.gitignore

@@ -1,6 +1,12 @@
 # Generated pipeline artifacts - reproducible from specs + rules + code
 # (see docs/rules/build-pipeline-tasks.md)
-out/
+out/*
+!out/report/
+!out/report/**
+!out/config/
+!out/config/**
+!out/.done/
+!out/.done/**
 
 # Python
 __pycache__/

out/.done/01.ok

@@ -0,0 +1,13 @@
+task: '01'
+status: ok
+config_file: C:/Projects/Public/LabDataStorageEvaluation/out/config/lab_config.yaml
+config_bytes: 5827
+seed: 20260711
+batches: 4
+wafers: 12
+coupons: 588
+friction_coupons: 480
+tracks: 1440
+cycle_rows: 1440000
+loop_points: 2880000
+xrf_points: 235200

out/.done/02.ok

@@ -0,0 +1,6 @@
+task: '02'
+status: ok
+process_flow_file: C:/Projects/Public/LabDataStorageEvaluation/out/report/process_flow.md
+process_flow_bytes: 4205
+diagrams: 6
+diagram_bytes: 2924

out/.done/03.ok

@@ -0,0 +1,11 @@
+task: '03'
+status: ok
+csv_root: C:/Projects/Public/LabDataStorageEvaluation/out/csv
+files: 8718
+total_rows: 4636776
+total_bytes: 148654472
+coupons: 588
+tracks: 1440
+cycle_rows: 1440000
+loop_points: 2880000
+xrf_points: 235200

out/.done/04.ok

@@ -0,0 +1,11 @@
+task: '04'
+status: ok
+full_files: 588
+full_bytes: 311300222
+hybrid_bytes: 1887322
+coupons: 588
+tracks: 1440
+cycle_rows: 1440000
+loop_points: 2880000
+proc_peak_rss_mb: 119.1
+proc_cpu_seconds: 19.1

out/.done/05.ok

@@ -0,0 +1,12 @@
+task: '05'
+status: ok
+db_file: C:/Projects/Public/LabDataStorageEvaluation/out/sqlite/tribo.db
+db_bytes: 123400192
+tables: 15
+total_rows: 4638223
+friction_cycles: 1440000
+friction_loop_points: 2880000
+tracks: 1440
+track_summary: 1440
+proc_peak_rss_mb: 323.0
+proc_cpu_seconds: 19.9

out/.done/06.ok

@@ -0,0 +1,18 @@
+task: '06'
+status: ok
+database: lab_data
+tables: 15
+total_rows: 4638223
+live_bytes: 397467648
+friction_cycles_bytes: 99753984
+friction_loop_points_bytes: 267796480
+copy_seconds: 19.8
+total_seconds: 23.0
+dump: skipped (pg_dump unavailable on this host)
+proc_peak_rss_mb: 58.6
+proc_cpu_seconds: 18.7
+host_cpu_avg_pct: 2.4
+host_cpu_max_pct: 3.7
+host_ram_used_baseline_mb: 617
+host_ram_used_peak_mb: 681
+host_ram_used_delta_mb: 64

out/.done/07.ok

@@ -0,0 +1,13 @@
+task: '07'
+status: ok
+triples: 17419713
+nt_gz_bytes: 126487650
+ttl_bytes: 596401229
+store_bytes: 1739414085
+store_load_seconds: 33.6
+coupons: 588
+tracks: 1440
+cycle_nodes: 1440000
+loop_nodes: 2880000
+proc_peak_rss_mb: 2185.2
+proc_cpu_seconds: 151.8

out/.done/08.ok

@@ -0,0 +1,19 @@
+task: '08'
+status: ok
+query_files: 56
+q1_rows: 1000
+q1_sha256: bb6d871275d0
+q2_rows: 33
+q2_sha256: 62ca30e729a8
+q3_rows: 480
+q3_sha256: a3a73414201f
+q4_rows: 469
+q4_sha256: 38281dcf7896
+q5_rows: 4
+q5_sha256: f3ee32dbc981
+q6_rows: 480
+q6_sha256: 9cc28d51ee35
+q7_rows: 2
+q7_sha256: 1991f8bf2217
+proc_peak_rss_mb: 61.1
+proc_cpu_seconds: 1.7

out/.done/09.ok

@@ -0,0 +1,14 @@
+task: '09'
+status: ok
+cells_total: 35
+cells_ok: 35
+cells_invalid: 0
+cells_timeout: 0
+cells_error: 0
+session_wall_s: 915.5
+cold_cache_pass: skipped (Windows host)
+session_host_cpu_avg_pct: 0.4
+session_host_cpu_max_pct: 9.2
+session_host_ram_used_baseline_mb: 909
+session_host_ram_used_peak_mb: 914
+session_host_ram_used_delta_mb: 5

out/.done/10.ok

@@ -0,0 +1,16 @@
+task: '10'
+status: ok
+extrapolation_rows: 105
+sizing_rows: 15
+flags_ok: 53
+flags_impractical: 35
+flags_fail: 17
+pg_index_share: 0.341
+pg_index_mb: 128.5
+prices_as_of: 2026-07-11
+note_pandas: pandas CSV variant not measured; its RAM is O(n) - infeasible above ~10 GB (spec 10)
+coeff_csv: 1.0
+coeff_json: 2.094
+coeff_sqlite: 0.83
+coeff_pg: 2.674
+coeff_rdf: 11.701

out/.done/11.ok

@@ -0,0 +1,12 @@
+task: '11'
+status: ok
+charts: 14
+tables: 5
+report_bytes: 16091
+winner_600gb: pg
+prices_as_of: 2026-07-11
+score600_csv: 28.9
+score600_json: 24.0
+score600_sqlite: 47.0
+score600_pg: 58.6
+score600_rdf: 0.9

out/config/hw_prices.yaml

@@ -0,0 +1,18 @@
+# Hardware cost parameters for extrapolation (task 10).
+# Street prices retrieved 2026-07-11 from the sources below (server DRAM is
+# in a documented 2025-2026 price surge - see market_context). The cost
+# model buys whole components: 64 GB RDIMM modules and 7.68 TB NVMe drives.
+# Operator-editable; re-run extrapolate.py after changes (code-config-yaml).
+as_of: "2026-07-11"
+ram_module_gb: 64
+ram_module_usd: 1887.0       # A-Tech 64GB (2x32GB) DDR5-5600 ECC RDIMM
+nvme_drive_tb: 7.68
+nvme_drive_usd: 3995.0       # Cloud Ninjas NEW 7.68TB NVMe U.2 1DWPD (Dell 14-16G)
+server_16_core_usd: 4618.0   # Supermicro AS-1015CS-TNR 1U (EPYC 9004/9005), Broadberry starting config
+server_32_core_usd: 6272.0   # Supermicro AS-1115CS-TNR 1U, Broadberry starting config
+extra_node_usd: 4618.0       # one additional entry 1U node (AS-1015CS-TNR chassis)
+sources:
+  ram: https://atechmemory.com/collections/ddr5-memory-ram
+  nvme: https://cloudninjas.com/products/new-7-68tb-nvme-u-2-1dwpd-sie-2-5-enterprise-solid-state-drive-for-14th-15th-16th-gen-dell
+  servers: https://www.broadberry.com/amd-epyc-9004-supermicro-servers
+  market_context: https://www.techpowerup.com/342331/server-dram-pricing-jumps-50-only-70-of-orders-getting-filled

