「classifier」の検索結果

End-to-end biomarker discovery workflow from expression data to validated biomarker panels. Covers feature selection with Boruta/LASSO, classifier training with nested CV, and SHAP interpretation. Use when building and validating diagnostic or prognostic biomarker signatures from omics data.

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。

Identifies essential genes from CRISPR-Cas9 fitness screens using BAGEL2 (Kim & Hart 2021 Genome Med), a Bayesian classifier scoring per-gene Bayes Factors via log-likelihood ratios over per-sgRNA fold changes, calibrated against CEGv2 core-essentials (Hart 2017 G3, ~684 genes) and NEGv1 non-essentials (Hart 2014, ~927 genes). Covers the fc + bf + pr workflow, the linear-extrapolation improvement over BAGEL1 truncation, multi-target off-target correction, tumor-suppressor sensitivity (BAGEL2 detects enrichment), and BF-to-FDR calibration (BF >6 ≈ FDR 0.05 from Hart 2017). Use when classifying essential vs non-essential genes, calibrating BAGEL2 thresholds against PR curves, identifying tumor suppressors alongside essentials, comparing BAGEL2 hits to MAGeCK / drugZ, or generating publication-quality essentiality calls.

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。

Add fast, local, typed decisions to any project with Laya, an open-source non-generative decision model (pip install laya). It classifies, routes, scores and answers yes/no questions about a piece of text, returning calibrated probabilities in roughly 20-35 ms on a laptop GPU, with no LLM call and no data leaving the machine. Use this skill whenever the user wants to classify or route text, triage tickets or emails, detect spam, phishing, toxicity or intent, put a guardrail in front of an agent or LLM, score something against a rubric, or replace an LLM-based classifier to cut latency or cost. Also use it when they mention Laya, Jev, a "System 1 model", "typed decisions" or a "decision model", even if they never name Laya.

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。

Transparent, itemized impressions of AI-generated WRITING STYLE — the repo's ONLY non-integrity track. Two passes: a deterministic defensive-hedge density screen (tools/check_ai_style.py, AIS-DEFENSIVE-HEDGE) plus a fresh cross-model GROSS-cases-only semantic pass over the 13 AIS-* style tells (broken narrative arc, LLM phrase tics, jargon-stuffing, invented codenames, clause/formula walls, gratuitous pseudocode, bullet overuse, bold-module spam, restatement loops, focus drift, single-style figures, appendix dumping). Every finding is named, LOCATED, span-anchored to the evidence ledger (claims.json), carries not_integrity_finding:true + false_positive_risk:high + an fp_case, and gets ZERO verdict weight: the adjudicator forces it to info, excludes it from overall_verdict, and renders it in a SEPARATE report section. NOT an AI-text classifier — no scores, no "this is AI-written", no authorship probability; a paper can be CLEAN_GIVEN_EVIDENCE and still list many. Emits ai-style-impressions.findings.json; computes NO verdict; if a tell is actually substantive it routes to the integrity auditor. Triggers: "AI style", "vibe check", "writing fingerprint", "AI 文风", "vibe 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。

End-to-end substantive-integrity forensic sweep of a research paper (especially autoresearch / AI-Scientist-style output). Orchestrates the whole pipeline: ingest (arxiv-id | pdf | dir → working dir + pdftotext for L0) → /evidence-ledger (artifact manifest + observability level L0/L1/L2 + span-anchored claims.json) → fan out the integrity auditor skills (consistency, citation, baseline, experiment, presentation, proof-derivation, eval-design — each reads the ledger, emits span-anchored findings) + the zero-verdict-weight AIS writing-style track → advisory memos (/adversarial-case-builder + /novelty-duplication-advisory, no verdict weight) → deterministic tools/adjudicate_findings.py (--ledger REQUIRED) → reviewer-ready Integrity Forensics Report. Cross-model (fresh codex per dimension) and reviewer≠adjudicator: the model proposes findings, the deterministic adjudicator decides the verdict. Observability-aware, detect-only, never an opaque AI-text classifier (a separate zero-weight AIS section lists AI writing-style impressions, never moving the verdict). Triggers: "anti-autoresearch", "integrity audit this paper", "forensic review", "audit a submission", "审一篇投稿的诚信".

