Delete 2026-06-10-what-the-organism-does.md

Create 2026-06-19-abstract-pattern-expression.md
2026-06-19 11:19:42 +02:00 · 2026-06-19 11:18:52 +02:00
2 changed files with 423 additions and 252 deletions
@@ -1,252 +0,0 @@
 ---
 include_toc: true
 ---
 # What the Organism Is Trying to Achieve
 The organism exists in a world that is partially predictable and partially surprising. Its fundamental challenge is to become progressively better at navigating that world — to recognize patterns that matter, respond to them effectively, and build on past experience to improve future behavior. This requires the organism to continuously update its internal structure based on what it encounters, while remaining stable enough that not every transient experience rewrites everything it has learned.
 The organism is therefore solving a **selective memory problem**: out of the continuous flood of experience, identify what is genuinely significant, strengthen the neural pathways that processed it, and let everything less significant fade — all within the constraints of finite energy and finite biological material.
 ---
 ## How the Organism Achieves This — The Spatial Hierarchy
 The organism solves this problem through a hierarchy of structures operating at different spatial scales, each sensitive to different aspects of experience.
 **At the organismic level**, dedicated organs monitor the overall state of the organism and its relationship to the world. The **VTA** tracks reward and surprise — whether outcomes were better or worse than predicted. The **locus coeruleus** tracks novelty and arousal — whether the current situation demands heightened attention. The **basal forebrain** tracks attentional state — whether the organism is in a mode where new patterns should be encoded. These organs integrate across the entire organism's experience — sensory input, motor output, internal state, social context — and translate their assessment into **neuromodulatory broadcasts**: dopamine, norepinephrine, and acetylcholine signals that diffuse widely across the brain and simultaneously shift the operating state of millions of synapses. These broadcasts are the organism's way of saying to its own neural tissue: what is happening right now is worth remembering, or is not.
 **At the neural circuit level**, populations of neurons integrate signals across sensory, motor, and associative areas, building representations of the current situation and generating behavioral responses. The circuit level is where the content of experience is processed — what was seen, what was done, what happened as a result. This is the level at which patterns are recognized and predictions are formed.
 **At the cellular level**, individual neurons and their associated astrocytes are the elementary units of pattern storage. Each neuron integrates inputs from thousands of synapses, each synapse reflecting a different aspect of the patterns the neuron participates in representing. The neuron's job is to detect coincidences — to fire when a particular combination of inputs arrives — and to strengthen the connections that reliably contribute to its firing.
 **At the synaptic level**, the individual synapse — composed of presynapse, postsynapse, and astrosynapse — is where the actual structural change happens. This is the elementary unit of memory: a physical modification of the connection between two neurons that makes future transmission across that connection more or less effective.
 ---
 ## The Neuron and Its Compartments
 A neuron is not a simple input-output device. It is a spatially extended system whose different parts perform different computations and operate on different timescales.
 The **soma** is the neuron's integrating and decision-making center. It sums all the inputs arriving from its dendritic tree, decides whether the combined input crosses the threshold for firing an action potential, and manages the production of structural proteins that all other compartments depend on. It is also the point where the organism-level validation signal — dopamine arriving via neuromodulatory broadcast — coincides with the neuron-level activity signal — nuclear calcium accumulating from recent firing — to produce the gene expression mandate that drives structural change during the night.
 The **axon** is the neuron's output channel. It carries the action potential from the soma to every presynaptic bouton, reliably and rapidly. It is also the supply line that transports vesicle proteins, mitochondria, and scaffold components from the soma to the boutons. Its structural integrity determines both how reliably APs reach their destination and how quickly boutons can be resupplied after structural remodeling.
 The **dendritic tree** is the neuron's input collection system. It receives signals from thousands of synapses and propagates them toward the soma. But it is not a passive cable — it actively integrates, amplifies, and filters. Individual dendritic branches perform local computations, summing inputs from their spines and deciding whether the local pattern is strong enough to propagate. The branch also carries the back-propagating action potential from soma to spines, providing each spine with the retrograde confirmation signal needed for coincidence detection. The branch is the resource distribution channel between soma and spines, delivering proteins, mRNA, and energy to wherever demand is highest.
