17Appendix: every item
Every scored item with each question's gold label, ember's answer, and its signal (confidence for choice, P(true) for noul, expected value for score). The raw run data ships next to this report in data/.
| Item | Recipe | Split | Result | Questions: gold -> ember (signal) |
|---|---|---|---|---|
intent_001 | Intent and readiness | dev | incorrect | intent: question -> question (ok, 0.90) specific_enough: True -> False (miss, 0.21) |
intent_002 | Intent and readiness | test | correct | intent: question -> question (ok, 0.96) specific_enough: True -> True (ok, 0.75) |
intent_003 | Intent and readiness | dev | incorrect | intent: question -> question (ok, 0.95) specific_enough: True -> False (miss, 0.45) |
intent_004 | Intent and readiness | test | incorrect | intent: question -> question (ok, 0.95) specific_enough: True -> False (miss, 0.48) |
intent_005 | Intent and readiness | dev | incorrect | intent: question -> question (ok, 0.95) specific_enough: True -> False (miss, 0.29) |
intent_006 | Intent and readiness | test | correct | intent: question -> question (ok, 0.84) specific_enough: False -> False (ok, 0.08) |
intent_007 | Intent and readiness | dev | correct | intent: question -> question (ok, 0.97) specific_enough: False -> False (ok, 0.20) |
intent_008 | Intent and readiness | dev | correct | intent: implement -> implement (ok, 0.96) specific_enough: False -> False (ok, 0.09) |
intent_009 | Intent and readiness | dev | correct | intent: implement -> implement (ok, 0.92) specific_enough: True -> True (ok, 0.91) |
intent_010 | Intent and readiness | test | correct | intent: implement -> implement (ok, 0.92) specific_enough: True -> True (ok, 0.84) |
intent_011 | Intent and readiness | dev | correct | intent: implement -> implement (ok, 0.95) specific_enough: True -> True (ok, 0.81) |
intent_012 | Intent and readiness | test | correct | intent: implement -> implement (ok, 0.97) specific_enough: True -> True (ok, 0.72) |
intent_013 | Intent and readiness | dev | incorrect | intent: implement -> fix (miss, 0.48) specific_enough: False -> False (ok, 0.06) |
intent_014 | Intent and readiness | test | correct | intent: implement -> implement (ok, 0.93) specific_enough: False -> False (ok, 0.18) |
intent_015 | Intent and readiness | dev | correct | intent: investigate -> investigate (ok, 0.94) specific_enough: True -> True (ok, 0.57) |
intent_016 | Intent and readiness | test | correct | intent: investigate -> investigate (ok, 0.98) specific_enough: True -> True (ok, 0.69) |
intent_017 | Intent and readiness | dev | correct | intent: investigate -> investigate (ok, 0.99) specific_enough: True -> True (ok, 0.78) |
intent_018 | Intent and readiness | test | correct | intent: investigate -> investigate (ok, 0.97) specific_enough: True -> True (ok, 0.65) |
intent_019 | Intent and readiness | dev | correct | intent: investigate -> investigate (ok, 0.97) specific_enough: True -> True (ok, 0.77) |
intent_020 | Intent and readiness | test | correct | intent: investigate -> investigate (ok, 0.97) specific_enough: False -> False (ok, 0.36) |
intent_021 | Intent and readiness | dev | incorrect | intent: investigate -> investigate (ok, 0.98) specific_enough: False -> True (miss, 0.51) |
intent_022 | Intent and readiness | test | correct | intent: fix -> fix (ok, 0.96) specific_enough: True -> True (ok, 0.75) |
intent_023 | Intent and readiness | dev | correct | intent: fix -> fix (ok, 0.94) specific_enough: True -> True (ok, 0.81) |
intent_024 | Intent and readiness | test | correct | intent: fix -> fix (ok, 0.96) specific_enough: True -> True (ok, 0.78) |
intent_025 | Intent and readiness | dev | correct | intent: fix -> fix (ok, 0.89) specific_enough: True -> True (ok, 0.75) |
intent_026 | Intent and readiness | test | correct | intent: fix -> fix (ok, 0.93) specific_enough: False -> False (ok, 0.12) |
