All authors
Claude Skills by VectorSpaceLab
github.com/VectorSpaceLab6,028 skills13 installs7,823 views
- Sequential Apt LoopRun a bounded sequential APT proxy loop that updates proposals after corrected atomic training.Votes: 0GitHub stars: 247
- Benchmark Recovery HarnessRun an auditable reduced recovery experiment for the SBI benchmark by composing generated task, sampling, and C2ST skills.Votes: 0GitHub stars: 247
- C2st Metric EvaluationCompute a deterministic classifier two-sample accuracy proxy for comparing posterior sample distributions.Votes: 0GitHub stars: 247
- Posterior Sampling BaselineGenerate deterministic reference and approximate posterior samples for bounded simulation-based inference recovery experiments.Votes: 0GitHub stars: 247
- Sbibm Task ProtocolBuild validated simulation-based inference benchmark task items with prior, simulator, observation, and reference posterior metadata.Votes: 0GitHub stars: 247
- Annealed Langevin SamplingRun bounded annealed Langevin posterior sampling from composed score functions for score-based SBI recovery.Votes: 0GitHub stars: 247
- Diffused Score TrainingBuild and validate reduced denoising score-training traces for single-observation simulation-based inference posteriors.Votes: 0GitHub stars: 247
- Factorized Score CompositionCompose F-NPSE and PF-NPSE posterior scores from prior corrections and per-condition score estimates.Votes: 0GitHub stars: 247
- Posterior Mmd RecoveryCompute squared MMD for posterior samples and package score-based SBI recovery-result metadata.Votes: 0GitHub stars: 247
- Ln Summary ProtocolBuild likelihood-free linear-nonlinear neural simulations and STA/firing-rate summaries for SNPE-style posterior recovery.Votes: 0GitHub stars: 247
- Posterior EstimatorFit a conditional Gaussian posterior surrogate from simulated summary/parameter pairs without likelihood evaluations.Votes: 0GitHub stars: 247
- Posterior Predictive ValidationValidate SNPE-style posterior recovery using parameter correlation, posterior predictive summary error, and mechanism checks.Votes: 0GitHub stars: 247
- Snpe Round ControllerCoordinate prior and posterior-guided simulation rounds for a bounded SNPE-style recovery experiment.Votes: 0GitHub stars: 247
- Sbi Neural Inference Family SelectorSelect SNPE, SNLE, or SNRE for a simulation-based inference task from estimator and posterior-access requirements.Votes: 0GitHub stars: 247
- Sbi Posterior Interface And DiagnosticsSummarize posterior samples and validate SBI uncertainty with finite-sample and reference checks.Votes: 0GitHub stars: 247
- Sbi Recovery Experiment HarnessRun a bounded source-boundary-safe recovery experiment for the sbi toolkit workflow.Votes: 0GitHub stars: 247
- Sbi Simulator Prior ProtocolPrepare simulator, prior, observation, and simulated pair contracts for simulation-based inference workflows.Votes: 0GitHub stars: 247
- Sbi Snpe Training LoopRun a bounded SNPE-style conditional posterior training loop for mechanism-faithful SBI recovery.Votes: 0GitHub stars: 247
- Score Sde FamilyDefine VE, VP, and sub-VP SDE contracts plus reverse-time SDE and probability-flow ODE dynamics for score-based generative modeling.Votes: 0GitHub stars: 247
- Score Sde LossConstruct continuous-time denoising score matching losses and tiny optimizer-step checks for Score SDE recovery.Votes: 0GitHub stars: 247
- Score Sde Pc SamplerRun bounded predictor-corrector reverse sampling diagnostics for score-based SDE mechanisms.Votes: 0GitHub stars: 247
- Score Sde Probability FlowBuild deterministic probability-flow ODE diagnostics and one-dimensional likelihood corrections for Score SDE recovery.Votes: 0GitHub stars: 247
- Score Sde Recovery HarnessExecute a bounded soft-mode Score SDE recovery experiment using generated skills and mechanism checks.Votes: 0GitHub stars: 247
- Tsnpe Hpr Truncated ProposalCompute TSNPE high-posterior-density truncation thresholds and rejection samples from a bounded prior.Votes: 0GitHub stars: 247
- Tsnpe Pooled Mle TrainingFit a reduced Gaussian posterior surrogate with pooled maximum-likelihood updates.Votes: 0GitHub stars: 247
