Dataset Viewer
Auto-converted to Parquet Duplicate
id
stringlengths
64
64
messages
listlengths
3
3
metadata
dict
schema_version
stringclasses
1 value
c7619ec45eeaaea5cade9d2e30c26838824f025532210e72c5949a1e5865e211
[ { "content": "You are a cold-chain dispatch coordinator. Return a JSON dispatch plan with simulation-derived metrics; never claim unproven optimality or food-safety clearance.", "role": "system" }, { "content": "Coordinate cold-zone dispatch for this warehouse. Temperatures are Celsius, time minutes...
{ "augmentation_variant": "normal", "base_case_id": "7778ad75091616f6502bdff98a517eb40b7b169a8f50d15eac21805d9dc0637e", "baseline_config": { "ambient_c": 22, "augmentation_variant": "normal", "coordinate_scale_m": 1, "dispatch_xy": [ 66, -29 ], "disruptions": [], "duration_...
stage1-v1
471a8462e998008c12d3d494947a7bb5b0130a931a7236e250af0644513822cc
[ { "content": "You are a cold-chain dispatch coordinator. Return a JSON dispatch plan with simulation-derived metrics; never claim unproven optimality or food-safety clearance.", "role": "system" }, { "content": "Coordinate cold-zone dispatch for this warehouse. Temperatures are Celsius, time minutes...
{ "augmentation_variant": "near_expiry", "base_case_id": "7778ad75091616f6502bdff98a517eb40b7b169a8f50d15eac21805d9dc0637e", "baseline_config": { "ambient_c": 22, "augmentation_variant": "near_expiry", "coordinate_scale_m": 1, "dispatch_xy": [ 66, -29 ], "disruptions": [], ...
stage1-v1
d8ea8028e36b35651a2fab4969ea93ee462b9cf5663f244dbe25e3a6b0d16dbd
[ { "content": "You are a cold-chain dispatch coordinator. Return a JSON dispatch plan with simulation-derived metrics; never claim unproven optimality or food-safety clearance.", "role": "system" }, { "content": "Coordinate cold-zone dispatch for this warehouse. Temperatures are Celsius, time minutes...
{ "augmentation_variant": "sensor_drift", "base_case_id": "7778ad75091616f6502bdff98a517eb40b7b169a8f50d15eac21805d9dc0637e", "baseline_config": { "ambient_c": 22, "augmentation_variant": "sensor_drift", "coordinate_scale_m": 1, "dispatch_xy": [ 66, -29 ], "disruptions": [ ...
stage1-v1
5f13ee4bd46bd0bf54c7db2e93651219d7165b6a0f42c784a183ee69e8017929
[{"content":"You are a cold-chain dispatch coordinator. Return a JSON dispatch plan with simulation-(...TRUNCATED)
{"augmentation_variant":"disruption","base_case_id":"7778ad75091616f6502bdff98a517eb40b7b169a8f50d15(...TRUNCATED)
stage1-v1
f3fee22cedfa826cb7d81f2c17e959ff6f78847481e18cdc28a9be240983049d
[{"content":"You are a cold-chain dispatch coordinator. Return a JSON dispatch plan with simulation-(...TRUNCATED)
{"augmentation_variant":"normal","base_case_id":"3fbf4e1bd03794aa2a290d1214e50aa54562635cb59fda39b61(...TRUNCATED)
stage1-v1
6ce0c7d95bcde8933ff74c8351a01cb7770b34d51b3d2f205007a16578c0fad2
[{"content":"You are a cold-chain dispatch coordinator. Return a JSON dispatch plan with simulation-(...TRUNCATED)
{"augmentation_variant":"near_expiry","base_case_id":"3fbf4e1bd03794aa2a290d1214e50aa54562635cb59fda(...TRUNCATED)
stage1-v1
05f4e0e6cf1d6c99240a3486561faf6f4cc13c421c4920e1c09e353c3df299c6
[{"content":"You are a cold-chain dispatch coordinator. Return a JSON dispatch plan with simulation-(...TRUNCATED)
{"augmentation_variant":"sensor_drift","base_case_id":"3fbf4e1bd03794aa2a290d1214e50aa54562635cb59fd(...TRUNCATED)
stage1-v1
64073dd7176b17e82dbace04a9f777ae910558e0831962dadf8dbc2c7b0680e2
[{"content":"You are a cold-chain dispatch coordinator. Return a JSON dispatch plan with simulation-(...TRUNCATED)
{"augmentation_variant":"disruption","base_case_id":"3fbf4e1bd03794aa2a290d1214e50aa54562635cb59fda3(...TRUNCATED)
stage1-v1
d75c362a82b2d9208897bf468860d7a65b295966eb464bb5ee16ebe022687652
[{"content":"You are a cold-chain dispatch coordinator. Return a JSON dispatch plan with simulation-(...TRUNCATED)
{"augmentation_variant":"normal","base_case_id":"7b245124080a44a31e11a27c98a1f6b2c502ada03aa2baaa076(...TRUNCATED)
stage1-v1
4828b2d07f828b8e2cc0ac67ee58c43b2bbd06b0293f0fd8d7303a18b506a36e
[{"content":"You are a cold-chain dispatch coordinator. Return a JSON dispatch plan with simulation-(...TRUNCATED)
{"augmentation_variant":"near_expiry","base_case_id":"7b245124080a44a31e11a27c98a1f6b2c502ada03aa2ba(...TRUNCATED)
stage1-v1
End of preview. Expand in Data Studio

