%------------------------------------------------------------------------------
% File : iProver---3.9.4
% Problem : CAT004-3 : TPTP v9.3.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_iprover 300 /export/starexec/sandbox/benchmark/theBenchmark.p THM
% Computer : n009.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 : Fri Sep 25 01:01:07 PM UTC 2026
% Result : Unsatisfiable 3.77s 1.15s
% Output : CNFRefutation 3.77s
% Verified :
% SZS Type : Refutation
% Derivation depth : 7
% Number of leaves : 5
% Syntax : Number of formulae : 18 ( 8 unt; 0 def)
% Number of atoms : 30 ( 29 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 26 ( 14 ~; 12 |; 0 &)
% ( 0 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 4 avg)
% Maximal term depth : 3 ( 1 avg)
% Number of types : 1 ( 0 usr)
% Number of type conns : 0 ( 0 >; 0 *; 0 +; 0 <<)
% Number of predicates : 2 ( 0 usr; 1 prp; 0-2 aty)
% Number of functors : 5 ( 5 usr; 4 con; 0-2 aty)
% Number of variables : 26 ( 0 sgn 26 !; 0 ?; 13 :)
% Comments :
%------------------------------------------------------------------------------
fof(f9,axiom,
! [X2,X0,X1] : compose(X0,compose(X1,X2)) = compose(compose(X0,X1),X2),
file('/export/starexec/sandbox/benchmark/Axioms/CAT003-0.ax',associativity_of_compose) ).
fof(f21,axiom,
! [X2,X0,X1] :
( X0 = X2
| compose(X2,a) != X1
| compose(X0,a) != X1 ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',cancellation_for_product1) ).
fof(f22,axiom,
! [X2,X0,X1] :
( X0 = X2
| compose(X2,b) != X1
| compose(X0,b) != X1 ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',cancellation_for_product2) ).
fof(f24,axiom,
compose(h,compose(a,b)) = compose(g,compose(a,b)),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',h_ab_equals_g_ab) ).
fof(f25,negated_conjecture,
h != g,
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_h_equals_g) ).
fof(f26,plain,
! [X2,X0] :
( X0 = X2
| compose(X0,a) != compose(X2,a) ),
inference(equality_resolution,[],[f21]) ).
fof(f27,plain,
! [X2,X0] :
( X0 = X2
| compose(X0,b) != compose(X2,b) ),
inference(equality_resolution,[],[f22]) ).
tcf(c_72,plain,
! [X0: $i,X1: $i] :
( ( X0 = X1 )
| ( compose(X0,a) != compose(X1,a) ) ),
inference(cnf_transformation,[],[f26]) ).
tcf(c_73,plain,
! [X0: $i,X1: $i] :
( ( X0 = X1 )
| ( compose(X0,b) != compose(X1,b) ) ),
inference(cnf_transformation,[],[f27]) ).
tcf(c_74,plain,
compose(h,compose(a,b)) = compose(g,compose(a,b)),
inference(cnf_transformation,[],[f24]) ).
tcf(c_75,negated_conjecture,
h != g,
inference(cnf_transformation,[],[f25]) ).
tcf(c_76,plain,
! [X0: $i,X1: $i,X2: $i] : compose(compose(X0,X1),X2) = compose(X0,compose(X1,X2)),
inference(cnf_transformation,[],[f9]) ).
tcf(c_153,plain,
! [X0: $i,X1: $i,X2: $i] :
( ( compose(X0,X1) = X2 )
| ( compose(X0,compose(X1,b)) != compose(X2,b) ) ),
inference(superposition,[status(thm)],[c_76,c_73]) ).
tcf(c_182,plain,
! [X0: $i] :
( ( compose(g,a) = X0 )
| ( compose(h,compose(a,b)) != compose(X0,b) ) ),
inference(superposition,[status(thm)],[c_74,c_153]) ).
tcf(c_198,plain,
( ( h = g )
| ( compose(h,a) != compose(g,a) ) ),
inference(instantiation,[status(thm)],[c_72]) ).
tcf(c_203,plain,
! [X0: $i,X1: $i] :
( ( compose(X0,X1) = compose(g,a) )
| ( compose(X0,compose(X1,b)) != compose(h,compose(a,b)) ) ),
inference(superposition,[status(thm)],[c_76,c_182]) ).
tcf(c_320,plain,
compose(h,a) = compose(g,a),
inference(equality_resolution,[status(thm)],[c_203]) ).