out/config/lab_config.yaml

@@ -0,0 +1,246 @@
+# Generated by make_lab_config.py (task 01) from docs/specs/01_lab_configuration.md.
+# Do not hand-edit: regenerate via `python make_lab_config.py`.
+project: LabDataStorageEvaluation
+description: Simulated tribology laboratory (Sandia Pt-Au LDRD context)
+spec: docs/specs/01_lab_configuration.md
+seed: 20260711
+material_system:
+  substrate:
+    material: Ti-6Al-4V
+    dimensions_mm:
+    - 10
+    - 10
+    - 3
+  adhesion_layer:
+    material: Cr
+    process: sputtered
+  coating:
+    material: Pt-Au
+    deposition: composition gradient across each wafer
+    thickness_um_range:
+    - 0.3
+    - 1.1
+instruments:
+- instrument_id: rapid
+  role: friction
+  name: RAPID custom high-throughput parallelized 6-probe tribometer
+  data_produced: COF vs cycle per track; test conditions
+- instrument_id: ti980
+  role: nanoindentation
+  name: Bruker TI980 TriboIndenter
+  data_produced: hardness, reduced modulus (25 indents per coupon)
+- instrument_id: m4_tornado
+  role: composition
+  name: Bruker M4 Tornado micro-XRF
+  data_produced: Pt/Au wt% map per coupon (20x20 grid)
+- instrument_id: pvd200
+  role: deposition
+  name: Kurt J. Lesker PVD 200 sputter-down
+  data_produced: batch deposition parameters
+- instrument_id: afm
+  role: surface_roughness
+  name: AFM
+  data_produced: topography image metadata + Ra/Rq per coupon
+- instrument_id: profilometer
+  role: film_thickness
+  name: Optical profilometry
+  data_produced: thickness map per coupon (10x10 grid)
+- instrument_id: simtra
+  role: simulation
+  name: SIMTRA sputter transport Monte-Carlo
+  data_produced: deposition atom-energy / composition profiles per deposition run
+deposition_matrix:
+- batch_code: B721
+  pt_gun_tilt_deg: 20
+  au_gun_tilt_deg: 0
+  pt_power_W: 150
+  au_power_W: 50
+  pt_discharge_V: 432
+  au_discharge_V: 311
+- batch_code: B722
+  pt_gun_tilt_deg: 20
+  au_gun_tilt_deg: 20
+  pt_power_W: 100
+  au_power_W: 100
+  pt_discharge_V: 399
+  au_discharge_V: 352
+- batch_code: B723
+  pt_gun_tilt_deg: 20
+  au_gun_tilt_deg: 20
+  pt_power_W: 150
+  au_power_W: 50
+  pt_discharge_V: 430
+  au_discharge_V: 311
+- batch_code: B724
+  pt_gun_tilt_deg: 0
+  au_gun_tilt_deg: 20
+  pt_power_W: 50
+  au_power_W: 150
+  pt_discharge_V: 376
+  au_discharge_V: 340
+hierarchy:
+  batches: 4
+  wafers_per_batch: 3
+  coupon_grid_per_wafer:
+  - 7
+  - 7
+  coupons_per_wafer: 49
+friction_assignment:
+  friction_coupons_total: 480
+  reserve_coupons_total: 108
+  runs: 4
+  coupons_per_run: 120
+  plates_per_run: 5
+  probes_per_plate: 6
+  coupons_per_probe_square: 4
+  tracks_per_friction_coupon: 3
+  counterfaces_per_holder: 3
+  fresh_counterface_per_track: true
+  reserve_grid_positions:
+  - 1
+  - 4
+  - 7
+  - 22
+  - 25
+  - 28
+  - 43
+  - 46
+  - 49
+volumes:
+  coupons_total: 588
+  tracks_total: 1440
+  cycles_per_track: 1000
+  cycle_rows_total: 1440000
+  loop_every_n_cycles: 100
+  loops_per_track: 10
+  loop_points_per_loop: 200
+  loop_points_total: 2880000
+  xrf_grid:
+  - 20
+  - 20
+  xrf_points_per_coupon: 400
+  xrf_points_total: 235200
+  profilometry_grid:
+  - 10
+  - 10
+  profilometry_points_per_coupon: 100
+  nanoindentation_indents_per_coupon: 25
+  simtra_rows_per_batch: 1000
+runs:
+- run_code: R1
+  batch_code: B721
+  environment: lab_air
+  date: '2026-04-06'
+  operator: A. Reyes
+- run_code: R2
+  batch_code: B722
+  environment: lab_air
+  date: '2026-04-13'
+  operator: K. Patel
+- run_code: R3
+  batch_code: B723
+  environment: dry_n2
+  date: '2026-04-20'
+  operator: A. Reyes
+- run_code: R4
+  batch_code: B724
+  environment: dry_n2
+  date: '2026-04-27'
+  operator: M. Novak
+schedule:
+  deposition_start_date: '2026-03-02'
+  batch_interval_days: 7
+  characterization_lag_days: 3
+  run_start_time: 09:00:00
+  track_interval_s: 2100
+test_conditions:
+  normal_load_mN: 100
+  stroke_mm: 1.0
+  speed_mm_s: 1.0
+  counterface:
+    material: ruby (Al2O3)
+    diameter_mm: 3.175
+  rh_pct:
+    lab_air: 45
+    dry_n2: 2
+  temperature_C: 23
+  temperature_tolerance_C: 1
+physical_models:
+  au_gradient:
+    description: linear Au wt% gradient along wafer x, batch-dependent center
+    batch_center_wtpct:
+      B721: 8
+      B722: 25
+      B723: 10
+      B724: 60
+    wafer_span_wtpct: 5
+    xrf_noise_sd_wtpct: 0.3
+  cof_run_in:
+    formula: cof(c) = cof_ss + (cof_0 - cof_ss) * exp(-c / tau) + N(0, sigma)
+    cof_0_range:
+    - 0.35
+    - 0.5
+    tau_cycles_range:
+    - 100
+    - 400
+    noise_sd: 0.01
+  cof_steady_state:
+    formula: cof_ss = intercept + slope_per_au_wtpct * au_wtpct_mean, clamped to >= floor
+    lab_air:
+      intercept: 0.32
+      slope_per_au_wtpct: -0.0015
+    dry_n2:
+      intercept: 0.24
+      slope_per_au_wtpct: -0.0012
+    floor: 0.12
+  hardness_GPa:
+    formula: H = intercept + slope_per_au_wtpct * au_wtpct_mean + N(0, noise_sd)
+    intercept: 8.5
+    slope_per_au_wtpct: -0.05
+    noise_sd: 0.25
+  reduced_modulus_GPa:
+    formula: Er = intercept + slope_per_au_wtpct * au_wtpct_mean + N(0, noise_sd)
+    intercept: 190
+    slope_per_au_wtpct: -0.6
+    noise_sd: 4
+  roughness_ra_nm:
+    distribution: lognormal
+    median_nm: 5
+    sigma_log: 0.3
+    rq_over_ra: 1.25
+  thickness_um:
+    profile: radial parabolic across wafer plus noise
+    center_um: 1.05
+    edge_um: 0.35
+    noise_sd_um: 0.02
+    range_um:
+    - 0.3
+    - 1.1
+  wear_archard:
+    formula: V = k * F * s; k = k0 * (1 + slope_per_au_wtpct * au_wtpct_mean), lognormal noise, clamped
+      to >= k_floor
+    k0_mm3_per_N_m:
+      lab_air: 1.5e-07
+      dry_n2: 6.0e-08
+    slope_per_au_wtpct:
+      lab_air: -0.008
+      dry_n2: -0.01
+    k_floor_mm3_per_N_m: 1.0e-09
+    noise_sigma_log: 0.15
+  friction_loop:
+    force_noise_sd_mN: 0.3
+  nanoindentation:
+    max_load_mN: 10
+    indent_grid:
+    - 5
+    - 5
+    grid_pitch_um: 20
+  simtra:
+    angle_deg_range:
+    - 0
+    - 90
+    energy_eV_max: 50
+    surface_binding_energy_eV:
+      pt: 5.84
+      au: 3.81
+    flux_per_W: 0.02

