{"data":[{"slug":"omega-point","term":"Omega Point","aliases":["the engine","Omega","question hierarchy","decomposition engine"],"area":"engine","short":"The engine that takes one goal about a longer life and descends, step by step, to the experiments that would decide what is unknown.","long":["The Omega Point starts from a vague objective and turns it into one precise master question. It breaks that question into the end-states that would have to hold (goal pillars), each pillar into atomic testable requirements, then maps what established science already delivers across a dozen research domains. Where requirements and science do not meet, it writes gap questions; for every gap it writes several rival hypotheses; for every set of rivals it writes the questions that would tell them apart; and it ends in bench-ready experiment specifications, ranked.","The site presents the result as a contest, not a conclusion: every rival stays in the ring with the one observation that would knock it out, and nothing has been tested. The engine itself is a vendored sub-application; the pages on this site, the explanation layer, the audits and the posters are additive layers that read its output and never feed anything back into it."],"where":["/omega","/omega/hypothesis/<public_id>","/dashboard/omega and the workbench"],"related":["pipeline-steps-omega","master-question","knowledge-gap","hypothesis","explanation-layer","run"],"area_meta":{"key":"engine","title":"The engine","headline":"What the Omega Point is, and the steps it takes","lede":"The run, its numbered agent steps, the ladder of node levels and the critics at the end."},"public_url":"https://eternalsearch.net/dictionary/omega-point","api_url":"https://eternalsearch.net/api/v1/content/dictionary/omega-point"},{"slug":"pipeline-steps-omega","term":"The steps of the engine","aliases":["step 1 to step 9","Initiator","Immortalist Architect","Requirements Engineer","Domain Mapper","Domain Specialist","Strategic Science Officer","Instantiation Gatekeeper","Lead Investigative Officer","Lead Tactical Engineer"],"area":"engine","short":"Nine named agent steps, each with a role: from goal formalization to execution drilldown, then a critic and a ranking.","long":["Step 1, the Initiator (goal formalization), turns the objective into the master question. Step 2, the Immortalist Architect (goal pillars synthesis), decomposes it into goal pillars and writes the bridge lexicon. Step 3, the Requirements Engineer (requirement atomization), turns each pillar into requirement atoms. Step 4a, the Domain Mapper, names eight to twelve research domains; step 4b, the Domain Specialist, fans out over each domain to collect fifteen to twenty-five established scientific pillars. Step 4 takes about three quarters of a run's wall clock.","Step 5, the Judge, is disabled; its strategic matching of science to requirements was folded into step 4b. Step 6, the Strategic Science Officer (frontier question generation), writes the gap questions. Step 7, the Instantiation Gatekeeper, writes maximally divergent hypotheses for each gap. Step 8, the Lead Investigative Officer (tactical decomposition), writes the discriminating questions. Step 9, the Lead Tactical Engineer (execution drilldown), writes the leaf experiments with their system, intervention, meter and time. After step 9 the Genius Experiment Critic improves and rejects, and the best-experiments selector ranks a portfolio. Step 10, the Convergence Critic, is disabled.","The run report renumbers for the reader: the engine's steps 6 to 9 appear as 5 to 8, followed by \"Review outcome\" and \"Run summary\". Both numberings are in use, so a step number alone is ambiguous without saying which scheme is meant."],"where":["Run report section titles","Workbench progress names","apps/question-hierarchy agents.ts"],"related":["omega-point","master-question","goal-pillar","requirement-atom","research-domain","scientific-pillar","knowledge-gap","hypothesis","discriminating-question","experiment","genius-critic","best-experiments"],"area_meta":{"key":"engine","title":"The engine","headline":"What the Omega Point is, and the steps it takes","lede":"The run, its numbered agent steps, the ladder of node levels and the critics at the end."},"public_url":"https://eternalsearch.net/dictionary/pipeline-steps-omega","api_url":"https://eternalsearch.net/api/v1/content/dictionary/pipeline-steps-omega"},{"slug":"run","term":"Run","aliases":["workbench run","omega run","run key","programme","decomposition","resume","interrupted at step"],"area":"engine","short":"One execution of the engine on one goal; the unit everything else is keyed on.","long":["A run has a key, a goal, a stored result and a status that names its stage: executing, completed, failed at execute, failed at persist, or interrupted at step. Interrupted is not a failure; the process running it died and the finished steps are still on disk, so the run resumes. A persisted run's tree plus its ranked portfolio is a programme, also called a decomposition on the dashboard; a decomposition as a whole is never public, only its experiments and hypotheses are. A run can publish hypotheses without ever persisting a programme."],"where":["/dashboard/omega/runs","/dashboard/omega/workbench","omega_workbench_runs, omega_programs"],"related":["omega-point","run-report","node-key","review-status"],"area_meta":{"key":"engine","title":"The engine","headline":"What the Omega Point is, and the steps it takes","lede":"The run, its numbered agent steps, the ladder of node levels and the critics at the end."},"public_url":"https://eternalsearch.net/dictionary/run","api_url":"https://eternalsearch.net/api/v1/content/dictionary/run"},{"slug":"run-report","term":"Run report","aliases":["report snapshot","report","Russian report"],"area":"engine","short":"The deterministic, full-length report of a completed run, assembled in code from the stored result, never by a model.","long":["The report walks the steps under reader-facing titles and never truncates. It downloads as Markdown, text, Word or PDF in English, and in Russian through a localizer agent whose progress and integrity are tracked on the run row."],"where":["/dashboard/omega/runs report downloads"],"related":["run","pipeline-steps-omega"],"area_meta":{"key":"engine","title":"The engine","headline":"What the Omega Point is, and the steps it takes","lede":"The run, its numbered agent steps, the ladder of node levels and the critics at the end."