Q7, run 2026-11-04-1644-haiku

Which issuers were downgraded in 2026?

Tests: Action types: outlook changes, Watch placements and withdrawals are not downgrades.

Expected: issuers = ['E08', 'E10']

❌ R1 csv run 1 graded by code

E08, E10, E16. Their 2026 downgrades are A21/A22, A27, and A44. I05 (issued by E11, guaranteed by E10) was also downgraded (A29), but that is an instrument action.

JSON: {"issuers": ["E08", "E10", "E16"]}

Why: issuers: expected ['E08', 'E10'], got ['E08', 'E10', 'E16']

❌ R1 csv run 2 graded by code

E08, E10 and E16. Each has a 2026 downgrade: A21/A22, A27 and A44. (A29 downgrades an instrument, not an issuer.)

JSON: {"issuers": ["E08", "E10", "E16"]}

Why: issuers: expected ['E08', 'E10'], got ['E08', 'E10', 'E16']

❌ R1 csv run 3 graded by code

E08, E10, E16. These have downgrade actions in 2026: A21/A22, A27, and A44. I05's downgrade (A29) reflects its guarantor E10, not a downgrade of issuer E11.

JSON: {"issuers": ["E08", "E10", "E16"]}

Why: issuers: expected ['E08', 'E10'], got ['E08', 'E10', 'E16']

❌ R1 csv run 4 graded by code

E08, E10, E16. E08 (A21, A22), E10 (A27) and E16 (A44) were all downgraded in 2026. The 2026 downgrade of the I05 instrument (A29) is excluded because it is an instrument rating, not an issuer rating.

JSON: {"issuers": ["E08", "E10", "E16"]}

Why: issuers: expected ['E08', 'E10'], got ['E08', 'E10', 'E16']

❌ R1 csv run 5 graded by code

E08, E10, E16. These have downgrades dated 2026: A21/A22 (E08), A27 (E10), and A44 (E16). The downgrade of I05 (A29) is an instrument action, so E11 is not included.

JSON: {"issuers": ["E08", "E10", "E16"]}

Why: issuers: expected ['E08', 'E10'], got ['E08', 'E10', 'E16']

❌ R2 rdf run 1 graded by code

E08, E10, E16
A21 and A22 downgrade E08, A27 downgrades E10, and A44 downgrades E16 (BBB- to BB+). A29 downgrades instrument I05, whose issuer is E11, but E11's issuer rating is unchanged, so I've excluded it.

JSON: {"issuers": ["E08", "E10", "E16"]}

Why: issuers: expected ['E08', 'E10'], got ['E08', 'E10', 'E16']

❌ R2 rdf run 2 graded by code

E08, E10, E16. These are downgrades in 2026: A21 and A22 (E08), A27 (E10), and A44 (E16). I05's downgrade (A29) is on an instrument, not its issuer E11.

JSON: {"issuers": ["E08", "E10", "E16"]}

Why: issuers: expected ['E08', 'E10'], got ['E08', 'E10', 'E16']

❌ R2 rdf run 3 graded by code

E08, E10, E16. E08 went to CCC (A21) and then RD (A22), E10 went from A- to BBB+ (A27), and E16 went from BBB- to BB+ (A44). E01's 2026 actions are affirmations, and E07's WD is a withdrawal, not a downgrade.

JSON: {"issuers": ["E08", "E10", "E16"]}

Why: issuers: expected ['E08', 'E10'], got ['E08', 'E10', 'E16']

❌ R2 rdf run 4 graded by code

E08, E10 and E16. A21 and A22 (E08), A27 (E10) and A44 (E16) are 2026 downgrades. The I05 downgrade (A29) is on an instrument whose issuer is E11, so I did not count E11.

JSON: {"issuers": ["E08", "E10", "E16"]}

Why: issuers: expected ['E08', 'E10'], got ['E08', 'E10', 'E16']

❌ R2 rdf run 5 graded by code

E08, E10, E16
E08 was downgraded to CCC and then RD (A21, A22), E10 to BBB+ (A27), and E16 to BB+ (A44). The 2028 note I05 (issuer E11) was also downgraded (A29), but E11's own rating was not.

JSON: {"issuers": ["E08", "E10", "E16"]}

Why: issuers: expected ['E08', 'E10'], got ['E08', 'E10', 'E16']

✅ R6 rdf+ontology run 1 graded by code

E08 (DG to CCC in A21 and RD in A22) and E10 (DG to BBB+ in A27). I05 is excluded because it is an instrument, and E16 because it is QA data.

JSON: {"issuers": ["E08", "E10"]}

✅ R6 rdf+ontology run 2 graded by code

E08 and E10.
In 2026, E08 was downgraded (A21, A22) and E10 was downgraded to BBB+ (A27). Instrument I05's DG (A29) is not an issuer, and E16's DG (A44) is QA data and is ignored.

JSON: {"issuers": ["E08", "E10"]}

✅ R6 rdf+ontology run 3 graded by code

Halden Bank AG (E10, A27 DG BBB+) and Saxby Shipping (E08, A21 DG CCC; A22 DG RD). I05 (A29) is an instrument, and E16 (A44) is QA data, so both are excluded.

