「science」の検索結果

Advises on setting up LLM-based text classification as a validated measurement design. Covers codebook construction, learning-regime and model choice, prompt construction, validation against human coding with kappa and F1, hybrid human-LLM review, downstream measurement error, and reporting, plus a short resumable batch pattern with a rule-based baseline for repeated free text against a closed codebook. Use when the user wants to classify, code, or label text at scale. Category discovery goes to topic-modeling.

日本語の概要は準備中です。原文の説明を表示しています。

Launches and configures the standalone presubmit CLI, an API-driven adversarial peer-review pipeline with 30-plus stages, including Red Team finders, Blue Team defence, verification cascade, legal pass, and copyedit, producing one consolidated report on disk. Verifies installation and API key, chooses the output location and smoke, standard, or custom mode, launches the run, and reports the result path. Use when the user asks to run presubmit, wants a deep unattended pre-submission audit, or needs a math or replication-code audit. Everyday self-audits go to paper-review-lite, and external refereeing to journal-review.

日本語の概要は準備中です。原文の説明を表示しています。

Drafts or audits a scientific paper’s introduction and framing — the real-world "why", an evidence audit, the funnel from theory to a falsifiable if-then with a named estimand, bridges across experiments, and a contribution list matched to the design. Use when the user asks to write, restructure, or critique an introduction, motivate or frame a paper, repair a gap-in-the-literature opening, sharpen or calibrate a contribution claim, or connect experiments into one argument. Sentence-level flow and wording are out of scope.

日本語の概要は準備中です。原文の説明を表示しています。

Reads model uncertainty from token log-probabilities. Covers collecting logprobs and aggregating multi-token labels, confidence tiers and margins for triage, calibration assessment with ECE, Brier scores, and reliability diagrams against human labels, responsible downstream use of confidence, and reproducibility archives. Use when the user asks about classifier confidence by item, logprobs, top-k tokens, calibration, ECE, Brier, reliability diagrams, or routing low-confidence cases to human review. Codebook and validation design go to text-classification.

日本語の概要は準備中です。原文の説明を表示しています。

Opens a talk, module, paper, chapter, or referee report as a multi-session deliverable. Interviews the author, then scaffolds deliverable.yml, HANDOFF.md, the planning/ wiki, inbox/, and checks/. Use for deadline-driven work spanning sessions.

日本語の概要は準備中です。原文の説明を表示しています。

Design and format publication-quality tables. Use for column order, row grouping, notes, statistical precision, accessibility, and reproducibility.

日本語の概要は準備中です。原文の説明を表示しています。

Typeset a working paper or journal submission in house-style LaTeX from Markdown, Word, TeX, ODT, RTF, or HTML. Use to convert drafts, build PDFs, or prepare journal-specific spacing, limits, anonymization, disclosures, and citations.

日本語の概要は準備中です。原文の説明を表示しています。

Writes or reviews a pre-analysis plan before data collection: registry choice (OSF, AEA, AsPredicted, registered reports), locked models and decision rules, code run on simulated data, contingencies, and deviation records. Use when drafting or auditing a pre-registration or PAP, choosing a registry, or handling a deviation.

日本語の概要は準備中です。原文の説明を表示しています。

Organize an author's response to peer review: extract every referee point, order the revision by dependency, flag possible pushbacks, and build the response-letter skeleton the author fills in. Use for revise-and-resubmit planning, response letters, or checking every point was answered.

日本語の概要は準備中です。原文の説明を表示しています。

Designs multi-country survey experiments, covering case selection with a stated comparative logic, instrument localization and TRAPD translation, stimulus calibration, per-country power, and pooled versus per-country analysis with measurement-equivalence checks. Use when the user fields the same experiment in several countries, asks which countries to include, how to adapt an instrument without breaking comparability, whether to pool, or how large each country sample must be. Question wording goes to survey-design, reporting to methods-reporting, the study plan to pre-registration-writing.

日本語の概要は準備中です。原文の説明を表示しています。

Audits a manuscript's citations for fabricated or nonexistent sources, DOIs that resolve to a different work, mismatches between in-text citations and the reference list, APA 7 or journal style, and whether each source supports the claim it is attached to. Checks entries against Crossref, OpenAlex, and DataCite and labels anything it could not verify NOT CHECKED. Use to check citations, references, a .bib file, or DOIs, or when a source may be AI-invented. Figures and tables go to figure-table-audit.

