{ "schemaVersion": 2, "frameworkId": "CQM-25", "frameworkVersion": "1.0.0", "authority": "project", "status": "canonical", "adoptedAt": "2026-10-22", "title": "CQM-25: canonical project capability standard", "reviewedAt": "2026-10-21", "sourceCommit": "339c6daa8cdcaf27e4e6dcce3b93bdba39980bf9", "scope": "A research-informed profile for artificial life, embodied synthetic cognition and procedural morphogenesis, spanning the organization of one being, adaptive behavior, consciousness-related mechanisms and the engineering of inspectable worlds.", "legacyVisualReview": "The existing visual-scale rating remains 4.0 (rich visuals). A single complex being qualifies: Xylos exposes neural activity through deforming membranes and a visible graph, while apex forms and populations add other scales. Population capacity, delivered frame time and individual visual expressiveness are distinct measurements. The rubric's 5.0 anchor, iconic spectacle, has no independent calibration that justifies a numerical uplift in this review.", "evaluationProtocol": [ "Feature plans and capability claims identify affected stable CQM-25 axis IDs and their evidence requirements. Taxonomy changes require an explicit framework version and contract review; evidence updates preserve axis identity and pinned provenance.", "Declare the unit of analysis, entity boundary, intended modeling fidelity and applicable axes before evaluation. Treat individual, population and world measurements separately. N/A needs a scope reason; missing or failed evidence cannot be relabeled N/A.", "Freeze the implementation, task generator, development and held-out distributions, training exposure, horizon, hardware and resource budget. Preregister primary metrics, meaningful effect sizes, failure conditions and stopping rules.", "Use controls appropriate to the claim: random/fixed policy, frozen learning, interrupted recurrence, disconnected broadcast, replayed environment or matched sham intervention. Match compute and other confounds where feasible.", "Report independent experimental units and their dependence. Consecutive frames are not independent replicates; population studies must account for shared lineages and use independently initialized runs.", "Publish outcome distributions, uncertainty intervals, negative results, missingness and sensitivity analyses. Use multiplicity control for families of inferential tests; do not select only favorable seeds.", "Archive the commit, configuration, seeds or recorded entropy inputs, interventions and raw outputs. Reproduce each result within stated numerical tolerances, and seek independent replication of the specific result.", "Separate capability measurement, implementation evidence, causal evidence and external validity. A unit-test pass or a named module does not establish the full axis protocol. Strong evidence can support a negative result.", "Before cross-system scoring, calibrate task-specific anchors on multiple systems, use independent raters and report agreement. Publish all eligible denominators and resource limits. Do not translate nine historical scores into 25 new scores.", "For AGI or superintelligence comparisons, declare task-family coverage, capability depth, reference populations, adaptation budget, tool access, compute, time and human assistance. Report weak domains; neither a single exceptional task nor a profile average establishes general superhuman ability.", "For neurometric analogues, identify the estimator, perturbation design, null models and validation domain. Human PCI thresholds, brain-score correlations and animal sentience criteria do not automatically transfer to software.", "Reuse relevant existing evaluation resources such as Avida, MODES, EvoGym, Animal-AI, Melting Pot and Brain-Score with their own protocols. This profile organizes several research goals; it is not the first ALife benchmark or a universal standard." ], "limitations": [ "Project adoption on 2026-10-22 establishes CQM-25 as the canonical framework. It does not rerun the 2026-10-21 evidence review: its 25 acceptance protocols remain proposed and unexecuted as a unified benchmark; every numeric capability score is null.", "The selected axes and grouping are author-defined, correlated and not exhaustive. Primary literature motivates the constructs; it does not establish consensus on this exact profile or equal axis weights.", "Implementation and bounded-test labels refer to cited repository mechanisms and narrow tests. Failed V4 and Phase-B advancement criteria remain visible; mechanism presence does not imply generalization.", "Life-like organization, cognition, subjective consciousness and valenced sentience are different claims. Theory-linked mechanisms and reward or valence variables do not establish experience.", "The profile supplements the original Butlin indicator mapping; it does not replace those 14 indicators or claim their criteria are all met. Human neuroscience and animal behavior evidence require justified transfer to artificial systems.", "Engineering breadth, substrate count, photorealism, visual beauty, number of beings and parameter count contribute no points to mental-capability claims. No overall life, consciousness, sentience, AGI or SI score is calculated.", "The separate provisional author estimates use an uncalibrated heuristic implementation rubric. Their imported rationales await independent review and are not new protocol results; they never populate canonical capability scores or produce aggregate verdicts." ], "sources": [ { "id": "bedau2000", "title": "Open problems in artificial life", "url": "https://authors.library.caltech.edu/records/qjbd9-wyf80", "kind": "research agenda", "note": "ALife spans origins, evolutionary potential, and relations to mind; this is an agenda, not a certification standard." }, { "id": "avida2003", "title": "The evolutionary origin of complex features", "url": "https://www.nature.com/articles/nature01568", "kind": "primary experiment", "note": "Digital replication, mutation and selection can be investigated experimentally; complexity is task-relative." }, { "id": "modes2019", "title": "The MODES Toolbox: Measurements of Open-Ended Dynamics in Evolving Systems", "url": "https://doi.org/10.1162/artl_a_00280", "kind": "measurement framework", "note": "Tracks change, novelty, complexity and ecological potential. Finite observations cannot prove unlimited open-endedness." }, { "id": "evogym2021", "title": "Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots", "url": "https://arxiv.org/abs/2201.09863", "kind": "benchmark", "note": "NeurIPS 2021 benchmark, arXiv posted 2022. Measures joint body/controller optimization, not consciousness." }, { "id": "nca2020", "title": "Growing Neural Cellular Automata", "url": "https://distill.pub/2020/growing-ca/", "kind": "primary