tangxiangru/AutoR

A Deliverable Is Not an Instruction helps separate research deliverables from harness instructions when building a study plan and checking coverage. Use it to keep `report_plan.json` focused on findings and to mark genuinely unreachable items honestly.

A Value You Did Not Measure Still Has A Source explains how to handle deliverables this run cannot measure or produce, using attributed published values instead of fabricating or omitting them. It covers where to place cited values and how to compare them to your own results.

Answer The Why, Not Only The What helps you write results and discussion sections that explain why an effect happens, not just whether it happened. Use it when a reviewer or task asks for mechanism claims, competing explanations, or limits on what the data support.

Assume This Stage Is The Last One You Get advises planning each early stage of a timed research run so it leaves a valid model, score, and rerunnable script if the later stages never happen. It is used when wall-clock limits make deferred work unlikely to execute.

Astronomy Caption Specification turns figure captions into a plotting specification for reproducing astronomy figures when the rendered source is unavailable. Use it to keep panel order, series, colors, references, normalization, and error bars aligned with the paper.

Astronomy Error Budget Audit Trail helps you document uncertainty propagation, fit bookkeeping, and residual diagnostics before quoting a result. Use it when a measurement depends on calibration chains, covariance, or a model fit.

Astronomy Figure Is The Unit Of Result guides study design and writing when reporting astronomy results. It explains why results should be shown as figures, how to decompose aggregates, and which comparison panels a paper should include.

Astronomy Published Table Chains rebuilds a published table of means and 1-sigma errors as synthetic chains for comparison plots. Use it when a paper releases only summarized posteriors and you need GetDist-compatible samples for each model.

Auditable Method Choice helps you decide whether a more complex method fits the remaining clock by timing a small run, extrapolating full cost, and writing a go/no-go before you commit. It also covers checkpointing and split/seed control so the stronger option can fail safely.

Chemistry Ablations And Curves helps plan ablation tables and curve-based evidence when a model can’t be trained at full scale. It distinguishes component ablations from input ablations and suggests the highest-fidelity curve you can still ship.

Chemistry Accuracy And Cost For Every Module You Swap In helps evaluate drop-in replacement modules by reporting both accuracy and cost for each alternative. Use it when a paper claims a substituted layer is more accurate and cheaper, and you need matched comparisons and normalized runtime ratios.

Chemistry Canonical Units Thresholds Incumbent helps compare computational chemistry results against the field’s incumbent code, report in canonical units, and convert errors into threshold success rates. Use it for study design, analysis, and paper reporting.

Chemistry Group Attribution Across Splits defines how to evaluate substructure attributions over a held-out split instead of one molecule. It also compares the same attribution on a baseline model and treats learned masks as outputs.

Chemistry Ranked Entities And Property Curves helps plan analysis reports that need a named ranked list of chemical entities or a property-versus-coordinate curve. Use it when you must print per-entity scores, scan ranges, and the key constants or errors from a sweep.

Chemistry Reproduction Path helps you reproduce a published benchmark score by matching the source's exact scoring path before changing anything. Use it to document splits, filtering, ordering, checkpoint choice, pooling, and seed aggregation, then compare each step against your own run.

Citation Discipline helps verify citations, BibTeX entries, and claim support during Stage 07 writing. Use it when a reference is unresolved, a paper may not support a claim, or citation_verification.json needs to be filled.

Comparator Table Coverage helps you transcribe a source table into row-level targets, audit your inclusion filter against each row, and report one run per class the table distinguishes. Use it when study design could otherwise drop whole comparator rows.

Detection Score Population Claims explains how to compare detection or ranking scores across studies by publishing the candidate population, checking prevalence effects, and describing extra detections. Use it when a score or arm comparison could be distorted by different denominators or unlabeled items.

Interaction Inventory Of The Modelled Complex compares reference and predicted molecular interfaces by contact class, listing recovered, missed, and spurious interactions. Use it for docked or co-folded complexes when RMSD or DockQ alone does not explain the binding chemistry.

Joint Posterior Triangle Plot shows overlaid triangle plots for two or more models on the source's parameter axes. Use it when comparing how models shift parameters and whether their joint contours overlap or diverge.

Null Bounds First helps you report a headline estimate and a noise bound as separate results, especially after permutation or placebo tests. It also enforces value lines for every condition and keeps bounds from replacing the answer.

Refutation Banner Over A Confirming Panel checks report titles, headings, and figure labels for verdict words and internal labels that can misstate a result. Use it after a run or revision pass when a fidelity finding must stay in the right section and the rest of the report should stay neutral.

Scoreable File First tells you to create a valid predictions file in the first hour and keep improving it in place. Use it when a run can be scored only if a submission file exists and stays valid.

Supplied Parameter Ledger turns shipped parameter files into a claim ledger, with one row per named value, range, case, or condition. Use it when a study file must be audited, reproduced, and reported in the file's own labels and units.

Variant Analysis Integrity helps you track which model variant produced each table row, case study, saliency map, or ablation before you cut or shrink a family member. It also clarifies what evidence from one variant does and does not support about the larger method family.