yogsoth-ai
- 1.8k skills
- 0 followers
- 512 repo stars
- yesterday last updated
- ▌ Reformulation Synthesis 2 · yogsoth-ai bundleCompile all problem reformulation analyses into a coherent report with a recommended new problem definition.
- ▌ Salience Classification 2 · yogsoth-ai bundleClassify stakeholders by Mitchell et al. framework (Power, Legitimacy, Urgency). Assigns salience category and identifies systematically excluded parties.
- ▌ Systematic Perturbation 2 · yogsoth-aiMulti-axis systematic perturbation — define variation axes, perturb along each, measure degradation, construct validity envelope.
- ▌ Uncertainty Propagation 2 · yogsoth-aiPropagate input uncertainties through the model via Monte Carlo sampling. Identifies which input uncertainties contribute most to output uncertainty.
- ▌ Scaling Regime Detection 2 · yogsoth-ai bundleDetect regime changes in scaling behavior — breakpoints where behavior qualitatively shifts, mechanisms behind transitions.
- ▌ Stakeholder Confirmation 2 · yogsoth-ai bundleSimulate stakeholder perspectives to validate gap priorities. Assesses gap value from researcher, practitioner, funder, and end-user viewpoints.
- ▌ Paper Fetch 2 · yogsoth-ai bundleRetrieve one specified academic paper (by title, arXiv ID, DOI, URL, or a local .md/.txt/.pdf path the caller already has) and land it on disk as source.md plus a source.meta.json carrying a line-number section index. Checks context/papers/ for an existing copy first; local files and direct PDF URLs are read directly with no search at all, while other references use alphaxiv, Semantic Scholar routing, then bioRxiv/medRxiv. Use this as the mandatory first step whenever any other paper-reading SOP in this package needs the actual text of a paper — it is the sole entry point of the pipeline and every downstream SOP reads the files it lands, so do not bypass it even when the caller already has the file. If it returns not_found, halt immediately; do not fabricate content or guess at the paper's likely contents.
- ▌ Deep Insight Paper Search 2 · yogsoth-aiAI-powered paper summary and search. Import of literature-engine/literature-search skill. AI summary level — cite as "AI-extracted" not "paper states".
- ▌ Deep Insight Web Research 2 · yogsoth-aiDeep web research with full page fetching via Apify. Import of web-browsing/web-research skill. Must fetch full page — no conclusions from previews.
- ▌ Dialectical Reformulation 2 · yogsoth-aiSurface Argyris governing variables and test whether the problem dissolves under alternative governing variables (double-loop learning).
- ▌ Variation Axis Definition 2 · yogsoth-ai bundleIdentify orthogonal axes along which a method's validity might vary. Ensures axes are independent, measurable, and span the relevant parameter space.
- ▌ Ahrq Reason Classification 2 · yogsoth-ai bundleClassify gap root causes using AHRQ 4-reason framework (insufficient info, biased info, inconsistent info, not yet integrated).
- ▌ Multi Worldview Comparison 2 · yogsoth-aiMulti-worldview comparison — CATWOE from multiple perspectives, reframing matrix across professional lenses, identify overlooked framings. Reveals what single-perspective analysis misses.
- ▌ Claim Writing 2 · yogsoth-ai bundleBlind-rewrite a citing sentence (citance) from another paper into a single atomic, independently-verifiable claim (SciFact's annotation protocol) — never looking at the cited paper's content while rewriting. Use this when you have a specific citing sentence and want it decomposed into checkable atomic claims, as the first step before rationale-selection and claim-label-prediction.
- ▌ Star Awarding 2 · yogsoth-ai bundleAward NOS's (Newcastle-Ottawa Scale) stars item-by-item across Selection (up to 4), Comparability (up to 2), and Outcome/Exposure (up to 3) — a binary award-or-not action per item, distinct from a 5-value signalling judgment. Use this after study-design-tool-gate has dispatched to NOS, as the first step before sum-threshold-scoring.
- ▌ Concept Matrix Construction 2 · yogsoth-ai bundleBuild articles × concepts coverage matrix to visualize research landscape and identify empty cells as gap candidates.