intent_027 | Intent and readiness | dev | correct | intent: fix -> fix (ok, 0.97) specific_enough: False -> False (ok, 0.36) |
intent_028 | Intent and readiness | test | correct | intent: fix -> fix (ok, 0.93) specific_enough: False -> False (ok, 0.20) |
failure_001 | Failure triage | dev | correct | failure_kind: logic_bug -> logic_bug (ok, 0.93) retry: False -> False (ok, 0.03) |
failure_002 | Failure triage | test | correct | failure_kind: logic_bug -> logic_bug (ok, 0.90) retry: False -> False (ok, 0.04) |
failure_003 | Failure triage | dev | correct | failure_kind: logic_bug -> logic_bug (ok, 0.88) retry: False -> False (ok, 0.05) |
failure_004 | Failure triage | test | correct | failure_kind: logic_bug -> logic_bug (ok, 0.59) retry: False -> False (ok, 0.02) |
failure_005 | Failure triage | dev | correct | failure_kind: logic_bug -> logic_bug (ok, 0.67) retry: False -> False (ok, 0.10) |
failure_006 | Failure triage | test | correct | failure_kind: logic_bug -> logic_bug (ok, 0.44) retry: False -> False (ok, 0.24) |
failure_007 | Failure triage | dev | correct | failure_kind: environment -> environment (ok, 0.84) retry: False -> False (ok, 0.16) |
failure_008 | Failure triage | test | correct | failure_kind: environment -> environment (ok, 0.88) retry: False -> False (ok, 0.02) |
failure_009 | Failure triage | dev | correct | failure_kind: environment -> environment (ok, 0.85) retry: False -> False (ok, 0.03) |
failure_010 | Failure triage | test | incorrect | failure_kind: environment -> flaky (miss, 0.46) retry: False -> False (ok, 0.07) |
failure_011 | Failure triage | dev | correct | failure_kind: environment -> environment (ok, 0.82) retry: False -> False (ok, 0.06) |
failure_012 | Failure triage | test | incorrect | failure_kind: environment -> flaky (miss, 0.40) retry: False -> False (ok, 0.31) |
failure_013 | Failure triage | dev | correct | failure_kind: flaky -> flaky (ok, 0.84) retry: True -> True (ok, 0.68) |
failure_014 | Failure triage | test | correct | failure_kind: flaky -> flaky (ok, 0.95) retry: True -> True (ok, 0.70) |
failure_015 | Failure triage | dev | correct | failure_kind: flaky -> flaky (ok, 0.96) retry: True -> True (ok, 0.89) |
failure_016 | Failure triage | test | correct | failure_kind: flaky -> flaky (ok, 0.79) retry: True -> True (ok, 0.55) |
failure_017 | Failure triage | dev | correct | failure_kind: flaky -> flaky (ok, 0.93) retry: True -> True (ok, 0.63) |
failure_018 | Failure triage | test | correct | failure_kind: flaky -> flaky (ok, 0.96) retry: True -> True (ok, 0.91) |
failure_019 | Failure triage | test | correct | failure_kind: test_bug -> test_bug (ok, 0.94) retry: False -> False (ok, 0.02) |
failure_020 | Failure triage | dev | correct | failure_kind: test_bug -> test_bug (ok, 0.85) retry: False -> False (ok, 0.02) |
failure_021 | Failure triage | test | correct | failure_kind: test_bug -> test_bug (ok, 0.92) retry: False -> False (ok, 0.02) |
failure_022 | Failure triage | dev | correct | failure_kind: test_bug -> test_bug (ok, 0.89) retry: False -> False (ok, 0.02) |
failure_023 | Failure triage | test | incorrect | failure_kind: test_bug -> logic_bug (miss, 0.46) retry: False -> False (ok, 0.13) |
failure_024 | Failure triage | dev | correct | failure_kind: test_bug -> test_bug (ok, 0.57) retry: False -> False (ok, 0.02) |
risk_001 | Change risk | dev | incorrect | risk: 0 -> 1 (miss, 0.68) needs_review: False -> False (ok, 0.09) |
risk_002 | Change risk | test | incorrect | risk: 0 -> 1 (miss, 0.53) needs_review: False -> False (ok, 0.11) |
risk_003 | Change risk | dev | incorrect | risk: 0 -> 1 (miss, 0.51) needs_review: False -> False (ok, 0.06) |
risk_004 | Change risk | test | incorrect | risk: 0 -> 1 (miss, 0.68) needs_review: False -> False (ok, 0.11) |