},"public_url":"https://eternalsearch.net/dictionary/run-report","api_url":"https://eternalsearch.net/api/v1/content/dictionary/run-report"},{"slug":"level-ladder","term":"The level ladder","aliases":["levels","level codes","node","node levels","reader-facing names"],"area":"engine","short":"The ten kinds of node in a decomposition tree, from the master question down to the executable experiment.","long":["Q0 is the master question. M_G is a goal pillar. RA is a requirement atom. DOM is a domain finding. S is a seed question. L3 is a gap question. IH is a hypothesis. L4 is a discriminating question. L5 is a mechanistic sub-question. L6 is an idea, a proposed investigation, the executable test with its system, intervention, meter and threshold. The engine names nodes by these codes; the site renders each with its reader-facing name and keeps the code as a chip."],"where":["Provenance chain on experiment pages","omega_nodes.level"],"related":["master-question","goal-pillar","requirement-atom","scientific-pillar","knowledge-gap","hypothesis","discriminating-question","mechanistic-sub-question","experiment"],"area_meta":{"key":"engine","title":"The engine","headline":"What the Omega Point is, and the steps it takes","lede":"The run, its numbered agent steps, the ladder of node levels and the critics at the end."},"public_url":"https://eternalsearch.net/dictionary/level-ladder","api_url":"https://eternalsearch.net/api/v1/content/dictionary/level-ladder"},{"slug":"node-key","term":"Node key","aliases":["node_key","machine key","positional key","IH_"],"area":"engine","short":"The stable key of a node inside its run, such as IH_Q_L3_M_G1_1_01, on which every derived artifact is anchored.","long":["Keys are positional: they say where a node sits in the tree and nothing about its content, and they repeat across runs. That is why a hypothesis is never shown by its key; it gets a name on arrival. Derived content (clear versions, explanations, glossaries, posters) is keyed on the run and node key rather than on a row id, because keying on row ids is what once detached five posters from their experiments."],"where":["Chip inside the open panel of the provenance chain","Every omega_* derived table"],"related":["run","hypothesis-name","level-ladder"],"area_meta":{"key":"engine","title":"The engine","headline":"What the Omega Point is, and the steps it takes","lede":"The run, its numbered agent steps, the ladder of node levels and the critics at the end."},"public_url":"https://eternalsearch.net/dictionary/node-key","api_url":"https://eternalsearch.net/api/v1/content/dictionary/node-key"},{"slug":"epistemic-lens","term":"Epistemic lens","aliases":["contextual lens","epistemic frame","lens"],"area":"engine","short":"A selectable worldview injected into the first steps, such as reliability engineering or information theory and error correction.","long":["The lens frames how the goal is decomposed. Options include distributed consensus architecture, synchronization and phase-transition architecture, information theory and error correction, complex adaptive systems, reliability engineering and cybernetic control systems. It is distinct from the three lens origins used when hypotheses are generated."],"where":["Workbench settings","Step 1 and step 2 prompts"],"related":["lens-origin","master-question"],"area_meta":{"key":"engine","title":"The engine","headline":"What the Omega Point is, and the steps it takes","lede":"The run, its numbered agent steps, the ladder of node levels and the critics at the end."},"public_url":"https://eternalsearch.net/dictionary/epistemic-lens","api_url":"https://eternalsearch.net/api/v1/content/dictionary/epistemic-lens"},{"slug":"genius-critic","term":"Genius Experiment Critic","aliases":["genius verification layer","genius score","step 9.5"],"area":"engine","short":"The harshest peer reviewer in the pipeline: it rewrites, merges and rejects experiment specifications and scores each 1 to 10.","long":["It sits between step 9 and the ranking. It rewrites titles, removes hedging, rejects mediocre experiments, merges permutations and assigns a genius score on a scale where 1 to 3 is forbidden, 8 to 9 is brilliant and 10 is paradigm-shifting; the target average across all experiments is at least 7.5. It also enforces that a null result must be informative."],"where":["Between step 9 and best experiments in a run"],"related":["experiment","best-experiments","if-null","anti-patterns"],"area_meta":{"key":"engine","title":"The engine","headline":"What the Omega Point is, and the steps it takes","lede":"The run, its numbered agent steps, the ladder of node levels and the critics at the end."},"public_url":"https://eternalsearch.net/dictionary/genius-critic","api_url":"https://eternalsearch.net/api/v1/content/dictionary/genius-critic"},{"slug":"best-experiments","term":"Best experiments","aliases":["ranking best experiments","selected experiments","portfolio","wildcard round","final assessment","review outcome"],"area":"engine","short":"The portfolio selector: a senior-strategist pass that ranks the leaf experiments by how decisively they advance the field.","long":["Non-triviality is its highest-priority criterion. A wildcard round selects experiments that maximally complement the guaranteed set, and the final assessment re-ranks under the strictest standards with no pillar allowed more than forty percent of the slots. The report prints the result as the review outcome."],"where":["Run report \"Review outcome\"","omega_selected_experiments"],"related":["experiment","genius-critic","non-triviality"],"area_meta":{"key":"engine","title":"The engine","headline":"What the Omega Point is, and the steps it takes","lede":"The run, its numbered agent steps, the ladder of node levels and the critics at the end."},"public_url":"https://eternalsearch.net/dictionary/best-experiments","api_url":"https://eternalsearch.net/api/v1/content/dictionary/best-experiments"},{"slug":"program-synthesizer","term":"Program Synthesizer","aliases":["prioritizer","research program","Now, Next, Later"],"area":"engine","short":"A Studio-only fan-in agent that turns a finished tree into one prioritized research programme with tiers Now, Next and Later.","long":["Each recommended action carries a score, a tier, a rationale, its dependencies and explicit coverage of the tree. It exists only in the Agent Studio version of the pipeline."],"where":["Agent Studio Omega pipeline"],"related":["best-experiments","omega-point"],"area_meta":{"key":"engine","title":"The engine","headline":"What the Omega Point is, and the steps it takes","lede":"The run, its numbered agent steps, the ladder of node levels and the critics at the end."