Rifqi Hafizuddin
[NOTICKET] feat(eval): knowledge-extraction gold set, scorer + frozen prototype baseline
60cf4a8
Raw
History Blame
9.91 kB
# PROVISIONAL gold set — bootstrapped by reading the source PDF, NOT yet expert-reviewed.
# Reviewer: Mas Beta. Until reviewed, every score derived from this file carries that caveat.
#
# Labelling rules used:
# - `term` is the string a reader would look up.
# - `full_name` is the LITERAL source wording, not a normalised or corrected form.
# (e.g. the STD writes "Physical of Availability (PA)" in the heading and
# "Physical Availability" in the legend — both are recorded as variants.)
# - `definition_contains` are substrings that MUST appear in a correct definition.
# Substring matching, not exact match, so a correct-but-differently-worded
# extraction is not scored as a miss (spec §5).
doc_id: STD_2026_006_MNO
status: provisional
labelled_by: claude-bootstrap
labelled_on: 2026-08-13
source_pages: 9
terms:
- term: Production
full_name: Production
variants: ["Production", "produksi"]
definition_contains: ["nilai tambah", "sumber daya"]
formula_present: true
page: 2
- term: MOHH
full_name: Machine on Hand Hours
variants: ["MOHH"]
definition_contains: ["Machine on Hand Hours"]
formula_present: false
page: 2
- term: Qty
full_name: Quantity (Qty)
variants: ["Qty", "Quantity", "quantity"]
definition_contains: ["jumlah equipment", "periode"]
formula_present: true
page: 2
- term: PA
full_name: Physical of Availability (PA)
variants: ["PA", "Physical Availability", "Physical of Availability"]
definition_contains: ["ketersediaan fisik", "available"]
formula_present: true
page: 4
- term: UA
full_name: Utilization of Availability (UA)
variants: ["UA", "Utilization of Availability"]
definition_contains: ["efektifitas penggunaan", "working hours"]
formula_present: true
page: 4
- term: Pty
full_name: Productivity (Pty)
variants: ["Pty", "PTY", "Productivity", "Produktivitas"]
definition_contains: ["efektifitas penggunaan sumber daya", "output"]
formula_present: true
page: 5
- term: ECA
full_name: Equipment Capacity Analysis (ECA)
variants: ["ECA", "Equipment Capacity Analysis"]
definition_contains: ["ketidaktercapaian", "kapasitas produksi"]
formula_present: false
page: 6
- term: INPR
full_name: in operation
variants: ["INPR", "in operation", "INPR Hours"]
definition_contains: ["in operation"]
formula_present: false
page: 2
- term: Total Hours
full_name: Total Hours
variants: ["Total Hours", "total jam"]
definition_contains: ["total jam"]
formula_present: true
page: 2
- term: Breakdown
full_name: Breakdown
variants: ["Breakdown", "breakdown"]
definition_contains: []
formula_present: true
page: 4
- term: Working Hours
full_name: Working Hours
variants: ["Working Hours", "working hours"]
definition_contains: ["waktu kerja"]
formula_present: true
page: 4
- term: EWH
full_name: Effective Working Hours (EWH)
variants: ["EWH", "Effective Working Hours", "productive working hours"]
definition_contains: ["waktu kerja efektif"]
formula_present: false
page: 5
- term: Land clearing
full_name: land clearing
variants: ["land clearing"]
definition_contains: []
formula_present: false
page: 2
- term: Overburden removal
full_name: pengupasan lapisan penutup (overburden removal)
variants: ["overburden removal", "pengupasan lapisan penutup"]
definition_contains: []
formula_present: false
page: 2
- term: Coal mining
full_name: penambangan batubara (coal mining)
variants: ["coal mining", "Coal Mining", "CM", "penambangan batubara"]
definition_contains: []
formula_present: false
page: 2
- term: Coal hauling
full_name: pengangkutan batubara (coal hauling/coal transporting)
variants: ["coal hauling", "coal transporting", "Coal Transport", "CT"]
definition_contains: []
formula_present: false
page: 2
- term: Coal barging
full_name: coal barging atau ship loading
variants: ["coal barging", "ship loading", "pengapalan"]
definition_contains: []
formula_present: false
page: 2
- term: Waste Removal
full_name: Waste Removal (WR)
variants: ["Waste Removal", "WR", "waste removal"]
definition_contains: []
formula_present: false
page: 3
- term: General Work
full_name: General Work
variants: ["General Work"]
definition_contains: []
formula_present: false
page: 3
- term: Rental
full_name: Rental
variants: ["Rental"]
definition_contains: []
formula_present: false
page: 3
- term: Grouping (Composite)
full_name: Grouping (Composite)
variants: ["Grouping (Composite)", "grouping (composite)", "Composite"]