 The **presynaptic bouton** is the neuron's output terminal at each individual synapse. It converts the electrical action potential into a chemical signal by releasing neurotransmitter into the synaptic cleft. Its release capacity — how much NT it can release per AP — is determined by the size of its active zone, the density of its vesicle docking slots, and the proximity of its calcium channels to those slots. All of these are structural properties that are remodeled during the night based on the bouton's recent activity history and its validation by the organism-level reward signal.
 The **postsynaptic spine** is the neuron's input terminal at each individual synapse. It detects the neurotransmitter released by the presynapse and converts it back into an electrical signal. Its sensitivity — how strongly it responds to a given NT release — is determined by the number of AMPA receptors anchored in its postsynaptic density and the physical size of the spine head. These structural properties are also remodeled during the night. The spine is also the primary site of coincidence detection: it requires both the forward glutamate signal from the presynapse and the retrograde bAP signal from the soma to arrive within a precise time window in order to trigger the cascade that leads to potentiation.
 ---
 ## The Astrocyte and the Astrosynapse
 The astrocyte is not a supporting cell. It is a full partner in synaptic function, and its perisynaptic process — the **astrosynapse** — is the third component of every synapse alongside pre and post.
 The astrosynapse controls two things that neither the presynapse nor the postsynapse can control for themselves. First, it determines how long glutamate remains in the cleft by clearing it through transporter proteins — setting the effective duration and concentration of the presynaptic signal. Second, it determines whether the postsynapse is permitted to open its NMDA receptors by supplying D-serine as the obligatory co-agonist — acting as a permissive gate on coincidence detection and therefore on the entire LTP induction cascade.
 By physically moving closer to or further from the synaptic cleft — retracting its walls inward during potentiation and extending them outward during depotentiation — the astrosynapse amplifies the direction of structural change that the synapse has already committed to. A tightly wrapped astrosynapse makes every future glutamate signal more concentrated and the NMDA gate more reliably open, making the synapse easier to potentiate further. A loosely wrapped astrosynapse dilutes the signal and starves the NMDA gate, making the synapse progressively harder to rescue. This self-reinforcing property makes the astrosynapse the most powerful single determinant of the long-term trajectory of a synapse.
 The astrocyte cell body integrates signals across its entire territory — which wraps hundreds of thousands of synapses — and provides the astrosynapse with the raw materials it needs: D-serine precursors, ECM proteins, process extension machinery, and energy in the form of lactate. The astrocyte is also the primary energy supplier to the entire synapse: it absorbs glucose from the blood vasculature, converts it to lactate, and delivers it to presynapse, postsynapse, and dendritic branch alike. The vascular glucose supply is the hard energy ceiling of the entire system — the one constraint that no molecular mechanism can overcome.
 ---
 ## The Temporal Hierarchy — DAY and NIGHT
 The system operates across two temporal scopes that correspond to the organism's activity cycle.
 During the **DAY**, the organism is acting in the world and the neural system is processing experience. At the fastest timescale — milliseconds — individual synapses are transmitting signals, calcium is flowing, vesicles are releasing. At the intermediate timescale — seconds to minutes — patterns of activity are building up traces within each compartment: residual calcium encoding recent firing history, possible tagging variables accumulating evidence of sustained recruitment, dopamine transients arriving and intersecting with local eligibility windows. All of these traces are graded, decaying, and reversible. No permanent structural change occurs during DAY. The architecture is fixed but tunable and the system operates within these constraints.
 The key DAY event is **tagging**: the coincidence of local eligibility — the component was recently and significantly active — and global validation — the organism-level neuromodulatory signal says this activity was worth preserving. When both coincide within the decay window of the local trace, a tag is set. The tag is the DAY scope's record of what the organism found significant. It is not binary — it is graded by how strong the activity was and how strong the validation was — and it decays slowly, surviving the full DAY scope to reach NIGHT.