risk_005 | Change risk | dev | incorrect | risk: 0 -> 1 (miss, 0.60) needs_review: False -> False (ok, 0.06) |
risk_006 | Change risk | test | correct | risk: 0 -> 0 (ok, 0.43) needs_review: False -> False (ok, 0.04) |
risk_007 | Change risk | test | correct | risk: 1 -> 1 (ok, 0.85) needs_review: False -> False (ok, 0.24) |
risk_008 | Change risk | dev | correct | risk: 1 -> 1 (ok, 0.88) needs_review: False -> False (ok, 0.28) |
risk_009 | Change risk | test | correct | risk: 1 -> 1 (ok, 0.80) needs_review: False -> False (ok, 0.16) |
risk_010 | Change risk | dev | correct | risk: 1 -> 1 (ok, 0.79) needs_review: False -> False (ok, 0.12) |
risk_011 | Change risk | test | correct | risk: 1 -> 1 (ok, 0.92) needs_review: False -> False (ok, 0.12) |
risk_012 | Change risk | dev | correct | risk: 1 -> 1 (ok, 1.03) needs_review: False -> False (ok, 0.48) |
risk_013 | Change risk | test | correct | risk: 2 -> 2 (ok, 2.00) needs_review: True -> True (ok, 0.84) |
risk_014 | Change risk | dev | correct | risk: 2 -> 2 (ok, 2.33) needs_review: True -> True (ok, 0.90) |
risk_015 | Change risk | test | correct | risk: 2 -> 2 (ok, 1.77) needs_review: True -> True (ok, 0.78) |
risk_016 | Change risk | dev | incorrect | risk: 2 -> 1 (miss, 1.30) needs_review: True -> False (miss, 0.29) |
risk_017 | Change risk | test | correct | risk: 2 -> 2 (ok, 2.20) needs_review: True -> True (ok, 0.87) |
risk_018 | Change risk | dev | incorrect | risk: 2 -> 3 (miss, 2.54) needs_review: True -> True (ok, 0.91) |
risk_019 | Change risk | dev | incorrect | risk: 3 -> 2 (miss, 2.01) needs_review: True -> True (ok, 0.84) |
risk_020 | Change risk | test | correct | risk: 3 -> 3 (ok, 2.69) needs_review: True -> True (ok, 0.92) |
risk_021 | Change risk | dev | correct | risk: 3 -> 3 (ok, 2.59) needs_review: True -> True (ok, 0.92) |
risk_022 | Change risk | test | incorrect | risk: 3 -> 2 (miss, 1.67) needs_review: True -> False (miss, 0.45) |
risk_023 | Change risk | dev | incorrect | risk: 3 -> 2 (miss, 1.97) needs_review: True -> True (ok, 0.84) |
risk_024 | Change risk | test | incorrect | risk: 3 -> 2 (miss, 2.41) needs_review: True -> True (ok, 0.78) |
routing_001 | Routing and ownership | test | correct | owner: api -> api (ok, 0.96) |
routing_002 | Routing and ownership | dev | correct | owner: api -> api (ok, 0.62) |
routing_003 | Routing and ownership | test | correct | owner: api -> api (ok, 0.95) |
routing_004 | Routing and ownership | dev | correct | owner: api -> api (ok, 0.90) |
routing_005 | Routing and ownership | test | correct | owner: storage -> storage (ok, 0.81) |
routing_006 | Routing and ownership | dev | correct | owner: storage -> storage (ok, 0.98) |
routing_007 | Routing and ownership | test | correct | owner: storage -> storage (ok, 0.97) |
routing_008 | Routing and ownership | dev | correct | owner: storage -> storage (ok, 0.95) |
routing_009 | Routing and ownership | test | correct | owner: ui -> ui (ok, 0.92) |
routing_010 | Routing and ownership | dev | correct | owner: ui -> ui (ok, 0.95) |
routing_011 | Routing and ownership | test | correct | owner: ui -> ui (ok, 0.94) |
routing_012 | Routing and ownership | dev | correct | owner: ui -> ui (ok, 0.94) |
routing_013 | Routing and ownership | test | correct | owner: infra -> infra (ok, 0.95) |
routing_014 | Routing and ownership | dev | correct | owner: infra -> infra (ok, 0.94) |
routing_015 | Routing and ownership | test | correct | owner: infra -> infra (ok, 0.94) |
routing_016 | Routing and ownership | dev | correct | owner: infra -> infra (ok, 0.96) |
routing_017 | Routing and ownership | test | correct | owner: unclear -> unclear (ok, 0.59) |
routing_018 | Routing and ownership | dev | correct | owner: unclear -> unclear (ok, 0.77) |
routing_019 | Routing and ownership | test | correct | owner: unclear -> unclear (ok, 0.49) |