- ▌ Cross Database Verification 2 · yogsoth-ai bundleVerify gap existence across multiple databases (Semantic Scholar, Google Scholar, arXiv, domain-specific). Distinguishes database-specific gaps from universal gaps.
- ▌ Deep Insight Paper Overview 2 · yogsoth-aiPaper metadata and abstract-level overview. Import of literature-engine/literature-overview skill. Abstracts only — no substantive claims without deeper reading.
- ▌ Deep Insight Paper Research 2 · yogsoth-aiFull-text paper reading via three-pass Keshav method. Import of literature-engine/literature-research skill. Authoritative source for claims about paper content.
- ▌ Gap Typology Classification 2 · yogsoth-ai bundleClassify gaps using Miles 7-type taxonomy (theoretical, methodological, empirical, population, practical, knowledge void, evidence gap).
- ▌ Multi Perspective Reframing 2 · yogsoth-aiApply CATWOE from multiple stakeholder viewpoints and reframing matrix to reveal aspects invisible from the dominant perspective.
- ▌ Alternative Model Generation 2 · yogsoth-ai bundleGenerate alternative model formulations by relaxing, replacing, or generalizing specific assumptions.
- ▌ Critical Path Identification 2 · yogsoth-ai bundleIdentify which input uncertainties contribute most to output uncertainty and compute EVPI for research prioritization.
- ▌ Dominant Idea Identification 2 · yogsoth-ai bundleIdentify dominant paradigms and assumptions constraining thinking in a research field.
- ▌ Governing Variable Surfacing 2 · yogsoth-ai bundleApply Argyris framework to identify governing variables — the unstated rules driving behavior in a research field.
- ▌ Screening Then Decomposition 2 · yogsoth-aiTwo-phase sensitivity — Morris quick screening to eliminate unimportant factors, then Sobol precise decomposition on survivors. Efficient allocation of analytical effort.
- ▌ Temporal Sensitivity Testing 2 · yogsoth-ai bundleTest whether a gap persists across different time windows (2/5/10 years). Determines if gap is narrowing, widening, or stable over time.
- ▌ First Pass Skim 3 · yogsoth-ai bundleKeshav's first pass over one paper — a 5-10 minute skim of title, abstract, headings, figures, and conclusion only, producing skim notes and a read-deeper judgment. Use this as the first step whenever a paper is being read via the Keshav three-pass method; always precedes second-pass-grasp and never reads section bodies itself.
- ▌ Reforms Grading 2 · yogsoth-aiTactic: Grade an ML/CS paper's reproducibility configuration reporting as complete, partial, or none after checking that clinical appraisal tools do not apply. Use when the question is whether the work can be rerun.
- ▌ Counter Assumption Generation 2 · yogsoth-ai bundleGenerate dialectical opposites for governing variables — coherent alternative worldviews where the opposite is true.
- ▌ Qalmri Worksheet 2 · yogsoth-aiTactic: Fill a six-slot QALMRI worksheet for one paper: Question, Alternatives, Logic, Method, Results, and Inference. Use for a structured reading worksheet rather than a graded evaluation.
- ▌ Question Framing 2 · yogsoth-ai bundleFill a slot-based question-framing schema (PICO, PECO, or SPIDER) from a paper's stated research question. Use this whenever the user wants a paper's research question structured into one of these standard clinical/qualitative-research question frames; this frames what question is being asked, it does not read or evaluate the paper's content otherwise.
- ▌ Acu Nugget Recall 2 · yogsoth-aiTactic: Extract atomic units from one paper and score how much of a caller-supplied summary covers. Use for ACU-style binary or Nugget-style ternary recall checks; cannot run without a target summary.
- ▌ Keshav Three Pass 2 · yogsoth-aiTactic: Read one paper by Keshav's three-pass method — a shallow skim, a contribution-grasping full read, then a deep virtual re-implementation. Use when the goal is understanding a paper rather than extracting a fixed schema.