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。

Suede AI eval design and coverage audit: AI-SPEC, failure-mode rubric with severity scoring, concrete pass/fail eval cases, coverage and infrastructure scores, and mechanical acceptance gates. Use when a change ships LLM, RAG, agent, classifier, prompt, or generated-media behavior, or when asked to write evals for an AI feature, design test cases for a model surface, audit existing eval coverage, or judge whether AI behavior is safe to ship. No AI-SPEC means no eval plan, and no eval plan holds the recommended ship verdict. NOT FOR: reviewing or grading the implementation code behind the AI surface (use suede-code); wiring a passing suite into CI as a required check (use suede-ci-gate); UAT of the built feature beyond the eval suite (a private Suede Labs companion, not in this pack).

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 local AI engines for iOS. Use when wiring Apple Foundation Models, local classifiers, extraction, summarization, grounded answers, and cloud fallbacks.

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 guardrail layers — input classifiers, output validators, PII scrubbers, policy rule engines. Use when asked to "add safety filters", "scrub PII from LLM output", or "design content moderation".

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。

Reads a model's own uncertainty from token log-probabilities: collecting and aggregating label logprobs, confidence tiers and margins for triage, calibration against human labels (ECE, Brier, reliability diagrams), downstream use, and reproducibility. Use for per-item classifier confidence 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。

Organizational Development Manager (R31): guides the subject from an organizational change request (self/team/organization) to a concrete first step from SE/SM/PE. Step 0 — system type classifier (MIM.M.030, 7 questions). Step 3 — routing-table (MIM.M.031).

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。

Read-only runbook for how the VNX fabric actually works — state resolution, the single-entry dispatch door, gate invocation, the horizon planning layer, the plan-gate panel, and the hard gotchas that repeatedly bite (PATH-break, dual-CLI, codex-cert, classifier-protected actions). Use when you need to look up a fabric operation instead of rediscovering it, or when a fabric command behaves unexpectedly. Companion to the t0-orchestrator skill (judgment) and vnx-manager (infra maintenance); this one is pure reference.

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。

Bypass AI safety filters by encoding malicious prompts using ciphers and obfuscation techniques (e.g., Base64, ROT13, Leetspeak, Morse code). This skill exploits the gap where the LLM can decode the request, but intermediate keyword-based safety classifiers cannot.

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。

Build human adjudication / hand-labeling sheets from LLM-pipeline data without evidence truncation. Use when: (1) preparing a CSV/Excel sheet for a human to rule on cases an LLM classifier or rater panel judged, (2) a labeler reports "there is no information to label from" or cells look empty in Excel, (3) excerpt columns cluster at one exact length (e.g. all 1,500 chars — a hard truncation cap). Covers: full rating-basis recovery, Excel 32,767-char cell cap, multi-line CSV mangling, ruling dropdowns, companion text files.

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。

Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-coded label set, (2) a label-replication model shows low recall concentrated in a label subset and the diagnosis on offer is "the label's information is not in the features", (3) reviewers propose construct splits (e.g. "designation vs record-evident"), adjudication sittings, or per-domain stop rules to explain residual disagreement with gold, (4) validating an extraction pipeline against labels transcribed from a source document. Symptom of the underlying failure: elaborate theory accumulates to explain why gold is "partially unpredictable" when the model was simply never shown the document the annotators read.

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。

Diagnose whether an LLM classifier's validation-gate failure is GOLD-BOUND before spending on prompt revision or model changes. Use when: (1) a scoring pipeline over-predicts a label (precision low, recall high) and a prompt clarification is proposed to tighten it, (2) a pilot/validation gate fails and the fix candidates are prompt edits, (3) inter-rater agreement on the weak label was already low (κ < ~0.6). Core check: if gold POSITIVES share the exact feature the revision would exclude, no prompt can pass a gold-scored gate — recall craters while precision barely moves. Also documents the verified surgical-pilot design (single-section diff, tune/holdout split, pre-registered gate, perturbation check on untouched sections).

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。

Use when a task needs the judgment of a Crushing/Grinding Machine Operator — recognizing that classifier cut point, not mill residence time alone, determines what reports to finished product in a closed-circuit grinding operation, monitoring circulating load as a distinct diagnostic variable, matching grinding media size to the target size reduction, or verifying product size via actual sieve/laser analysis rather than mill parameters.