routing_020 | Routing and ownership | dev | correct | owner: unclear -> unclear (ok, 0.52) |
effort_001 | Effort and approach | test | correct | effort: 0 -> 0 (ok, 0.22) approach: minimal_patch -> minimal_patch (ok, 0.96) |
effort_002 | Effort and approach | dev | incorrect | effort: 0 -> 1 (miss, 0.51) approach: minimal_patch -> minimal_patch (ok, 0.92) |
effort_003 | Effort and approach | test | incorrect | effort: 0 -> 1 (miss, 0.56) approach: minimal_patch -> minimal_patch (ok, 0.95) |
effort_004 | Effort and approach | test | correct | effort: 1 -> 1 (ok, 0.89) approach: minimal_patch -> minimal_patch (ok, 0.93) |
effort_005 | Effort and approach | dev | correct | effort: 1 -> 1 (ok, 1.17) approach: minimal_patch -> minimal_patch (ok, 0.70) |
effort_006 | Effort and approach | test | incorrect | effort: 1 -> 2 (miss, 1.50) approach: refactor -> refactor (ok, 0.74) |
effort_007 | Effort and approach | test | correct | effort: 2 -> 2 (ok, 1.86) approach: refactor -> refactor (ok, 0.84) |
effort_008 | Effort and approach | dev | correct | effort: 2 -> 2 (ok, 2.23) approach: refactor -> refactor (ok, 0.69) |
effort_009 | Effort and approach | test | incorrect | effort: 2 -> 3 (miss, 2.78) approach: refactor -> refactor (ok, 0.86) |
effort_010 | Effort and approach | dev | correct | effort: 2 -> 2 (ok, 1.88) approach: refactor -> refactor (ok, 0.88) |
effort_011 | Effort and approach | test | correct | effort: 3 -> 3 (ok, 2.71) approach: new_component -> new_component (ok, 0.46) |
effort_012 | Effort and approach | test | correct | effort: 2 -> 2 (ok, 1.63) approach: new_component -> new_component (ok, 0.78) |
effort_013 | Effort and approach | dev | incorrect | effort: 3 -> 2 (miss, 2.01) approach: new_component -> new_component (ok, 0.58) |
effort_014 | Effort and approach | dev | correct | effort: 2 -> 2 (ok, 1.52) approach: new_component -> new_component (ok, 0.97) |
effort_015 | Effort and approach | test | incorrect | effort: 3 -> 2 (miss, 1.85) approach: new_component -> new_component (ok, 0.52) |
effort_016 | Effort and approach | dev | incorrect | effort: 0 -> 1 (miss, 1.29) approach: ask_user -> ask_user (ok, 0.88) |
effort_017 | Effort and approach | dev | incorrect | effort: 1 -> 2 (miss, 1.61) approach: ask_user -> ask_user (ok, 0.46) |
effort_018 | Effort and approach | test | incorrect | effort: 1 -> 2 (miss, 2.38) approach: ask_user -> ask_user (ok, 0.67) |
effort_019 | Effort and approach | dev | incorrect | effort: 1 -> 2 (miss, 1.75) approach: ask_user -> ask_user (ok, 0.77) |
effort_020 | Effort and approach | dev | incorrect | effort: 3 -> 2 (miss, 1.58) approach: ask_user -> minimal_patch (miss, 0.38) |
intent_029 | Intent and readiness | test | incorrect | intent: question -> question (ok, 0.95) specific_enough: True -> False (miss, 0.30) |
intent_030 | Intent and readiness | test | correct | intent: question -> question (ok, 0.95) specific_enough: True -> True (ok, 0.53) |
intent_031 | Intent and readiness | dev | incorrect | intent: question -> question (ok, 0.97) specific_enough: True -> False (miss, 0.23) |
intent_032 | Intent and readiness | test | incorrect | intent: question -> question (ok, 0.97) specific_enough: True -> False (miss, 0.49) |
intent_033 | Intent and readiness | dev | correct | intent: question -> question (ok, 0.96) specific_enough: True -> True (ok, 0.57) |
intent_034 | Intent and readiness | test | correct | intent: question -> question (ok, 0.96) specific_enough: False -> False (ok, 0.09) |
intent_035 | Intent and readiness | dev | correct | intent: question -> question (ok, 0.97) specific_enough: False -> False (ok, 0.19) |
intent_036 | Intent and readiness | test | correct | intent: implement -> implement (ok, 0.97) specific_enough: True -> True (ok, 0.84) |
intent_037 | Intent and readiness | test | correct | intent: implement -> implement (ok, 0.96) specific_enough: True -> True (ok, 0.78) |