- ▌ Second Pass Grasp 3 · yogsoth-ai bundleKeshav's second pass — a careful full read (ignoring proof/derivation detail) producing prose-level understanding sufficient to explain the paper's main contribution and evidence to a colleague. Use this after first-pass-skim, as the main content-grasping pass of the Keshav three-pass method; do not force its output into a structured data schema.
- ▌ Unit Segmentation 2 · yogsoth-ai bundleSplit a paper's text into sentence- or clause-level units (with character offsets) for downstream classification, at a caller-specified granularity and scope (full text, abstract-only, or intro-only). Use this as the mandatory first step whenever any sentence/clause-level classification method (Argumentative Zoning, CoreSC, PubMed-RCT, CSAbstruct, Swales move analysis, CODA-19) needs its input pre-segmented — always precedes unit-classification.
- ▌ Worst Case Lookup 2 · yogsoth-ai bundleTake the single most severe domain/item judgment as the overall verdict, for RoB2 (3-value), ROBINS-I (5-value), or AMSTAR-2 (pre-filtered by critical-domain status before worst-case). Use this after domain-level-judgment (for RoB2/ROBINS-I) or quality-appraisal-checklist (for AMSTAR-2) has produced per-domain/item judgments — this SOP has two structurally distinct upstream callers and must identify which value domain it received before applying the matching lookup rule. QUADAS-2 never reaches this SOP; it terminates one step earlier at domain-level-judgment.
- ▌ Deep Insight Gap Identification 2 · yogsoth-aiIdentify research gaps via PICOS frameworks, concept matrices, evidence gap maps, keyword extraction, citation analysis, and topic modeling. Systematic discovery of what is missing in the literature.
- ▌ Deep Insight Gap Prioritization 2 · yogsoth-aiScore and rank validated gaps on importance, feasibility, novelty, and urgency. Multi-criteria decision analysis with stakeholder confirmation.
- ▌ Qasper Evidence QA 2 · yogsoth-ai bundleAnswer a specific question about a paper, grounding the answer in exact quoted evidence spans from the text (QASPER-style question-driven QA with span-level evidence, no schema categorization). Use this whenever the user asks a specific factual question about a paper and wants the answer traceable to exact text spans.
- ▌ Abp Vulnerability Classification 2 · yogsoth-ai bundleClassify assumptions on 2 axes — load-bearing (how much conclusion depends on it) × vulnerable (how likely to be false). Focuses attention on High-Load × High-Vulnerable quadrant.
- ▌ Atomic Unit Writing 2 · yogsoth-ai bundleExtract (ACU-style) or freshly author (Nugget-style) a list of atomic content units from a paper, optionally tagged vital/okay for importance. Use this as the first step whenever building a reference set of atomic facts for later recall-checking a summary or abstract against the paper — always precedes atomic-unit-matching.
- ▌ Rationale Selection 2 · yogsoth-ai bundleSelect the minimal set of 1-3 verbatim sentences from a candidate paper/abstract sufficient to entail or refute an atomic claim (SciFact's rationale-selection step). Use this after claim-writing has produced an atomic claim, as the evidence-gathering step before claim-label-prediction; an empty rationale set is a valid outcome, not an error.
- ▌ Unit Classification 2 · yogsoth-ai bundleClassify each pre-segmented text unit independently against a fixed label set (Argumentative Zoning, CoreSC, PubMed-RCT, Swales move/step, CODA-19, TDMS, or CSFCube's facet labels), single-layer with no cross-unit dependency. Use this after unit-segmentation has split the text, whenever a sentence- or clause-level rhetorical/functional classification is needed; do not use this for methods requiring document-level coreference reasoning (see multi-stage-cascade-extraction instead).
- ▌ Deep Insight Assumption Surfacing 2 · yogsoth-ai bundleSystematically extract implicit assumptions from methods, frameworks, or arguments. Identifies what is taken for granted without explicit justification.
- ▌ Argumentative Zoning 2 · yogsoth-aiTactic: Label every sentence of one paper with its rhetorical role using Argumentative Zoning. Use when fixed rhetorical labels and cross-paper alignment matter.