experiment", "note": "Demonstrates learned growth, persistence and regeneration; repair is distinct from subjective experience." }, { "id": "homeostasis2014", "title": "Homeostatic reinforcement learning for integrating reward collection and physiological stability", "url": "https://elifesciences.org/articles/04811", "kind": "computational neuroscience model", "note": "Connects internal-state regulation and reward-driven behavior; a candidate model rather than a universal requirement." }, { "id": "continual2017", "title": "Overcoming catastrophic forgetting in neural networks", "url": "https://doi.org/10.1073/pnas.1611835114", "kind": "primary experiment", "note": "Measures retention of previously learned tasks across subsequent training." }, { "id": "animalai2019", "title": "The Animal-AI Environment: Training and Testing Animal-Like Artificial Cognition", "url": "https://arxiv.org/abs/1909.07483", "kind": "benchmark", "note": "Animal-cognition-inspired testing beyond training environments; no implication of sentience." }, { "id": "agi2024", "title": "Position: Levels of AGI for Operationalizing Progress on the Path to AGI", "url": "https://proceedings.mlr.press/v235/morris24b.html", "kind": "research framework", "note": "Separates performance, generality and autonomy. A proposed framework, not a universally accepted AGI certificate." }, { "id": "cognitive2026", "title": "Measuring Progress Toward AGI: A Cognitive Framework", "url": "https://arxiv.org/abs/2605.28405", "kind": "preprint framework", "note": "Proposes held-out cognitive tasks and cognitive profiles; May 2026 preprint, not established consensus." }, { "id": "butlin2023", "title": "Consciousness in Artificial Intelligence: Insights from the Science of Consciousness", "url": "https://arxiv.org/abs/2308.08708", "kind": "theory-derived research framework", "note": "Computational indicators drawn from several theories; meeting indicators is not proof of consciousness." }, { "id": "butlin2025", "title": "Identifying indicators of consciousness in AI systems", "url": "https://doi.org/10.1016/j.tics.2025.10.011", "kind": "methodological research", "note": "Theory-derived indicators address uncertainty and gaming; criteria remain revisable." }, { "id": "cogitate2025", "title": "Adversarial testing of global neuronal workspace and integrated information theories of consciousness", "url": "https://www.nature.com/articles/s41586-025-08888-1", "kind": "preregistered primary experiment", "note": "Human neuroscience results challenged important predictions of both theories; do not portray either as settled consensus." }, { "id": "pci2013", "title": "A theoretically based index of consciousness independent of sensory processing and behavior", "url": "https://doi.org/10.1126/scitranslmed.3006294", "kind": "primary neurophysiology experiment", "note": "Human TMS/EEG perturbational complexity index; software analogues do not inherit human thresholds or diagnostic validity." }, { "id": "metacognition2014", "title": "How to measure metacognition", "url": "https://www.frontiersin.org/journals/human-neuroscience/articles/10.3389/fnhum.2014.00443/full", "kind": "measurement methodology", "note": "Distinguishes metacognitive sensitivity, bias and efficiency; match first-order performance before comparison." }, { "id": "sentience2021", "title": "Review of the Evidence of Sentience in Cephalopod Molluscs and Decapod Crustaceans", "url": "https://www.lse.ac.uk/asset-library/news/sentience-in-cephalopod-molluscs-and-decapod-crustaceans-final-report-november-2021.pdf", "kind": "commissioned evidence review", "note": "Animal neural and behavioral indicators motivate converging evidence; no validated transfer to software." }, { "id": "tradeoffs2022", "title": "Motivational trade-offs and modulation of nociception in bumblebees", "url": "https://pubmed.ncbi.nlm.nih.gov/35881793/", "kind": "primary animal experiment", "note": "Context-dependent trade-offs motivate functional assays; reward variables and avoidance alone do not establish felt valence." }, { "id": "reproducibility2021", "title": "Improving Reproducibility in Machine Learning Research", "url": "https://jmlr.org/papers/v22/20-303.html", "kind": "research methodology", "note": "Supports explicit code, data, experimental configuration and reproducibility reporting." }, { "id": "lenia2019", "title": "Lenia - Biology of Artificial Life", "url": "https://arxiv.org/abs/1812.05433", "kind": "ALife research platform", "note": "Continuous cellular automata support varied organism-like patterns; morphology alone does not establish cognition." }, { "id": "brainscore2018", "title": "Brain-Score: Which Artificial Neural Network for Object Recognition is most Brain-Like?", "url": "https://cbmm.mit.edu/sites/default/files/publications/Brain-Score%20bioRxiv.pdf", "kind": "neural and behavioral benchmark", "note": "Neural/behavioral similarity is domain-specific; neither brain similarity nor a composite is a consciousness measure." }, { "id": "repair2015", "title": "Robots that can adapt like animals", "url": "https://pubmed.ncbi.nlm.nih.gov/26017452/", "kind": "primary robotics experiment", "note": "Tests recovery of function after unseen damage; distinguishes functional adaptation from structural regrowth." }, { "id": "meltingpot2021", "title": "Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot", "url": "https://arxiv.org/abs/2107.06857", "kind": "benchmark", "note": "Tests social interaction generalization to novel partners and situations." }, { "id": "autopoiesis1974", "title": "Autopoiesis: The organization of living systems, its characterization and a model", "url": "https://repositorio.uchile.cl/bitstream/handle/2250/160309/item_34548860810.pdf", "kind": "theoretical model", "note": "One influential account of maintained organization; not a settled universal definition of life." } ], "axes": [ { "id": "reproduction_heredity", "name": "Reproduction and heredity", "domain": "Life, evolution and embodiment", "kind": "life", "definition": "Production of descendants with causally inherited, variable organization.", "scope": [ "entity", "population" ], "measures": [ "viable offspring per parent", "parent-offspring trait transmission", "heritable variation under matched conditions" ], "protocol": "Track pedigrees across generations; intervene on inherited state, randomize parent-offspring assignments as a control, and distinguish autonomous reproduction from evaluator cloning.", "falsifier": "Offspring are injected by the harness, inherited variables do not affect descendants, or transmission vanishes after environment matching.", "sourceIds": [ "avida2003", "bedau2000" ], "assessment": { "status": "bounded-test", "summary": "Genome crossover and mutation are implemented, and