Skip to content
← All cases

date_ambiguity

date_ambiguity-2026150002

Some dates are swapped to an ambiguous convention.

expects date_ambiguity

Statement files

3 highlighted lines differ from the same seed rendered without perturbations. That difference is the trap.

bnp_camt053.xmlUntouched by this perturbation
<?xml version='1.0' encoding='utf-8'?>
<Document xmlns="urn:iso:std:iso:20022:tech:xsd:camt.053.001.02">
<BkToCstmrStmt>
<GrpHdr>
<MsgId>LB-acct-2026150002-2-2025-11-30</MsgId>
<CreDtTm>2025-11-30T23:59:00+00:00</CreDtTm>
</GrpHdr>
<Stmt>
<Id>acct-2026150002-2</Id>
<ElctrncSeqNb>1</ElctrncSeqNb>
<CreDtTm>2025-11-30T23:59:00+00:00</CreDtTm>
<FrToDt>
<FrDtTm>2025-11-01T00:00:00+00:00</FrDtTm>
<ToDtTm>2025-11-30T23:59:59+00:00</ToDtTm>
</FrToDt>
<Acct>
<Id>
<IBAN>GB82LBEN53185143441500</IBAN>
</Id>
<Ccy>GBP</Ccy>
</Acct>
<Bal>
<Tp>
<CdOrPrtry>
<Cd>OPBD</Cd>
</CdOrPrtry>
</Tp>
<Amt Ccy="GBP">90707.26</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Dt>
<Dt>2025-11-01</Dt>
</Dt>
</Bal>
<Ntry>
<Amt Ccy="GBP">6000.21</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-02</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-02</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t008</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPO BRAMBLE LOGISTICS REF354759</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">1923.38</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-03</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-03</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t007</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>BP CASTLEGATE PROPERTY REF385430</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">8559.61</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-03</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-03</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t010</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>BP FENWICK &amp; PARTNERS REF165058</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">14816.29</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-04</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-04</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t001</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPO BRAMBLE LOGISTICS REF690424</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">9523.19</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-04</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-04</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t011</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPI FENWICK &amp; PARTNERS REF139705</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">2301.32</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-04</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-04</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t015</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>TFR GREENHOLM FOODS REF334566</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">9515.37</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-05</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-05</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t006</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>BP JUNIPER PAYROLL REF243476</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">1567.23</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-05</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-05</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t017</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>BP HARBOURLIGHT IT REF873046</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">8540.91</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-06</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-06</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t002</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>DD MOORLAND TELECOM REF305121</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">9489.15</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-08</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-08</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t005</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>FPI DELPHINIUM MEDIA REF882561</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">5966.46</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-09</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-09</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t004</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>SO EASTFIELD ENERGY REF259513</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">9366.22</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-11</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-11</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t014</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>SO EASTFIELD ENERGY REF941706</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">139.05</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-11</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-11</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t016</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>BP NORTHGATE CLEANING REF775380</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">13628.64</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-12</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-12</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t018</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>DD FENWICK &amp; PARTNERS REF897754</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">5900.32</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-14</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-14</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t020</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>BP EASTFIELD ENERGY REF728694</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">8791.64</Amt>
