Method composition
A method is rarely atomic. Theseus's published methods rest on each other: an extractor feeds a coherence judge, which feeds a synthesis step. This map shows the public-visible portion of that dependency graph. The internal version of this graph carries drift state and failure-mode flags; only the structure is published here.
Methods and their dependencies
The same dependency structure drawn above, as a card per method — this is the primary view on a phone, where the radial map is too dense to read.
- classify_claim_typev1.0.0Classifies a claim into discourse categories (METHODOLOGICAL, SUBSTANTIVE, etc.).composes: —
- contradiction_geometryv1.0.0Detects contradiction via Hoyer sparsity of embedding difference vectors.composes: —
- contradiction_probev1.0.0Predicts the embedding-space neighborhood where a new proposition's logical contradiction should lie, then surfaces nearby existing propositions as unconfirmed candidates.composes: contradiction_geometry
- decompose_voicev1.0.0Decomposes a founder's voice into an intellectual profile with orientation scores.composes: —
- external_claim_matchv1.0.0Ingests external literature and matches claims against internal positions.composes: —
- extract_claimsv1.0.0Extracts atomic truth-apt claims from a text chunk using an LLM.composes: —
- extract_methodologyv1.0.0Extracts portable methodology profiles from a source text.composes: —
- extract_predictionv1.0.0Extracts falsifiable world predictions from a single claim using an LLM.composes: —
- method_candidate_extractorv1.0.0Scans ingested artifacts for passages describing a methodology and extracts structured method candidates via regex + LLM.composes: —
- nli_scorerv1.0.0NLI cross-encoder scorer for claim pair coherence using DeBERTa.composes: —
- six_layer_coherencev1.0.0Six-layer coherence aggregation with 4/6 majority voting.composes: nli_scorer
- suggest_researchv1.0.0Generates research topics, empirical anchors, and reading lists after a discussion.composes: —
- synthesize_conclusionv1.0.0Registers a substantive conclusion and returns method calibration feedback.composes: extract_claims · nli_scorer · six_layer_coherence
Snapshot regenerated on each deploy. The same depends-on declarations drive both this page and the internal composition view.