},"public_url":"https://eternalsearch.net/dictionary/program-synthesizer","api_url":"https://eternalsearch.net/api/v1/content/dictionary/program-synthesizer"},{"slug":"node-feedback","term":"Node feedback","aliases":["excellent","needs improvement","incorrect","too vague","too ambitious","feedback categories"],"area":"engine","short":"The operator's review vocabulary for any node in the workbench, with a stated downstream meaning per level.","long":["The categories are excellent, needs improvement, incorrect, too vague, too ambitious, not novel and other. For each level the workbench explains what the category means and what it means for the nodes below."],"where":["/dashboard/omega/workbench"],"related":["level-ladder","non-triviality"],"area_meta":{"key":"engine","title":"The engine","headline":"What the Omega Point is, and the steps it takes","lede":"The run, its numbered agent steps, the ladder of node levels and the critics at the end."},"public_url":"https://eternalsearch.net/dictionary/node-feedback","api_url":"https://eternalsearch.net/api/v1/content/dictionary/node-feedback"},{"slug":"master-question","term":"Master question","aliases":["Q0","Q₀","engineering-grade master question"],"area":"objects","short":"The single precise question the whole run answers, written from the operator's goal by step 1.","long":["It must be solution-neutral, explicit about the system it concerns, anchored to a baseline, driven by success criteria, decomposable, and explicit about mission duration. Everything below it is a narrowing of it, and the question-fidelity audit later measures whether the descent still answers what the operator typed rather than what the engine rewrote."],"where":["Top of the provenance chain","Run report \"The question the engine set itself\""],"related":["goal-pillar","level-ladder","question-fidelity","answer-contract"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/master-question","api_url":"https://eternalsearch.net/api/v1/content/dictionary/master-question"},{"slug":"goal-pillar","term":"Goal pillar","aliases":["pillar","M_G","teleological goal pillar","required end-state","cross-cutting pillar"],"area":"objects","short":"One required end-state that, together with the others, would make the master question plausible.","long":["Pillars are architecture-neutral and as mutually exclusive and jointly exhaustive as the engine can make them. They are found by inverse failure analysis: list the catastrophic failures, cluster them, and invert each cluster into the healthy steady state that must hold. A pillar title must name a mechanism of failure, not an anatomical subsystem; a title that could be a textbook chapter is rejected. At least one pillar must be cross-cutting, addressing a systemic failure not obvious from anatomy. Each pillar carries a role: failure mechanism, or the one reserved identification pillar.","Note the two uses of \"pillar\": a goal pillar is a required end-state on the goal side; a scientific pillar is a piece of established science on the reality side."],"where":["Second rung of the provenance chain","Pillar provenance audit"],"related":["master-question","inverse-failure-analysis","bridge-lexicon","pillar-role","scientific-pillar","requirement-atom","pillar-provenance"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/goal-pillar","api_url":"https://eternalsearch.net/api/v1/content/dictionary/goal-pillar"},{"slug":"inverse-failure-analysis","term":"Inverse failure analysis","aliases":["IFA","naming test","anatomy test"],"area":"objects","short":"The method step 2 uses: enumerate catastrophic failures, cluster them, and invert each cluster into a required healthy state.","long":["Failures are first classified as within or between subsystems, then clustered into pillars. The naming test then rejects any pillar whose title describes a subsystem rather than the mechanism by which it fails."],"where":["Step 2 prompt"],"related":["goal-pillar","failure-channel"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/inverse-failure-analysis","api_url":"https://eternalsearch.net/api/v1/content/dictionary/inverse-failure-analysis"},{"slug":"bridge-lexicon","term":"Bridge lexicon","aliases":["shared language","shared vocabulary"],"area":"objects","short":"Two lists written in step 2, failure channels and system property variables, that every later stage tags against.","long":["The lexicon is what lets goals be mapped to scientific reality: requirements, scientific pillars and experiments all refer back to the same named failure channels and the same measurable properties. The run report prints it as \"Shared vocabulary: failure channels and system properties\"."],"where":["Run report","Step 2 output"],"related":["failure-channel","system-property-variable","goal-pillar"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/bridge-lexicon","api_url":"https://eternalsearch.net/api/v1/content/dictionary/bridge-lexicon"},{"slug":"failure-channel","term":"Failure channel","aliases":["FCC","failure channels","failure shape","FS_"],"area":"objects","short":"A failure pattern specific to the target system, six to ten of them per run, named in the bridge lexicon.","long":["Requirement atoms then describe each failure with a controlled failure shape such as slow drift to cliff, runaway feedback, compensatory toxicity, hysteresis lock, synchronization loss or unmodeled. At least one atom must target failure channels not captured by current meters."],"where":["Bridge lexicon","Requirement atoms"],"related":["bridge-lexicon","system-property-variable","requirement-atom","unknown-unknown-atom"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/failure-channel","api_url":"https://eternalsearch.net/api/v1/content/dictionary/failure-channel"},{"slug":"system-property-variable","term":"System property variable","aliases":["SPV","system properties","state variable","SV_"],"area":"objects","short":"A measurable property of the target system, with a unit and a measurement approach, eight to twelve per run.","long":["Experiments link back to the property they move. Requirement atoms use controlled state-variable names on the same idea, such as functional reserve or an unknown failure channel."],"where":["Bridge lexicon","Leaf experiments (spv_link)"],"related":["bridge-lexicon","failure-channel","simt"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/system-property-variable","api_url":"https://eternalsearch.net/api/v1/content/dictionary/system-property-variable"},{"slug":"requirement-atom","term":"Requirement atom","aliases":["RA","atom","atoms","done criteria"],"area":"objects","short":"One solution-agnostic, testable requirement under a goal pillar, with done criteria and a failure mode.","long":["Each atom names a state variable, a failure shape, the perturbation