Scores are almost the same for RF-Score-VS on PDBbind

[RJ-Li]

Dear developer,
When I use your binary RF-Score-VS to dock multiple complexes in PDBbind2019, they just get almost the same score (near 6), which is unbelievable terrible!

pdb_id,prot_name,rf_score_vs_v2,ref_affinity
1a1e,1a1e_pocket,6.00580229596,6.00
1a4k,1a4k_pocket,6.00794721751,8.00
1a4r,1a4r_pocket,6.20134056292,6.66
1a4w,1a4w_pocket,6.38927082738,5.92
1a9m,1a9m_pocket,6.1346691244,6.92
1a9q,1a9q_pocket,5.97711068812,6.17
1a28,1a28_pocket,7.25402944261,8.29
1a69,1a69_pocket,6.15717254042,5.30
1a94,1a94_pocket,6.76315462617,7.85
1a99,1a99_pocket,5.98602117631,5.70
1aaq,1aaq_pocket,6.08011277506,8.40
1add,1add_pocket,6.31263890627,6.74
1adl,1adl_pocket,5.97653251803,5.36
1ado,1ado_pocket,5.62528809888,6.00
1afk,1afk_pocket,6.07168576653,6.62
1afl,1afl_pocket,6.14445310932,6.28
1ai4,1ai4_pocket,6.06714064078,2.50
1ai5,1ai5_pocket,6.01511559545,3.72
1ai7,1ai7_pocket,5.97128016745,4.09
1aid,1aid_pocket,6.00623191904,4.82
1aj7,1aj7_pocket,6.04805370093,3.87
1ajn,1ajn_pocket,6.01279242565,2.63
1ajp,1ajp_pocket,6.12961282626,2.23

The following is part of my code:

    for prot_ in os.listdir(datasets_pro_dir):
        prot_name = prot_[:-4]
        pdb_id = prot_[:4]
        pocket_file = os.path.join(datasets_pro_dir, prot_)
        ligand_file = os.path.join(datasets_lig_dir, f'{pdb_id}_ligand.mol2')
        
        if pocket_file and ligand_file:
            command = f'./rf-score-vs --receptor {pocket_file} {ligand_file} -o csv --field "name" --field "RFScoreVS_v2"'
            output = subprocess.check_output(command, shell=True).decode('utf-8')
            rf_score = output.split('\n')[1].split(',')[1]
            writer.writerow({'pdb_id': pdb_id, 'prot_name': prot_name,'rf_score_vs_v2': rf_score})

[RJ-Li]

I don't believe the RF-Score could be so awful, is there any potential bug about my code? Is this binary rf-score-vs unable to score any more?