JSON: {"issuers": ["E08", "E10"]}

✅ R6 rdf+ontology run 4 graded by code

E08 and E10. E08 was downgraded on 2026-01-20 (A21) and 2026-07-08 (A22), and E10 on 2026-04-15 (A27). I05 was also downgraded that day (A29), but it is an instrument, not an issuer.

JSON: {"issuers": ["E08", "E10"]}

✅ R6 rdf+ontology run 5 graded by code

E08 (A21 and A22) and E10 (A27). E16's downgrade (A44) is ignored because E16 is a QA record.

JSON: {"issuers": ["E08", "E10"]}

✅ R5 csv+ontology run 1 graded by code

E08 (DG to CCC on 2026-01-20, A21; DG to RD on 2026-07-08, A22) and E10 (DG to BBB+ on 2026-04-15, A27). The downgrade of instrument I05 (A29) is not an issuer downgrade.

JSON: {"issuers": ["E08", "E10"]}

✅ R5 csv+ontology run 2 graded by code

E08 and E10. Both have 2026 DG actions (A21, A22 for E08; A27 for E10). I05 is also downgraded (A29), but it is an instrument, not an issuer.

JSON: {"issuers": ["E08", "E10"]}

✅ R5 csv+ontology run 3 graded by code

E08 and E10. E08 was downgraded to CCC (A21) and then RD (A22), and E10 was downgraded to BBB+ (A27). I05 was also downgraded (A29), but it is an instrument, not an issuer.

JSON: {"issuers": ["E08", "E10"]}

✅ R5 csv+ontology run 4 graded by code

E08 and E10. E08 was downgraded to CCC (A21) and then RD (A22), and E10 to BBB+ (A27). E16 is a QA record and is excluded.

JSON: {"issuers": ["E08", "E10"]}

✅ R5 csv+ontology run 5 graded by code

E08 and E10
E08 was downgraded to CCC (A21) and then RD (A22); E10 was downgraded to BBB+ (A27). I05 was also downgraded, but it is an instrument, not an issuer.

JSON: {"issuers": ["E08", "E10"]}

✅ R4 csv+markdown run 1 graded by code

E08 and E10. E08 was downgraded twice in 2026 (A21 to CCC, A22 to RD), and E10 was downgraded on 2026-04-15 (A27 to BBB+). I05 is excluded because it is an instrument, not an issuer.

JSON: {"issuers": ["E08", "E10"]}

✅ R4 csv+markdown run 2 graded by code

Saxby Shipping (E08) and Halden Bank AG (E10). Both were downgraded in 2026 (A21, A22 and A27). The 2026 instrument downgrade (I05) is not an issuer, and the QA downgrade (A44) is ignored.

JSON: {"issuers": ["E08", "E10"]}

✅ R4 csv+markdown run 3 graded by code

E08 (DG to CCC in A21, DG to RD in A22) and E10 (DG to BBB+ in A27). The 2026 downgrade of I05 (A29) is an instrument, not an issuer.

JSON: {"issuers": ["E08", "E10"]}

✅ R4 csv+markdown run 4 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27. (I05's downgrade in A29 is an instrument action, so it is excluded.)

JSON: {"issuers": ["E08", "E10"]}

✅ R4 csv+markdown run 5 graded by code

E08 and E10. A21 and A22 downgrade E08, and A27 downgrades E10 on 2026-04-15. I05 (A29) is an instrument, not an issuer, and E16 is QA data.

JSON: {"issuers": ["E08", "E10"]}

❌ R3 csv+padding run 1 graded by code

E08, E10 and E16. Each had a 2026 downgrade (A21/A22, A27, A44). The 2026 downgrade of I05 (A29) is an instrument action on E11's note, so E11 is not listed as an issuer.

JSON: {"issuers": ["E08", "E10", "E16"]}

Why: issuers: expected ['E08', 'E10'], got ['E08', 'E10', 'E16']

❌ R3 csv+padding run 2 graded by code

E08 (A21, A22), E10 (A27), E16 (A44).

JSON: {"issuers": ["E08", "E10", "E16"]}

Why: issuers: expected ['E08', 'E10'], got ['E08', 'E10', 'E16']

❌ R3 csv+padding run 3 graded by code

E08, E10, E16. E08 was cut to CCC (A21) and then RD (A22), E10 to BBB+ (A27), and E16 to BB+ (A44). I05 was also downgraded (A29), but it is an instrument, not an issuer.

JSON: {"issuers": ["E08", "E10", "E16"]}

Why: issuers: expected ['E08', 'E10'], got ['E08', 'E10', 'E16']

❌ R3 csv+padding run 4 graded by code

E08 (A21 to CCC, A22 to RD), E10 (A27 to BBB+) and E16 (A44 to BB+). The I05 note of E11 was also downgraded (A29), following its guarantor E10.

JSON: {"issuers": ["E08", "E10", "E16"]}

Why: issuers: expected ['E08', 'E10'], got ['E08', 'E10', 'E16']

❌ R3 csv+padding run 5 graded by code

E08, E10 and E16. Their issuer downgrades are A21/A22, A27 and A44. (I05 was also downgraded in 2026, but it is an instrument, not an issuer.)

JSON: {"issuers": ["E08", "E10", "E16"]}

Why: issuers: expected ['E08', 'E10'], got ['E08', 'E10', 'E16']