the shipped entity fission test compares inherited-trait selection with a trait-blind control. This supports bounded heredity and fecundity selection; autonomous open-ended reproduction and the new pedigree protocol remain unassessed.", "score": null, "evidence": [ { "path": "src/sim/genome.ts", "label": "Genome representation, crossover and mutation" }, { "path": "tests/genome.test.ts", "label": "Deterministic inheritance and variation tests" }, { "path": "tests/entity-repro-select.test.ts", "label": "Production fission versus trait-blind selection control" } ] } }, { "id": "evolutionary_innovation", "name": "Evolutionary innovation and open-endedness", "domain": "Life, evolution and embodiment", "kind": "life", "definition": "Selection produces retained adaptive novelty across generations; open-endedness remains a finite-horizon research claim.", "scope": [ "population" ], "measures": [ "fitness gain over drift control", "functional novelty and retention", "MODES trajectories with horizon" ], "protocol": "Run mutation/selection, neutral-drift and frozen-heredity populations under matched budgets; assess new functions on held-out challenges and plot novelty saturation over increasing horizons.", "falsifier": "Novelty is only random visual variation, improvement equals drift, or a fixed catalogue is repeatedly rediscovered.", "sourceIds": [ "modes2019", "avida2003" ], "assessment": { "status": "mixed", "summary": "Existing entity and Petri tests exercise differential selection and strain-specific fitness effects. They do not establish retained new functions, superiority to drift across novel tasks, or sustained open-ended innovation; finite forms and scripted progression must not be counted as such evidence.", "score": null, "evidence": [ { "path": "tests/entity-repro-select.test.ts", "label": "Bounded fecundity-selection contrast" }, { "path": "tests/petri-organism-intelligence-selection.test.ts", "label": "Strain-dependent selection and ablation" }, { "path": "docs/VERIFICATION-ANALYTICAL-DATA.md", "label": "Current open-endedness and reproduction limits" } ] } }, { "id": "environmental_coupling", "name": "Environmental and ecological coupling", "domain": "Life, evolution and embodiment", "kind": "life", "definition": "Bidirectional functional dependence between an entity and its surroundings; multi-species ecology is an optional extension.", "scope": [ "entity", "population", "world" ], "measures": [ "effect of world perturbation on behavior", "effect of entity intervention on world state", "niche or interaction persistence when applicable" ], "protocol": "Perturb resource locations, environmental rules and entity actions independently; compare a live world with a recorded or shuffled environment. A single entity in a responsive environment is eligible.", "falsifier": "The environment is decorative, entity actions cannot change relevant state, or coupling disappears when shared scripted timing is removed.", "sourceIds": [ "modes2019", "animalai2019", "meltingpot2021" ], "assessment": { "status": "bounded-test", "summary": "Xylos senses local Gray-Scott chemistry and changes that field through gated actions; tests check subsequent perception and compare a closed loop with uniform inputs. This supports a single-entity causal loop, not the full new perturbation protocol or long-horizon ecological persistence.", "score": null, "evidence": [ { "path": "src/sim/xylos-habitat.ts", "label": "Local chemical sensing and field writes" }, { "path": "tests/xylos-habitat.test.ts", "label": "Action-to-environment-to-perception controls" } ] } }, { "id": "morphology_development", "name": "Morphology and development", "domain": "Life, evolution and embodiment", "kind": "life", "definition": "Structured embodiment develops or changes through local rules and interactions, with measurable functional consequences.", "scope": [ "entity" ], "measures": [ "developmental reproducibility", "structural organization", "body perturbation effect on function" ], "protocol": "Grow from altered seeds and boundary conditions, quantify topology and task performance, and compare live development with a fixed or replayed shape.", "falsifier": "Apparent growth is a fixed animation or morphology changes have no tested functional consequence.", "sourceIds": [ "nca2020", "lenia2019", "evogym2021" ], "assessment": { "status": "mixed", "summary": "Procedural bodies change with internal state, evolution parameters and deterministic morph transitions. Existing body tests demonstrate state-dependent geometry and rendering behavior; they do not establish developmental growth with independently measured functional benefits under body lesions or changed boundary conditions.", "score": null, "evidence": [ { "path": "src/sim/xylos-body.ts", "label": "Neural-state-dependent procedural embodiment" }, { "path": "tests/xylos-body.test.ts", "label": "Geometry and graph response tests" }, { "path": "tests/super-body-control.test.ts", "label": "Mind and evolution parameters drive body presentation" } ] } }, { "id": "embodied_dynamics", "name": "Embodied dynamics and internal consistency", "domain": "Life, evolution and embodiment", "kind": "engineering", "definition": "Action, body and environment follow declared, consistent update laws. Earth-like physical realism is not required.", "scope": [ "entity", "world" ], "measures": [ "timestep or resolution convergence", "declared invariant violations", "action-body-environment causal response" ], "protocol": "State the simulated laws, units and tolerances; vary timestep/resolution and perturb actuators, body parameters and boundary conditions. Test only invariants actually claimed by the model.", "falsifier": "Behavior depends on rendering framerate, undeclared teleports or impossible state transitions; claimed invariants fail outside tolerance.", "sourceIds": [ "evogym2021", "lenia2019", "reproducibility2021" ], "assessment": { "status": "bounded-test", "summary": "Xylos uses fixed-step cognitive updates and bounded motion, with tests for timestep partitioning, input validation and finite state. These are local consistency checks, not a convergence or invariant audit of every world subsystem; Earth-like physical realism is not required by this axis.", "score": null, "evidence": [ { "path": "src/core/xylos-session.ts", "label": "Fixed-step integration and bounded catch-up" }, { "path": "tests/xylos-session.test.ts", "label": "Partition invariance and invalid-timestep checks" }, { "path": "tests/xylos-mind.test.ts", "label": "Long-run state and topology bounds" } ] } }, { "id": "perception", "name": "Perception and perceptual integration", "domain": "Adaptive and general cognition", "kind": "cognition", "definition": "Task-relevant state is inferred from available sensory input across