IDEA DISCOVERY / VERSION LIBRARY
From contribution lenses to source-conditioned research action.
Earlier versions preserve the evolution of design and implementation; the current project entry is Aletheia v7.3.0.
Choose a contribution lens and fix the field and priors before developing research questions.
This stage organizes research ideation around twelve contribution types, including methods, theory, perspectives and measurement. It fixes the subfield and essential prior work, combines first-principles kernels with transferable anchors, and develops candidates with a clear difference, risk and decisive test.
Version detailsCandidate trees, state lifecycles, provenance gates and stage scheduling enter the engineering scaffolding.
V4 expands the one-shot protocol into seven search spaces: domains, contribution lenses, kernels and anchors, mathematics, physics, experiments and reviewer attacks. The scope and budget are fixed first; candidates and refutations become structured state before review, repair and termination.
Version detailsHill focuses on engineering reliability. A model-call bridge and structural and semantic validation turn missing responses, placeholders and empty refutation ledgers into pauses or explicit invalid states, with review records saved separately.
Version detailsOcean assigns tree expansion to specialized model roles for field splitting, kernel mapping, anchor transfer, mechanism construction, experiment design and refutation. Python wraps and records their responses; the mathematics–physics bridge becomes a staged model-call pipeline.
Version detailsStars repairs advancement after a pause, frontier construction without a literature response and incomplete final-report fields. Operators are scheduled by node type, with visits and attempted actions recorded to make process state explicit.
Version detailsJupiter separates draft, checked, refuted and internally accepted candidate states. Ledger decisions return to the tree and block unsuitable candidates; state changes and events are saved so the tree and final report remain consistent.
Version detailsGalaxy accepts both single-node and list model responses, injects kernel and anchor seeds and uses provenance flags to keep seed-only candidates out of the internal acceptance path. Reviewer rejection, candidate–ledger binding and call budgets become runtime constraints.
Version detailsCosmos uses stage-bucket scheduling to connect mechanism, experiment, attack and candidate stages, reducing the starvation of later-stage nodes by exploration scores. It also tightens model-field coverage, ledger identity binding and renewed refutation after repairs.
Version detailsNova replaces random mathematics–physics triggering with a deterministic depth condition, prioritizes the main candidate path until a first candidate exists and limits bridge branches. Terminal progress and repair-budget guards reduce branch starvation and unchecked repair growth.
Version detailsVerification, surrogate simulation, micro-worlds and evidence binding develop alongside implementations corrected by later audits.
Makes verification a separate execution layer. Candidate artifacts start unverified, and explicit checks govern promotion, rejection, unresolved evidence and honest failure.
Version detailsMoves upstream from filtering false originality to organizing candidate discovery: frontier tensions drive typed operators, equation genomes, mathematical objects, definitions and conjectures before Aurora review.
Version detailsRetains Eureka’s discovery layer while repairing its verification interface: translates discovery objects into Aurora payloads and reconciles every output to one terminal verdict.
Version detailsRoutes harvested equation payloads into verification and extends the Equation Lab with canonical forms, a prior-equation library, small numerical probes and physics diagnostics.
Version detailsAdds explicit viability and bridge firewalls before idea harvesting. Failed candidates remain legible in structured failure records with repair reasons instead of being packaged as discoveries.
Version detailsWires Forge’s standalone components into the live discovery chain: resolved units, viability records, repair traces, CoMath state and prior caps contribute to one package.
Version detailsExpands from equation-term mutation to the choice of mathematical descriptors. Domain, math and physics search trees produce first-class mappings and structured equation ASTs.
Version detailsAdds compatibility, execution and quality constraints to Origin: prune mappings, select diverse elites, execute supported AST terms and route proof strategies by conjecture type.
Version detailsCloses the ontology-to-idea evidence chain around one candidate ID. The release focuses on linkage, property provenance and replay rather than adding mappings or solvers.
Version detailsTyped candidates, evidence governance, module interventions and observation-driven revision form a research-software line.
Extends idea generation into mathematics, algorithms and architectures, organizing candidates through evidence graphs, strongest-prior checks and route-specific gates.
Version detailsHardens Archimedes with subprocess timeouts, numeric benchmarks, finite-graph execution, candidate-ID binding and required-route checks.
Version detailsTurns candidates into compilable objects: equations use registered operator semantics, algorithms face subprocess tests and fixed benchmarks, and architectures produce executable forward paths, all bound to evidence and prior deltas.
Version detailsAdds a generation-side concept-space layer: explicit axiom cards, twelve T operators, diversity archives, quarantined failures, taste forecasts, reality bets and strategy genomes.
Version detailsTurns criticism into executable counterexamples and discriminating experiments, and organizes candidates as research-programme sequences through provenance, re-instantiation, null models, paired bets, anomalies and question genomes.
Version detailsOrganizes research around challenge responses, preregistered predictions and explanatory obligations, adding world-evidence accounting, learning-progress curiosity, prequential meters, explanation checks and world witnesses.
Version detailsTreats reports as evidence indexes: true audits, answer-free sealed challenges, adjudicator-minted settlements, stable hash identities and prosecutor replay must agree, with demonstrations isolated as PASS_DEMO.
Version detailsReplaces one-shot prose with ResearchDelta objects that record questions, representations, assumptions, mechanisms, falsifiers and lineage, organizing multi-generation search through isolated populations, multi-niche archives and independent event replay.
Version detailsUpgrades the default path to an observation-driven controller: HTTP model providers propose constrained candidates, the operator locks tasks and baselines, execution yields concrete counterevidence and revision obligations, and evidence authorizes representation changes.
Version detailsAletheia focuses on source-conditioned questions, rivals, actions and a persistent frontier. The current version is 7.3.0.
Inherit v6.8 engineering mechanisms and add primary-text evidence, rival explanations, typed actions, explicit stopping, Fusion contracts and local receipts in a standalone Aletheia module. Synthetic demos and fixed-weight meta evaluation check execution paths.
Version detailsAdd conditional rival updates and a persistent frontier. The macro loop retains branches and deferred actions; the micro loop connects predictions, host attestation, observations and revision contracts, repairing unrelated-observation admission, zero-action quota and silent rival resurrection.
Version detailsAdd an authenticated Codex proposal provider and signed paired pilots. The model selected different correct next measurements under two observations. After same-case field clarification, both proposals passed revision and host contracts. Initial failures, usage and execution-gate repairs remain recorded.
Version detailsRecord the authorized literature-development loop and frozen eight-state A/B/C/D/E comparison, repairing source fields, query context, acquisition receipts, stop closure and observed-action registration. Feedback control is supported; ordinary active design matches the paired result, leaving separate harness gains unestablished.
Version detailsThe introduction draws on bundled notes, changelogs and central code. Software tests, synthetic diagnostics and scientific effectiveness use different evidence standards.