Research

IPC/CPC hierarchy drill-down and lateral expansion for patent discovery

Understand what resources the user has available for research — compute, timeline, collaboration, data access, experimental environment. Every item accepts 'TBD' as a valid answer.

Propose a refined claim that survives counterexamples while preserving maximum explanatory power (Lakatos lemma-incorporation).

Patent claim syntax parsing — independent/dependent relationships and element extraction

Formally negate the core claim, producing the logical complement for reductio testing.

Deep claim scope analysis — decompose independent/dependent claims and assess protection scope breadth. Budget: 30 patent families, 30 claim parses, 20 web searches.

Build and analyze patent citation networks — main path analysis, PageRank, cluster detection

Forward and backward citation tracing tactic — expand paper coverage by tracing citation networks in both directions from seed/key papers. Alternates forward (who cited this) and backward (what this cited) passes until saturation.

Checkpoint state before risky operations, detect anomalies, and recover gracefully

Non-threatening 'Why?' questioning of current practices to reveal historical accidents vs. genuine constraints.

Non-threatening 'Why?' questioning of current practices (de Bono Challenge)

Build logical causal trees from symptoms to root causes — list UDEs, connect causal chains, validate logic, locate root causes. Combines ishikawa-decomposition, current-reality-tree, and clr-validation SOPs.

Tactic: Extract causal claims, evaluate probability of necessity (PN) and sufficiency (PS) for each, classify into necessity-sufficiency quadrants.

Extract all causal claims (X causes Y, X leads to Y, X enables Y) from an artifact, producing a structured list of cause-effect pairs.

Trace UDE to root cause via IF...THEN...BECAUSE logic chains

Apply Checkland's CATWOE analysis from a specific stakeholder perspective to reveal how the problem looks from that viewpoint.

Classify candidates into predefined categories using ELECTRE-Tri, FlowSort, AHPSort, or DRSA methods.

Cluster papers by theme, method, or timeline. Produces natural groupings from a paper collection. Used by scoping-survey and narrative-review.

Build capability taxonomy, map existing benchmark coverage

Structured questioning SOP to determine which campaigns to include, emphasize, or skip. Used during spec generation.

Calculate project, feeding, and resource buffers — shared with implementation-planning

Optimize experiment design under compute and time budget constraints

Validate analogy depth and transfer viability. Ensures only deep structural analogies (not surface-level similarities) proceed to transfer.

Test a claim at extreme parameter values and detect the precise point where it breaks down.