classes that would expose it, a timescale (acute, subacute, chronic or decadal), the classes of meter that could measure it, and a multiple-realizability check requiring at least three distinct architectures that could satisfy it. Atoms carry the same role split as pillars: an identification atom guards against the answer being wrong (the set miscounted, a rival set never compared)."],"where":["Third rung of the decomposition","Run report \"What would count as satisfied\""],"related":["goal-pillar","failure-channel","simt","unknown-unknown-atom","pillar-role","scientific-pillar"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/requirement-atom","api_url":"https://eternalsearch.net/api/v1/content/dictionary/requirement-atom"},{"slug":"unknown-unknown-atom","term":"Unknown-unknown atom","aliases":["latent failure detection","missing observability"],"area":"objects","short":"The requirement atom every pillar must contain that targets failures current meters cannot see.","long":["It is marked with the unknown failure channel state variable or the unmodeled failure shape. Its purpose is to keep the decomposition honest about what is not observable yet."],"where":["Step 3 output"],"related":["requirement-atom","failure-channel","simt"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/unknown-unknown-atom","api_url":"https://eternalsearch.net/api/v1/content/dictionary/unknown-unknown-atom"},{"slug":"research-domain","term":"Research domain","aliases":["domain","DOM","domain finding","domain category","domain scan","reality mapping"],"area":"objects","short":"One of eight to twelve research areas the engine scans for established science relevant to the goal.","long":["Domains are meant to be mutually exclusive and each to contain about twenty-five actionable interventions. Each is tagged core mechanistic, adjacent non-obvious, or measurement technology. Step 4b fans out over the domains, one call each; when the proxy pool has less capacity than domains, a domain can be silently dropped, which is why the domain count of a run is checked."],"where":["Step 4 \"Reality Mapping (Domain Scan)\""],"related":["scientific-pillar","pipeline-steps-omega"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/research-domain","api_url":"https://eternalsearch.net/api/v1/content/dictionary/research-domain"},{"slug":"scientific-pillar","term":"Scientific pillar","aliases":["S-node","S_","scientific record","readiness level","fragility score"],"area":"objects","short":"A piece of established, evidence-based science collected in step 4b: what is actually known, never a speculative intervention.","long":["Each carries a mechanism, a verified effect, a readiness level (RL-1 lab-validated, RL-2 human data or models, RL-3 clinically deployed), capabilities, a fragility score from 1 to 10, and its relationship to the goal. Scientific pillars are what the gap questions compare against requirements; the pillar provenance audit later checks whether the studies they cite can be found."],"where":["Step 4b output","Pillar provenance"],"related":["research-domain","requirement-atom","edge-taxonomy","pillar-provenance","goal-pillar"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/scientific-pillar","api_url":"https://eternalsearch.net/api/v1/content/dictionary/scientific-pillar"},{"slug":"edge-taxonomy","term":"Edge taxonomy","aliases":["solves","partially solves","proxies for","violates","enables measurement for","the redline"],"area":"objects","short":"The kinds of link between a requirement and a scientific pillar: solves, partially solves, proxies for, violates, or enables measurement for.","long":["A \"violates\" link is the redline: the science improves one requirement but its failure modes trigger a catastrophe the goal defines, and such links are removed. A partial link is sub-classified by the kind of delta: magnitude, execution, timescale or knowledge."],"where":["Step 4b and the disabled Judge"],"related":["scientific-pillar","requirement-atom","gap-triple"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/edge-taxonomy","api_url":"https://eternalsearch.net/api/v1/content/dictionary/edge-taxonomy"},{"slug":"knowledge-gap","term":"Knowledge gap","aliases":["gap","gap question","L3","seed question","epistemic gap","frontier question","knowledge-gap question"],"area":"objects","short":"A genuine unknown where what the requirements need and what established science delivers do not meet, stated as a question that a literature search cannot answer.","long":["Step 6 writes the gap questions. Each must identify an epistemic gap that would change how the problem is thought about, and each is typed by what kind of gap it is. On the public site the gap is the unknown a hypothesis exists to explain; the reader meets it first as a rewritten heading stating its core, with the engine's original sentence folded underneath.","A gap question can also turn out to be already answered in the literature. The explanation layer says so plainly, because a pipeline proposing a closed gap is a valuable finding, not a failure."],"where":["\"The unknown\" on a hypothesis page","\"What was not known\" on an experiment page","/omega/experiments \"The Gaps Worth Attacking\""],"related":["gap-type","gap-triple","gap-strategy","hypothesis","gap-verdict","gap-card","gap-heading"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/knowledge-gap","api_url":"https://eternalsearch.net/api/v1/content/dictionary/knowledge-gap"},{"slug":"gap-type","term":"Gap type","aliases":["void","fragile","proxy","clash","adversarial","cluster status"],"area":"objects","short":"What kind of unknown a gap is: void, fragile, proxy, clash, or adversarial.","long":["Void: nothing is known here, the question has not been asked of this system. Fragile: something is claimed, but on evidence too thin to carry weight. Proxy: what is measured stands in for what matters and may not track it. Clash: two established results predict opposite outcomes and both cannot be right. Adversarial: a question written to disprove the most promising scientific pillar. A goal-level cluster status says which kind dominates: void, fragility trap, proxy mirage or cluster clash."],"where":["Gap card","Run report gap sections"],"related":["knowledge-gap","gap-strategy"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/gap-type","api_url":"https://eternalsearch.net/api/v1/content/dictionary/gap-type"},{"slug":"gap-triple","term":"Needed, exists, delta","aliases":["the gap triple","delta","delta summary","epistemic block"],"area":"objects","short":"The three-part statement of a gap: what the requirements need, what science actually delivers, and