Q7, run 2026-11-05-1227-sonnet

← back to the run

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 and E16. E08 had A21 and A22, E10 had A27, and E16 had A44; A29 is an instrument downgrade and A17 is only a watch.

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. The 2026 downgrades are A21 and A22 (E08), A27 (E10) and A44 (E16). A17 is a watch action, not a downgrade. I05 (A29) was also downgraded, but it is 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 and E16. They were downgraded in A21/A22, A27 and A44. E06 only went on watch (A17), and E14's downgrade was in 2024 (A36).

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

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

❌ R1 csv run 4 graded by code

E08, E10 and E16. They were downgraded in A21/A22, A27 and A44. A29 downgrades an instrument (I05), not an issuer.

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

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

❌ R1 csv run 5 graded by code

E08, E10 and E16. They were downgraded in 2026 by A21 and A22 (E08), A27 (E10) and A44 (E16). A17 for E06 is a watch, not a downgrade.

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

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

❌ R2 rdf run 1 graded by code

E08 (A21, A22), E10 (A27) and E16 (A44). I05's downgrade (A29) is an instrument rating whose issuer is E11, so I left E11 out.

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

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

❌ R2 rdf run 2 graded by code

E08, E10 and E16. They were downgraded in A21/A22, A27 and A44. A29 is a downgrade of the instrument I05, not of an issuer.

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

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

❌ R2 rdf run 3 graded by code

E08, E10 and E16. Their 2026 downgrades are A21 and A22, A27, and A44. I05 (A29) is an instrument downgrade, not an issuer one.

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. They were downgraded in A21/A22, A27 and A44. I05 was also downgraded, but it is an instrument, not an issuer.

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

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

❌ R2 rdf run 5 graded by code

E08, E10 and E16. Their 2026 downgrades are A21 and A22 (E08), A27 (E10) and A44 (E16). I05's downgrade (A29) is an instrument rating, so I did not count it.

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

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

✅ R6 rdf+ontology run 1 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27. A29 is an instrument downgrade, and A44 belongs to QA record E16, which is ignored.

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

✅ R6 rdf+ontology run 2 graded by code

E08 and E10. E08 was downgraded on 2026-01-20 and 2026-07-08 (A21, A22), and E10 on 2026-04-15 (A27). E16's downgrade (A44) is QA test data and is ignored, and E06's Watch (A17) is not a downgrade.

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

✅ R6 rdf+ontology run 3 graded by code

E08 and E10. E08 was downgraded by A21 and A22, and E10 (same LEI as E17) by A27. A44 is a QA record and is ignored, and the instrument downgrades (e.g. A29) are not issuer downgrades.

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

✅ R6 rdf+ontology run 4 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27. A29 is an instrument rating, and E16's downgrade (A44) is QA test data and is ignored.

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

✅ R6 rdf+ontology run 5 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27. E16's downgrade (A44) is QA test data and is ignored, and A29 is an instrument rating.

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

✅ R5 csv+ontology run 1 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27. The other 2026 downgrades are not issuer downgrades: A29 is an instrument and A44 is a QA record.

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

✅ R5 csv+ontology run 2 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27. A29 is an instrument rating, and A44 is on QA record E16, which is ignored.

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

✅ R5 csv+ontology run 3 graded by code

E08 and E10. E08 had downgrades A21 and A22, and E10 had A27. E16's A44 is QA test data and is ignored.

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

✅ R5 csv+ontology run 4 graded by code

E08 and E10. E08 was downgraded by A21 and A22, and E10 by A27. A29 is an instrument rating and A44 is a QA record, so both are excluded.

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

✅ R5 csv+ontology run 5 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27. A44 is on E16, a QA record, so it is ignored. A29 is a downgrade of an instrument (I05), not of an issuer.

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

✅ R4 csv+markdown run 1 graded by code

E08 (A21, A22) and E10 (A27). The I05 downgrade (A29) is an instrument action, and E16 is QA data and ignored.

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

✅ R4 csv+markdown run 2 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27. A29 is an instrument action, and A44 is on QA record E16, which is ignored.

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

✅ R4 csv+markdown run 3 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27. A44 is a QA record and is ignored, and A29 is an instrument rating, not an issuer rating.

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

✅ R4 csv+markdown run 4 graded by code

E08 and E10. E08 was downgraded by A21 and A22, and E10 by A27. A29 downgrades an instrument, and A44 is a QA record, so both are excluded.

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

✅ R4 csv+markdown run 5 graded by code

E08 (A21 and A22) and E10 (A27). The E16 downgrade (A44) is QA test data and is ignored.