 During the **NIGHT**, the organism is at rest and the neural system shifts into a structural rewriting mode. Budgets are replenished from the soma's protein synthesis machinery, which peaks during slow-wave sleep driven by the CREB gene expression program activated during DAY. Tagged synapses draw from these replenished pools to commit structural changes: larger active zones, more anchored receptors, tighter astrosynaptic wrapping. The magnitude of each structural change is proportional to the tag strength and bounded by the available budget. Untagged synapses receive only what remains after potentiation has drawn its share — and since structural maintenance requires a continuous resource allocation, synapses that receive less than their maintenance cost drift passively toward lower structural states. Depotentiation is not an active process. It is the shadow of potentiation — the inevitable consequence of finite resources being redirected toward what the organism found significant.
 ---
 ## The Integration That Makes It Work
 The entire system is fundamentally an **integration machine** operating across space and time simultaneously.
 In space, it integrates from the molecular level — calcium ions, receptor phosphorylation states, vesicle docking — through the synaptic level — pre, post, and astrosynapse cooperating — through the cellular level — soma integrating thousands of synaptic inputs — through the circuit level — populations of neurons collectively representing experience — to the organismic level — the VTA and locus coeruleus assessing the global significance of what is happening. Each level integrates experiences that the level below cannot generate from within itself. The organism's assessment of significance — dopamine — is not computable from the synapse's local activity. The synapse's coincidence detection — the bAP meeting the NMDA calcium signal — is not visible at the organismic level. Both are necessary. Neither is sufficient alone.
 In time, it integrates from the millisecond scale — individual spikes and calcium transients — through the second-to-minute scale — spike trains and trace accumulation — through the hour scale — tag persistence and protein synthesis — through the day-night cycle — structural commit and budget replenishment — through the multi-day scale — queued deficits resolved across consecutive nights and structural consolidation completed. Each timescale feeds forward into the next: what happens in milliseconds determines what the traces look like over minutes, which determines what gets tagged over hours, which determines what gets structurally committed over nights, which determines how the system responds to experience over weeks.
 The result is a system that is simultaneously **sensitive and stable**: sensitive because it continuously updates its structure based on recent significant experience, stable because the update process is slow, gated, resource-limited, and requires validation from the organism level before anything permanent is written. Fast enough to learn from today's experience. Slow enough that yesterday's learning is not erased by today's noise.
 # High level description of the components
 ## Presynaptic Bouton
 ### What Does the Presynaptic Bouton Actually Do?
 The presynaptic bouton has three distinct functions:
 **Neurotransmitter release** — it converts the arriving action potential into a chemical signal by releasing neurotransmitter into the synaptic cleft. The release is driven by calcium influx through voltage-gated calcium channels, which triggers vesicle fusion at the active zone. The rate of NT release — the NT flux — is determined by how much calcium arrives and how much NT is currently available in the readily-releasable pool. This is the bouton's primary fast function and its sole output to the synapse.
 **Release probability modulation** — it adjusts how effectively each AP drives NT release based on its own recent history. Residual calcium left from prior spikes accumulates in the bouton and biases the release machinery toward higher output — this is short-term facilitation. Depletion of the readily-releasable pool under sustained high-frequency firing reduces output regardless of calcium drive — this is short-term depression. Both are entirely local to the bouton and require no signal from outside.
 **Active zone maintenance** — it maintains the physical docking infrastructure at the active zone: the scaffold proteins that hold vesicles in position, the calcium channels clustered beneath the docking slots, and the reserve pool of vesicles ready to replenish the readily-releasable pool. The integrity of this infrastructure determines the ceiling on what the bouton can do moment to moment.
 ### Occupancy vs Capacity for the Presynaptic Bouton
 **DAY occupancy** — how effectively the bouton is currently releasing NT, driven by `pre_fast_trace`:
 - Current NT flux — the rate of neurotransmitter entering the cleft right now, driven by calcium and RRP level
 - Current RRP level — how full the readily-releasable pool is at this moment, fluctuating with release and refill rates
 - Current release probability — biased upward by residual calcium from recent spikes, downward by RRP depletion
 All three fluctuate continuously during DAY and reverse automatically when activity ceases. No structural variable is written.