out/report/REPORT.md

@@ -0,0 +1,318 @@
+# Laboratory Data Storage Format Evaluation - Final Report
+
+Generated by task 11 (report.py) from the measured benchmark matrix (task 09) and the extrapolation model (task 10). Every number at scales beyond the 150 MB corpus is a PROJECTION and is labeled as such; scaling assumptions are listed in section 6.
+
+## 1. Executive summary
+
+**Recommendation: PostgreSQL as the system of record.** The measured matrix and the projections confirm the expected outcome:
+
+- **PostgreSQL** is the only format whose seven benchmark queries stay below the 1-hour practicality bound at every projected scale (600 GB, 1.2 TB, 6 TB); at 6 TB it needs one 16-core node with 551 GB RAM at an estimated $33,586 (bill of materials, prices as of 2026-07-11). Partitioned parallel scans and the track_summary materialized view are the scaling levers.
+- **CSV** remains the canonical raw archive: byte-reproducible, instrument-native, and the best compressor (tar.gz ~2.8x); its full scans exceed 1 h beyond ~600 GB, so it is an archive, not a query layer.
+- **SQLite** is an excellent single-user store up to ~600 GB (all queries OK), then its single-threaded scans degrade (Q5/Q7 IMPRACTICAL at 1.2 TB).
+- **Hybrid JSON-LD** (metadata + sourceFile links, 1.8 MiB at 150 MB corpus) is the exchange format; the FULL variant re-reads the whole corpus per scan and becomes impractical past 600 GB.
+- **RDF (materialized triplestore)** fails at scale: 11.7x storage blow-up, 5 of 7 queries FAIL at 6 TB, and the hot set needs 13.7 TB RAM across 14 nodes (~$527,732 projected). Semantic access should be a virtual layer (e.g. Ontop OBDA) over PostgreSQL instead.
+
+## 2. Methodology snapshot
+
+35 cells (Q1-Q7 x 5 formats); per cell 1 warm-up + 3 measured runs in isolated subprocesses sampled with psutil at 50 ms; randomized cell order; 30-min timeout; every run validated against canonical results (PostgreSQL cross-validated with SQLite, tolerance 1e-9). Medians are reported; raw runs and min/max live in out/bench/results_raw.csv. The cold-cache pass is skipped on this Windows host and marked as such. PostgreSQL runs on a remote host; its wall times include the LAN round-trip, and server-side metrics come from pg_stat_statements and Prometheus (docs/rules/bench-methodology.md section 6).
+
+## 3. Environment
+
+```
+benchmark_host_os: Windows-2025Server-10.0.26100-SP0
+benchmark_host_cpu: Intel64 Family 6 Model 141 Stepping 1, GenuineIntel
+benchmark_host_cores_logical: 4
+benchmark_host_cores_physical: 4
+benchmark_host_ram_gib: 8.0
+python: 3.12.10
+benchmark_host_disks: VMware Virtual NVMe Disk / SSD / 100 GB
+sqlite: 3.49.1
+psycopg: 3.3.4
+pyoxigraph: 0.5.9
+ijson: 3.5.1
+psutil: 7.2.2
+postgresql_server: PostgreSQL 16.14 (Ubuntu 16.14-0ubuntu0.24.04.1) on x86_64-pc-linux-gnu, compiled by gcc (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0, 64-bit
+postgresql_host: 192.168.10.73 (remote; 4 cores / 3.8 GiB, see .done/06.ok)
+cold_cache_pass: skipped (Windows host, no page-cache drop - bench-methodology section 6)
+pg_backend_sampling: not possible for a remote server; Prometheus windows + pg_stat_statements deltas instead
+```
+
+## 4. Storage footprint
+
+| format | measured | vs CSV | archival (compressed) | projected @600 GB | projected @1.2 TB | projected @6 TB |
+|---|---|---|---|---|---|---|
+| CSV | 149 MB | 1.00x | 53 MB | 600 GB | 1.20 TB | 6.00 TB |
+| JSON-LD | 311 MB | 2.09x | 57 MB | 1.26 TB | 2.51 TB | 13 TB |
+| SQLite | 123 MB | 0.83x | 55 MB | 498 GB | 996 GB | 4.98 TB |
+| PostgreSQL | 397 MB | 2.67x | 53 MB | 1.60 TB | 3.21 TB | 16 TB |
+| RDF triplestore | 1.74 GB | 11.70x | 126 MB | 7.02 TB | 14 TB | 70 TB |
+
+![C1 - disk footprint](charts/c1_disk_footprint.png)
+
+## 5. Measured performance (150 MB corpus)
+
+| format | query | wall time | peak RSS | CPU util | read |
+|---|---|---|---|---|---|
+| CSV | q1 | 0.06 s | 4 MB | 0% | 0.0 MB |
+| CSV | q2 | 0.17 s | 20 MB | 16% | 2.5 MB |
+| CSV | q3 | 1.15 s | 21 MB | 24% | 31.8 MB |
+| CSV | q4 | 0.71 s | 21 MB | 22% | 16.8 MB |
+| CSV | q5 | 1.09 s | 21 MB | 23% | 31.8 MB |
+| CSV | q6 | 0.28 s | 20 MB | 17% | 1.2 MB |
+| CSV | q7 | 1.27 s | 21 MB | 23% | 32.5 MB |
+| JSON-LD | q1 | 0.11 s | 22 MB | 10% | 1.4 MB |
+| JSON-LD | q2 | 1.48 s | 24 MB | 24% | 53.1 MB |
+| JSON-LD | q3 | 9.94 s | 24 MB | 25% | 297.6 MB |
+| JSON-LD | q4 | 9.92 s | 24 MB | 25% | 297.8 MB |
+| JSON-LD | q5 | 9.96 s | 24 MB | 25% | 297.6 MB |
+| JSON-LD | q6 | 9.79 s | 24 MB | 24% | 297.8 MB |
+| JSON-LD | q7 | 10 s | 24 MB | 24% | 297.9 MB |
+| SQLite | q1 | 0.06 s | 4 MB | 0% | 0.0 MB |
+| SQLite | q2 | 0.06 s | 4 MB | 0% | 0.0 MB |
+| SQLite | q3 | 0.11 s | 4 MB | 0% | 0.0 MB |
+| SQLite | q4 | 0.06 s | 4 MB | 0% | 0.0 MB |
+| SQLite | q5 | 0.77 s | 25 MB | 23% | 117.9 MB |
+| SQLite | q6 | 0.06 s | 4 MB | 0% | 0.0 MB |
+| SQLite | q7 | 0.71 s | 25 MB | 23% | 93.0 MB |
+| PostgreSQL | q1 | 0.22 s | 42 MB | 18% | 4.1 MB |
+| PostgreSQL | q2 | 0.22 s | 42 MB | 20% | 4.1 MB |
+| PostgreSQL | q3 | 0.22 s | 42 MB | 18% | 4.1 MB |
+| PostgreSQL | q4 | 0.22 s | 42 MB | 18% | 4.1 MB |
+| PostgreSQL | q5 | 0.44 s | 42 MB | 10% | 4.1 MB |
+| PostgreSQL | q6 | 0.22 s | 42 MB | 19% | 4.1 MB |
+| PostgreSQL | q7 | 0.33 s | 42 MB | 12% | 4.1 MB |
+| RDF triplestore | q1 | 0.11 s | 32 MB | 17% | 3.6 MB |
+| RDF triplestore | q2 | 2.81 s | 85 MB | 24% | 375.6 MB |
+| RDF triplestore | q3 | 46 s | 264 MB | 25% | 5445.1 MB |