Phase 1 Cold-Chain Warehouse Dispatch

This export contains 4,000 simulation-labeled examples, built from 1,000 source picking-wave cohorts × four scenario variants.

Split Examples JSONL CSV
Train 3,192 train.jsonl train.csv
Validation 380 validation.jsonl validation.csv
Test 428 test.jsonl test.csv

CSV and JSONL were exported as alternative representations of the same examples, not separate datasets. manifest.json records the original file checksums, counts, run fingerprint, and validation summary. A locally edited file may no longer match that manifest; compare its checksum before using it as the original export.

Dataset description

This English instruction/response dataset pairs warehouse states with structured JSON dispatch plans. It combines real footwear picking workloads with synthetic produce inventory, literature-conditioned shelf-life models and simulated thermal disruptions. The reference answers are generated by exhaustive search with a deterministic simulator. This release uses schema stage1-v1.

Full Code: https://github.com/MeRichard123/Dynamic_FEFO_Cold-Zone_Dispatch

Intended uses

  • Supervised fine-tuning for warehouse-state-to-JSON dispatch generation.
  • Zero-shot and few-shot research on constrained picking and temperature decisions.
  • Evaluation against reproducible simulation actions and outcomes, with source workload cohorts kept separate across training and evaluation.

Direct deployment for refrigeration control, food-safety clearance or claims of measured waste reduction is outside the dataset's validated scope. There are no reported trained-model results or leaderboard scores for this release.

Dataset structure and fields

Each JSONL line is one object:

Field Type Meaning
id string SHA-256 fingerprint of the input prompt and schema
schema_version string stage1-v1
messages list of role/content objects System instructions, user warehouse task, assistant reference JSON
metadata object Source lineage, solver status, baseline metrics and replay configurations

The user message contains prose followed by separate JSON blocks for warehouse state, decision domain and objective weights. The assistant's content is a JSON-encoded string, not an already parsed object. Parse it with json.loads. Its keys are dispatch_plan, optimization_status, kg_food_saved, food_saved_baseline and metrics. dispatch_plan contains put_away, pick_priorities, chiller_adjustments, alerts and execution.

CSV columns are id, schema_version, system, input, output, variant, kg_food_saved, optimization_status and metadata_json. The last column is JSON-encoded audit metadata. Numerical units are Celsius, minutes, kg, kWh, kg CO2 and reference-temperature remaining-life hours as specified in the prompt.

Loading a local example

This dependency-free example loads the original JSONL without inferring a nested Arrow schema for the heterogeneous replay metadata:

import json
from pathlib import Path

with Path("dataset/train.jsonl").open(encoding="utf-8") as stream:
    example = json.loads(next(stream))

prompt = [m for m in example["messages"] if m["role"] != "assistant"]
ground_truth = json.loads(next(
    m["content"] for m in example["messages"] if m["role"] == "assistant"
))
print(json.dumps(ground_truth, indent=2))

When running from the dataset directory itself, use train.jsonl instead of dataset/train.jsonl.