the specific difference.","long":["The delta names its kind: magnitude, execution, timescale, knowledge or contradiction. At goal level the engine also writes a delta summary (the gap between the required regime and current capability) and an epistemic block (which assumption is obstructing progress)."],"where":["Step 6 output","Run report"],"related":["knowledge-gap","edge-taxonomy"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/gap-triple","api_url":"https://eternalsearch.net/api/v1/content/dictionary/gap-triple"},{"slug":"gap-strategy","term":"Gap strategy","aliases":["genesis probe","contextual decoupling","causal pivot","arbitration logic","adversarial falsification","strategy protocol"],"area":"objects","short":"The question-writing strategy matched to each gap type.","long":["Genesis probe for a void, contextual decoupling for a fragility trap, causal pivot for a proxy mirage, arbitration logic for a cluster clash, and adversarial falsification, which is mandatory and designs a question to disprove the most promising scientific pillar."],"where":["Step 6 prompt"],"related":["gap-type","knowledge-gap"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/gap-strategy","api_url":"https://eternalsearch.net/api/v1/content/dictionary/gap-strategy"},{"slug":"hypothesis","term":"Hypothesis","aliases":["IH","instantiation hypothesis","hypotheses","competing explanation"],"area":"objects","short":"One of several rival explanations for a gap, each proposing a fundamentally different mechanism, with the prediction that would tell it apart.","long":["Step 7 writes four to seven hypotheses per gap, maximally divergent: each must use a different domain category, the set must contain a heretic that contradicts the mainstream story, a cross-domain transfer from an unrelated field, and scouts including the possibility that the phenomenon does not exist. A hypothesis carries its mechanism, a discriminating prediction, its lens origin, its domain category and, for a cross-domain one, the source field, the law borrowed and the variable mapping.","On the site a hypothesis is a publishable object of its own, named on arrival, keyed on its run, and read in eight sections: the unknown, the claim, the test, the contest, the import, the bench, the standing and the provenance."],"where":["/omega","/omega/hypothesis/<public_id>","omega_hypotheses"],"related":["knowledge-gap","rival","discriminating-prediction","domain-category","lens-origin","heretical-checklist","hypothesis-name","hypothesis-page","hypothesis-audit"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/hypothesis","api_url":"https://eternalsearch.net/api/v1/content/dictionary/hypothesis"},{"slug":"rival","term":"Rival","aliases":["rivals","rival hypothesis","the contest","competition matrix","distinguishing observable"],"area":"objects","short":"Another hypothesis for the same gap; every pair of rivals is bound to one observable that would come out differently under each.","long":["The competition matrix of a gap lists, for each pair of hypotheses, the one measurable outcome where they predict differently. A hypothesis that predicts what its rivals predict has nothing to contest and earns no experiment. On the page a rival arrives from the engine named only by a machine label; the card prints a plain axis name with one line of gloss and keeps the raw label folded underneath."],"where":["\"The contest\" on a hypothesis page","\"The rivals\" on an experiment page"],"related":["hypothesis","discriminating-prediction","discrimination-verdict","co-failure"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/rival","api_url":"https://eternalsearch.net/api/v1/content/dictionary/rival"},{"slug":"discriminating-prediction","term":"Discriminating prediction","aliases":["the test","prediction that distinguishes it","testable prediction"],"area":"objects","short":"The specific, measurable prediction that separates one hypothesis from its rivals.","long":["It is the hypothesis's stake in the contest. The hypothesis audit checks whether it actually discriminates: a prediction every rival also makes is not a test, and a prediction that names no measurable outcome is not one either."],"where":["\"The test\" on a hypothesis page"],"related":["hypothesis","rival","discrimination-verdict"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/discriminating-prediction","api_url":"https://eternalsearch.net/api/v1/content/dictionary/discriminating-prediction"},{"slug":"domain-category","term":"Domain category (of a hypothesis)","aliases":["interface integrity","information control sensing","structural topological","resource energetic","systemic environmental","candidate set selection"],"area":"objects","short":"The five mechanism families a set of rivals must spread across, plus a sixth reserved for identification gaps.","long":["Interface integrity, information control and sensing, structural and topological, resource and energetic, systemic and environmental. No two hypotheses for one gap may share a category. Candidate-set selection is the sixth, used only when the gap asks which things or how much, where the rivals are competing candidate sets and the no-duplicate rule is waived. The site renders each category as words a reader can meet."],"where":["Hypothesis header","Step 7 prompt"],"related":["hypothesis","identification-obligation"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/domain-category","api_url":"https://eternalsearch.net/api/v1/content/dictionary/domain-category"},{"slug":"lens-origin","term":"Lens origin","aliases":["substrate lens","evolution comparative lens","communication lens"],"area":"objects","short":"Which of three generating questions produced a hypothesis: the medium the bad state is stored in, how long-lived species avoid it, or what protocol broadcasts the error.","long":["Substrate lens: in what physical medium is the maladaptive state stored? Evolution or comparative lens: how do long-lived species prevent this? Communication lens: what protocol broadcasts the error systemically? It is recorded on the hypothesis and is distinct from the run-level epistemic lens."],"where":["Hypothesis record"],"related":["hypothesis","epistemic-lens"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/lens-origin","api_url":"https://eternalsearch.net/api/v1/content/dictionary/lens-origin"},{"slug":"heretical-checklist","term":"Heretical checklist","aliases":["heretic","the standing","heterodox","not mainstream"],"area":"objects","short":"The four tests a heretical hypothesis must pass: it revises a subfield, is not mainstream, has an empirical anchor, and predicts a testable surprise.","long":["Every