# Systematic trading research-data audit

Generated: `2026-07-29T10:59:01.011124+00:00`

Source role: `production_runtime_export`

Data directory: `/freqtrade/user_data/data/binance/futures`

This is a read-only coverage and integrity audit. It does **not** prove which
strategy or dataset is deployed. A result with source role `research_cache` is
provisional; deployment/runtime truth requires running the same script against
the production container's mounted data and preserving that exported manifest.

## Outputs

- `data_manifest.json`: full provenance, schema, hashes, NaN and interval data.
- `data_coverage.csv`: one flattened row per pair and dataset.
- `gap_details.csv`: fixed-grid internal gaps and conservative funding-event
  gap candidates.

## Summary

- Pairs: 12
- Expected files: 48
- Read successfully: 48
- Missing files: 0
- Read/validation errors: 0
- Files with internal gap candidates: 0
- Detailed gap rows: 0

## Interpretation rules

- The first and last observed timestamps are coverage boundaries. They are not
  counted as internal gaps and are not automatically treated as listing dates.
- `pre_listing` is only populated when authoritative metadata is supplied with
  `--listing-dates`; the script never guesses a listing date from the first bar.
- 5m futures, 1d futures and 1h mark data use fixed expected grids.
- Funding is an event series and Binance can change the settlement interval.
  Only deltas greater than the configured 8h
  maximum are emitted as `funding_event_gap_candidate`; this is conservative
  and is not proof that an event is missing.
- Daily rows report the first causally eligible 28-day XSMOM endpoint and
  whether the latest 29 daily observations are contiguous.
- Funding rows report `funding_coverage_feasibility`; this only assesses event
  coverage and does not equate settled historical funding with the live
  exchange's predicted/current funding response.
- SHA256 covers the source Feather file. Source files are never modified.