- ▌ Atomic Unit Matching 2 · yogsoth-ai bundleJudge, per atomic content unit, whether a target text (summary, abstract, or other candidate text) contains it — binary present/absent (ACU) or ternary support/partial_support/not_support (Nugget), per caller's value domain. Use this after atomic-unit-writing has produced the reference units, as the matching step before recall aggregation.
- ▌ Third Pass Deep Read 2 · yogsoth-ai bundleKeshav's third pass — the heaviest of the three, a full sentence-by-sentence re-read including proofs/derivations, attempting a virtual re-implementation of the paper to surface implicit assumptions and concrete improvement points. Use this after second-pass-grasp, as the terminal step of the Keshav three-pass method, whenever genuine mastery of a paper (not just a summary) is needed. This is not a skippable recap — treat "nothing new to add" as suspicious, not a default outcome.
- ▌ Conclusion Sensitivity Measurement 2 · yogsoth-ai bundleQuantify how much conclusions change across all assumption negations and produce a sensitivity ranking.
- ▌ Deep Insight Assumption Extraction 2 · yogsoth-ai bundleSystematically extract all assumptions (stated, implicit, boundary, mathematical, practical) from a method or model.
- ▌ Domain Level Judgment 2 · yogsoth-ai bundleFold raw signalling-question answers into domain-level judgments for RoB2, ROBINS-I, or QUADAS-2, per each tool's own lookup rules — the first of two aggregation levels these tools define. QUADAS-2 is dual-axis (risk-of-bias AND applicability-concern per domain, D1-D3) and terminates here with no further rollup; RoB2/ROBINS-I continue on to worst-case-lookup for an overall verdict. Use this after signalling-question-answering has produced the raw answers.
- ▌ Sum Threshold Scoring 2 · yogsoth-ai bundleSum NOS's item-level stars and bucket into good (≥7)/fair (4-6)/poor (≤3) — a fixed threshold lookup, structurally distinct from worst-case-lookup's take-the-worst-value approach. Use this after star-awarding has produced the per-item stars; this is NOS's terminal step.
- ▌ Template Slot Filling 2 · yogsoth-ai bundleFill a paper's reported values into an already-given comparison-template attribute schema (e.g. Task/Dataset/Metric/Value) — the executable half of ORKG's comparison-template method. Use this when a template's attribute schema is already fixed and you need one paper's row filled in; this does NOT build new templates (that half is a human-curator task, out of scope).
- ▌ Deep Insight Assumption Enumeration 2 · yogsoth-ai bundleSystematically identify all assumptions in a method/model — structural, parametric, distributional, and scope assumptions.
- ▌ Deep Insight Dialectical Escalation 2 · yogsoth-aiDouble-loop learning escalation — surface governing variables, generate counter-assumptions, test if problem dissolves under alternatives, score wickedness if it persists.
- ▌ Deep Insight Multi Criteria Scoring 2 · yogsoth-ai bundleScore gaps on multiple dimensions (importance, feasibility, novelty, urgency, impact) using weighted multi-criteria decision analysis.
- ▌ Deep Insight Provocation Generation 2 · yogsoth-ai bundleGenerate de Bono lateral thinking provocations to challenge dominant ideas using escape, reversal, exaggeration, and distortion.
- ▌ Claim Label Prediction 2 · yogsoth-ai bundleJudge a three-way SUPPORTS/REFUTES/NOINFO label for an atomic claim, based only on its selected rationale sentences (SciFact's final classification step). Use this after rationale-selection has produced the evidence sentences — this is the terminal step of the SciFact chain, producing the complete (claim, abstract, label, rationale) tuple.
- ▌ Dual Column Self Check 2 · yogsoth-ai bundleRun one of the ML/CS reproducibility checklists (ML Reproducibility Checklist, REFORMS, NeurIPS Paper Checklist, Model Cards, Datasheets for Datasets) against a paper as a reader-side audit, producing a category (Yes/No/NA) plus free-text reason per item. Use this whenever the user wants a reproducibility/completeness self-check run on an ML or CS paper — invoke this directly, it has no study-design gate in this package since these checklists are engineering self-audits, not clinical-study tools.