Sources used in this export

Warehouse layout and picking workloads

Rodrigo Furlan de Assis (2024), Order Picking Dataset from a Warehouse of a Footwear Manufacturing Company, Mendeley Data, version 1, DOI: 10.17632/pf2w725pw3.1. The accompanying article is de Assis, de Paula Ferreira and Ouhimmou (2025), Data in Brief 61, 111837, DOI: 10.1016/j.dib.2025.111837.

The local input is Order Picking Dataset from a Warehouse of a Footwear Manufacturing Company.zip in the repository root. The pipeline reads Storage_Location.csv for coordinates, Picking_Wave.csv for picks, and Customer_Order.csv for wave dates. The archive contains 2,292 storage slots, 215,192 picking rows and 9,707 waves. Of those waves, 9,143 contain storage-location picks and 564 are ineligible for this build.

These are footwear operations. Produce identities, mass conversion, stock ages, thermal zones and food-quality behavior were added by this project; the source contains no measured produce spoilage outcomes.

Fruit shelf-life parameters

Zou et al. (2025), DOI: 10.1016/j.jfoodeng.2025.112577, with the supplied supplement 1-s2.0-S0260877425001128-mmc1.docx.

Product Evidence used Simulation model
Apples Supplement S8: b* shelf-life endpoints, 240/171/78/36 days at 0/5/15/25 °C Linear interpolation of reciprocal lifetime (quality-loss rate)
Strawberries Supplement S5: 18/11.1/7/4.2/2.8 days at 4/10/15/20/25 °C Linear interpolation of reciprocal lifetime (quality-loss rate)
Oranges S17 Q10 = 2 and Annex II citrus lifetime of 56 days at 4 °C Literature-prior lifetime with the implemented linear Q10 temperature factor

A normalized remaining-quality budget starts at 1 and expires at 0. For apple and strawberry endpoints, rate is 1 / shelf_life_hours; interpolation is in rate, not lifetime. Remaining life is expressed in reference-temperature hours at 4 °C. Full reference lifetimes are approximately 4,354.38 hours for apples, 1,344 hours for oranges and 432 hours for strawberries. Curve extrapolation is rejected. The supplement's printed k0 values were not used because their units and normalization do not consistently reconcile with its reported lifetimes.

See parameter derivation and assumptions and the supplement importer. These parameters condition the simulator; they do not validate individual warehouse batches.

Electricity carbon intensity

The official GB Carbon Intensity API supplied the cached response for 5 January 2023. The preserved input is data/grid-2023-01-05.json. It stores the raw response and the simulation's time-indexed intensity intervals in kg CO2/kWh, beginning at 2023-01-05T07:42:00+00:00.

All workloads reuse this cached interval. Their original source dates are not matched to separate historical grid days. Although interval values are marked actual, the benchmark explicitly makes the entire grid schedule available as known scenario context; this is not a causal evaluation using only forecasts available at each operational instant.

Recorded model-generated disruption

data/generated-42.json preserves one Ollama qwen2.5:7b response, quantized as Q4_K_M, generated with seed 42. It includes the request, response and parsed event. The structured event is a cooling failure in the cool zone, starting at minute 60, lasting 30 minutes, with available cooling fraction 0.7.

The simulator uses that structured event. The generated prose's assertion of a 3 °C rise is not an imposed physical observation or temperature trajectory. This one response is replayed across 500 workloads; it is not 500 independent model generations. All other faults are explicitly procedural.

Earlier experiments excluded from the final label source

The downloaded Datcolabssnet Cold Chain Logistics dataset, local Cold_Chain_Logistics_Dataset.csv, was inspected for an earlier aggregate estimated-freshness calibration experiment. Its 7,000 rows do not supply the final apple/orange/strawberry kinetic profile or dispatch ground truths.

The fruit-image Kaggle dataset and Mendeley czz68d9fwj discussed in the source assessment were candidate inputs, not data imported into these 4,000 examples.

Creation process

The implementation is in batch.py, pmc.py, scenarios.py, engine.py, optimizer.py and dataset.py.

