lineage.yml

pretraining_corpus:
  table: null
  repo: HuggingFaceBio/carbon-pretraining-corpus
  config: null
  upstream: null
  access_mode: streaming
  description: Root source corpus (eukaryote_generator/train split).
cpu_enriched:
  table: carbon.cpu_enriched_sequences
  repo: AINovice2005/carbon-cpu-enriched-sequences
  config: null
  upstream: pretraining_corpus
  access_mode: catalog
  description: CPU-derived sequence features from the 75% pretraining split.
sampled_cpu:
  table: carbon.pilot_corpus_dedup
  repo: AINovice2005/carbon-cpu-enriched-sequences-sampled
  config: null
  upstream: cpu_enriched
  access_mode: catalog
  description: Stratified CPU-enriched population used as the GPU input corpus. HF
    artifact name contains 'dedup', but the lineage edge is deterministic per-row-hash
    sampling with representativeness validation, not deduplication.
tokenized:
  table: carbon.tokenized_corpus
  repo: AINovice2005/carbon-tokenized-corpus
  config: null
  upstream: sampled_cpu
  access_mode: catalog
  description: Model-ready tokenized input from the sampled CPU population.
likelihood_stats:
  table: carbon.likelihood_stats
  repo: AINovice2005/carbon-likelihood-stats
  config: null
  upstream: tokenized
  access_mode: catalog
  description: Per-sequence model likelihood statistics from GPU enrichment.
embeddings:
  table: carbon.embeddings
  repo: AINovice2005/carbon-embeddings
  config: null
  upstream: tokenized
  access_mode: catalog
  description: Model-derived sequence embeddings from GPU enrichment.