- ▌ Study Design Tool Gate 2 · yogsoth-ai bundleClassify a paper's study design (RCT, cohort, case-control, diagnostic-accuracy, systematic-review, animal-study, prediction-model, etc., or not_applicable) and dispatch to the correct downstream bias-risk/quality/reporting tool and specific variant (CASP has 8 variants, JBI ~6, RoB2 has parallel/cluster/crossover versions). Use this as the mandatory first step before running ANY of CASP, JBI, AMSTAR-2, NOS, RoB2, ROBINS-I, QUADAS-2, CONSORT, STROBE, ARRIVE, SPIRIT, TRIPOD, or engineering-config-grading — these tools are all study-design-conditional and picking the wrong variant produces meaningless results. It is entirely correct and common for this gate to determine that none of these medically-descended tools applies (e.g. most CS/ML papers) — that is a valid, complete answer, not a failure.
- ▌ Deep Insight Assumption Perturbation 2 · yogsoth-aiOne-at-a-time assumption perturbation — extract assumptions, define negations, re-derive conclusions under each negation, measure sensitivity. Identifies which assumptions are load-bearing.
- ▌ Deep Insight Failure Mode Cataloging 2 · yogsoth-aiSystematic failure mode cataloging — generate boundary inputs, observe failures, cluster by mechanism, identify triggers, estimate frequency.
- ▌ Deep Insight Validity Envelope Mapping 2 · yogsoth-aiMap multi-dimensional validity envelopes — define variation axes, perturb systematically, measure degradation, construct boundary surface.
- ▌ Engineering Config Grading 2 · yogsoth-ai bundle(Proposal, unverified) Grade reproducibility-relevant engineering configuration items (hyperparameter search range, compute budget, seed handling, dataset splits) on a complete/partial/none scale, requiring the grader to first define what "complete" means per item before judging against it. Use this after study-design-tool-gate has dispatched an ML/CS engineering paper here; this is a graded QUALITY judgment, distinct from dual-column-self-check's binary Yes/No/NA self-audit checklists.
- ▌ Quality Appraisal Checklist 2 · yogsoth-ai bundleRun CASP (8 study-type variants), JBI (~6 variants), or AMSTAR-2 quality-appraisal checklists — each ending in the tool's own required integrated judgment, not just item tallies. Also runs a proposal "rhetorical-completeness-check" mode (entry_mode="completeness_check") that instead diffs unit-classification's rhetorical labels against a target checklist's expected label set. Use this after study-design-tool-gate has dispatched to CASP/JBI/AMSTAR-2 (mode a), or directly after unit-classification when checking for missing argumentative moves (mode b, proposal/unverified).
- ▌ First Pass Skim 2 · yogsoth-ai bundleFive-minute skim pass over a single academic paper (title, abstract, headings, figures, conclusion only) to classify the paper's type and draft candidate public-audience angles before any deep reading happens. Use this as the entry point whenever the user gives you one specific paper to summarize, explain, or turn into a WeChat/blog article, and you haven't classified the paper yet. Always run this before second-pass-grasp.
- ▌ Second Pass Grasp 2 · yogsoth-ai bundleFull-text deep-read of a paper's Introduction, Method, and Results sections to draft the structured bundle (problem, method, key results with hedge levels, limitations), each field carrying a precise source anchor. Use this after first-pass-skim has classified the paper and drafted candidate angles — this is the main content-extraction pass of the reading pipeline.
- ▌ Deep Insight Web Search · yogsoth-aiQuick web scanning for landscape understanding. Import of web-browsing/web-search skill. Snippets only — no conclusions from snippets alone.
- ▌ Provocation Generation · yogsoth-aiGenerate PO provocations and extract constructive movement. Orchestrates assumption surfacing → provocation creation → movement extraction → idea formation.
- ▌ Intake · yogsoth-aiLightweight intent clarification dialogue — only invoked when the entry point cannot determine the correct strategy from context alone. Maximum 3 questions. Pure routing, not profiling.