+| RDF triplestore | q4 | 20 s | 168 MB | 25% | 2694.6 MB |
+| RDF triplestore | q5 | 60 s | 264 MB | 25% | 5390.5 MB |
+| RDF triplestore | q6 | 0.17 s | 46 MB | 16% | 15.9 MB |
+| RDF triplestore | q7 | 41 s | 264 MB | 25% | 5380.5 MB |
+
+Sub-interval note: cells faster than the 50 ms sampling cadence (fast SQLite/CSV point reads) under-report client RSS/CPU; wall times are exact.
+
+![C2 - RAM requirement](charts/c2_ram_requirement.png)
+
+Per-query charts: [Q1](charts/c3_q1_wall_time.png), [Q2](charts/c3_q2_wall_time.png), [Q3](charts/c3_q3_wall_time.png), [Q4](charts/c3_q4_wall_time.png), [Q5](charts/c3_q5_wall_time.png), [Q6](charts/c3_q6_wall_time.png), [Q7](charts/c3_q7_wall_time.png)
+
+## 6. Projections (600 GB / 1.2 TB / 6 TB)
+
+All values in this section are projected, never measured. Laws per access pattern (spec 10): flat / index-depth log / linear result set / linear x depth / full scan / parallel partitioned scan; constants calibrated on the measured point after subtracting the per-format harness floor. Flags: IMPRACTICAL > 1 h, FAIL > 24 h.
+
+Projected wall times at 600 GB:
+
+| format | query | projected wall time | flag |
+|---|---|---|---|
+| CSV | q1 | 0.06 s | OK |
+| CSV | q2 | 7.1 min | OK |
+| CSV | q3 | 73.5 min | IMPRACTICAL |
+| CSV | q4 | 44.1 min | OK |
+| CSV | q5 | 69.6 min | IMPRACTICAL |
+| CSV | q6 | 14.5 min | OK |
+| CSV | q7 | 81.6 min | IMPRACTICAL |
+| JSON-LD | q1 | 0.11 s | OK |
+| JSON-LD | q2 | 92.0 min | IMPRACTICAL |
+| JSON-LD | q3 | 11.0 h | IMPRACTICAL |
+| JSON-LD | q4 | 11.0 h | IMPRACTICAL |
+| JSON-LD | q5 | 11.0 h | IMPRACTICAL |
+| JSON-LD | q6 | 10.9 h | IMPRACTICAL |
+| JSON-LD | q7 | 11.2 h | IMPRACTICAL |
+| SQLite | q1 | 0.06 s | OK |
+| SQLite | q2 | 1.27 s | OK |
+| SQLite | q3 | 5.7 min | OK |
+| SQLite | q4 | 0.06 s | OK |
+| SQLite | q5 | 47.5 min | OK |
+| SQLite | q6 | 5.18 s | OK |
+| SQLite | q7 | 43.7 min | OK |
+| PostgreSQL | q1 | 0.22 s | OK |
+| PostgreSQL | q2 | 0.22 s | OK |
+| PostgreSQL | q3 | 3.42 s | OK |
+| PostgreSQL | q4 | 11 s | OK |
+| PostgreSQL | q5 | 3.7 min | OK |
+| PostgreSQL | q6 | 4.06 s | OK |
+| PostgreSQL | q7 | 115 s | OK |
+| RDF triplestore | q1 | 0.11 s | OK |
+| RDF triplestore | q2 | 3.0 h | IMPRACTICAL |
+| RDF triplestore | q3 | 2.1 d | FAIL |
+| RDF triplestore | q4 | 22.1 h | IMPRACTICAL |
+| RDF triplestore | q5 | 2.8 d | FAIL |
+| RDF triplestore | q6 | 5.9 min | OK |
+| RDF triplestore | q7 | 45.3 h | FAIL |
+
+Degradation by data size: [point read](charts/c4_degradation_point_read.png), [indexed / join](charts/c4_degradation_indexed.png), [full scan](charts/c4_degradation_full_scan.png)
+
+## 7. Hardware sizing and cost at 600 GB (projected)
+
+Bill-of-materials costing with street prices as of **2026-07-11** (sources below). Every configuration buys whole components: 64 GB DDR5 ECC RDIMM modules, 7.68 TB enterprise NVMe U.2 drives, and a priced 1U chassis; disk capacity includes 30% free-space headroom.
+
+| format | configuration | chassis | RAM | disk | extra nodes | total |
+|---|---|---|---|---|---|---|
+| CSV | 1 x 1U Supermicro AS-1015CS-TNR (16 cores); 1 x 64 GB DDR5 ECC RDIMM; 1 x 7.68 TB NVMe U.2 | $4,618 | $1,887 | $3,995 | $0 | $10,500 |
+| JSON-LD | 1 x 1U Supermicro AS-1015CS-TNR (16 cores); 1 x 64 GB DDR5 ECC RDIMM; 1 x 7.68 TB NVMe U.2 | $4,618 | $1,887 | $3,995 | $0 | $10,500 |
+| SQLite | 1 x 1U Supermicro AS-1015CS-TNR (16 cores); 1 x 64 GB DDR5 ECC RDIMM; 1 x 7.68 TB NVMe U.2 | $4,618 | $1,887 | $3,995 | $0 | $10,500 |
+| PostgreSQL | 1 x 1U Supermicro AS-1015CS-TNR (16 cores); 1 x 64 GB DDR5 ECC RDIMM; 1 x 7.68 TB NVMe U.2 | $4,618 | $1,887 | $3,995 | $0 | $10,500 |
+| RDF triplestore | 2 x 1U Supermicro AS-1015CS-TNR (16 cores); 22 x 64 GB DDR5 ECC RDIMM; 2 x 7.68 TB NVMe U.2 | $4,618 | $41,514 | $7,990 | $4,618 | $58,740 |
+
+Component prices (retrieved 2026-07-11):
+
+- 64 GB DDR5-5600 ECC RDIMM (A-Tech, 2x32GB kit): $1,887 - <https://atechmemory.com/collections/ddr5-memory-ram>
+- 7.68 TB NVMe U.2 1DWPD enterprise SSD (Dell 14-16G compatible, Cloud Ninjas): $3,995 - <https://cloudninjas.com/products/new-7-68tb-nvme-u-2-1dwpd-sie-2-5-enterprise-solid-state-drive-for-14th-15th-16th-gen-dell>
+- 1U AMD EPYC 9004/9005 chassis (Broadberry starting configurations): Supermicro AS-1015CS-TNR $4,618, Supermicro AS-1115CS-TNR $6,272 - <https://www.broadberry.com/amd-epyc-9004-supermicro-servers>
+- Market context - server DRAM is in a documented 2025-2026 price surge: <https://www.techpowerup.com/342331/server-dram-pricing-jumps-50-only-70-of-orders-getting-filled>
+
+Full sizing at 1.2 TB and 6 TB: out/bench/hardware_sizing.csv. RDF exceeds the 1 TB single-node RAM ceiling already at 600 GB and reaches 14 nodes at 6 TB.
+
+![C6 - cost vs performance](charts/c6_cost_vs_performance.png)
+
+## 8. Weighted scoring
+
+Subscores are 10 x best/value per metric; weights: search x5, RAM economy x2, disk economy x1; max 80. Search uses the inverse geometric mean of Q1-Q7 (FAIL at 600 GB zeroes the search subscore). Left: measured scale; right: projected 600 GB.
+
+Measured scale (150 MB):
+
+| format | search (x5) | RAM (x2) | disk (x1) | total (max 80) |
+|---|---|---|---|---|
+| SQLite | 50.0 | 16.9 | 10.0 | 76.9 |
+| CSV | 15.5 | 20.0 | 8.3 | 43.8 |
+| PostgreSQL | 26.2 | 10.0 | 3.1 | 39.3 |
+| JSON-LD | 1.7 | 17.2 | 4.0 | 22.9 |
+| RDF triplestore | 1.3 | 1.6 | 0.7 | 3.6 |
+
+Projected at 600 GB:
+
+| format | search (x5) | RAM (x2) | disk (x1) | total (max 80) |
+|---|---|---|---|---|