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。

任意输入的路由分类器。在输入意图不明确时，判断应走「认知更新路径A（cognitive-capture-fragment）」还是「任务执行路径B（对应任务Skill）」，输出明确路由结论 + 判断理由，不自动触发下游。触发词：「帮我判断这是认知更新还是任务执行」「这个输入是什么类型」「先分类再执行」「路由分类一下」。不应触发：关于计算机网络路由算法的技术问题。

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。

Extracts cfDNA fragmentomics features (DELFI genome-wide short/long ratios, WPS nucleosome positioning, Griffin GC-corrected accessibility profiles, end-motifs/MDS, OCF) for cancer detection and tissue-of-origin from plasma WGS. Centers on the nuclease-footprint reframe (every feature re-reads one nucleosome object), the mandatory GC correction, and the cross-protocol non-comparability that breaks naive classifiers. Runs FinaleToolkit (real CLI/Python, MIT) and the Griffin Snakemake pipeline; DELFI is a method, not a package. Use when deriving fragment-based signal from cfDNA, choosing a feature family for detection vs subtyping, or diagnosing why a fragmentomic model failed validation.

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。

Processes eDNA metabarcoding from raw paired-end reads to species tables, navigating ASV (DADA2, UNOISE3) vs OTU (swarm v2) decision (Callahan 2017 vs Schloss multi-copy-16S critique), marker/primer choice (Leray COI, MiFish 12S, 515F/806R 16S, ITS2) with primer-specific bias, OBITools3 v3 command-name break (obi stats plural; .tar.gz taxonomy), tag-jumping with dual-indexing (Schnell 2015; NovaSeq 10x MiSeq), decontam as screening-not-classifier (Davis 2018), read-counts-not-abundance critique (Lamb 2019), site-occupancy modeling (Ficetola 2015), Naive-Bayes calibration limits (Bokulich 2018), and eDNA decay (Strickler 2015). Use when going from raw eDNA FASTQ to species tables, picking marker + denoising pipeline, deciding whether read counts represent abundance, applying occupancy modeling, configuring OBITools3 v3, or interpreting decontam output. Not for clinical 16S microbiome (see microbiome/amplicon-processing).

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。

Identifies essential genes from CRISPR-Cas9 fitness screens using BAGEL2 (Kim & Hart 2021 Genome Med), a Bayesian classifier scoring per-gene Bayes Factors via log-likelihood ratios over per-sgRNA fold changes, calibrated against CEGv2 core-essentials (Hart 2017 G3, ~684 genes) and NEGv1 non-essentials (Hart 2014, ~927 genes). Covers the fc + bf + pr workflow, the linear-extrapolation improvement over BAGEL1 truncation, multi-target off-target correction, tumor-suppressor sensitivity (BAGEL2 detects enrichment), and BF calibration (BF >6 ≈ 90% posterior per Hart 2017; ~5% FDR by BAGEL convention). Use when classifying essential vs non-essential genes, calibrating BAGEL2 thresholds against PR curves, identifying tumor suppressors alongside essentials, comparing BAGEL2 hits to MAGeCK / drugZ, or generating publication-quality essentiality calls.

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。

Resolve the architecture of focal oncogene amplifications — extrachromosomal DNA (ecDNA), breakage-fusion-bridge (BFB) cycles, homogeneously staining regions (HSR), and linear amplification — from whole-genome sequencing with AmpliconArchitect, the AmpliconSuite pipeline, and AmpliconClassifier. Covers copy-number seed selection, breakpoint-graph reconstruction, balanced-flow optimization, ecDNA classification, and the limits of depth-only amplification calls. Use when a focal amplification needs structural characterization, when distinguishing ecDNA from chromosomal amplification, suspecting ecDNA-driven oncogene amplification or therapy resistance, or selecting copy-number seeds for amplicon reconstruction.

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。

Classify the severity of hypercalcemia at the bedside — mild, moderate, or severe — by combining the corrected/ionized calcium level with the acuity and symptom pattern, and decide whether the patient needs urgent therapy. Trigger when a clinician asks "is this hypercalcemia severe", "how bad is this calcium level", "when to admit for hypercalcemia", "is this hypercalcemic crisis", "how to grade hypercalcemia", or shares a calcium level and asks how worried to be.

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。

Scans CopilotKit's public product / pricing / Premium pages at the start of every weekly report to produce the authoritative list of COMMERCIAL surfaces (Premium · CopilotKit Enterprise · Intelligence Platform · paid tiers) and detect any newly-added or changed commercial feature since last week. This list defines what the report's 🏢 Enterprise section is about — CopilotKit's commercial/paid product, NOT "CopilotKit running inside an enterprise company." Emits the surface list + a free-vs-paid classifier the report uses to decide "does this issue hit a commercial surface?", plus a diff of what changed. Runs as a subagent (many web fetches) so the orchestrator's context stays small. Invoked by weekly-report (spawned at report start) and the enterprise skill; also triggers on "scan product surfaces", "what's premium", "commercial surfaces", "did we add a premium feature".

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。