tcf(c_331,plain,
$false,
inference(prop_impl_just,[status(thm)],[c_320,c_198,c_75]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : CAT004-3 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.04 % Command : run_iprover 300 /export/starexec/sandbox/benchmark/theBenchmark.p THM
% 0.09/0.34 % Computer : n009.cluster.edu
% 0.09/0.34 % Model : x86_64 x86_64
% 0.09/0.34 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/0.34 % Memory : 8046.5625MB
% 0.09/0.34 % OS : Linux 6.8.0-71-generic
% 0.09/0.34 % CPULimit : 300
% 0.09/0.34 % WCLimit : 300
% 0.09/0.34 % DateTime : Fri Sep 25 06:51:58 UTC 2026
% 0.09/0.35 % CPUTime :
% 0.09/0.35 Running run_iprover 300 /export/starexec/sandbox/benchmark/theBenchmark.p THM
% 0.13/0.38 Running first-order theorem proving
% 0.13/0.38 Running: /export/starexec/sandbox/solver/bin/iproveropt-multi-core.sh -d -n -l tptp -s fof_schedule -t 300 /export/starexec/sandbox/benchmark/theBenchmark.p
% 0.13/0.39
% 0.13/0.39 % ======== iProver multi-core TPTP/SMT =========
% 0.13/0.39
% 0.13/0.40 % Detected problem language: tptp
% 0.13/0.40 % Proving...
% 3.77/1.15 % SZS status Started for theBenchmark.p
% 3.77/1.15 % SZS status Unsatisfiable for theBenchmark.p
% 3.77/1.15
% 3.77/1.15 %---------------- iProver v3.9.4 (pre CASC 2026/SMT-COMP 2026) ----------------%
% 3.77/1.15
% 3.77/1.15 % ------ iProver source info
% 3.77/1.15
% 3.77/1.15 % git: date: 2026-07-19 20:42:38 +0200
% 3.77/1.15 % git: sha1: 804e7d636a263075307957e923b7a22a4035de61
% 3.77/1.15 % git: non_committed_changes: false
% 3.77/1.15
% 3.77/1.15 % ------ Parsing...% successful
% 3.77/1.15
% 3.77/1.15
% 3.77/1.15 % ------ Clausification by vclausify_rel & Parsing by iProver...%
% 3.77/1.15
% 3.77/1.15 % ------ Preprocessing... sup_sim: 0 sf_s rm: 0 0s sf_e pe_s pe_e %
% 3.77/1.15
% 3.77/1.15 % ------ Preprocessing... gs_s sp: 0 0s gs_e snvd_s sp: 0 0s snvd_e %
% 3.77/1.15
% 3.77/1.15 % ------ Preprocessing... sf_s rm: 0 0s sf_e
% 3.77/1.15 % ------ Proving...
% 3.77/1.15 % ------ Problem Properties
% 3.77/1.15
% 3.77/1.15 %
% 3.77/1.15 % clauses 5
% 3.77/1.15 % conjectures 1
% 3.77/1.15 % EPR 1
% 3.77/1.15 % Horn 5
% 3.77/1.15 % unary 3
% 3.77/1.15 % binary 2
% 3.77/1.15 % lits 7
% 3.77/1.15 % lits eq 7
% 3.77/1.15 % fd_pure 0
% 3.77/1.15 % fd_pseudo 0
% 3.77/1.15 % fd_cond 0
% 3.77/1.15 % fd_pseudo_cond 2
% 3.77/1.15 % AC symbols 0
% 3.77/1.15
% 3.77/1.15 % ------ Schedule dynamic 5 is on
% 3.77/1.15
% 3.77/1.15 % ------ Input Options "--resolution_flag false --inst_lit_sel_side none" Time Limit: 10.
% 3.77/1.15
% 3.77/1.15
% 3.77/1.15 % ------
% 3.77/1.15 % Current options:
% 3.77/1.15 % ------
% 3.77/1.15
% 3.77/1.15
% 3.77/1.15 %
% 3.77/1.15
% 3.77/1.15 % ------ Proving...
% 3.77/1.15 %
% 3.77/1.15
% 3.77/1.15 % SZS status Unsatisfiable for theBenchmark.p
% 3.77/1.15
% 3.77/1.15 % SZS output start CNFRefutation for theBenchmark.p
% See solution above
% 3.77/1.15
% 3.77/1.15
%------------------------------------------------------------------------------