 **NIGHT capacity** — the ceiling on DAY occupancy, set by `pre_structure`:
 - Active zone size — the number of docking slots available, determining the RRP ceiling
 - VGCC clustering — the proximity of calcium channels to docking slots, determining the efficiency of calcium-triggered release
 - RRP refill ceiling — the maximum rate at which the reserve pool can replenish the readily-releasable pool, determined by transport machinery and VATPase pump density
 ---
 ## Postsynaptic Spine
 ### What Does the Postsynaptic Spine Actually Do?
 The postsynaptic spine has three distinct functions:
 **Glutamate detection** — it detects the NT released by the presynapse through AMPA receptors on its surface, converting the chemical signal back into an electrical current that depolarizes the spine membrane. The magnitude of this current is determined by how many AMPA receptors are currently anchored at the postsynaptic density. This is the spine's primary fast function and its direct response to presynaptic output.
 **Coincidence detection** — it determines whether the incoming glutamate signal coincides with a retrograde signal from the soma. The NMDA receptor acts as the molecular coincidence detector: it requires both glutamate binding and sufficient membrane depolarization to eject its magnesium block, AND D-serine from the astrosynapse as a co-agonist. When all three conditions are met simultaneously, calcium enters through the NMDA channel and encodes the coincidence as a graded calcium signal whose amplitude and rise speed carry the instruction for future structural change.
 **Synaptic tagging** — it records the occurrence of a significant coincidence event by accumulating a graded tag variable that survives to the NIGHT scope. The tag is built in two stages: a candidate phase set by the local calcium event, which is then stabilized if dopamine arrives within the stabilization window. Only spines that were genuinely active during the day AND received organismic validation accumulate a stable tag strong enough to draw structural resources during NIGHT.
 ### Occupancy vs Capacity for the Postsynaptic Spine
 **DAY occupancy** — how effectively the spine is currently detecting and encoding signals, driven by `post_fast_trace`:
 - Current AMPA current — the immediate electrical response to glutamate, fluctuating with moment-to-moment receptor surface availability via lateral diffusion and rapid recycling
 - Current calcium amplitude and rise speed — the coincidence signal encoding the LTP versus LTD instruction, driven by NMDA opening
 - Current possible tagging level — the graded accumulation of participation evidence building toward a stable tag
 All three fluctuate during DAY. The transient receptor insertions and internalizations that drive AMPA current fluctuation are reversible — they reflect occupancy of existing anchoring slots, not creation of new ones.
 **NIGHT capacity** — the ceiling on DAY occupancy, set by `post_structure`:
 - Anchoring slot count — the number of positions in the PSD scaffold that can hold AMPA receptors, determining the ceiling on effective surface receptor count
 - Spine volume — the physical size of the spine head, determining the local endosomal receptor reserve and actin machinery available for rapid DAY trafficking
 - Local receptor reserve — the endosomal pool of AMPA receptors held near the spine, available for rapid insertion without waiting for somatic synthesis
 ---
 ## Dendritic Branch
 ### What Does the Dendritic Branch Actually Do?
 The dendritic branch has three distinct functions:
 **Bidirectional signal propagation** — it carries the summed electrical activity of its spines toward the soma, contributing to the somatic integration that determines whether an AP fires. It simultaneously propagates the back-propagating action potential from the soma toward the spines, providing each spine with the retrograde confirmation signal required for coincidence detection. The fidelity of bAP propagation decreases with distance from the soma, meaning distal spines receive a weaker confirmation signal than proximal ones — a spatial gradient that makes distal spines inherently harder to potentiate.
 **Local resource distribution** — it is the logistics channel between the soma and its spines, carrying proteins, mRNA, receptors, and mitochondria from the soma's production machinery to wherever spine-level demand is highest. Tagged spines receive priority allocation of these resources. The branch is not a passive pipe — it actively gates and directs the flow based on local demand signals.
 **Local protein synthesis** — it has its own ribosomes and stored mRNA pool that can produce structural proteins locally and rapidly, without waiting for somatic delivery. This local translation is activated when the branch itself is sufficiently recruited — when enough of its spines are co-active — providing a fast protein supply that supports early structural changes within minutes rather than hours.