intent_038 | Intent and readiness | dev | correct | intent: implement -> implement (ok, 0.97) specific_enough: True -> True (ok, 0.81) |
intent_039 | Intent and readiness | test | correct | intent: implement -> implement (ok, 0.95) specific_enough: True -> True (ok, 0.92) |
intent_040 | Intent and readiness | dev | correct | intent: implement -> implement (ok, 0.73) specific_enough: False -> False (ok, 0.16) |
intent_041 | Intent and readiness | test | correct | intent: implement -> implement (ok, 0.95) specific_enough: False -> False (ok, 0.15) |
intent_042 | Intent and readiness | dev | correct | intent: implement -> implement (ok, 0.52) specific_enough: False -> False (ok, 0.17) |
intent_043 | Intent and readiness | test | correct | intent: investigate -> investigate (ok, 0.98) specific_enough: True -> True (ok, 0.70) |
intent_044 | Intent and readiness | test | correct | intent: investigate -> investigate (ok, 0.97) specific_enough: True -> True (ok, 0.71) |
intent_045 | Intent and readiness | dev | correct | intent: investigate -> investigate (ok, 0.98) specific_enough: True -> True (ok, 0.66) |
intent_046 | Intent and readiness | test | correct | intent: investigate -> investigate (ok, 0.99) specific_enough: True -> True (ok, 0.63) |
intent_047 | Intent and readiness | dev | correct | intent: investigate -> investigate (ok, 0.96) specific_enough: False -> False (ok, 0.25) |
intent_048 | Intent and readiness | test | incorrect | intent: investigate -> investigate (ok, 0.97) specific_enough: False -> True (miss, 0.50) |
intent_049 | Intent and readiness | dev | correct | intent: investigate -> investigate (ok, 0.94) specific_enough: False -> False (ok, 0.32) |
intent_050 | Intent and readiness | dev | correct | intent: fix -> fix (ok, 0.90) specific_enough: True -> True (ok, 0.82) |
intent_051 | Intent and readiness | test | correct | intent: fix -> fix (ok, 0.93) specific_enough: True -> True (ok, 0.83) |
intent_052 | Intent and readiness | dev | correct | intent: fix -> fix (ok, 0.95) specific_enough: True -> True (ok, 0.85) |
intent_053 | Intent and readiness | test | correct | intent: fix -> fix (ok, 0.85) specific_enough: True -> True (ok, 0.79) |
intent_054 | Intent and readiness | dev | correct | intent: fix -> fix (ok, 0.96) specific_enough: False -> False (ok, 0.25) |
intent_055 | Intent and readiness | test | correct | intent: fix -> fix (ok, 0.91) specific_enough: False -> False (ok, 0.17) |
intent_056 | Intent and readiness | dev | correct | intent: fix -> fix (ok, 0.77) specific_enough: False -> False (ok, 0.20) |
failure_025 | Failure triage | test | correct | failure_kind: logic_bug -> logic_bug (ok, 0.83) retry: False -> False (ok, 0.02) |
failure_026 | Failure triage | dev | correct | failure_kind: logic_bug -> logic_bug (ok, 0.59) retry: False -> False (ok, 0.05) |
failure_027 | Failure triage | test | correct | failure_kind: logic_bug -> logic_bug (ok, 0.71) retry: False -> False (ok, 0.18) |
failure_028 | Failure triage | dev | correct | failure_kind: logic_bug -> logic_bug (ok, 0.35) retry: False -> False (ok, 0.30) |
failure_029 | Failure triage | test | correct | failure_kind: logic_bug -> logic_bug (ok, 0.88) retry: False -> False (ok, 0.01) |
failure_030 | Failure triage | dev | correct | failure_kind: logic_bug -> logic_bug (ok, 0.76) retry: False -> False (ok, 0.04) |
failure_031 | Failure triage | test | correct | failure_kind: environment -> environment (ok, 0.71) retry: False -> False (ok, 0.06) |
failure_032 | Failure triage | dev | correct | failure_kind: environment -> environment (ok, 0.64) retry: False -> False (ok, 0.12) |
failure_033 | Failure triage | test | correct | failure_kind: environment -> environment (ok, 0.80) retry: False -> False (ok, 0.03) |