+| PostgreSQL | 50.0 | 5.5 | 3.1 | 58.6 |
+| SQLite | 21.8 | 15.2 | 10.0 | 47.0 |
+| CSV | 0.6 | 20.0 | 8.3 | 28.9 |
+| JSON-LD | 0.1 | 20.0 | 4.0 | 24.0 |
+| RDF triplestore | 0.0 | 0.2 | 0.7 | 0.9 |
+
+![C5 - weighted score](charts/c5_weighted_score.png)
+
+## 9. Use-case mapping
+
+| Use case | Recommended format(s) |
+|---|---|
+| Interactive analysis (joins, aggregations) | PostgreSQL; SQLite acceptable single-user up to ~600 GB |
+| Report generation (repeated summaries) | PostgreSQL (track_summary materialized view) |
+| Search / filtering | PostgreSQL or SQLite (indexed); flat formats need full scans |
+| Archiving | CSV tree + tar.gz (canonical raw) plus pg_dump of the system of record |
+| Inter-lab exchange | Hybrid JSON-LD (metadata + sourceFile links to CSV) |
+| Semantic / ontology queries | Virtual RDF layer over PostgreSQL (e.g. Ontop OBDA), not a materialized triplestore |
+
+## 10. Limitations
+
+- Single-node measurements on one Windows host + one remote PostgreSQL host; no cluster or cloud variance.
+- The corpus is simulated (physically plausible models, fixed seed 20260711); real instrument data may have different value distributions, though volumes and shapes match the lab.
+- Extrapolation uses analytic laws calibrated on a single 150 MB point; no intermediate-scale validation runs were performed.
+- Client wall times include a per-format harness floor (interpreter start, imports, connection); the floor is assumed constant across scales. The cheapest cell of each format therefore projects flat.
+- The cold-cache matrix pass is skipped (no page-cache drop on Windows); all measured runs are warm-cache.
+- The pandas CSV variant was not measured; its RAM is O(n) and it is infeasible above roughly 10 GB (spec 10).
+- RDF numbers reflect the compact modeling and a client that derives run-in / steady-state from raw cycles; SPARQL-side aggregation engines could shift (not remove) the scan penalty.
+- Hardware prices are spot street prices retrieved 2026-07-11 during a documented server-DRAM price surge; re-cost by editing out/config/hw_prices.yaml and re-running tasks 10-11.
+
+## Appendix A - process flow diagrams (task 02)
+
+### D1 - Coupon assembly
+
+```mermaid
+flowchart LR
+    A([Ti-6Al-4V Base 10x10x3 mm]) --> B[Cleaning]
+    B --> B1([Rinsed in deionized water])
+    B1 --> B2([Sonicated in cleaning solution])
+    B --> C[Smearing Adhesive]
+    C --> C1([Cr adhesive coating])
+    C --> D[Vapor Deposition System<br/>Kurt J. Lesker PVD 200]
+    D --> D1([PtAu sputter coating, gradient])
+    D --> E([Test Coupon])
+```
+
+### D2 - Characterization and batch assembly
+
+```mermaid
+flowchart LR
+    TC([Test Coupon]) --> S[SIMTRA simulation<br/>composition / atom energies]
+    S --> OP[Optical profilometry<br/>film thickness 0.3-1.1 um]
+    OP --> TW[Assemble Test Wafer<br/>x49 coupons]
+    TW --> TB[Assemble Test Batch<br/>x3 wafers]
+    TB --> B721[B721<br/>Pt 150 W / Au 50 W]
+    TB --> B722[B722<br/>Pt 100 W / Au 100 W]
+    TB --> B723[B723<br/>Pt 150 W / Au 50 W]
+    TB --> B724[B724<br/>Pt 50 W / Au 150 W]
+```
+
+### D3 - Testing tree
+
+```mermaid
+flowchart TD
+    TC([Test Coupon]) --> F[Friction<br/>RAPID 6-probe tribometer]
+    F --> FA([Lab Air -> COF dataset mu_normal])
+    F --> FN([Dry N2 -> COF dataset mu_dry_nit])
+    TC --> NI[Nanoindentation<br/>Bruker TI980]
+    NI --> NIR([Hardness, reduced modulus<br/>25 indents per coupon])
+    TC --> AF[AFM]
+    AF --> AFR([Topography -> Ra / Rq])
+    TC --> XR[micro-XRF<br/>Bruker M4 Tornado]
+    XR --> XRR([Pt/Au wt% map, 20x20 grid])
+```
+
+### D4 - Tribometer session sequence
+
+```mermaid
+sequenceDiagram
+    actor Op as Operator
+    participant Prep as Sample Prep
+    participant Plan as Excel Test Plan
+    participant SW as Control Software
+    participant TR as RAPID Tribometer
+
+    Op->>Prep: Request test
+    Op->>Prep: Get samples
+    Op->>Prep: Load samples onto plates
+    Op->>Prep: Load ball holders (3 counterfaces per holder)
+    Op->>Plan: Create test plan<br/>(Sample Plate, Plate Location, Sample ID, Save Location,<br/>Folder Name, X/Y/Z Offset, Load, Iterations)
+    Op->>TR: Transfer plates to tribometer
+    Op->>TR: Set up platter
+    Op->>SW: Activate software
+    Op->>SW: Load plan
+    SW->>TR: Activate tribometer
+    TR-->>SW: Run reciprocating tests (execution loop, see D5)
+    Op->>SW: Software stop
+    SW-->>Op: Save avg files
+    Op->>TR: Remove plates and platters
+    Op->>SW: Close software
+    Op->>TR: Pull equipment out
+```
+
+### D5 - Execution loop
+
+```mermaid
+flowchart TD
+    L[Load all counterfaces] --> P{5 plates}
+    P -->|for each plate| PR{6 probes in parallel}
+    PR -->|for each probe| C{4 coupons on coupon square}
+    C -->|for each coupon| T[Draw track]
+    T --> RC[Rotate counterface - fresh ball per track]
+    RC -->|3 tracks per coupon| T
+    T --> DONE([120 coupons x 3 tracks = 360 tracks per run])
+```
+
+### D6 - Data hierarchy
+
+```mermaid
+erDiagram
+    DEPOSITION_RUN ||--|| SIMTRA_PROFILE : produces
+    DEPOSITION_RUN ||--|| BATCH : creates
+    BATCH ||--|{ WAFER : contains
+    WAFER ||--|{ COUPON : contains
+    COUPON ||--|| XRF_MAP : has
+    COUPON ||--|| NANOINDENTATION : has
+    COUPON ||--|| AFM : has
+    COUPON ||--|| PROFILOMETRY : has
+    COUPON ||--o{ TRACK : "friction coupons only"
+    TRACK ||--|{ CYCLE : has
+    TRACK ||--|{ LOOP_POINT : has
+    TRACK ||--|| WEAR : has
+```
+