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

❌ R3 csv+padding run 1 graded by code

E08, E10 and E16. They were downgraded by A21/A22, A27 and A44. The E06 action (A17) is a watch, not a downgrade.

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

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

❌ R3 csv+padding run 2 graded by code

E08, E10 and E16 had issuer downgrades in 2026 (A21, A22, A27, A44). I05's downgrade (A29) is on an instrument, not an issuer rating.

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

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

❌ R3 csv+padding run 3 graded by code

E08, E10 and E16 were downgraded in 2026 (A21/A22, A27, A44). E06's A17 is a watch placement, not a downgrade.

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

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

❌ R3 csv+padding run 4 graded by code

E08, E10 and E16 were downgraded in 2026 (A21 and A22, A27, A44). E06's action was a Watch (A17), not a downgrade.

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 were downgraded in 2026 (A21, A22, A27, A44). I05's downgrade (A29) is an instrument action, and E17 is a duplicate of E10.

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

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

✅ R10 executed run 1 graded by code

E08 and E10. E08 went to CCC (A21) and then RD (A22), and E10 went to BBB+ (A27). E11's note I05 was also downgraded (A29), but E11 itself has no issuer rating.

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

✅ R10 executed run 2 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).

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

✅ R10 executed run 3 graded by code

Saxby Shipping (E08) and Halden Bank (E10). E08 was downgraded on 2026-01-20 and 2026-07-08 (A21, A22), and E10 on 2026-04-15 (A27).

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

✅ R10 executed run 4 graded by code

E08 and E10. E08 was downgraded to CCC (A21) and RD (A22), and E10 to BBB+ (A27).

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

✅ R10 executed run 5 graded by code

E08 and E10. E08 was downgraded to CCC (A21) and then RD (A22), and E10 to BBB+ (A27). E11 was not included because it has no issuer rating of its own.

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

✅ R7 csv+neutral run 1 graded by code

E08 and E10. E08 was downgraded by A21 and A22, and E10 by A27 (E17 is the same entity as E10). A29 downgraded instrument I05, not an issuer, and A44 is on QA record E16, which is ignored.

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

✅ R7 csv+neutral run 2 graded by code

E08 (A21, A22) and E10 (A27, same entity as E17) were downgraded in 2026. The instrument downgrade A29 is not an issuer downgrade, and A44 is on a QA record, so it is ignored.

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

✅ R7 csv+neutral run 3 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27. E16's downgrade (A44) is QA data and ignored, and A29 is an instrument rating.

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

✅ R7 csv+neutral run 4 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27. I05's downgrade (A29) is an instrument rating, and E16 (A44) is QA data and ignored.

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

✅ R7 csv+neutral run 5 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27. E16's downgrade (A44) is QA test data, and A29 is an instrument rating.

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

✅ R8 csv+axioms run 1 graded by code

E08 and E10. E08 was downgraded by A21 and A22, and E10 by A27. E16's downgrade (A44) is on a QA test record, so I excluded it.

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

✅ R8 csv+axioms run 2 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27. E16's downgrade (A44) is excluded because it is a QA test record, and A29 is an instrument rating.

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

✅ R8 csv+axioms run 3 graded by code

E08 and E10. E08 was downgraded by A21 and A22, and E10 by A27. A29 is an instrument and E16 is a QA test record, so neither counts.

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

✅ R8 csv+axioms run 4 graded by code

E08 (A21, A22) and E10 (A27). E16's downgrade (A44) is a QA test record and doesn't count. The instrument downgrade A29 is not an issuer action.

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

✅ R8 csv+axioms run 5 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27. E16's downgrade (A44) is excluded because it is a QA test record, and I05's downgrade is an instrument rating, not an issuer's.

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

✅ R9 csv+axioms+markdown run 1 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27. E16's downgrade (A44) is QA data and is ignored, and A29 is an instrument rating.

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

✅ R9 csv+axioms+markdown run 2 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27. The other 2026 downgrades are on an instrument (A29) and on a QA record (A44), so they don't count.

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

✅ R9 csv+axioms+markdown run 3 graded by code

E08 (A21, A22) and E10 (A27). A29 is an instrument downgrade, and A44 is a QA record, so it is ignored.

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

✅ R9 csv+axioms+markdown run 4 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27. The other 2026 downgrades are on an instrument (A29) and a QA record (A44), so they don't count.

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

✅ R9 csv+axioms+markdown run 5 graded by code

E08 and E10. E08 was downgraded in A21 and A22, and E10 in A27 (E17 is the same entity as E10). A29 is an instrument action, and A44 is on a QA record, which is ignored.

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