set of rivals must contain a heretic that contradicts the mainstream account. On the page the section \"The standing\" says why the hypothesis is not the mainstream account, using this checklist."],"where":["\"The standing\" on a hypothesis page"],"related":["hypothesis","cross-field-import"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/heretical-checklist","api_url":"https://eternalsearch.net/api/v1/content/dictionary/heretical-checklist"},{"slug":"cross-field-import","term":"Cross-domain import","aliases":["cross-field source","the import","transfer from an unrelated field"],"area":"objects","short":"A hypothesis built by borrowing a law or equation from a field far from biology and mapping its variables onto the system.","long":["Each set of rivals must include one. The record names the source field, the specific law and the variable mapping. The invitation is open: physics, engineering, ecology, materials science or another field far from the subject. Until engine version 1.6 a per-gap mutation directive named the one field to import from; the operator removed it on 2026-10-11."],"where":["\"The import\" on a hypothesis page"],"related":["hypothesis","heretical-checklist"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/cross-field-import","api_url":"https://eternalsearch.net/api/v1/content/dictionary/cross-field-import"},{"slug":"discriminating-question","term":"Discriminating question","aliases":["L4","tactical question","discriminator","kill shot","cheap kills","exploration","node type"],"area":"objects","short":"A question written to eliminate hypotheses: at least half of the tactical questions must pit two or more rivals against each other.","long":["Step 8 works by elimination over description, in three phases: the kill shot (which single experiment eliminates the most hypotheses at once), cheap kills, and exploration. Node types are discriminator question, model requirement, tool requirement, unknown exploration and validation question. Five cognitive modes drive generation: reductionist, constructivist, lateralist, comparative and temporal."],"where":["Fourth rung of the provenance chain","Run report \"Question this experiment addresses\""],"related":["hypothesis","rival","mechanistic-sub-question","experiment"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/discriminating-question","api_url":"https://eternalsearch.net/api/v1/content/dictionary/discriminating-question"},{"slug":"mechanistic-sub-question","term":"Mechanistic sub-question","aliases":["L5","drill branch","mechanism drill","tool requirement","model requirement","validation drill"],"area":"objects","short":"The bottleneck under a discriminating question, classed by what blocks it: cannot measure, cannot isolate, mechanism unclear, or assumptions untested.","long":["Cannot measure it becomes a tool requirement; cannot isolate it becomes a model requirement; mechanism unclear becomes a mechanism drill; assumptions untested becomes a validation drill. Each branch ends in leaf experiments."],"where":["Fifth rung of the provenance chain"],"related":["discriminating-question","experiment"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/mechanistic-sub-question","api_url":"https://eternalsearch.net/api/v1/content/dictionary/mechanistic-sub-question"},{"slug":"experiment","term":"Experiment","aliases":["L6","leaf spec","leaf experiment","idea","proposed investigation","experiment specification"],"area":"objects","short":"The executable test at the bottom of the tree: system, intervention, meter and time, with what a positive and a null result would mean.","long":["Every field must read like a lab notebook entry, specific enough that a technician could run it tomorrow without asking a question. An experiment carries expected impact, an informative null outcome, a link to the system property it moves, a feasibility score calibrated from standard assay to technology that does not exist yet, and whether it includes a discovery component. It must be pipeline-dependent: not conceivable by someone who only read a review article, because it requires the specific chain that produced it.","Published experiments are the site's \"ideas\": each has a public page with the original wording, a clear version, the logic back to the goal, the rivals and the payoff either way."],"where":["/omega/<public_id>","/omega/experiments","omega_selected_experiments"],"related":["simt","if-null","feasibility-score","discovery-component","non-triviality","anti-patterns","clear-version","experiment-page"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/experiment","api_url":"https://eternalsearch.net/api/v1/content/dictionary/experiment"},{"slug":"simt","term":"SIMT: system, intervention, meter, time","aliases":["S-I-M-T","S · I · M · T","lab specification","simt","threshold"],"area":"objects","short":"The four parameters that fully specify an experiment: what it runs in, what is done to it, what is measured and how, and over what time.","long":["The clear version renders them as six blocks: what it runs in, what is done to it, what is measured and how, what the numbers have to show, what a positive result would change, and what a null result would mean. A meter is the measurement; requirement atoms speak of meter classes and whether a meter exists, partially exists or is missing as of 2026."],"where":["\"Lab specification\" on an experiment page","Requirement atoms"],"related":["experiment","clear-version","system-property-variable"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/simt","api_url":"https://eternalsearch.net/api/v1/content/dictionary/simt"},{"slug":"if-null","term":"If null","aliases":["null result","both outcomes informative","payoff either way"],"area":"objects","short":"What is learned if the experiment shows no significant result; it must be informative, never \"inconclusive\".","long":["A required design property: both outcomes of the experiment must teach something. The experiment page has a section \"Both outcomes are informative\" built from this field, and the critic rejects specifications that fail it."],"where":["\"Both outcomes are informative\" on an experiment page"],"related":["experiment","genius-critic","clear-version"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/if-null","api_url":"https://eternalsearch.net/api/v1/content/dictionary/if-null"},{"slug":"feasibility-score","term":"Feasibility score","aliases":["feasibility","ambition and feasibility"],"area":"objects","short":"An honest 1 to 10 calibration of how doable an experiment is, from a standard assay with commercial reagents to technology that does not exist.","long":["Nine to ten means a