1.43 % (244013)First to succeed.
% 3.57/1.43 % (244013)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-244003"
% 3.57/1.43 % (244012)Instruction limit reached!
% 3.57/1.43 % (244012)------------------------------
% 3.57/1.43 % (244012)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.57/1.43 % (244012)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.57/1.43 % (244012)CaDiCaL version: 2.1.3
% 3.57/1.43 % (244012)Termination reason: Instruction limit
% 3.57/1.43 % (244012)Termination phase: Saturation
% 3.57/1.43 % (244012)Time elapsed: 0.054 s
% 3.57/1.43 % (244012)Peak memory usage: 88 MB
% 3.57/1.43 % (244012)Instructions burned: 120 (million)
% 3.57/1.43 % (244022)lrs+10_1_sil=8000:sp=occurrence:random_seed=1732417884:i=285:sd=3:ss=axioms:sgt=8_2998 on theBenchmark for (2998ds/285Mi)
% 3.57/1.43 % (244022)Also succeeded, but the first one will report.
% 3.57/1.43 % (244011)------------------------------
% 3.57/1.43 % (244011)------------------------------
% 3.57/1.43 % (244014)------------------------------
% 3.57/1.43 % (244014)------------------------------
% 3.57/1.43 % (244013)Refutation found. Thanks to Tanya!
% 3.57/1.43 % SZS status Theorem for theBenchmark
% 3.57/1.43 % SZS output start Proof for theBenchmark
% See solution above
% 3.57/1.43 % (244013)------------------------------
% 3.57/1.43 % (244013)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.57/1.43 % (244013)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.57/1.43 % (244013)CaDiCaL version: 2.1.3
% 3.57/1.43 % (244013)Termination reason: Refutation
% 3.57/1.43 % (244013)Time elapsed: 0.003 s
% 3.57/1.43 % (244013)Peak memory usage: 90 MB
% 3.57/1.43 % (244013)Instructions burned: 2 (million)
% 3.57/1.43 % (244013)------------------------------
% 3.57/1.43 % (244013)------------------------------
% 3.57/1.43 % (244003)Success in time 0.412 s
% 3.57/1.43 % Vampire exiting
%------------------------------------------------------------------------------