  1. Load the preserved simulation template. examples/paper-template.json sets seed 42, a 480-minute horizon, one-minute ticks, ambient temperature 22 °C, one picker, walking speed 1.2 m/s, two-minute picks, coordinate scale 1 metre per unit, and dispatch coordinates [66, -29]. Thermal capacities, conductances, cooling capacities and COP values are explicit scenario parameters stored in that template, not measurements fitted from the footwear dataset.

  2. Index and select workloads. Read the archive, group picks by source wave, and select the first 1,000 eligible waves, with one wave per cohort and eligible-wave offset 0. Source wave IDs, original archive hash and exclusion counts are retained. Navigation-only waves are skipped rather than converted into invented inventory.

  3. Convert footwear workloads into synthetic produce cases. Map aisles A–F to chilled/apples (532 slots), G–L to cool/oranges (852), and M–R to temperate/strawberries (908). Within each zone, retain at most the first two lexicographically sorted storage slots touched by the selected wave. Record picks excluded for nonstorage locations or for being outside that decision window. Convert each source unit into one synthetic kg. Aggregate demand by wave and mapped SKU, and create one initial pallet per retained slot with its corresponding aggregate quantity. Pallet IDs are PMC-<source slot>; original product references are retained for lineage. Wave times are relative to the cohort's earliest date with time scale 1.0. The batch increments the template seed by the zero-based cohort index.

  4. Assign synthetic initial remaining life. Ordinary cases draw uniformly from 50–100% of each product's full reference lifetime. The near-expiry variant redraws ages uniformly from 0.01–0.8%. These are synthetic ages, not receiving dates or measured source quality. FIFO uses assumed arrival time (default 0) and pallet ID to break ties.

  5. Attach the cached grid and create four variants per cohort.

    Variant Count Construction
    normal 1,000 Ordinary stock; no fault
    near_expiry 1,000 Same workload; synthetic aged stock; no fault
    sensor_drift 1,000 Ordinary stock; seeded negative sensor bias
    disruption 1,000 Even cohort indices replay the saved Ollama event; odd indices alternate procedural cooling failure and stuck door

    Procedural random seed is config.seed * 1009 + cohort_index, plus 1 for sensor drift or 2 for the disruption variant. A random zone is selected; start time is uniform from 0 to min(30, 0.2 * horizon) minutes, and duration is uniform from 30 to 90 minutes, capped by the remaining horizon. Parameters are rounded to three decimals. Sensor bias is uniform from −2 to −0.4 °C; cooling availability is uniform from 0 to 0.15; a stuck door has value 1. Events must satisfy the disruption schema and horizon constraints.

    Totals are 2,000 controls, 1,500 procedural-fault cases and 500 recorded-model replays. Fault kinds total 1,000 sensor-bias, 750 cooling-failure and 250 stuck-door cases.

  6. Generate the ground truth using exhaustive simulation search. Enumerate pallet permutations within each SKU and all allowed static zone setpoints: chilled [0, 1], cool [2, 3], temperate [4, 5] °C. Put-away is fixed by the existing greedy rule, wave arrival order is fixed, and idling/relocation are excluded. The default per-case exact-search budget is 2,000 candidates; this build used 105,696 candidate evaluations in total. Minimize:

    expired_kg
    + 2.0 * unfilled_kg
    + 0.1 * compressor_kwh
    + 0.1 * grid_kg_co2
    - 0.001 * dispatched_life_kg_hours
    

    Simulate the chosen plan and matched FIFO/FEFO baselines. The exported food-saving target is FIFO expired_kg - chosen_plan expired_kg under the same initial stock, demand, disruptions and horizon. All 4,000 exported records are labeled optimal_in_declared_domain; this means exact within this finite domain, not globally optimal warehouse control.

  7. Construct prompt/answer pairs. The system message defines a cold-chain coordinator. The user message contains the state, known disruption/grid schedules, decision domain and objective weights. The assistant target contains put-away assignments, pallet priorities, chiller adjustments, alerts, execution events, optimization status, food saved and metrics. Labels come from the solver/simulator, not from the scenario-generating LLM. Metadata stores provenance, configurations and baseline results for replay.

  8. Split by source cohort, then export. base_case_id fingerprints the source archive hash and sorted selected wave IDs. Calculate int(sha256(base_case_id.encode()).hexdigest()[:8], 16) % 100: buckets 0–79 are train, 80–89 validation, and 90–99 test. All four variants stay together. This produces 3,192/380/428 examples rather than enforcing exact row-level 80/10/10 quotas. Each split is provided as JSONL and CSV.

