List of all items

Structs

• MissingAcquisition
• assemble::AssemblyInput
• assemble::RetentionChoice
• baseline::Baseline
• baseline::BaselineCohort
• baseline::BaselineMetric
• baseline::Exceedance
• batch_qualification::AgreementBound
• batch_qualification::BatchQualification
• batch_qualification::BatchingConfig
• batch_qualification::Bindings
• batch_qualification::PairedAnswer
• batch_qualification::Ratio
• batch_qualification::Spend
• batch_qualification::Stage1Result
• batch_qualification::Stage2
• bundle::LoadFailure
• compare::Compared
• comparison::Comparison
• comparison::ComparisonMetric
• comparison::ComparisonRow
• comparison::NamedCandidate
• comparison::RepeatEvidence
• config::Agreement
• config::ConfigAdapter
• config::ConfigError
• config::EvaluatorConfig
• config::Gate
• config::MetricFormula
• dataset::AdapterRef
• dataset::AdmissionRecord
• dataset::Admitted
• dataset::AgreementStatistic
• dataset::DatasetCase
• dataset::DatasetManifest
• dataset::Exposure
• dataset::LabelMapping
• dataset::LabelingMethod
• dataset::LicenseTerms
• dataset::ModelRef
• dataset::OwnerReview
• dataset::Population
• dataset::PrivacyBasis
• dataset::SliceSize
• dataset::SplitAssignment
• dataset::TaskMapping
• diff::CaseDistribution
• diff::ChangedCase
• diff::DiffCohort
• diff::DiffMetric
• diff::EvalDiff
• diff::TopKCount
• dynamic::DynamicCase
• dynamic::DynamicDataset
• dynamic::DynamicEvalReport
• dynamic::DynamicEvaluatorConfig
• dynamic::DynamicGate
• dynamic::GateResult
• dynamic::IncomparableCase
• dynamic::QuestionSchema
• eval_cases::CaseMeasures
• eval_cases::EvalCases
• explain::ExplainError
• explain::ExplainOptions
• fit::CalibrationFit
• fit::FitTarget
• generator::SplitMix64
• generator::Xoshiro256StarStar
• gold::Gold
• holdout::Append
• holdout::HeldOutRecord
• holdout::HoldoutLedger
• holdout::LedgerEntry
• live::LiveCase
• measured::Measured
• measured::NewMetric
• measures::ConstraintDecl
• measures::FieldDecl
• measures::Measures
• measures::RankingDecl
• metrics::Bin
• metrics::CostSeries
• metrics::Scored
• optimization::ExternalMeasurements
• optimization::OptimizationEvaluation
• origin::OriginCase
• ranking_metrics::Ranked
• ranking_metrics::RankedList
• ranking_metrics::RankingCase
• ranking_metrics::Relevance
• remote_evidence::AttemptAvailability
• repeat::CohortReport
• repeat::HeldOutInput
• repeat::MetricReport
• repeat::RepeatInputs
• repeat::RepeatReport
• repeat::Run
• repeat::RunRef
• repeat_config::BootstrapSpec
• repeat_config::KSd
• repeat_config::Noise
• repeat_config::NoiseOverride
• repeat_config::RepeatConfig
• repeat_config::SliceSpec
• repeat_config::TopK
• repeat_stats::Bootstrap
• repeat_stats::MetricCases
• repeat_stats::RunStats
• replay::ReplayConfig
• replay::Reproduced
• replay::RetainedSupply
• report::Candidate
• report::CandidateBinding
• report::CaseDetail
• report::ClaimRequest
• report::Count
• report::EvalDetail
• report::Evaluated
• report::FreezeInputs
• report::Frozen
• report::Inputs
• report::Measurement
• report::ObservedInputs
• report::QualificationRecord
• report::RoleFigures
• report::Row
• report::ScopedClaim
• report::SliceRows
• resolve::Budget
• resolve::NoExternal
• scores::CaseView
• scores::ProposalView
• scores::ScoreEntry
• scores::ScoreViews
• scores::Scores
• scores::ViewEntry
• scoring::AgreementDecl
• scoring::Declarations
• scoring::HumanScale
• scoring::JudgeRef
• scoring::RubricMetric
• scoring::ScorerDescriptor
• selection::CandidateSelection
• selection::ClauseResult
• selection::HeldOutLimit
• selection::Selection
• selection::SelectionGate
• selection::SliceResult
• selection::Unranked