definition_contains: ["type", "class"]
formula_present: true
page: 3
- term: EX2500
full_name: EX2500
variants: ["EX2500"]
definition_contains: []
formula_present: false
page: 3
- term: Time Performance MCD Application
full_name: raw data Time Performance MCD Application
variants: ["Time Performance MCD Application", "MCD Application", "MCD"]
definition_contains: []
formula_present: false
page: 3
- term: Joint survey
full_name: joint survey
variants: ["joint survey"]
definition_contains: []
formula_present: false
page: 5
- term: Truck count
full_name: truck count
variants: ["truck count"]
definition_contains: []
formula_present: false
page: 5
- term: Weight average
full_name: rata-rata tertimbang (weight average)
variants: ["weight average", "rata-rata tertimbang", "pembobotan"]
definition_contains: []
formula_present: false
page: 4
- term: Gain/Loss
full_name: Gain/Loss
variants: ["Gain/Loss", "Gain / Loss"]
definition_contains: ["plan", "actual"]
formula_present: true
page: 6
- term: Plan
full_name: rencana (plan)
variants: ["plan", "Plan", "rencana", "P(M)", "P(G)"]
definition_contains: []
formula_present: false
page: 6
- term: Actual
full_name: realisasi (actual)
variants: ["actual", "Actual", "realisasi", "A(M)", "A(G)"]
definition_contains: []
formula_present: false
page: 6
- term: Model Unit
full_name: Model Unit
variants: ["Model Unit", "model unit", "(M)", "Model"]
definition_contains: []
formula_present: true
page: 6
- term: Standby
full_name: Delay/Standby
variants: ["Standby", "standby", "Delay/Standby", "Gap Standby"]
definition_contains: []
formula_present: true
page: 6
- term: BCM
full_name: BCM
variants: ["BCM"]
definition_contains: []
formula_present: false
page: 6
- term: Waterfall Analysis
full_name: Waterfall Analysis
variants: ["Waterfall Analysis", "grafik Waterfall"]
definition_contains: ["visualisasi", "Gain/Loss"]
formula_present: false
page: 8
- term: Other Activity
full_name: Other Activity
variants: ["Other Activity"]
definition_contains: ["tidak sesuai", "direncanakan"]
formula_present: false
page: 8
- term: Loader
full_name: loader
variants: ["loader", "PA Loader"]
definition_contains: []
formula_present: false
page: 8
- term: Hauler
full_name: hauler
variants: ["hauler"]
definition_contains: []
formula_present: false
page: 8
- term: Hierarki Level Analysis
full_name: Hierarki Level Analyisis
variants: ["Hierarki Level Analyisis", "Hierarki Level Analysis"]
definition_contains: ["level"]
formula_present: false
page: 9
- term: Uncontrollable
full_name: Uncontrollable
variants: ["Uncontrollable", "uncontrollable"]
definition_contains: ["level 1"]
formula_present: false
page: 9
- term: Controllable
full_name: controllable
variants: ["controllable", "UA Controllable"]
definition_contains: ["level 1"]
formula_present: false
page: 9
- term: Fleet management
full_name: fleet management
variants: ["fleet management"]
definition_contains: []
formula_present: false
page: 9
- term: Mineplan
full_name: mineplan
variants: ["mineplan"]
definition_contains: []
formula_present: false
page: 9
rules:
- rule_id: QTY_PER_ACTIVITY
statement_contains: ["Qty", "kategori aktivitas", "terpisah"]
page: 3
- rule_id: QTY_GROUPING_SUM
statement_contains: ["Qty Grouping", "menjumlahkan"]
page: 3
- rule_id: ACTIVITY_CLASSIFICATION_SOURCE
statement_contains: ["status equipment", "Time Performance MCD"]
page: 3
- rule_id: PA_COMPOSITE_WEIGHTED
statement_contains: ["weight average", "Quantity", "pembobot"]
page: 4
- rule_id: UA_BY_ACTIVITY
statement_contains: ["UA", "kategori aktivitas"]
page: 4
- rule_id: PTY_PRODUCTION_SOURCE
statement_contains: ["joint survey", "truck count"]
page: 5
- rule_id: PTY_WORKING_HOURS_DEFINITION
statement_contains: ["Effective Working Hours", "waktu kerja efektif"]
page: 5
- rule_id: PTY_COMPOSITE_WEIGHTED
statement_contains: ["Pty", "pembobotan", "Quantity"]
page: 5
- rule_id: GAINLOSS_QTY_ZERO_PLAN
statement_contains: ["QtyP(M) = 0", "QtyA(M) > 0"]
page: 6
- rule_id: GAINLOSS_COMPOSITE_SUM
statement_contains: ["grouping", "penjumlahan", "model unit"]
page: 6
- rule_id: GAINLOSS_UNITS
statement_contains: ["BCM", "ton", "jam"]
page: 6
- rule_id: QTY_ACTUAL_ZERO_PLAN_ALT
statement_contains: ["QtyA", "QtyP", "0"]
page: 7
- rule_id: QTY_PHYSICAL_REPORTING
statement_contains: ["fisik unit", "INPR"]
page: 7
- rule_id: ECA_OTHER_ACTIVITY
statement_contains: ["alokasi", "tidak sesuai", "direncanakan"]
page: 8
- rule_id: WATERFALL_TWO_METHODS
statement_contains: ["Waterfall", "dua metode"]
page: 8