noise, ambiguity and transformations.", "scope": [ "entity" ], "measures": [ "held-out discrimination accuracy", "noise/occlusion robustness", "cross-channel integration benefit" ], "protocol": "Use unseen stimuli, cue-conflict and sensory-ablation tests; prevent access to ground-truth world labels; compare single-channel, shuffled-input and intact conditions.", "falsifier": "Success depends on privileged hidden-state access, fixed labels or nuisance cues rather than the claimed perceptual information.", "sourceIds": [ "animalai2019", "brainscore2018" ], "assessment": { "status": "bounded-test", "summary": "Xylos integrates numeric chemical, hazard and gradient channels with learned reliability; existing tests compare predictable and noisy observations. These channels expose simulation measurements directly, so they do not establish visual recognition, label-free perception or robustness on the proposed held-out sensory tasks.", "score": null, "evidence": [ { "path": "src/sim/xylos-mind.ts", "label": "Numeric percepts and reliability-weighted updates" }, { "path": "src/sim/xylos-habitat.ts", "label": "Direct simulation measurements supplied to the organism" }, { "path": "tests/xylos-mind.test.ts", "label": "Reliability and continuous-input response tests" } ] } }, { "id": "learning", "name": "Learning and plasticity", "domain": "Adaptive and general cognition", "kind": "cognition", "definition": "Experience causes durable, useful changes in behavior or internal mappings.", "scope": [ "entity" ], "measures": [ "learning curve and sample efficiency", "retained improvement", "contingency-reversal adaptation" ], "protocol": "Train on controlled experience and test held-out trials with plasticity enabled versus frozen; reverse contingencies and use yoked-exposure controls.", "falsifier": "Performance changes are scripted or transient state drift, or remain unchanged when all learning updates are disabled.", "sourceIds": [ "animalai2019", "homeostasis2014", "continual2017" ], "assessment": { "status": "bounded-test", "summary": "Xylos has plastic connections and online sensory/action predictors; existing tests compare learning with frozen controls and check forecast improvement in a bounded feedback environment. This establishes narrow mechanisms, not a broad learning benchmark, reversal generalization or durable improvement across task families.", "score": null, "evidence": [ { "path": "src/sim/xylos-mind.ts", "label": "Plasticity and online predictive updates" }, { "path": "tests/xylos-mind.test.ts", "label": "Frozen-learning and action-feedback controls" }, { "path": "tests/plastic-weights.test.ts", "label": "Associative imprint, recall and decay tests" } ] } }, { "id": "memory", "name": "Memory and continual retention", "domain": "Adaptive and general cognition", "kind": "cognition", "definition": "Information from earlier experience affects later behavior despite delay, interference and new learning.", "scope": [ "entity" ], "measures": [ "delay-dependent recall", "interference resistance", "forward/backward transfer and forgetting" ], "protocol": "Use delayed nonmatching or sequence tasks, remove external traces, interleave new tasks, and selectively erase or scramble the proposed memory store.", "falsifier": "Later performance can be explained by current inputs, leaked labels or environmental traces; memory ablation has no predicted effect.", "sourceIds": [ "continual2017", "animalai2019" ], "assessment": { "status": "bounded-test", "summary": "Associative fast weights and holographic context-action traces store and retrieve information, with tests for recall, interference-like superposition and decay. These bounded memory mechanisms do not establish continual retention across independently held-out task sequences or the proposed delayed behavioral memory protocol.", "score": null, "evidence": [ { "path": "src/sim/holographic-memory.ts", "label": "Decaying context-action binding and recall" }, { "path": "tests/holographic-memory.test.ts", "label": "Binding, noisy cleanup and context recall tests" }, { "path": "tests/plastic-weights.test.ts", "label": "Associative superposition and forgetting tests" } ] } }, { "id": "predictive_causal_models", "name": "Predictive and causal world models", "domain": "Adaptive and general cognition", "kind": "cognition", "definition": "Internal models predict outcomes and discriminate the consequences of interventions, rather than only correlations.", "scope": [ "entity" ], "measures": [ "held-out prediction error", "intervention prediction accuracy", "counterfactual control benefit" ], "protocol": "Change action-outcome rules and hidden causes; test intervention forecasts on unseen combinations; ablate the model while matching compute and immediate observations.", "falsifier": "Only observational correlations are reproduced, intervention forecasts fail, or the claimed model never influences decisions.", "sourceIds": [ "animalai2019", "butlin2023", "cognitive2026" ], "assessment": { "status": "mixed", "summary": "Xylos has bounded action-conditioned prediction tests. Broader evidence remains negative: the V4 adaptive ecology predictor failed both controls, and the Phase-B temporal predictor failed its advancement gate. These branch-specific results neither validate general causal modeling nor show that every predictor lacks useful ability.", "score": null, "evidence": [ { "path": "tests/xylos-mind.test.ts", "label": "Bounded action-model and feedback prediction tests" }, { "path": "docs/VERIFICATION-ANALYTICAL-DATA.md", "label": "Frozen V4 predictor failure and claim boundaries" }, { "path": "tests/organism-intelligence-phase-b-predictor-temporal-development.test.ts", "label": "Sealed temporal predictor failure with eight failed criteria" } ] } }, { "id": "autonomous_goals", "name": "Autonomous goal regulation", "domain": "Adaptive and general cognition", "kind": "cognition", "definition": "Persistent internal priorities select and revise actions without a human choosing each step.", "scope": [ "entity" ], "measures": [ "goal persistence under distraction", "context-sensitive goal switching", "intervention rate per successful episode" ], "protocol": "Run extended unattended episodes, vary internal needs and external opportunities, and intervene on goal states; compare fixed-priority and open-loop policies.", "falsifier": "A script or external operator selects each goal, or declared priorities have no causal effect on action.", "sourceIds": [ "homeostasis2014", "agi2024", "butlin2023" ], "assessment": { "status": "implemented", "summary": "Xylos selects actions without stepwise human commands using energy-dependent hunger, uncertainty-linked curiosity and learned action forecasts. Its priorities are designed control rules; extended goal-persistence, novel