- Tsnpe Reduced Recovery HarnessRun a bounded mechanism-faithful TSNPE proxy recovery experiment.Votes: 0GitHub stars: 247
- Tsnpe Sbcc DiagnosticsCompute TSNPE support inclusion and simulation-based coverage calibration diagnostics after each truncated proposal training round.Votes: 0GitHub stars: 247
- Tsnpe Sir Fallback SamplerRun deterministic sampling-importance-resampling diagnostics for narrow TSNPE proposals.Votes: 0GitHub stars: 247
- Invalid Simulation CorrectionEstimate validity probabilities and correct likelihood-method posterior scores for invalid simulator outputs.Votes: 0GitHub stars: 247
- Sequential Sbi LoopRun a bounded sequential simulation-based inference loop that updates proposals from variational posterior estimates.Votes: 0GitHub stars: 247
- Sir Posterior RefinementApply sampling importance resampling to refine variational posterior samples using likelihood-prior weights.Votes: 0GitHub stars: 247
- Variational ObjectivesCompute stable mass-covering variational objective diagnostics for SNVI-style posterior optimization.Votes: 0GitHub stars: 247
- Conditioning Dropout TrainingPrepare classifier-free diffusion conditioning-dropout batches and tiny denoising training traces for reduced recovery.Votes: 0GitHub stars: 247
- Diffusion Sampler ProxyRun a tiny reverse-diffusion-like sampler that exercises classifier-free guided score calls at each step.Votes: 0GitHub stars: 247
- Guidance Tradeoff EvaluationEvaluate classifier-free guidance sweeps with proxy confidence and diversity trade-off metrics.Votes: 0GitHub stars: 247
- Guided Score CombinationCompute classifier-free guided diffusion score estimates from conditional and unconditional predictions.Votes: 0GitHub stars: 247
- Coherence Alpha SelectionSelect a coherence boosting alpha from cached validation likelihoods without model finetuning.Votes: 0GitHub stars: 247
- Coherence Boosted ScoringApply the coherence boosting log-linear scoring rule to full-context and premise-free answer likelihoods.Votes: 0GitHub stars: 247
- Coherence Context ProtocolBuild and validate full-context and premise-free-context records for coherence boosting answer-selection experiments.Votes: 0GitHub stars: 247
- Coherence Recovery EvaluationEvaluate coherence boosting recovery metrics and source-boundary mechanism checks for proxy experiments.Votes: 0GitHub stars: 247
- Cad Decoding PolicySelect tokens from regular or CAD-adjusted logits using comparable greedy or top-p decoding policies.Votes: 0GitHub stars: 247
- Cad Logit AdjustmentApply the Context-aware Decoding contrastive logit formula and report mechanism diagnostics for recovery experiments.Votes: 0GitHub stars: 247
- Cad Prompt ProtocolBuild and validate context-aware decoding prompt parts with separated evidence context, query, and generation prefix.Votes: 0GitHub stars: 247
- Cad Recovery EvaluationEvaluate CAD conflict-recovery runs with exact-match metrics and mechanism-check summaries.Votes: 0GitHub stars: 247
- Constraint CompositionCompose multiple FUDGE future constraints, especially topic-word constraints, by summing weighted log probabilities.Votes: 0GitHub stars: 247
- Fudge Logit RescoringApply the FUDGE decoding rule by combining base candidate logits with future-discriminator probabilities and renormalizing.Votes: 0GitHub stars: 247
- Future Discriminator DataBuild prefix-level future-discriminator examples for FUDGE-style controlled generation from completed token sequences and sequence/target-word labels.Votes: 0GitHub stars: 247
- Topic Proxy EvaluationEvaluate reduced FUDGE topic-control recovery with topic-token metrics and explicit mechanism checks.Votes: 0GitHub stars: 247
- Gedi Guided DecodingReweight base language-model token probabilities with GeDi posteriors and apply GeDi cumulative-mass filtering for controlled decoding.Votes: 0GitHub stars: 247
- Gedi Hybrid TrainingCompute and test GeDi's hybrid discriminative-generative objective with a deterministic tiny optimizer step.Votes: 0GitHub stars: 247