- ▌ Paper Overview · yogsoth-aiAbstract-level paper scanning for broad coverage. Import of literature-engine/literature-overview skill. Abstract-level only — no methodology conclusions from abstracts.
- ▌ Qalmri · yogsoth-ai bundleProduce a six-slot QALMRI worksheet (Question, Alternatives, Logic, Method, Results, Inference) as free-text notes on one paper — a structured note-taking format, not a scored evaluation. Use this whenever the user wants a QALMRI-style reading worksheet for a specific paper.
- ▌ Paper Fetch · yogsoth-ai bundleRetrieve one specified academic paper (by title, arXiv ID, DOI, URL, or a local .md/.txt/.pdf path the caller already has) and land it on disk as source.md plus a source.meta.json carrying a line-number section index. Checks context/papers/ for an existing copy first; local files and direct PDF URLs are read directly with no search at all, while other references use alphaxiv, Semantic Scholar routing, then bioRxiv/medRxiv. Use this as the mandatory first step whenever any other paper-reading SOP in this package needs the actual text of a paper — it is the sole entry point of the pipeline and every downstream SOP reads the files it lands, so do not bypass it even when the caller already has the file. If it returns not_found, halt immediately; do not fabricate content or guess at the paper's likely contents.
- ▌ Claim Writing · yogsoth-ai bundleBlind-rewrite a citing sentence (citance) from another paper into a single atomic, independently-verifiable claim (SciFact's annotation protocol) — never looking at the cited paper's content while rewriting. Use this when you have a specific citing sentence and want it decomposed into checkable atomic claims, as the first step before rationale-selection and claim-label-prediction.
- ▌ Star Awarding · yogsoth-ai bundleAward NOS's (Newcastle-Ottawa Scale) stars item-by-item across Selection (up to 4), Comparability (up to 2), and Outcome/Exposure (up to 3) — a binary award-or-not action per item, distinct from a 5-value signalling judgment. Use this after study-design-tool-gate has dispatched to NOS, as the first step before sum-threshold-scoring.
- ▌ First Pass Skim · yogsoth-ai bundleKeshav's first pass over one paper — a 5-10 minute skim of title, abstract, headings, figures, and conclusion only, producing skim notes and a read-deeper judgment. Use this as the first step whenever a paper is being read via the Keshav three-pass method; always precedes second-pass-grasp and never reads section bodies itself.
- ▌ Reforms Grading · yogsoth-aiTactic: Grade an ML/CS paper's reproducibility configuration reporting as complete, partial, or none after checking that clinical appraisal tools do not apply. Use when the question is whether the work can be rerun.
- ▌ Qalmri Worksheet · yogsoth-aiTactic: Fill a six-slot QALMRI worksheet for one paper: Question, Alternatives, Logic, Method, Results, and Inference. Use for a structured reading worksheet rather than a graded evaluation.
- ▌ Question Framing · yogsoth-ai bundleFill a slot-based question-framing schema (PICO, PECO, or SPIDER) from a paper's stated research question. Use this whenever the user wants a paper's research question structured into one of these standard clinical/qualitative-research question frames; this frames what question is being asked, it does not read or evaluate the paper's content otherwise.
- ▌ Acu Nugget Recall · yogsoth-aiTactic: Extract atomic units from one paper and score how much of a caller-supplied summary covers. Use for ACU-style binary or Nugget-style ternary recall checks; cannot run without a target summary.
- ▌ Keshav Three Pass · yogsoth-aiTactic: Read one paper by Keshav's three-pass method — a shallow skim, a contribution-grasping full read, then a deep virtual re-implementation. Use when the goal is understanding a paper rather than extracting a fixed schema.
- ▌ Second Pass Grasp · yogsoth-ai bundleKeshav's second pass — a careful full read (ignoring proof/derivation detail) producing prose-level understanding sufficient to explain the paper's main contribution and evidence to a colleague. Use this after first-pass-skim, as the main content-grasping pass of the Keshav three-pass method; do not force its output into a structured data schema.