failure_034 | Failure triage | dev | correct | failure_kind: environment -> environment (ok, 0.84) retry: False -> False (ok, 0.07) |
failure_035 | Failure triage | test | correct | failure_kind: environment -> environment (ok, 0.60) retry: False -> False (ok, 0.04) |
failure_036 | Failure triage | dev | correct | failure_kind: environment -> environment (ok, 0.90) retry: False -> False (ok, 0.10) |
failure_037 | Failure triage | test | correct | failure_kind: flaky -> flaky (ok, 0.96) retry: True -> True (ok, 0.85) |
failure_038 | Failure triage | dev | correct | failure_kind: flaky -> flaky (ok, 0.85) retry: True -> True (ok, 0.72) |
failure_039 | Failure triage | test | correct | failure_kind: flaky -> flaky (ok, 0.91) retry: True -> True (ok, 0.79) |
failure_040 | Failure triage | dev | correct | failure_kind: flaky -> flaky (ok, 0.91) retry: True -> True (ok, 0.53) |
failure_041 | Failure triage | test | correct | failure_kind: flaky -> flaky (ok, 0.93) retry: True -> True (ok, 0.76) |
failure_042 | Failure triage | dev | correct | failure_kind: flaky -> flaky (ok, 0.94) retry: True -> True (ok, 0.83) |
failure_043 | Failure triage | test | correct | failure_kind: test_bug -> test_bug (ok, 0.86) retry: False -> False (ok, 0.02) |
failure_044 | Failure triage | dev | correct | failure_kind: test_bug -> test_bug (ok, 0.89) retry: False -> False (ok, 0.01) |
failure_045 | Failure triage | test | correct | failure_kind: test_bug -> test_bug (ok, 0.73) retry: False -> False (ok, 0.03) |
failure_046 | Failure triage | dev | correct | failure_kind: test_bug -> test_bug (ok, 0.94) retry: False -> False (ok, 0.01) |
failure_047 | Failure triage | test | correct | failure_kind: test_bug -> test_bug (ok, 0.87) retry: False -> False (ok, 0.01) |
failure_048 | Failure triage | dev | correct | failure_kind: test_bug -> test_bug (ok, 0.95) retry: False -> False (ok, 0.02) |
risk_025 | Change risk | test | incorrect | risk: 0 -> 1 (miss, 0.64) needs_review: False -> False (ok, 0.10) |
risk_026 | Change risk | dev | incorrect | risk: 0 -> 1 (miss, 0.58) needs_review: False -> False (ok, 0.06) |
risk_027 | Change risk | test | incorrect | risk: 0 -> 1 (miss, 0.65) needs_review: False -> False (ok, 0.06) |
risk_028 | Change risk | dev | incorrect | risk: 0 -> 1 (miss, 0.63) needs_review: False -> False (ok, 0.07) |
risk_029 | Change risk | test | correct | risk: 0 -> 0 (ok, 0.49) needs_review: False -> False (ok, 0.07) |
risk_030 | Change risk | dev | incorrect | risk: 0 -> 1 (miss, 0.73) needs_review: False -> False (ok, 0.13) |
risk_031 | Change risk | test | correct | risk: 1 -> 1 (ok, 0.96) needs_review: False -> False (ok, 0.29) |
risk_032 | Change risk | dev | correct | risk: 1 -> 1 (ok, 0.80) needs_review: False -> False (ok, 0.10) |
risk_033 | Change risk | test | correct | risk: 1 -> 1 (ok, 0.73) needs_review: False -> False (ok, 0.09) |
risk_034 | Change risk | dev | correct | risk: 1 -> 1 (ok, 0.78) needs_review: False -> False (ok, 0.11) |
risk_035 | Change risk | test | correct | risk: 1 -> 1 (ok, 0.83) needs_review: False -> False (ok, 0.19) |
risk_036 | Change risk | dev | correct | risk: 1 -> 1 (ok, 0.96) needs_review: False -> False (ok, 0.09) |
risk_037 | Change risk | test | correct | risk: 2 -> 2 (ok, 2.29) needs_review: True -> True (ok, 0.89) |
risk_038 | Change risk | dev | correct | risk: 2 -> 2 (ok, 1.66) needs_review: True -> True (ok, 0.72) |
risk_039 | Change risk | test | correct | risk: 2 -> 2 (ok, 2.15) needs_review: True -> True (ok, 0.86) |
risk_040 | Change risk | dev | correct | risk: 2 -> 2 (ok, 2.27) needs_review: True -> True (ok, 0.90) |
risk_041 | Change risk | test | correct | risk: 2 -> 2 (ok, 2.38) needs_review: True -> True (ok, 0.90) |
risk_042 | Change risk | dev | correct | risk: 2 -> 2 (ok, 2.07) needs_review: True -> True (ok, 0.85) |
risk_043 | Change risk | test | incorrect | risk: 3 -> 2 (miss, 2.01) needs_review: True -> True (ok, 0.84) |