out/report/diagrams/D1.mermaid

@@ -0,0 +1,9 @@
+flowchart LR
+    A([Ti-6Al-4V Base 10x10x3 mm]) --> B[Cleaning]
+    B --> B1([Rinsed in deionized water])
+    B1 --> B2([Sonicated in cleaning solution])
+    B --> C[Smearing Adhesive]
+    C --> C1([Cr adhesive coating])
+    C --> D[Vapor Deposition System<br/>Kurt J. Lesker PVD 200]
+    D --> D1([PtAu sputter coating, gradient])
+    D --> E([Test Coupon])

out/report/diagrams/D2.mermaid

@@ -0,0 +1,9 @@
+flowchart LR
+    TC([Test Coupon]) --> S[SIMTRA simulation<br/>composition / atom energies]
+    S --> OP[Optical profilometry<br/>film thickness 0.3-1.1 um]
+    OP --> TW[Assemble Test Wafer<br/>x49 coupons]
+    TW --> TB[Assemble Test Batch<br/>x3 wafers]
+    TB --> B721[B721<br/>Pt 150 W / Au 50 W]
+    TB --> B722[B722<br/>Pt 100 W / Au 100 W]
+    TB --> B723[B723<br/>Pt 150 W / Au 50 W]
+    TB --> B724[B724<br/>Pt 50 W / Au 150 W]

out/report/diagrams/D3.mermaid

@@ -0,0 +1,10 @@
+flowchart TD
+    TC([Test Coupon]) --> F[Friction<br/>RAPID 6-probe tribometer]
+    F --> FA([Lab Air -> COF dataset mu_normal])
+    F --> FN([Dry N2 -> COF dataset mu_dry_nit])
+    TC --> NI[Nanoindentation<br/>Bruker TI980]
+    NI --> NIR([Hardness, reduced modulus<br/>25 indents per coupon])
+    TC --> AF[AFM]
+    AF --> AFR([Topography -> Ra / Rq])
+    TC --> XR[micro-XRF<br/>Bruker M4 Tornado]
+    XR --> XRR([Pt/Au wt% map, 20x20 grid])

out/report/diagrams/D4.mermaid

@@ -0,0 +1,23 @@
+sequenceDiagram
+    actor Op as Operator
+    participant Prep as Sample Prep
+    participant Plan as Excel Test Plan
+    participant SW as Control Software
+    participant TR as RAPID Tribometer
+
+    Op->>Prep: Request test
+    Op->>Prep: Get samples
+    Op->>Prep: Load samples onto plates
+    Op->>Prep: Load ball holders (3 counterfaces per holder)
+    Op->>Plan: Create test plan<br/>(Sample Plate, Plate Location, Sample ID, Save Location,<br/>Folder Name, X/Y/Z Offset, Load, Iterations)
+    Op->>TR: Transfer plates to tribometer
+    Op->>TR: Set up platter
+    Op->>SW: Activate software
+    Op->>SW: Load plan
+    SW->>TR: Activate tribometer
+    TR-->>SW: Run reciprocating tests (execution loop, see D5)
+    Op->>SW: Software stop
+    SW-->>Op: Save avg files
+    Op->>TR: Remove plates and platters
+    Op->>SW: Close software
+    Op->>TR: Pull equipment out

out/report/diagrams/D5.mermaid

@@ -0,0 +1,8 @@
+flowchart TD
+    L[Load all counterfaces] --> P{5 plates}
+    P -->|for each plate| PR{6 probes in parallel}
+    PR -->|for each probe| C{4 coupons on coupon square}
+    C -->|for each coupon| T[Draw track]
+    T --> RC[Rotate counterface - fresh ball per track]
+    RC -->|3 tracks per coupon| T
+    T --> DONE([120 coupons x 3 tracks = 360 tracks per run])