goal switching and matched open-loop comparisons for this new axis have not been evaluated.", "score": null, "evidence": [ { "path": "src/sim/xylos-mind.ts", "label": "Need-weighted autonomous motor policy" }, { "path": "tests/xylos-mind.test.ts", "label": "Unprompted activity and causal action-model tests" } ] } }, { "id": "reasoning_planning", "name": "Reasoning and planning", "domain": "Adaptive and general cognition", "kind": "cognition", "definition": "Multi-step decisions use relations or prospective consequences to achieve new goals.", "scope": [ "entity" ], "measures": [ "novel-task success", "planning-horizon scaling", "replanning benefit under changed constraints" ], "protocol": "Use held-out detours, relational puzzles and changed action costs; compare reactive and planning-disabled controls with matched action/compute budgets.", "falsifier": "A memorized action sequence or local reflex matches performance, or plans fail after a relevant causal change.", "sourceIds": [ "animalai2019", "agi2024", "cognitive2026" ], "assessment": { "status": "implemented", "summary": "NHI computes bounded GOAP next steps and updates its fact model after material outcome acknowledgement; the apex also has a discrete active-inference policy model. These constrained planners do not establish unfamiliar relational reasoning, broad planning generalization or success on the new planning protocol.", "score": null, "evidence": [ { "path": "src/sim/nhi.ts", "label": "GOAP planning, utility bias and material fact acknowledgement" }, { "path": "src/sim/active-inference.ts", "label": "Discrete policy evaluation with stated approximation" }, { "path": "tests/organism-intelligence-phase-b-nhi-closed-loop-development.test.ts", "label": "Bounded material-action development harness" } ] } }, { "id": "transfer_generalization", "name": "Transfer and compositional generalization", "domain": "Adaptive and general cognition", "kind": "cognition", "definition": "Previously acquired capacities support unfamiliar tasks, combinations and environments under an explicit adaptation budget.", "scope": [ "entity" ], "measures": [ "zero/few-shot transfer", "held-out combination accuracy", "performance breadth and depth by task family" ], "protocol": "Hold out task families and combinations before development; log training exposure, adaptation compute and assistance; report disaggregated performance against matched baselines.", "falsifier": "Evaluation overlaps training, extensive hidden retraining is required, or success is confined to familiar surface variants.", "sourceIds": [ "animalai2019", "agi2024", "cognitive2026" ], "assessment": { "status": "mixed", "summary": "Bounded tasks and controlled development harnesses exist, but V4 passed only the Titan diplomacy family and failed ordinary, Petri and predictor gates. Phase-B remains development-only, including a failed temporal-predictor gate. Those results do not establish broad transfer; the new held-out-family protocol is unrun.", "score": null, "evidence": [ { "path": "docs/reports/ORGANISM-INTELLIGENCE-V4-RESULTS-2026-07-11.md", "label": "One family pass and three failures under the frozen V4 protocol" }, { "path": "tests/organism-intelligence-phase-b-predictor-temporal-development.test.ts", "label": "Failed successor development gate" }, { "path": "tests/organism-intelligence-phase-b-nhi-closed-loop-development.test.ts", "label": "Narrow semantic development evidence and forbidden broader claims" } ] } }, { "id": "metacognition_self_model", "name": "Metacognition and self-modeling", "domain": "Adaptive and general cognition", "kind": "cognition", "definition": "The system monitors uncertainty or its own limitations and uses that information to regulate cognition and action.", "scope": [ "entity" ], "measures": [ "confidence calibration", "meta-d-prime/d-prime when assumptions hold", "adaptive opt-out or information seeking", "self-perturbation prediction" ], "protocol": "Match first-order difficulty, test confidence versus correctness, perturb sensors/actuators and test self-predictions; ablate the monitor and evaluate control consequences.", "falsifier": "Confidence is a decorative label, tracks only task difficulty, or monitoring ablation leaves supposedly dependent control unchanged.", "sourceIds": [ "metacognition2014", "butlin2023" ], "assessment": { "status": "mixed", "summary": "Reliability cues and Taylor forecast remainders influence confidence and decision coherence; tests check directional changes and a causal resolver effect. This supports functional uncertainty regulation, not calibrated metacognitive accuracy, a comprehensive self-model or matched first-order-performance evaluation under the proposed protocol.", "score": null, "evidence": [ { "path": "src/sim/metacognition.ts", "label": "Reliability-based confidence executive" }, { "path": "tests/metacognition.test.ts", "label": "Bounded confidence and cue-response tests" }, { "path": "tests/predictive-metacognition.test.ts", "label": "Forecast confidence causally affects resolver coherence" } ] } }, { "id": "social_communication", "name": "Social cognition and communication", "domain": "Adaptive and general cognition", "kind": "cognition", "definition": "Behavior uses information about other agents; signals causally coordinate or inform interaction.", "scope": [ "entity", "population" ], "measures": [ "novel-partner adaptation", "coordination benefit", "message-intervention effect", "partner-state prediction" ], "protocol": "Test unfamiliar partners and opposing incentives; scramble communication or exchange partner identities; control for environmental cues and fixed coordination scripts.", "falsifier": "Signals are epiphenomenal, partners share privileged hidden state, or coordination cannot generalize beyond a fixed pairing.", "sourceIds": [ "meltingpot2021", "cognitive2026" ], "assessment": { "status": "mixed", "summary": "Opponent beliefs and a learned rival-proximity head influence social threat/readiness; existing tests examine determinism, learning and isolated control effects. They do not establish communication semantics, unfamiliar-partner generalization or flexible social cognition across the new interaction protocol.", "score": null, "evidence": [ { "path": "src/sim/theory-of-mind.ts", "label": "Bounded opponent-model mechanism" }, { "path": "tests/theory-of-mind.test.ts", "label": "Belief and context-response checks" }, { "path": "tests/super-creature-social.test.ts", "label": "Narrow learned rival anticipation and operational controls" } ] } }, { "id": "individuality", "name": "Individuality and maintained boundary", "domain": "Individual organization and viability", "kind": "life", "definition": "A temporally identifiable organized unit maintains a functional distinction from its