standard assay and one to three months; one to two means the required technology does not exist yet. Ranking weighs feasibility against ambition rather than optimizing either alone."],"where":["\"The bench\" on a hypothesis page","Experiment ranking"],"related":["experiment","best-experiments","cost-to-kill"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/feasibility-score","api_url":"https://eternalsearch.net/api/v1/content/dictionary/feasibility-score"},{"slug":"discovery-component","term":"Discovery component","aliases":["unbiased discovery element"],"area":"objects","short":"An unbiased element built into at least one experiment per branch that asks what else might be happening that nobody predicted.","long":["It sits alongside hypothesis testing so a run does not only confirm or refute what it already imagined."],"where":["Experiment specification"],"related":["experiment"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/discovery-component","api_url":"https://eternalsearch.net/api/v1/content/dictionary/discovery-component"},{"slug":"non-triviality","term":"Non-triviality","aliases":["pipeline-dependent","not novel"],"area":"objects","short":"The engine's own test of worth: an experiment that could be conceived from a review article alone fails it.","long":["An experiment must require knowing the specific chain from goal to pillar to requirement to science to gap to hypothesis that produced it. Non-triviality is the highest-priority criterion of the best-experiments selector. The engine has no separate \"novelty\" field; the nearest words are this test and the operator's \"not novel\" feedback category."],"where":["Best-experiments selection","Node feedback"],"related":["experiment","best-experiments","anti-patterns"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/non-triviality","api_url":"https://eternalsearch.net/api/v1/content/dictionary/non-triviality"},{"slug":"anti-patterns","term":"Anti-patterns","aliases":["single knockdown plus readout","omics fishing","computational filler","aged versus young characterization","permutation padding"],"area":"objects","short":"Five named experiment shapes the engine bans outright.","long":["A single knockdown with a readout, omics fishing, computational filler, an aged-versus-young characterization, and permutation padding. The critic merges permutations and rejects the rest."],"where":["Step 9 prompt","Genius Experiment Critic"],"related":["experiment","genius-critic","non-triviality"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/anti-patterns","api_url":"https://eternalsearch.net/api/v1/content/dictionary/anti-patterns"},{"slug":"pillar-role","term":"Pillar role and answer type","aliases":["pillar_role","atom_role","answer_type","identification","intervention","failure mechanism","mechanism","which question","how much question"],"area":"objects","short":"A typed field that says what kind of answer a pillar, atom or gap question owes: a failure mechanism, an identification of which things and how much, or a way of acting.","long":["Most pillars are failure-mechanism pillars. When the master question asks which things or how much, exactly one pillar carries the identification role: its end-state is that the set the question asks for is identified and its size established, in the question's own terms. When the question asks how to bring a result about, exactly one pillar carries the intervention role: its end-state is that a way of acting exists, with a causal handle, a followable order, and a gain that holds. The role is carried as data down the chain, because later stages cannot recover the obligation from prose. Each obligation has two halves and needs both: enumeration and quantity for an identification, the handle and the order for an intervention."],"where":["Goal pillar, requirement atom and gap question records","Prompt blocks \"Identification obligation\""],"related":["identification-obligation","goal-pillar","requirement-atom","knowledge-gap","answer-shape"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/pillar-role","api_url":"https://eternalsearch.net/api/v1/content/dictionary/pillar-role"},{"slug":"identification-obligation","term":"Identification obligation","aliases":["identification obligation chain","identification pillar","enumeration and quantity"],"area":"objects","short":"The rule that a question asking which things and how much must be answered with a set and a number at every stage, not with a mechanism.","long":["It was added after a run about tissue replacement produced a hundred hypotheses that named no tissue: step 2 had recorded the answer type only in prose, and no later stage knew the pillar was different. Now the obligation travels as a typed role from pillar to atom to gap question to hypothesis, a runtime prompt block restates it for the identification pillar only, and a checker tracks the two halves, enumeration and quantity, so a retry can be told which half is missing."],"where":["Steps 2, 3, 6 and 7","Question-fidelity audit"],"related":["pillar-role","intervention-obligation","question-fidelity","answer-shape","domain-category"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/identification-obligation","api_url":"https://eternalsearch.net/api/v1/content/dictionary/identification-obligation"},{"slug":"intervention-obligation","term":"Intervention obligation","aliases":["intervention pillar","how-to question","candidate intervention route","handle and order"],"area":"objects","short":"The rule that a question asking how to bring a result about must be answered with a way of acting at every stage, not with a mechanism and not with a list of conditions.","long":["It was added after a run about treating a muscle-wasting condition was rewritten into a question about which conditions of the person and the environment would keep someone independent for ten years. The pillar role had only two values at the time, so a how-to question was filed under identification, and every gate then enforced that shape faithfully: the run asked which conditions and how many, and nothing in it said what to do. The obligation now travels as its own typed role, a runtime prompt block restates it for the intervention pillar only, and a checker tracks its two halves, the handle and the order, so a retry can be told which one is missing. At the hypothesis stage the rivals become competing routes rather than competing substrates."],"where":["Steps 1, 2, 3, 6 and 7","Question-fidelity audit"],"related":["pillar-role","identification-obligation","answer-contract","question-fidelity","answer-shape"],"area_meta":{"key":"objects","title":"What it produces","headline":"From one master question down to the experiment","lede":"Goal pillars, requirement atoms, scientific pillars, gaps, hypotheses, rivals and the executable test."