<CdtDbtInd>DBIT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-16</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-16</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t013</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>DD JUNIPER PAYROLL REF476495</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">3550.59</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-18</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-18</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t012</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>CR DELPHINIUM MEDIA REF783413</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">1472.16</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-22</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-22</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t003</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>CR AURORA CONSULTING LTD REF655696</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">13018.03</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-22</Dt>
</BookgDt>
<ValDt>
<Dt>2025-11-22</Dt>
</ValDt>
<AcctSvcrRef>acct-2026150002-2-t009</AcctSvcrRef>
<NtryDtls>
<TxDtls>
<RmtInf>
<Ustrd>CR FENWICK &amp; PARTNERS REF284404</Ustrd>
</RmtInf>
</TxDtls>
</NtryDtls>
</Ntry>
<Ntry>
<Amt Ccy="GBP">3000.14</Amt>
<CdtDbtInd>CRDT</CdtDbtInd>
<Sts>BOOK</Sts>
<BookgDt>
<Dt>2025-11-28</Dt>
hsbc_statement.xlsxUntouched by this perturbation
[sheet: Statement]
HSBC Bank plc
Business Current Account Statement
Account name: LEDGERBENCH DEMO LTD
Sort code / Account number: 44-70-49 83855324
Account reference: acct-2026150002-1
Statement period: 01 Nov 2025 to 30 Nov 2025
Currency: GBP
Opening balance: 30507.86
Date Payment type Details Paid out Paid in
02 Nov 2025 DD IRONBRIDGE TOOLING REF357047 7707.43
03 Nov 2025 DD MOORLAND TELECOM REF952483 5194.03
03 Nov 2025 FPI BRAMBLE LOGISTICS REF602208 12179.56
06 Nov 2025 SO LARKSPUR TRAVEL REF926719 8965.21
09 Nov 2025 FPO JUNIPER PAYROLL REF619938 11912.46
11 Nov 2025 SO EASTFIELD ENERGY REF817505 11874.06
11 Nov 2025 FPI DELPHINIUM MEDIA REF776364 1767.00
14 Nov 2025 DD HARBOURLIGHT IT REF790099 3398.33
15 Nov 2025 SO DELPHINIUM MEDIA REF136080 4060.27
15 Nov 2025 CR FENWICK & PARTNERS REF558188 5687.61
16 Nov 2025 TFR JUNIPER PAYROLL REF961697 14131.51
16 Nov 2025 TFR HARBOURLIGHT IT REF986804 1812.20
16 Nov 2025 BP GREENHOLM FOODS REF326799 4099.11
17 Nov 2025 SO GREENHOLM FOODS REF577581 5345.76
18 Nov 2025 TFR DELPHINIUM MEDIA REF309680 5943.57
20 Nov 2025 FPO KESTREL INSURANCE REF630637 7817.99
21 Nov 2025 DD JUNIPER PAYROLL REF869591 571.65
21 Nov 2025 BP OSPREY LEASING REF104337 9142.30
22 Nov 2025 BP IRONBRIDGE TOOLING REF532149 2546.81
22 Nov 2025 DD HARBOURLIGHT IT REF147176 9695.75
23 Nov 2025 FPI JUNIPER PAYROLL REF302698 3873.06
23 Nov 2025 TFR DELPHINIUM MEDIA REF352811 12861.93
23 Nov 2025 FPI NORTHGATE CLEANING REF621473 4508.44
24 Nov 2025 BP IRONBRIDGE TOOLING REF769854 8434.55
24 Nov 2025 DD MOORLAND TELECOM REF579768 6192.66
25 Nov 2025 BP OSPREY LEASING REF273046 5958.61
25 Nov 2025 SO KESTREL INSURANCE REF996919 4656.29
26 Nov 2025 CR AURORA CONSULTING LTD REF390734 7035.26
26 Nov 2025 TFR KESTREL INSURANCE REF601262 3011.27
26 Nov 2025 SO IRONBRIDGE TOOLING REF337708 14485.94
27 Nov 2025 DD BRAMBLE LOGISTICS REF814190 1893.93
rbs_transactions.csv3 changed lines · first at line 3
"Date","Type","Description","Value","Account Name","Account Number","Ledger Ref"
"01/11/2025","BAL","OPENING BALANCE","184001.75","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"11/01/2025","DD","DD GREENHOLM FOODS REF218220","-10542.49","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"01/11/2025","TFR","TFR BRAMBLE LOGISTICS REF173850","9560.28","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"11/08/2025","CR","CR CASTLEGATE PROPERTY REF118420","4561.74","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"11/08/2025","TFR","TFR KESTREL INSURANCE REF813021","29.95","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"12/11/2025","DD","DD BRAMBLE LOGISTICS REF322188","-3384.58","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"14/11/2025","DD","DD AURORA CONSULTING LTD REF965159","-13156.46","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"14/11/2025","TFR","TFR LARKSPUR TRAVEL REF490030","12269.50","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"14/11/2025","DD","DD BRAMBLE LOGISTICS REF728382","-14141.63","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"16/11/2025","FPI","FPI GREENHOLM FOODS REF826159","1660.43","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"18/11/2025","FPI","FPI AURORA CONSULTING LTD REF432137","5571.15","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"19/11/2025","SO","SO KESTREL INSURANCE REF184371","-6364.31","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"19/11/2025","BP","BP JUNIPER PAYROLL REF474570","-8977.20","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"20/11/2025","TFR","TFR DELPHINIUM MEDIA REF195034","14198.19","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"20/11/2025","SO","SO DELPHINIUM MEDIA REF105952","-7679.45","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"21/11/2025","SO","SO FENWICK & PARTNERS REF399054","-5376.95","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"23/11/2025","SO","SO KESTREL INSURANCE REF314652","-10580.99","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"26/11/2025","DD","DD BRAMBLE LOGISTICS REF497484","-5596.87","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"26/11/2025","DD","DD MOORLAND TELECOM REF966845","-5692.68","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"27/11/2025","BP","BP KESTREL INSURANCE REF644901","-782.66","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
"29/11/2025","CR","CR HARBOURLIGHT IT REF679664","2985.22","LEDGERBENCH DEMO LTD","14-23-44 19549799","acct-2026150002-3"
 

Ground truth

Public here because the benchmark is open; it is the model's prompt path that can never reach these values, not human readers.

AccountClosing balance
acct-2026150002-1−£30,633.87
acct-2026150002-2£38,346.51
acct-2026150002-3£142,561.94

Recorded runs on this case

  • exactSingle prompt2 steps · 9,769 tokens · Confidence medium

    Model claude-sonnet-4-6Measured 2026-08-20Bench v1.0Run 11eaa71b2d02Commit 3d38c30

  • exactAgent with tools20 steps · 39,808 tokens · Confidence high

    Model claude-sonnet-4-6Measured 2026-08-20Bench v1.0Run f140aa1e57f4Commit 384d72d

Step through any of these on the demo page.