risk_044 | Change risk | dev | incorrect | risk: 3 -> 2 (miss, 2.19) needs_review: True -> True (ok, 0.71) |
risk_045 | Change risk | test | incorrect | risk: 3 -> 1 (miss, 1.37) needs_review: True -> False (miss, 0.35) |
risk_046 | Change risk | dev | incorrect | risk: 3 -> 2 (miss, 2.46) needs_review: True -> True (ok, 0.86) |
risk_047 | Change risk | test | incorrect | risk: 3 -> 1 (miss, 1.45) needs_review: True -> False (miss, 0.34) |
risk_048 | Change risk | dev | incorrect | risk: 3 -> 2 (miss, 1.98) needs_review: True -> False (miss, 0.40) |
routing_021 | Routing and ownership | test | correct | owner: api -> api (ok, 0.96) |
routing_022 | Routing and ownership | dev | correct | owner: api -> api (ok, 0.91) |
routing_023 | Routing and ownership | test | correct | owner: api -> api (ok, 0.91) |
routing_024 | Routing and ownership | dev | correct | owner: api -> api (ok, 0.97) |
routing_025 | Routing and ownership | test | correct | owner: storage -> storage (ok, 0.87) |
routing_026 | Routing and ownership | dev | correct | owner: storage -> storage (ok, 0.84) |
routing_027 | Routing and ownership | test | correct | owner: storage -> storage (ok, 0.97) |
routing_028 | Routing and ownership | dev | correct | owner: storage -> storage (ok, 0.94) |
routing_029 | Routing and ownership | test | correct | owner: ui -> ui (ok, 0.94) |
routing_030 | Routing and ownership | dev | correct | owner: ui -> ui (ok, 0.92) |
routing_031 | Routing and ownership | test | correct | owner: ui -> ui (ok, 0.77) |
routing_032 | Routing and ownership | dev | correct | owner: ui -> ui (ok, 0.94) |
routing_033 | Routing and ownership | test | correct | owner: infra -> infra (ok, 0.95) |
routing_034 | Routing and ownership | dev | correct | owner: infra -> infra (ok, 0.92) |
routing_035 | Routing and ownership | test | correct | owner: infra -> infra (ok, 0.95) |
routing_036 | Routing and ownership | dev | correct | owner: infra -> infra (ok, 0.96) |
routing_037 | Routing and ownership | test | correct | owner: unclear -> unclear (ok, 0.78) |
routing_038 | Routing and ownership | dev | correct | owner: unclear -> unclear (ok, 0.67) |
routing_039 | Routing and ownership | test | correct | owner: unclear -> unclear (ok, 0.70) |
routing_040 | Routing and ownership | dev | correct | owner: unclear -> unclear (ok, 0.40) |
effort_021 | Effort and approach | test | correct | effort: 1 -> 1 (ok, 0.67) approach: minimal_patch -> minimal_patch (ok, 0.92) |
effort_022 | Effort and approach | test | incorrect | effort: 0 -> 1 (miss, 0.71) approach: minimal_patch -> minimal_patch (ok, 0.94) |
effort_023 | Effort and approach | dev | incorrect | effort: 0 -> 1 (miss, 1.03) approach: minimal_patch -> minimal_patch (ok, 0.86) |
effort_024 | Effort and approach | dev | correct | effort: 1 -> 1 (ok, 1.12) approach: minimal_patch -> minimal_patch (ok, 0.82) |
effort_025 | Effort and approach | test | correct | effort: 1 -> 1 (ok, 1.30) approach: minimal_patch -> minimal_patch (ok, 0.84) |
effort_026 | Effort and approach | dev | correct | effort: 1 -> 1 (ok, 1.13) approach: refactor -> refactor (ok, 0.53) |
effort_027 | Effort and approach | test | incorrect | effort: 2 -> 3 (miss, 2.76) approach: refactor -> refactor (ok, 0.85) |
effort_028 | Effort and approach | dev | correct | effort: 2 -> 2 (ok, 1.72) approach: refactor -> refactor (ok, 0.79) |
effort_029 | Effort and approach | test | incorrect | effort: 1 -> 2 (miss, 1.77) approach: refactor -> refactor (ok, 0.55) |
effort_030 | Effort and approach | test | correct | effort: 2 -> 2 (ok, 1.86) approach: refactor -> refactor (ok, 0.79) |
effort_031 | Effort and approach | test | incorrect | effort: 3 -> 1 (miss, 1.36) approach: new_component -> new_component (ok, 0.49) |