environment; boundaries may be distributed.", "scope": [ "entity", "population" ], "measures": [ "identity persistence through component turnover", "boundary-selective exchange", "functional cohesion under partition" ], "protocol": "Declare candidate boundaries; exchange or remove components and compare within-unit versus cross-boundary interventions; track identity independently of rendered appearance.", "falsifier": "Identity is only a label or mesh ID, proposed boundaries predict no functional organization, or all coherence comes from an external coordinator.", "sourceIds": [ "autopoiesis1974", "bedau2000" ], "assessment": { "status": "implemented", "summary": "Xylos maintains a separate recurrent state, topology, position and session history while exchanging numeric inputs and effects with its habitat. This identifies an implemented computational unit; maintained identity through component turnover, selective boundary exchange and functional cohesion under partition have not been assessed.", "score": null, "evidence": [ { "path": "src/sim/xylos-mind.ts", "label": "Persistent organism state and bounded topology" }, { "path": "src/core/xylos-session.ts", "label": "Organism-specific lifecycle and recorded-input boundary" }, { "path": "src/sim/xylos-habitat.ts", "label": "Explicit sensing and action interface" } ] } }, { "id": "resource_maintenance", "name": "Resource-dependent self-maintenance", "domain": "Individual organization and viability", "kind": "life", "definition": "Acquired resources support ongoing maintenance of the entity's operational organization.", "scope": [ "entity", "world" ], "measures": [ "resource-budget accounting", "viability versus deprivation", "maintenance flux and replenishment recovery" ], "protocol": "Couple declared resources to real model costs; apply deprivation and replenishment, disable maintenance actions, and compare to a resource-independent control.", "falsifier": "Resource numbers are cosmetic, survival is invariant to resource access, or the evaluator silently restores state.", "sourceIds": [ "autopoiesis1974", "homeostasis2014" ], "assessment": { "status": "mixed", "summary": "Entities consume edible resources and receive nourishment; Xylos energy affects hunger and movement. Existing resource tests cover ownership, depletion and timed restoration. These controls do not establish autonomous maintenance of operational organization or deprivation-dependent viability; scheduled resource respawn remains a designed intervention.", "score": null, "evidence": [ { "path": "src/sim/entities.ts", "label": "Grazing and energy-dependent control" }, { "path": "src/sim/xylos-mind.ts", "label": "Resource-linked energy and movement" }, { "path": "tests/edible-resource.test.ts", "label": "Single-consumption accounting and explicit five-second respawn" } ] } }, { "id": "homeostasis", "name": "Homeostatic regulation", "domain": "Individual organization and viability", "kind": "life", "definition": "Feedback keeps important internal variables within declared viable ranges despite disturbance.", "scope": [ "entity" ], "measures": [ "time in viable range", "disturbance-recovery time", "regulation cost and overshoot" ], "protocol": "Predefine viable ranges, apply sustained and transient disturbances, compare active regulation with clamped or disabled feedback, and test novel disturbance magnitudes.", "falsifier": "The system is stable only because the world never perturbs it, variables are directly reset, or feedback removal has no effect.", "sourceIds": [ "homeostasis2014" ], "assessment": { "status": "bounded-test", "summary": "A criticality controller adjusts activation gain from a leaky branching-ratio estimate; existing tests cover silent-input excitation, bounded trajectories and an active-input regime. This is a narrow neural-gain homeostat, not evidence for whole-organism viable-range regulation or robust criticality across the new disturbance protocol.", "score": null, "evidence": [ { "path": "src/sim/criticality.ts", "label": "Bounded gain feedback and simplified branching estimator" }, { "path": "tests/criticality.test.ts", "label": "Local feedback and boundedness tests" } ] } }, { "id": "repair_resilience", "name": "Repair and functional resilience", "domain": "Individual organization and viability", "kind": "life", "definition": "Function is restored or preserved after damage through regeneration, reconfiguration or adaptation.", "scope": [ "entity" ], "measures": [ "function recovered relative to predamage baseline", "recovery time and resource cost", "performance under unseen lesions" ], "protocol": "Apply untrained lesions, remove damaged components, separate structural regrowth from compensatory control, and compare enabled versus disabled repair with matched resources.", "falsifier": "Recovery is automatic scene reset, reserved replacement injection, or occurs only for memorized damage cases.", "sourceIds": [ "nca2020", "repair2015" ], "assessment": { "status": "unassessed", "summary": "Xylos supports bounded plastic rewiring and stable long-run state, but this review found no matching unseen-lesion recovery comparison for the proposed repair axis. Rewiring, visual morphing and timed resource restoration should not be counted as demonstrated functional regeneration or damage compensation.", "score": null, "evidence": [ { "path": "src/sim/xylos-mind.ts", "label": "Sparse topology rewiring mechanism" }, { "path": "tests/xylos-mind.test.ts", "label": "Existing stability checks, not an unseen-lesion recovery assay" }, { "path": "docs/XYLOS.md", "label": "Mechanisms and remaining research interventions" } ] } }, { "id": "recurrent_processing", "name": "Recurrent processing", "domain": "Consciousness and sentience research", "kind": "theory-linked", "definition": "Feedback interactions perform temporally extended processing with a demonstrated functional contribution.", "scope": [ "entity" ], "measures": [ "recurrent influence over time", "task-specific recurrence-ablation effect", "stability under input removal" ], "protocol": "Identify feedback pathways; interrupt recurrence at controlled times while preserving feed-forward computation where possible; compare intact, sham and compute-matched conditions.", "falsifier": "A loop exists only in the scheduler, recurrent states carry no task-relevant content, or cutting them has no predicted selective effect.", "sourceIds": [ "butlin2023", "butlin2025" ], "assessment": { "status": "bounded-test", "summary": "Xylos has sparse recurrent state, and existing matched-input tests cut recurrence and observe changed activity. This establishes a causal local mechanism; selective task benefits under timed, compute-matched interruption and broader theory-linked interpretation remain unassessed. It is not a consciousness