out/report/diagrams/D6.mermaid

@@ -0,0 +1,13 @@
+erDiagram
+    DEPOSITION_RUN ||--|| SIMTRA_PROFILE : produces
+    DEPOSITION_RUN ||--|| BATCH : creates
+    BATCH ||--|{ WAFER : contains
+    WAFER ||--|{ COUPON : contains
+    COUPON ||--|| XRF_MAP : has
+    COUPON ||--|| NANOINDENTATION : has
+    COUPON ||--|| AFM : has
+    COUPON ||--|| PROFILOMETRY : has
+    COUPON ||--o{ TRACK : "friction coupons only"
+    TRACK ||--|{ CYCLE : has
+    TRACK ||--|{ LOOP_POINT : has
+    TRACK ||--|| WEAR : has

out/report/process_flow.md

@@ -0,0 +1,127 @@
+# Process Flow - Simulated Tribology Laboratory
+
+Generated by make_process_flow.py (task 02) from out/config/lab_config.yaml.
+Standalone diagram sources: ./diagrams/D1..D6.mermaid.
+
+## D1 - Coupon Assembly
+
+Substrate preparation, adhesion layer, and gradient Pt-Au sputter deposition.
+
+```mermaid
+flowchart LR
+    A([Ti-6Al-4V Base 10x10x3 mm]) --> B[Cleaning]
+    B --> B1([Rinsed in deionized water])
+    B1 --> B2([Sonicated in cleaning solution])
+    B --> C[Smearing Adhesive]
+    C --> C1([Cr adhesive coating])
+    C --> D[Vapor Deposition System<br/>Kurt J. Lesker PVD 200]
+    D --> D1([PtAu sputter coating, gradient])
+    D --> E([Test Coupon])
+```
+
+## D2 - Characterization and Batch Assembly
+
+Per-coupon simulation and thickness characterization, then assembly into wafers (x49 coupons) and batches (x3 wafers), deposited per the parameter table below.
+
+```mermaid
+flowchart LR
+    TC([Test Coupon]) --> S[SIMTRA simulation<br/>composition / atom energies]
+    S --> OP[Optical profilometry<br/>film thickness 0.3-1.1 um]
+    OP --> TW[Assemble Test Wafer<br/>x49 coupons]
+    TW --> TB[Assemble Test Batch<br/>x3 wafers]
+    TB --> B721[B721<br/>Pt 150 W / Au 50 W]
+    TB --> B722[B722<br/>Pt 100 W / Au 100 W]
+    TB --> B723[B723<br/>Pt 150 W / Au 50 W]
+    TB --> B724[B724<br/>Pt 50 W / Au 150 W]
+```
+
+Deposition matrix:
+
+| Batch | Pt:Au gun tilt | Pt power W | Au power W | Pt discharge V | Au discharge V |
+|---|---|---|---|---|---|
+| B721 | 20:0 deg | 150 | 50 | 432 | 311 |
+| B722 | 20:20 deg | 100 | 100 | 399 | 352 |
+| B723 | 20:20 deg | 150 | 50 | 430 | 311 |
+| B724 | 0:20 deg | 50 | 150 | 376 | 340 |
+
+## D3 - Testing Tree
+
+The four characterization/testing paths every coupon can take.
+
+```mermaid
+flowchart TD
+    TC([Test Coupon]) --> F[Friction<br/>RAPID 6-probe tribometer]
+    F --> FA([Lab Air -> COF dataset mu_normal])
+    F --> FN([Dry N2 -> COF dataset mu_dry_nit])
+    TC --> NI[Nanoindentation<br/>Bruker TI980]
+    NI --> NIR([Hardness, reduced modulus<br/>25 indents per coupon])
+    TC --> AF[AFM]
+    AF --> AFR([Topography -> Ra / Rq])
+    TC --> XR[micro-XRF<br/>Bruker M4 Tornado]
+    XR --> XRR([Pt/Au wt% map, 20x20 grid])
+```
+
+## D4 - Tribometer Session Sequence
+
+Operator workflow for one RAPID tribometer session, from test request to teardown.
+
+```mermaid
+sequenceDiagram
+    actor Op as Operator
+    participant Prep as Sample Prep
+    participant Plan as Excel Test Plan
+    participant SW as Control Software
+    participant TR as RAPID Tribometer
+
+    Op->>Prep: Request test
+    Op->>Prep: Get samples
+    Op->>Prep: Load samples onto plates
+    Op->>Prep: Load ball holders (3 counterfaces per holder)
+    Op->>Plan: Create test plan<br/>(Sample Plate, Plate Location, Sample ID, Save Location,<br/>Folder Name, X/Y/Z Offset, Load, Iterations)
+    Op->>TR: Transfer plates to tribometer
+    Op->>TR: Set up platter
+    Op->>SW: Activate software
+    Op->>SW: Load plan
+    SW->>TR: Activate tribometer
+    TR-->>SW: Run reciprocating tests (execution loop, see D5)
+    Op->>SW: Software stop
+    SW-->>Op: Save avg files
+    Op->>TR: Remove plates and platters
+    Op->>SW: Close software
+    Op->>TR: Pull equipment out
+```
+
+## D5 - Execution Loop
+
+Nested iteration executed by the tribometer within one run.
+
+```mermaid
+flowchart TD
+    L[Load all counterfaces] --> P{5 plates}
+    P -->|for each plate| PR{6 probes in parallel}
+    PR -->|for each probe| C{4 coupons on coupon square}
+    C -->|for each coupon| T[Draw track]
+    T --> RC[Rotate counterface - fresh ball per track]
+    RC -->|3 tracks per coupon| T
+    T --> DONE([120 coupons x 3 tracks = 360 tracks per run])
+```
+
+## D6 - Data Hierarchy
+
+Entity containment and per-entity measurement datasets (ERD-style).
+
+```mermaid
+erDiagram
+    DEPOSITION_RUN ||--|| SIMTRA_PROFILE : produces
+    DEPOSITION_RUN ||--|| BATCH : creates
+    BATCH ||--|{ WAFER : contains
+    WAFER ||--|{ COUPON : contains
+    COUPON ||--|| XRF_MAP : has
+    COUPON ||--|| NANOINDENTATION : has
+    COUPON ||--|| AFM : has
+    COUPON ||--|| PROFILOMETRY : has
+    COUPON ||--o{ TRACK : "friction coupons only"
+    TRACK ||--|{ CYCLE : has
+    TRACK ||--|{ LOOP_POINT : has
+    TRACK ||--|| WEAR : has
+```

out/report/tables/t1_storage_footprint.csv

@@ -0,0 +1,6 @@
+format,measured,vs CSV,archival (compressed),projected @600 GB,projected @1.2 TB,projected @6 TB
+CSV,149 MB,1.00x,53 MB,600 GB,1.20 TB,6.00 TB
+JSON-LD,311 MB,2.09x,57 MB,1.26 TB,2.51 TB,13 TB
+SQLite,123 MB,0.83x,55 MB,498 GB,996 GB,4.98 TB
+PostgreSQL,397 MB,2.67x,53 MB,1.60 TB,3.21 TB,16 TB
+RDF triplestore,1.74 GB,11.70x,126 MB,7.02 TB,14 TB,70 TB