- ▌ Unit Segmentation · yogsoth-ai bundleSplit a paper's text into sentence- or clause-level units (with character offsets) for downstream classification, at a caller-specified granularity and scope (full text, abstract-only, or intro-only). Use this as the mandatory first step whenever any sentence/clause-level classification method (Argumentative Zoning, CoreSC, PubMed-RCT, CSAbstruct, Swales move analysis, CODA-19) needs its input pre-segmented — always precedes unit-classification.
- ▌ Worst Case Lookup · yogsoth-ai bundleTake the single most severe domain/item judgment as the overall verdict, for RoB2 (3-value), ROBINS-I (5-value), or AMSTAR-2 (pre-filtered by critical-domain status before worst-case). Use this after domain-level-judgment (for RoB2/ROBINS-I) or quality-appraisal-checklist (for AMSTAR-2) has produced per-domain/item judgments — this SOP has two structurally distinct upstream callers and must identify which value domain it received before applying the matching lookup rule. QUADAS-2 never reaches this SOP; it terminates one step earlier at domain-level-judgment.
- ▌ Qasper Evidence QA · yogsoth-ai bundleAnswer a specific question about a paper, grounding the answer in exact quoted evidence spans from the text (QASPER-style question-driven QA with span-level evidence, no schema categorization). Use this whenever the user asks a specific factual question about a paper and wants the answer traceable to exact text spans.
- ▌ Atomic Unit Writing · yogsoth-ai bundleExtract (ACU-style) or freshly author (Nugget-style) a list of atomic content units from a paper, optionally tagged vital/okay for importance. Use this as the first step whenever building a reference set of atomic facts for later recall-checking a summary or abstract against the paper — always precedes atomic-unit-matching.
- ▌ Rationale Selection · yogsoth-ai bundleSelect the minimal set of 1-3 verbatim sentences from a candidate paper/abstract sufficient to entail or refute an atomic claim (SciFact's rationale-selection step). Use this after claim-writing has produced an atomic claim, as the evidence-gathering step before claim-label-prediction; an empty rationale set is a valid outcome, not an error.
- ▌ Unit Classification · yogsoth-ai bundleClassify each pre-segmented text unit independently against a fixed label set (Argumentative Zoning, CoreSC, PubMed-RCT, Swales move/step, CODA-19, TDMS, or CSFCube's facet labels), single-layer with no cross-unit dependency. Use this after unit-segmentation has split the text, whenever a sentence- or clause-level rhetorical/functional classification is needed; do not use this for methods requiring document-level coreference reasoning (see multi-stage-cascade-extraction instead).
- ▌ Argumentative Zoning · yogsoth-aiTactic: Label every sentence of one paper with its rhetorical role using Argumentative Zoning. Use when fixed rhetorical labels and cross-paper alignment matter.
- ▌ Atomic Unit Matching · yogsoth-ai bundleJudge, per atomic content unit, whether a target text (summary, abstract, or other candidate text) contains it — binary present/absent (ACU) or ternary support/partial_support/not_support (Nugget), per caller's value domain. Use this after atomic-unit-writing has produced the reference units, as the matching step before recall aggregation.
- ▌ Third Pass Deep Read · yogsoth-ai bundleKeshav's third pass — the heaviest of the three, a full sentence-by-sentence re-read including proofs/derivations, attempting a virtual re-implementation of the paper to surface implicit assumptions and concrete improvement points. Use this after second-pass-grasp, as the terminal step of the Keshav three-pass method, whenever genuine mastery of a paper (not just a summary) is needed. This is not a skippable recap — treat "nothing new to add" as suspicious, not a default outcome.
- ▌ Domain Level Judgment · yogsoth-ai bundleFold raw signalling-question answers into domain-level judgments for RoB2, ROBINS-I, or QUADAS-2, per each tool's own lookup rules — the first of two aggregation levels these tools define. QUADAS-2 is dual-axis (risk-of-bias AND applicability-concern per domain, D1-D3) and terminates here with no further rollup; RoB2/ROBINS-I continue on to worst-case-lookup for an overall verdict. Use this after signalling-question-answering has produced the raw answers.