effort_032 | Effort and approach | dev | incorrect | effort: 3 -> 1 (miss, 1.19) approach: new_component -> minimal_patch (miss, 0.66) |
effort_033 | Effort and approach | dev | incorrect | effort: 2 -> 1 (miss, 1.50) approach: new_component -> minimal_patch (miss, 0.52) |
effort_034 | Effort and approach | dev | incorrect | effort: 1 -> 1 (ok, 1.00) approach: new_component -> minimal_patch (miss, 0.50) |
effort_035 | Effort and approach | test | incorrect | effort: 2 -> 1 (miss, 1.23) approach: new_component -> new_component (ok, 0.70) |
effort_036 | Effort and approach | test | incorrect | effort: 0 -> 1 (miss, 0.75) approach: ask_user -> minimal_patch (miss, 0.81) |
effort_037 | Effort and approach | test | correct | effort: 1 -> 1 (ok, 1.39) approach: ask_user -> ask_user (ok, 0.74) |
effort_038 | Effort and approach | dev | incorrect | effort: 0 -> 1 (miss, 0.65) approach: ask_user -> minimal_patch (miss, 0.79) |
effort_039 | Effort and approach | test | incorrect | effort: 3 -> 1 (miss, 1.49) approach: ask_user -> new_component (miss, 0.41) |
effort_040 | Effort and approach | test | incorrect | effort: 0 -> 1 (miss, 1.07) approach: ask_user -> minimal_patch (miss, 0.67) |
vnoul_001 | vision_noul | test | correct | dominant_red: True -> True (ok, 0.97) |
vnoul_002 | vision_noul | test | correct | dominant_red: False -> False (ok, 0.01) |
vnoul_003 | vision_noul | dev | correct | dominant_red: False -> False (ok, 0.04) |
vnoul_004 | vision_noul | dev | correct | dominant_red: True -> True (ok, 0.97) |
vnoul_005 | vision_noul | test | correct | dominant_red: False -> False (ok, 0.07) |
vnoul_006 | vision_noul | test | correct | dominant_red: True -> True (ok, 0.86) |
vnoul_007 | vision_noul | dev | correct | dominant_red: True -> True (ok, 0.83) |
vnoul_008 | vision_noul | dev | correct | dominant_red: False -> False (ok, 0.01) |
vchoice_001 | vision_choice | test | correct | dominant_colour: red -> red (ok, 0.98) |
vchoice_002 | vision_choice | test | correct | dominant_colour: green -> green (ok, 0.97) |
vchoice_003 | vision_choice | test | correct | dominant_colour: blue -> blue (ok, 0.95) |
vchoice_004 | vision_choice | test | correct | dominant_colour: mixed -> mixed (ok, 0.88) |
vchoice_005 | vision_choice | dev | correct | dominant_colour: red -> red (ok, 0.98) |
vchoice_006 | vision_choice | dev | correct | dominant_colour: green -> green (ok, 0.97) |
vchoice_007 | vision_choice | dev | correct | dominant_colour: blue -> blue (ok, 0.95) |
vchoice_008 | vision_choice | dev | correct | dominant_colour: mixed -> mixed (ok, 0.88) |
vscore_001 | vision_score | test | correct | alert_level: 0 -> 0 (ok, 0.06) |
vscore_002 | vision_score | test | correct | alert_level: 1 -> 1 (ok, 1.09) |
vscore_003 | vision_score | test | correct | alert_level: 2 -> 2 (ok, 1.97) |
vscore_004 | vision_score | test | correct | alert_level: 3 -> 3 (ok, 2.90) |
vscore_005 | vision_score | dev | correct | alert_level: 0 -> 0 (ok, 0.14) |
vscore_006 | vision_score | dev | correct | alert_level: 1 -> 1 (ok, 0.99) |
vscore_007 | vision_score | dev | correct | alert_level: 2 -> 2 (ok, 1.87) |
vscore_008 | vision_score | dev | correct | alert_level: 3 -> 3 (ok, 2.75) |
vvideo_001 | vision_video | test | correct | colour_changed: True -> True (ok, 0.95) |
vvideo_002 | vision_video | test | correct | colour_changed: False -> False (ok, 0.10) |
vvideo_003 | vision_video | dev | correct | colour_changed: False -> False (ok, 0.06) |
vvideo_004 | vision_video | dev | correct | colour_changed: True -> True (ok, 0.94) |
vvideo_005 | vision_video | test | correct | colour_changed: True -> True (ok, 0.79) |
vvideo_006 | vision_video | test | correct | colour_changed: False -> False (ok, 0.10) |
vvideo_007 | vision_video | dev | correct | colour_changed: True -> True (ok, 0.95) |
vvideo_008 | vision_video | dev | correct | colour_changed: False -> False (ok, 0.11) |