Skip to content
View aarnavbhat23's full-sized avatar

Block or report aarnavbhat23

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. nature-compute-lab nature-compute-lab Public

    Small, reproducible experiments on development, catalysis, symbiosis, repair, immune memory, stable regimes and clocks.

    Python 1

  2. perturbation-composition-lab perturbation-composition-lab Public

    Two independent perturbation experiments: 289 combinations, matched neural/ridge/additive models, 20 dependent holdouts and released inference.

    Python 1

  3. evidence-retrieval-bench evidence-retrieval-bench Public

    Scientific retrieval and citation auditing: disjoint supervised groups, 300 verdicts, 1128 paired stress cases and a blinded unreviewed packet.

    Python 1

  4. bio-evidence bio-evidence Public

    Biological data and model-evaluation checks, with nine public-data applications and reproducible model failure cases.

    Python 1

  5. extrusion-net extrusion-net Public

    Chromatin loop extrusion as a sequence model's routing operator: 36 runs vs attention, BiLSTM and a one-arm ablation, 8x length and 300-sequence tests, learned CTCF orientation.

    Python 1

  6. next-token-bio next-token-bio Public

    How much of next-residue / next-nucleotide prediction is homology memorisation? n-grams vs parameter-matched LSTM/GPT on held-out protein families and E. coli codon positions.

    Python 1