out/report/tables/t2_measured_medians.csv

@@ -0,0 +1,36 @@
+format,query,wall time,peak RSS,CPU util,read
+CSV,q1,0.06 s,4 MB,0%,0.0 MB
+CSV,q2,0.17 s,20 MB,16%,2.5 MB
+CSV,q3,1.15 s,21 MB,24%,31.8 MB
+CSV,q4,0.71 s,21 MB,22%,16.8 MB
+CSV,q5,1.09 s,21 MB,23%,31.8 MB
+CSV,q6,0.28 s,20 MB,17%,1.2 MB
+CSV,q7,1.27 s,21 MB,23%,32.5 MB
+JSON-LD,q1,0.11 s,22 MB,10%,1.4 MB
+JSON-LD,q2,1.48 s,24 MB,24%,53.1 MB
+JSON-LD,q3,9.94 s,24 MB,25%,297.6 MB
+JSON-LD,q4,9.92 s,24 MB,25%,297.8 MB
+JSON-LD,q5,9.96 s,24 MB,25%,297.6 MB
+JSON-LD,q6,9.79 s,24 MB,24%,297.8 MB
+JSON-LD,q7,10 s,24 MB,24%,297.9 MB
+SQLite,q1,0.06 s,4 MB,0%,0.0 MB
+SQLite,q2,0.06 s,4 MB,0%,0.0 MB
+SQLite,q3,0.11 s,4 MB,0%,0.0 MB
+SQLite,q4,0.06 s,4 MB,0%,0.0 MB
+SQLite,q5,0.77 s,25 MB,23%,117.9 MB
+SQLite,q6,0.06 s,4 MB,0%,0.0 MB
+SQLite,q7,0.71 s,25 MB,23%,93.0 MB
+PostgreSQL,q1,0.22 s,42 MB,18%,4.1 MB
+PostgreSQL,q2,0.22 s,42 MB,20%,4.1 MB
+PostgreSQL,q3,0.22 s,42 MB,18%,4.1 MB
+PostgreSQL,q4,0.22 s,42 MB,18%,4.1 MB
+PostgreSQL,q5,0.44 s,42 MB,10%,4.1 MB
+PostgreSQL,q6,0.22 s,42 MB,19%,4.1 MB
+PostgreSQL,q7,0.33 s,42 MB,12%,4.1 MB
+RDF triplestore,q1,0.11 s,32 MB,17%,3.6 MB
+RDF triplestore,q2,2.81 s,85 MB,24%,375.6 MB
+RDF triplestore,q3,46 s,264 MB,25%,5445.1 MB
+RDF triplestore,q4,20 s,168 MB,25%,2694.6 MB
+RDF triplestore,q5,60 s,264 MB,25%,5390.5 MB
+RDF triplestore,q6,0.17 s,46 MB,16%,15.9 MB
+RDF triplestore,q7,41 s,264 MB,25%,5380.5 MB

out/report/tables/t3_projected_600gb.csv

@@ -0,0 +1,36 @@
+format,query,projected wall time,flag
+CSV,q1,0.06 s,OK
+CSV,q2,7.1 min,OK
+CSV,q3,73.5 min,IMPRACTICAL
+CSV,q4,44.1 min,OK
+CSV,q5,69.6 min,IMPRACTICAL
+CSV,q6,14.5 min,OK
+CSV,q7,81.6 min,IMPRACTICAL
+JSON-LD,q1,0.11 s,OK
+JSON-LD,q2,92.0 min,IMPRACTICAL
+JSON-LD,q3,11.0 h,IMPRACTICAL
+JSON-LD,q4,11.0 h,IMPRACTICAL
+JSON-LD,q5,11.0 h,IMPRACTICAL
+JSON-LD,q6,10.9 h,IMPRACTICAL
+JSON-LD,q7,11.2 h,IMPRACTICAL
+SQLite,q1,0.06 s,OK
+SQLite,q2,1.27 s,OK
+SQLite,q3,5.7 min,OK
+SQLite,q4,0.06 s,OK
+SQLite,q5,47.5 min,OK
+SQLite,q6,5.18 s,OK
+SQLite,q7,43.7 min,OK
+PostgreSQL,q1,0.22 s,OK
+PostgreSQL,q2,0.22 s,OK
+PostgreSQL,q3,3.42 s,OK
+PostgreSQL,q4,11 s,OK
+PostgreSQL,q5,3.7 min,OK
+PostgreSQL,q6,4.06 s,OK
+PostgreSQL,q7,115 s,OK
+RDF triplestore,q1,0.11 s,OK
+RDF triplestore,q2,3.0 h,IMPRACTICAL
+RDF triplestore,q3,2.1 d,FAIL
+RDF triplestore,q4,22.1 h,IMPRACTICAL
+RDF triplestore,q5,2.8 d,FAIL
+RDF triplestore,q6,5.9 min,OK
+RDF triplestore,q7,45.3 h,FAIL

out/report/tables/t4_hardware_600gb.csv

@@ -0,0 +1,6 @@
+format,configuration,chassis,RAM,disk,extra nodes,total
+CSV,1 x 1U Supermicro AS-1015CS-TNR (16 cores); 1 x 64 GB DDR5 ECC RDIMM; 1 x 7.68 TB NVMe U.2,"$4,618","$1,887","$3,995",$0,"$10,500"
+JSON-LD,1 x 1U Supermicro AS-1015CS-TNR (16 cores); 1 x 64 GB DDR5 ECC RDIMM; 1 x 7.68 TB NVMe U.2,"$4,618","$1,887","$3,995",$0,"$10,500"
+SQLite,1 x 1U Supermicro AS-1015CS-TNR (16 cores); 1 x 64 GB DDR5 ECC RDIMM; 1 x 7.68 TB NVMe U.2,"$4,618","$1,887","$3,995",$0,"$10,500"
+PostgreSQL,1 x 1U Supermicro AS-1015CS-TNR (16 cores); 1 x 64 GB DDR5 ECC RDIMM; 1 x 7.68 TB NVMe U.2,"$4,618","$1,887","$3,995",$0,"$10,500"
+RDF triplestore,2 x 1U Supermicro AS-1015CS-TNR (16 cores); 22 x 64 GB DDR5 ECC RDIMM; 2 x 7.68 TB NVMe U.2,"$4,618","$41,514","$7,990","$4,618","$58,740"

out/report/tables/t5_weighted_scores.csv

@@ -0,0 +1,11 @@
+scale,format,search_pts,ram_pts,disk_pts,total
+measured,CSV,15.5,20.0,8.3,43.8
+measured,JSON-LD,1.7,17.2,4.0,22.9
+measured,SQLite,50.0,16.9,10.0,76.9
+measured,PostgreSQL,26.2,10.0,3.1,39.3
+measured,RDF triplestore,1.3,1.6,0.7,3.6
+projected_600gb,CSV,0.6,20.0,8.3,28.9
+projected_600gb,JSON-LD,0.1,20.0,4.0,24.0
+projected_600gb,SQLite,21.8,15.2,10.0,47.0
+projected_600gb,PostgreSQL,50.0,5.5,3.1,58.6
+projected_600gb,RDF triplestore,0.0,0.2,0.7,0.9