  9. Verify the export. The recorded build replay-verified all 4,000 JSONL records: checksums, layout identity, actions, execution events, metrics, matched-FIFO food savings and source-cohort split isolation. Its manifest records 49 passing tests. These are historical build results; they do not certify later local edits. Checkpoints and historical run logs were removed after the final export; the input files and per-example replay metadata remain.

Regenerate or verify

Run from the repository root with a Python environment that can run this project:

python3 -m warehouse_sim.stage1 batch-build \
  --dataset 'Order Picking Dataset from a Warehouse of a Footwear Manufacturing Company.zip' \
  --template examples/paper-template.json \
  --scenario data/generated-42.json \
  --grid data/grid-2023-01-05.json \
  --variant-suite standard --cases 1000 --resume \
  --output runs/phase1-regenerated

This uses the preserved scenario without calling Ollama or downloading weights. Add --dry-run for a preflight. Use a fresh output directory for a new run; --resume applies to checkpoints created there, not the deleted original run. The command rebuilds the simulation pairs; the final CSV packaging is separate from the JSONL batch exporter.

python3 -m warehouse_sim.stage1 verify \
  --dataset 'Order Picking Dataset from a Warehouse of a Footwear Manufacturing Company.zip' \
  --export dataset

The replay verifier checks JSONL. CSV checksums must be compared separately against manifest.json.

Preserved input SHA-256 values

Input SHA-256
Footwear source ZIP 0de6901d639cae782e661ee63d479360b6942b31072e53d07bbde8313cbe9880
Zou supplement DOCX fd56de4d5ea43d55aabe331461e1d33d7b7864db8052e273919253b56387a43a
examples/paper-template.json b8b432185772aeebeae4b575f568e8655baf2ceaf0a6b6a436c61375f7cdc8cd
data/generated-42.json 6539033bf12ab82c541a656fa714229cff7bb38cc18f301f3621a86c48358216
data/grid-2023-01-05.json e2c6a0e3311f8b57779b28666c68fb425ac9e34e7d07aa30f6cc70c17f5d047f

Using the records and interpreting ground truth

For JSONL training, use messages; for CSV use system, input and output. metadata / metadata_json contain solver controls and replay information and must not be appended to model inputs. For evaluation, hold back the assistant answer and compare it with the model's response. EDA.py prints a small zero-shot pick-order exercise and its reference answer separately.

The full benchmark evaluates a model-conditioned planning task. It does not establish microbiological safety, measured food savings, or independent validation on real cold-chain batches. Only 192 examples have positive simulated food savings; the other 3,808 have zero. Replaying one model scenario and creating four variants per workload does not create 4,000 independent operational samples. See the expansion report and simulation methods for further detail.

Bias, risks and limitations

The source workload represents one footwear warehouse, while the cold-chain behavior is synthetic. Results may not transfer to other layouts, product cultivars, equipment, operators or demand distributions. Only three produce profiles and four standard variants are represented; the decision space is small and static. Parameters and objective weights encode project choices.

The 1,000 cohorts share the facility, grid day, parameter template and one recorded model scenario. Cohort isolation prevents wave variants leaking across splits, but does not test generalization to a new facility or unseen physical model. Positive savings occur in 192/4,000 examples (4.8%); a model predicting zero everywhere would match that scalar target on 95.2% of examples. Evaluate plan feasibility, action quality and simulator outcomes as well as scalar error.

Full future disruption schedules and cached grid intensities are disclosed in the inputs. This can overstate performance relative to an operational setting with uncertain forecasts. Reference labels are optimal only in the declared finite search domain. Human review of every generated example is not documented.

Personal and sensitive information

Prompts retain warehouse slot IDs; audit metadata retains source wave IDs, product references, timestamps and file hashes for lineage. The conversion does not intentionally add names or contact details, but this project has not performed a comprehensive privacy or re-identification audit of the original archive or generated export. Source operational identifiers should be treated as provenance rather than evidence of produce observations.

Licensing and distribution

MIT License see LICENSE

Downloads last month
85