Enums

• assemble::AssemblyError
• assemble::Content
• baseline::BaselineError
• baseline::Reproducibility
• batch_qualification::Agreement
• batch_qualification::Answer
• batch_qualification::BatchQualificationError
• batch_qualification::CaseOutcome
• batch_qualification::Stage1Case
• batch_qualification::Verdict
• bundle::BundleInput
• bundle::BundleLoad
• compare::CandidateIncomparable
• comparison::ComparisonResult
• config::AdapterRules
• config::Direction
• dataset::AdmissionError
• dataset::AdmissionSource
• dataset::DatasetError
• dataset::Label
• dataset::LabelProducer
• diff::DiffBool
• diff::DiffResult
• dynamic::CalibrationStatus
• dynamic::DynamicDatasetError
• dynamic::DynamicEvalError
• dynamic::DynamicIncomparable
• dynamic::DynamicReproduction
• dynamic::GateDirection
• dynamic::GateStatus
• dynamic::QualityClaim
• eval_cases::CaseMeasure
• explain::Evidence
• fit::FitError
• fit::Qualification
• gold::FieldGold
• gold::GoldValue
• gold::Match
• holdout::LedgerError
• judge::JudgeError
• measured::Scope
• measures::Against
• measures::ConstraintAggregate
• measures::ConstraintTest
• metrics::CaseOutcome
• metrics::Measure
• ranking_metrics::Gain
• ranking_metrics::RankingMetric
• remote_evidence::ExchangeLookup
• remote_evidence::RemoteAvailability
• repeat::BandDoc
• repeat::BasisDoc
• repeat::CohortStatus
• repeat::FigureDoc
• repeat::HeldOut
• repeat::IntervalDoc
• repeat::Observation
• repeat::RepeatError
• repeat::Source
• repeat::SplitRole
• repeat_config::BandRule
• repeat_stats::Band
• repeat_stats::Basis
• repeat_stats::Contribution
• repeat_stats::Figure
• repeat_stats::Form
• repeat_stats::Interval
• repeat_stats::StatsError
• replay::Incomparable
• replay::Inconsistency
• replay::ReplayOutcome
• replay::RetainedValue
• report::ClaimError
• report::EvalError
• report::ExactBaseline
• report::Figure
• report::GateResult
• report::Observation
• report::QualificationError
• report::Role
• report::Served
• resolve::ItemFailure
• resolve::Resolution
• scores::ScoreOutcome
• scoring::OriginFamily
• scoring::RubricAggregate
• scoring::ScorerKind
• scoring::ScorerOutput
• selection::BaselineTarget
• selection::Clause
• selection::ClauseOutcome
• selection::MetricClause
• selection::Per
• selection::Verdict
• selection::Within

Traits

• measures::MeasuredAdapter
• metrics::TaskAdapter
• remote_evidence::ExchangeStore
• resolve::Resolver
• scores::Scorer

Functions

• assemble::assemble
• assemble::assemble_with_sources
• baseline::record
• baseline::reproducibility
• baseline::valid_name
• compare::compare
• comparison::compare_candidates
• comparison::render_markdown
• dataset::admit
• diff::diff
• diff::render_markdown
• dynamic::evaluate
• dynamic::reproduce
• eval_cases::derived
• eval_cases::form_in
• eval_cases::form_of
• eval_cases::metric_cases
• eval_cases::reconcile
• explain::explain
• explain::explain_diff
• explain::render_markdown
• fit::fit_temperature
• fit::qualify
• generator::run_seed
• generator::stream
• generator::stream_seed
• gold::match_value
• holdout::entry_digest
• judge::judge_scores
• live::compare_live
• live::with_comparison
• measured::agreement_metrics
• measured::metrics
• measured::quadratic_weighted_kappa
• measured::rubric_metrics
• measures::declared_name
• metrics::brier
• metrics::brier_term
• metrics::cost
• metrics::generation
• metrics::log_loss_term
• metrics::mean_log_loss
• metrics::nearest_rank
• metrics::probabilities
• metrics::reliability
• metrics::reliability_bin
• optimization::optimization_metrics
• origin::origin_metrics
• ranking_metrics::backfill_case
• ranking_metrics::discount
• ranking_metrics::ranked_list
• ranking_metrics::ranking_case
• ranking_metrics::short_case
• remote_evidence::availability
• repeat::repeat
• repeat::repeat_held_out
• repeat::split_role
• repeat_config::parse_seed
• repeat_stats::across_runs
• repeat_stats::band
• repeat_stats::check_shape
• repeat_stats::intervals
• repeat_stats::percentile_ranks
• repeat_stats::run_stats
• replay::reproduce
• report::evaluate
• report::evaluate_gate
• report::evaluate_measured
• report::evaluate_measured_with_cases
• report::evaluate_measured_with_views
• report::evaluate_observed
• report::evaluate_observed_with_cases
• report::evaluate_views
• report::evaluate_with_cases
• report::freeze
• report::measure
• report::regression
• report::scope_claim
• report::split_name
• resolve::check_bytes
• resolve::item_bytes
• resolve::resolve_item
• scores::checked
• scores::reason_ok
• scores::score_ok
• scores::score_views
• scores::scorer_case
• scoring::check_prefix
• selection::evaluate_selection