日本語の概要は準備中です。原文の説明を表示しています。

End-of-session closure. Records what changed into the project's own handoff and log files, separating verified from attempted work, and reports what is uncommitted. Use when wrapping up a session. Twin of sitrep.

日本語の概要は準備中です。原文の説明を表示しています。

Turns a raw Qualtrics conjoint export into an analysis-ready long-format dataset, covering export settings, identifying the implementation, package or manual wide-to-long reshaping, choice-profile alignment, ratings, reference categories, pilot exclusion, and subgroup merges. Use when the user has a conjoint CSV to clean, reshape, or debug, cannot align choices with profiles, or asks what the data must look like before AMCE estimation. Design goes to conjoint-design, validity review to conjoint-diagnostics.

日本語の概要は準備中です。原文の説明を表示しています。

Designs conjoint and factorial-vignette experiments, covering attribute architecture and randomization restrictions, effective-N power, treatment realism, the choice among AMCE, marginal-mean, and AMIE estimands, forced-choice versus rating designs, and PAP tiers. Use when the user is planning a conjoint, drafting or critiquing an attribute table, asking how many respondents or tasks are needed, whether to report AMCEs or marginal means, or how to test interactions. Reviewing an existing design goes to conjoint-diagnostics, cleaning the export to conjoint-cleaning.

日本語の概要は準備中です。原文の説明を表示しています。

Interviews a researcher in rounds (idea, design, or defend stage) until no decision in a research idea, design, or draft is left assumed, recommending an answer to each question and writing settled decisions to a file. Use for 'grill me', stress-testing a design, or an idea not yet a design; --plan for software or process plans.

日本語の概要は準備中です。原文の説明を表示しています。

End-stage QA for a finished figure and table set (callouts, numbering, cross-references, text-to-exhibit consistency, captions and notes, accessibility, SI and replication linkage). Use when preparing a submission.

日本語の概要は準備中です。原文の説明を表示しています。

Scaffold or audit a research-project repository organized around its source library (PDFs, Markdown conversions, bibliography, intake pipeline) plus the analysis, manuscript, and review folders it needs. Use when starting or auditing a research repo. Not for one-PDF intake or publication replication packages.

日本語の概要は準備中です。原文の説明を表示しています。

Plans a research project as a durable decision map, resolving one design decision per session until the design is defensible and pre-registerable. Use at project start, when a design has more open decisions than one conversation holds, or when planning keeps restarting. Not for running analyses or writing the paper.

日本語の概要は準備中です。原文の説明を表示しています。

Run a pre-submission manuscript audit covering argument, numerics, references, writing, figures, methods, preregistration, and replication readiness. Add --codex for a cross-model pass in which Codex and Claude review independently and verify each other's findings.

日本語の概要は準備中です。原文の説明を表示しています。

Start-of-session report on where a repository stands. Reads the project's own handoff and log files, checks live git state, and reports objective, verified baseline, open tasks, blockers, and next actions. Use when resuming work. Twin of finished.

日本語の概要は準備中です。原文の説明を表示しています。

Reviews an existing conjoint study for threats to inference and returns severity-ranked findings on design integrity, estimation, measurement error, external validity, and interpretation, including the guardrail against reading an AMCE as majority preference. Use when the user asks whether a conjoint design or analysis holds up, has referee comments on a conjoint, or wants a second opinion on estimation or interpretation. New designs go to conjoint-design, reshaping to conjoint-cleaning.

日本語の概要は準備中です。原文の説明を表示しています。

Turns dictated captures in a deliverable's inbox/ into a proposed planning-wiki diff, classifying and tracing each statement; decisions need the author's assent. Use to intake notes or process the inbox.

日本語の概要は準備中です。原文の説明を表示しています。

Orchestrate complex work from an active gpt-6-astra or gpt-6.1-sol Codex session. The detected lead owns decomposition, integration, and verification; Astra keeps the hardest reasoning in the lead, while Sol escalates unusually difficult units to Astra. Both route bounded work to Sol at medium effort, mechanical work to Luna, and can use a cross-vendor Claude peer. Not for routine single-context work. Use when the user explicitly asks to orchestrate, delegate, fan out, parallelize, assign subagents, obtain independent checks, or have Codex act as tech lead.

日本語の概要は準備中です。原文の説明を表示しています。

Reviews a whole deliverable against its manifest without rewriting it — deterministic gate, per-section finders, a whole-work pass, and adjudicated findings.json and report.md with honest coverage. Use before shipping a deliverable or for the night shift.

日本語の概要は準備中です。原文の説明を表示しています。