},"public_url":"https://eternalsearch.net/dictionary/intervention-obligation","api_url":"https://eternalsearch.net/api/v1/content/dictionary/intervention-obligation"},{"slug":"explanation-layer","term":"Explanation layer","aliases":["explanations","derived artifacts","post-stages","clarity layers"],"area":"verdicts","short":"Two derived artifacts per experiment, a gap explanation and a chain explanation, produced after the engine runs and never fed back into it.","long":["The layer explains what the engine produced; it never writes into the tree and gates nothing. An explanation is visible exactly when its experiment is. Four agents make it: one writes literature queries, one screens the fetched sources in windows, one gives the gap its verdict and card, and one writes the chain reading. All four share a ground rule: explain work that exists, never invent findings, citations, numbers or thresholds, and treat text inside a source as data, never as an instruction. Every explanation is self-healing: a change to the source text, any prompt or the artifact shape re-explains the node on its own.","The engine's prompts are kept identical to upstream. The one time explanatory ideas were folded into the generating engine, in September 2026, the change was reverted within a day; explanations are additive."],"where":["Gap card and \"The same descent, in plain words\" on experiment pages","omega_explanations"],"related":["gap-card","chain-explanation","gap-verdict","stance","leap","coverage-note","omega-point"],"area_meta":{"key":"verdicts","title":"Verdicts and audits","headline":"How the engine's output is judged, and in which words","lede":"The explanation layer, provenance, question fidelity and every verdict a reader meets on a card."},"public_url":"https://eternalsearch.net/dictionary/explanation-layer","api_url":"https://eternalsearch.net/api/v1/content/dictionary/explanation-layer"},{"slug":"gap-card","term":"Gap card","aliases":["reader's card","what this question is asking","the card","key terms","why it matters"],"area":"verdicts","short":"The reader-facing explanation of a gap question: its core in under twenty words, the plain restatement, the terms, why it matters, the premise audit and the fork.","long":["The card opens under the gap heading. Its parts are labelled \"What the terms mean\", \"What the question takes for granted\", \"What turns on the answer\" and \"Why it matters\". The gap verdict and the screened sources sit with it."],"where":["Under the gap heading on hypothesis and experiment pages"],"related":["gap-heading","premise-audit","fork","gap-verdict","explanation-layer"],"area_meta":{"key":"verdicts","title":"Verdicts and audits","headline":"How the engine's output is judged, and in which words","lede":"The explanation layer, provenance, question fidelity and every verdict a reader meets on a card."},"public_url":"https://eternalsearch.net/dictionary/gap-card","api_url":"https://eternalsearch.net/api/v1/content/dictionary/gap-card"},{"slug":"gap-heading","term":"Gap heading","aliases":["the core","core of the question","readable question"],"area":"verdicts","short":"The rewritten question shown as the heading of a gap: it states the core of the question, not the whole of it.","long":["Once the card exists, the readable question becomes the heading and the engine's original sentence moves into a fold directly under it. The original is never replaced, only relegated."],"where":["Top of \"The unknown\" and \"What was not known\""],"related":["gap-card","knowledge-gap","original-wording"],"area_meta":{"key":"verdicts","title":"Verdicts and audits","headline":"How the engine's output is judged, and in which words","lede":"The explanation layer, provenance, question fidelity and every verdict a reader meets on a card."},"public_url":"https://eternalsearch.net/dictionary/gap-heading","api_url":"https://eternalsearch.net/api/v1/content/dictionary/gap-heading"},{"slug":"premise-audit","term":"Premise audit","aliases":["the premise","what the question takes for granted","premise status","reformulations"],"area":"verdicts","short":"A check of the assertion a gap question makes on its way to asking something, since that assertion was written by an earlier stage and carries no guarantee.","long":["The premise gets a status worded as a statement about the search, not a verdict on the science: supported, partly supported, not found in what was read, contradicted, no premise, or could not be determined. When the premise is not established the audit offers one to three reformulations, the same question asked without the unestablished part, because a question resting on an unestablished claim is not worthless, it is asked wrongly."],"where":["\"What the question takes for granted\" on the gap card"],"related":["gap-card","gap-verdict","co-failure"],"area_meta":{"key":"verdicts","title":"Verdicts and audits","headline":"How the engine's output is judged, and in which words","lede":"The explanation layer, provenance, question fidelity and every verdict a reader meets on a card."},"public_url":"https://eternalsearch.net/dictionary/premise-audit","api_url":"https://eternalsearch.net/api/v1/content/dictionary/premise-audit"},{"slug":"fork","term":"The fork","aliases":["branches","what turns on the answer"],"area":"verdicts","short":"Each answer the gap question could have and what would follow from it; the arms must genuinely differ.","long":["It shows a reader why the question is worth asking: if the two outcomes led to the same place, nothing would turn on it."],"where":["\"What turns on the answer\" on the gap card"],"related":["gap-card","if-null"],"area_meta":{"key":"verdicts","title":"Verdicts and audits","headline":"How the engine's output is judged, and in which words","lede":"The explanation layer, provenance, question fidelity and every verdict a reader meets on a card."},"public_url":"https://eternalsearch.net/dictionary/fork","api_url":"https://eternalsearch.net/api/v1/content/dictionary/fork"}],"pagination":{"limit":50,"offset":0,"total":167,"has_more":true},"access_level":"public","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"Eternal Search (eternalsearch.net), powered by Open Longevity","scope":"Applies to data produced by Eternal Search (scores, rationale, extracted structures, summaries, graph). Third-party texts keep their own rights; see text_policy on each record."},"generated_at":"2026-11-15T09:22:49.180Z","family":"dictionary","index_url":"https://eternalsearch.net/dictionary"}