Constants

• baseline::BASELINE
• baseline::MAX_NAME
• batch_qualification::BATCH_QUALIFICATION
• batch_qualification::MAX_PAIRS
• batch_qualification::MAX_TEXT_BYTES
• bundle::NOTE_MAX_BYTES
• comparison::COMPARISON
• comparison::MAX_CANDIDATES
• comparison::MAX_CANDIDATE_NAME
• config::EVALUATOR_CONFIG
• config::EVALUATOR_CONFIG_V2
• config::EVALUATOR_CONFIG_V3
• config::MAX_GRID
• dataset::DATASET
• dataset::DATASET_ADMISSION
• dataset::DATASET_V2
• diff::EVAL_DIFF
• diff::MAX_CHANGED_CASES
• dynamic::DYNAMIC_DATASET
• dynamic::DYNAMIC_EVALUATOR_CONFIG
• dynamic::DYNAMIC_REPORT
• eval_cases::COST_PER_1000_ESTIMATED
• eval_cases::COST_PER_1000_OBSERVED
• eval_cases::EVAL_CASES
• fit::CALIBRATION_FIT
• generator::GENERATOR
• generator::STREAM_TAG
• gold::ABSENT
• gold::MAX_ENTRIES
• gold::MAX_GRADE
• gold::MAX_NAME
• gold::MAX_PATH
• holdout::ENTRY_TAG
• holdout::HOLDOUT_LEDGER
• holdout::MAX_ENTRIES
• holdout::MAX_ENTRY_RUNS
• live::EXCLUSIONS
• live::LIMITATIONS
• measured::SCORES_MISSING
• measured::constraint_reason::EMPTY_RANKING
• measured::constraint_reason::NO_CHECKED_ITEMS
• measured::constraint_reason::NO_REFERENCE
• measured::constraint_reason::TYPE_MISMATCH
• measured::constraint_reason::UNKNOWN_ATTRIBUTE
• measures::MAX_BACKFILL_POSITIONS
• measures::MAX_DECLARATIONS
• measures::TASK_ADAPTER_V2
• origin::reason::ABSENT
• origin::reason::EMPTY
• origin::reason::NOT_IN_PLAN
• origin::reason::NOT_RUN
• origin::reason::NO_EVIDENCE
• origin::reason::NO_GOLD
• origin::reason::NO_OUTCOME
• origin::reason::NO_RESULT
• origin::reason::NO_SCREENED_FIELD
• origin::reason::NO_SLOT
• origin::reason::SKIPPED
• origin::reason::TYPE_MISMATCH
• origin::reason::UNCORROBORATED
• origin::reason::VALUE_NOT_RETAINED
• ranking_metrics::MAX_K
• ranking_metrics::reason::INVALID_RANKING
• ranking_metrics::reason::NOT_A_RANKING
• ranking_metrics::reason::NO_GOLD
• ranking_metrics::reason::NO_JUDGED_ITEMS
• ranking_metrics::reason::NO_ORIGIN
• ranking_metrics::reason::NO_POSITION
• ranking_metrics::reason::NO_RELEVANT
• ranking_metrics::reason::UNJUDGED_ITEMS
• repeat::REPEAT_REPORT
• repeat_config::MAX_RESAMPLES
• repeat_config::MAX_TOP_K
• repeat_config::METHOD
• repeat_config::MIN_RESAMPLES
• repeat_config::REPEAT_CONFIG
• repeat_stats::MAX_BOOTSTRAP_WORK
• repeat_stats::MAX_DENOMINATOR
• repeat_stats::MAX_LEVEL_UNITS
• repeat_stats::MAX_RUNS
• repeat_stats::MIN_LEVEL_UNITS
• report::EVAL_DETAIL
• report::QUALIFICATION
• scores::PROPOSAL_VIEW
• scores::SCORES
• scores::SCORE_VIEWS
• scores::reserved::ALL
• scores::reserved::INVALID_SCORE
• scores::reserved::JUDGE_BUNDLE_MISSING
• scores::reserved::JUDGE_NOT_REPRODUCED
• scores::reserved::JUDGE_UNRESOLVED
• scores::reserved::SCORER_DEADLINE
• scores::reserved::SCORER_FAILED
• scores::reserved::SCORER_OVERLOADED
• scores::reserved::SUBJECT_MISMATCH
• scoring::HUMAN_SIDE
• scoring::MAX_LEVELS
• scoring::MAX_SCORERS
• scoring::MODEL_PREFIX
• scoring::code::JUDGE_OUTPUT_KIND
• scoring::code::METRIC_UNAVAILABLE
• scoring::code::MODEL_PREFIX
• scoring::code::SCALE_MISMATCH
• selection::MAX_GATE_ITEMS
• selection::MAX_METRIC_NAME
• selection::SELECTION
• selection::SELECTION_GATE