- ▌ Sum Threshold Scoring · yogsoth-ai bundleSum NOS's item-level stars and bucket into good (≥7)/fair (4-6)/poor (≤3) — a fixed threshold lookup, structurally distinct from worst-case-lookup's take-the-worst-value approach. Use this after star-awarding has produced the per-item stars; this is NOS's terminal step.
- ▌ Template Slot Filling · yogsoth-ai bundleFill a paper's reported values into an already-given comparison-template attribute schema (e.g. Task/Dataset/Metric/Value) — the executable half of ORKG's comparison-template method. Use this when a template's attribute schema is already fixed and you need one paper's row filled in; this does NOT build new templates (that half is a human-curator task, out of scope).
- ▌ Claim Label Prediction · yogsoth-ai bundleJudge a three-way SUPPORTS/REFUTES/NOINFO label for an atomic claim, based only on its selected rationale sentences (SciFact's final classification step). Use this after rationale-selection has produced the evidence sentences — this is the terminal step of the SciFact chain, producing the complete (claim, abstract, label, rationale) tuple.
- ▌ Dual Column Self Check · yogsoth-ai bundleRun one of the ML/CS reproducibility checklists (ML Reproducibility Checklist, REFORMS, NeurIPS Paper Checklist, Model Cards, Datasheets for Datasets) against a paper as a reader-side audit, producing a category (Yes/No/NA) plus free-text reason per item. Use this whenever the user wants a reproducibility/completeness self-check run on an ML or CS paper — invoke this directly, it has no study-design gate in this package since these checklists are engineering self-audits, not clinical-study tools.
- ▌ Study Design Tool Gate · yogsoth-ai bundleClassify a paper's study design (RCT, cohort, case-control, diagnostic-accuracy, systematic-review, animal-study, prediction-model, etc., or not_applicable) and dispatch to the correct downstream bias-risk/quality/reporting tool and specific variant (CASP has 8 variants, JBI ~6, RoB2 has parallel/cluster/crossover versions). Use this as the mandatory first step before running ANY of CASP, JBI, AMSTAR-2, NOS, RoB2, ROBINS-I, QUADAS-2, CONSORT, STROBE, ARRIVE, SPIRIT, TRIPOD, or engineering-config-grading — these tools are all study-design-conditional and picking the wrong variant produces meaningless results. It is entirely correct and common for this gate to determine that none of these medically-descended tools applies (e.g. most CS/ML papers) — that is a valid, complete answer, not a failure.
- ▌ Engineering Config Grading · yogsoth-ai bundle(Proposal, unverified) Grade reproducibility-relevant engineering configuration items (hyperparameter search range, compute budget, seed handling, dataset splits) on a complete/partial/none scale, requiring the grader to first define what "complete" means per item before judging against it. Use this after study-design-tool-gate has dispatched an ML/CS engineering paper here; this is a graded QUALITY judgment, distinct from dual-column-self-check's binary Yes/No/NA self-audit checklists.
- ▌ Quality Appraisal Checklist · yogsoth-ai bundleRun CASP (8 study-type variants), JBI (~6 variants), or AMSTAR-2 quality-appraisal checklists — each ending in the tool's own required integrated judgment, not just item tallies. Also runs a proposal "rhetorical-completeness-check" mode (entry_mode="completeness_check") that instead diffs unit-classification's rhetorical labels against a target checklist's expected label set. Use this after study-design-tool-gate has dispatched to CASP/JBI/AMSTAR-2 (mode a), or directly after unit-classification when checking for missing argumentative moves (mode b, proposal/unverified).
- ▌ Research Question Appraisal · yogsoth-ai bundleJudge a paper's stated research question against the FINER criteria (Feasible, Interesting, Novel, Ethical, Relevant) — five independent judgments with justification, evaluating the question itself, not the paper's results. Use this whenever the user wants to know whether a paper is asking a good research question, distinct from whether it answered that question well.