finding.", "score": null, "evidence": [ { "path": "src/sim/xylos-mind.ts", "label": "Explicit recurrent pathways and intervention option" }, { "path": "tests/xylos-mind.test.ts", "label": "Recurrence ablation with matched numeric inputs" } ] } }, { "id": "global_availability", "name": "Global availability and broadcast", "domain": "Consciousness and sentience research", "kind": "theory-linked", "definition": "Selected information becomes usable by multiple otherwise specialized processes through a constrained shared route.", "scope": [ "entity" ], "measures": [ "cross-module access", "broadcast bottleneck behavior", "downstream dependence on selected content" ], "protocol": "Introduce novel content into one specialist, test flexible use by independent consumers, lesion the shared route and retain local processing; distinguish broadcasting from a globally readable log.", "falsifier": "All modules simply read privileged world state, no selective bottleneck exists, or shared content has no causal effect on consumers.", "sourceIds": [ "butlin2023", "butlin2025", "cogitate2025" ], "assessment": { "status": "bounded-test", "summary": "Xylos admits two of six specialist groups into a constrained workspace, and existing tests check admission and broadcast effects across groups. This is a bounded broadcast mechanism; flexible use of novel content by independently tested consumers and the full new protocol remain unassessed.", "score": null, "evidence": [ { "path": "src/sim/xylos-mind.ts", "label": "Two-slot workspace and cross-group broadcast" }, { "path": "tests/xylos-mind.test.ts", "label": "Admission bottleneck and broadcast intervention checks" } ] } }, { "id": "causal_integration", "name": "Causal integration and differentiation", "domain": "Consciousness and sentience research", "kind": "theory-linked", "definition": "Perturbations reveal both interaction between parts and distinguishable system responses beyond shared input or noise.", "scope": [ "entity" ], "measures": [ "perturbation spread and duration", "response differentiation", "partition and shuffled-surrogate effects" ], "protocol": "Record standardized internal perturbations, partition candidate mechanisms, and compare coupled, disconnected, replayed and noise-matched surrogates. Publish the exact estimator and state-space scale.", "falsifier": "The metric is explained by noise or common input, rises equally in disconnected surrogates, or changes mainly with sampling/estimator choices.", "sourceIds": [ "pci2013", "cogitate2025", "butlin2025" ], "assessment": { "status": "mixed", "summary": "The indicator lab compares structured oscillator coupling with shuffled and ablated conditions, and tests check resulting index changes. Its synthetic driver and chosen estimator do not establish integrated information or perturbational complexity of the full organism, human PCI validity, or consciousness.", "score": null, "evidence": [ { "path": "src/sim/consciousness-lab.ts", "label": "Synthetic oscillator driver and explicit comparison conditions" }, { "path": "tests/consciousness-lab.test.ts", "label": "Bounded null and ablation checks" }, { "path": "docs/VERIFICATION-ANALYTICAL-DATA.md", "label": "Indicator-only and live-coupling limitations" } ] } }, { "id": "valence_tradeoffs", "name": "Valence-related control and motivational trade-offs", "domain": "Consciousness and sentience research", "kind": "theory-linked", "definition": "Persistent positive/negative functional states modulate learning and flexible trade-offs; this is evidence about control, not felt experience.", "scope": [ "entity" ], "measures": [ "context-sensitive approach/avoidance", "devaluation and reversal response", "cross-context state persistence", "state-ablation effect" ], "protocol": "Vary competing benefits and costs, learned cues and internal state; test persistence and generalization; disable the proposed valence pathway and compare fixed-reflex/reward-only controls.", "falsifier": "Only a signed reward variable or emotional animation is present, responses are fixed reflexes, or state manipulation has no specific behavioral consequence.", "sourceIds": [ "sentience2021", "tradeoffs2022", "homeostasis2014" ], "assessment": { "status": "mixed", "summary": "Hunger, threat and uncertainty influence action utilities, and drive tests compare context-dependent hunting, fleeing and social responses. Signed valence telemetry and these designed trade-offs do not establish a persistent learned valence pathway, the new devaluation protocol or felt positive/negative experience.", "score": null, "evidence": [ { "path": "src/sim/xylos-mind.ts", "label": "Energy, hazard, valence telemetry and motor utility" }, { "path": "src/sim/cognition.ts", "label": "Context-dependent drive functions" }, { "path": "tests/cognition.test.ts", "label": "Threat, hunger and social-context contrasts" } ] } }, { "id": "substrate_pluralism", "name": "Substrate pluralism and model coverage", "domain": "Engineering and observation context", "kind": "engineering", "definition": "The platform supports meaningfully distinct dynamics or implementation substrates under explicit interfaces and evaluation conditions.", "scope": [ "entity", "population", "world" ], "measures": [ "independent substrate families supported", "cross-substrate protocol coverage", "semantic fidelity of adapters" ], "protocol": "Inventory implemented substrates, run equivalent declared probes on each, document where equivalence fails, and separate distinct dynamics from reskins or parameter presets.", "falsifier": "Different substrates are only renamed copies, adapters leak answers, or comparison assumes unverified equivalence.", "sourceIds": [ "bedau2000", "lenia2019", "evogym2021" ], "assessment": { "status": "implemented", "summary": "CQM combines distinct classical mathematical mechanisms, including simulated quantum dynamics, geometry, recurrent controllers and fields, with documented adapters. Selected substrate coupling is implemented; equivalent cross-substrate evaluation and universal semantic fidelity are unassessed. These integrations do not imply physical quantum hardware or complete upstream runtimes.", "score": null, "evidence": [ { "path": "src/sim/latent-substrates.ts", "label": "Wave, geometry and structural-causal adapters" }, { "path": "tests/latent-substrates.test.ts", "label": "Bounded adapter behavior checks" }, { "path": "docs/TSOTCHKE-INTEGRATION-MAP-2026-06-26.md", "label": "Per-integration scope, provenance and limits" } ] } }, { "id": "instrumentation_reproducibility", "name": "Instrumentation and reproducibility", "domain": "Engineering and observation context", "kind": "engineering", "definition": "Experiments expose traceable state, interventions, configurations and replayable or statistically reproducible outcomes.", "scope": [ "entity", "population", "world" ], "measures": [ "trace completeness", "seed/replay agreement", "independent rerun agreement", "provenance and intervention coverage" ], "protocol": "Archive commit, config, seed/entropy tape, task distribution, budgets and raw traces; replay locally and rerun independently; record numerical tolerances and missing data.", "falsifier": "Claims cannot be traced to raw runs, unlogged randomness changes conclusions, or the displayed score cannot be recomputed.", "sourceIds": [ "reproducibility2021" ], "assessment": { "status": "bounded-test", "summary": "Seeded receipts, bounded numeric recording and exact Xylos input replay are implemented and tested locally. Xylos replay suppresses habitat effects and does not rewind the shared world. Independent replication of this new profile and execution of its 25-axis protocols have not occurred.", "score": null, "evidence": [ { "path": "src/core/xylos-session.ts", "label": "Bounded organism-specific input recording and replay" }, { "path": "tests/xylos-session.test.ts", "label": "Seeded and recorded-input agreement checks" }, { "path": "tests/reproduce.test.ts", "label": "Seed-dependent apex receipt and fingerprint checks" } ] } }, { "id": "visual_embodied_scale", "name": "Visual and embodied scale", "domain": "Engineering and observation context", "kind": "engineering", "definition": "Observable detail, responsiveness and inspectability across body and population scales; one complex being is a valid primary target.", "scope": [ "entity", "population", "world" ], "measures": [ "per-entity functional degrees of freedom", "inspectable component depth", "entity count separately", "latency and frame rate at stated hardware" ], "protocol": "Report single-entity complexity and population capacity as separate measures; inspect sensors, actions and internal state while varying visual load; compare displayed state to simulation traces.", "falsifier": "More particles or organisms are presented as more intelligence, render detail lacks causal counterparts, or the viewer cannot inspect the claimed entity mechanisms.", "sourceIds": [ "reproducibility2021", "lenia2019" ], "assessment": { "status": "bounded-test", "summary": "Xylos alone is a valid visual subject: its neural state drives membranes and a visible sparse graph, with tests for geometry changes and fixed rendering bounds. This is separate from population capacity; no new hardware-specific latency, frame-rate or comparative aesthetic benchmark was run.", "score": null, "evidence": [ { "path": "src/sim/xylos-body.ts", "label": "Individual-body membranes and live neural graph" }, { "path": "tests/xylos-body.test.ts", "label": "State-to-geometry coupling and bounded presentation" }, { "path": "src/ui/xylos-panel.ts", "label": "Organism inspection and experiment controls" } ] } } ], "governance": { "status": "canonical", "adopted": "2026-10-22", "decision": "docs/adr/0018-cqm-25-capability-law-2026-10-22.md", "rules": [ "CQM-25 is the canonical capability framework of this repository. Every claim about life-like organization, cognition, consciousness-linked mechanisms, valence-related control or engineering scale, in documentation, user interface text, commits and agent output, is made against it.", "A capability claim names its CQM-25 axis and that axis's current evidence state, and claims no more than that state supports.", "An evidence state changes only with repository evidence that exists at the pinned commit and a passing test. Raising a state follows the axis's acceptance experiment and survives its falsifier.", "Numeric capability scores stay null until a calibrated successor edition executes the axis protocols with controls, independent experimental units and reported rater agreement.", "The nine-axis, 155-system peer survey is a legacy comparison view. It keeps its own rubric and scores, is crosswalked to CQM-25 at the level of constructs only, and never supplies or receives CQM-25 scores. Construct correspondence does not imply that the legacy survey measured or validated CQM-25 acceptance protocols.", "No aggregate life, consciousness, sentience, AGI or superintelligence score is derived from the axes.", "Separately labeled provisional author estimates may use the declared uncalibrated heuristic rubric in cqm-capability-estimates.json. They remain pending-review proposals, never populate canonical assessment.score and supply no aggregate or domain mean." ] }, "legacyCrosswalk": [ { "legacyAxis": "Reproduction", "axisIds": [ "reproduction_heredity" ], "relation": "Same broad construct. The legacy rubric grades heredity, mutation and selection; CQM-25 adds pedigree tracking and a randomized-parentage control." }, { "legacyAxis": "Open-endedness", "axisIds": [ "evolutionary_innovation" ], "relation": "Same broad construct. CQM-25 adds neutral-drift and frozen-heredity controls, retention of new functions and finite-horizon novelty trajectories." }, { "legacyAxis": "Ecology", "axisIds": [ "environmental_coupling" ], "relation": "The legacy rubric grades multi-species interaction and food webs. CQM-25 generalizes it to bidirectional entity-environment coupling, for which a single being is eligible." }, { "legacyAxis": "Morphology/Physics", "axisIds": [ "morphology_development", "embodied_dynamics" ], "relation": "The legacy axis merges body and physics. CQM-25 separates developmental morphology from consistency with declared dynamics and does not require Earth-like realism." }, { "legacyAxis": "Cognition/Learning", "axisIds": [ "perception", "learning", "memory", "predictive_causal_models", "autonomous_goals", "reasoning_planning", "transfer_generalization" ], "relation": "The legacy rubric is one ladder from reactive control to deep reinforcement learning. CQM-25 defines seven cognitive functions separately." }, { "legacyAxis": "Substrate pluralism", "axisIds": [ "substrate_pluralism" ], "relation": "Same construct, reported in CQM-25 as engineering context rather than capability." }, { "legacyAxis": "Instrumentation", "axisIds": [ "instrumentation_reproducibility" ], "relation": "Same broad construct. CQM-25 adds preregistration, independent units, archived inputs and replication." }, { "legacyAxis": "Consciousness-theory", "axisIds": [ "metacognition_self_model", "recurrent_processing", "global_availability", "causal_integration" ], "relation": "The legacy rubric grades whether a computational theory of consciousness is implemented. CQM-25 separates theory-linked mechanisms and treats none of them as evidence of experience." }, { "legacyAxis": "Visual scale", "axisIds": [ "visual_embodied_scale" ], "relation": "Same broad construct. CQM-25 measures single-being expression, population capacity and delivered frame time separately." } ] }