 ### Occupancy vs Capacity for the Dendritic Branch
 **DAY occupancy** — how effectively the branch is currently performing its three functions, driven by `dend_fast_trace`:
 - Current bAP propagation strength — how faithfully the bAP reaches distal spines right now, fluctuating with recent activity and local energy availability
 - Current protein flux rate — how much resource is flowing through the branch toward spines at this moment
 - Current local translation rate — how actively branch ribosomes are running, gated by branch tag status and local budget
 All three fluctuate during DAY and recover when activity and budget allow. No structural variable is written.
 **NIGHT capacity** — the ceiling on DAY occupancy, set by `dend_structure`:
 - Mitochondrial density — determines the local ATP ceiling, which sets both bAP propagation strength and local translation rate
 - Cytoskeletal integrity — determines transport speed from soma to spines and the physical geometry of bAP propagation
 - mRNA pool ceiling — the maximum stored mRNA available for local translation, set by how much Arc and plasticity-related mRNA was shipped from the soma during prior NIGHT cycles
 ---
 ## Soma
 ### What Does the Soma Actually Do?
 The soma has three distinct functions:
 **Input integration and AP generation** — it continuously sums the electrical signals arriving from all its dendritic branches and decides whether the combined input crosses the firing threshold. When it does, it generates an action potential that propagates simultaneously down the axon to all presynaptic boutons and back up the dendritic tree as the bAP. The firing threshold is not fixed — it rises with recent firing history through spike-frequency adaptation, falls with strong neuromodulatory drive, and is subject to a hard absolute refractory period immediately after each AP.
 **Organism-level signal integration** — it is the point where the neuron-level activity signal — nuclear calcium accumulating from recent firing — meets the organism-level validation signal — dopamine arriving via the VTA broadcast. Only when both are present simultaneously is the gene expression program activated. The soma is therefore the coincidence detector at the cellular scale, just as the NMDA receptor is the coincidence detector at the synaptic scale.
 **Structural protein production** — it is the upstream source of all structural proteins, receptors, organelles, and mRNA that the downstream compartments — dendritic branches, spines, and axonal boutons — depend on for their NIGHT structural commits. The rate of production during NIGHT is set by the CREB gene expression program activated during DAY. This makes the soma the production bottleneck for the entire system: the magnitude of structural change possible across all compartments during any given NIGHT is bounded above by what the soma synthesized.
 ### Occupancy vs Capacity for the Soma
 **DAY occupancy** — how effectively the soma is currently performing its three functions, driven by `soma_fast_trace`:
 - Current firing threshold — rises above baseline with each AP via spike-frequency adaptation driven by slow potassium channels, falls with neuromodulatory drive, and is temporarily infinite during the absolute refractory period
 - Current integration gain — how effectively dendritic inputs sum toward threshold, modulated continuously by norepinephrine and acetylcholine levels
 - Current nuclear calcium level — the fast trace that accumulates with each AP and gates the coincidence with dopamine needed to activate gene expression
 All three fluctuate during DAY. The threshold adjustments and nuclear calcium accumulation are reversible on a timescale of seconds.
 **NIGHT capacity** — the ceiling on DAY occupancy, set by `soma_structure`:
 - Baseline firing threshold — the resting threshold before any DAY modulation, set by ion channel density at the axon initial segment
 - AP generation capacity — determined by sodium channel density and distribution, setting the reliability and amplitude of generated APs
 - Protein synthesis ceiling — ribosome density and CREB machinery capacity, determining the maximum rate of structural protein production available to all downstream compartments during NIGHT
 ---
 ## Axon
 ### What Does the Axon Actually Do?
 The axon has three distinct functions:
 **AP propagation** — it carries the somatic action potential reliably and rapidly from the axon initial segment to every presynaptic bouton along its length. Reliability is not guaranteed under all conditions — at very high firing frequencies, propagation can fail at axonal branch points because sodium channels need a brief recovery period after each AP. This frequency-dependent propagation failure is the axon's only form of short-term depression and is entirely local to the axon.
 **Anterograde resource transport** — it carries vesicle scaffold proteins, mitochondria, calcium channel subunits, and other structural components from the soma to the presynaptic boutons via motor proteins moving along microtubule tracks. The transport rate determines how quickly boutons can be resupplied after structural remodeling during NIGHT and therefore sets the timescale over which presynaptic structural commits are fulfilled.
 **Bouton maintenance supply** — it continuously delivers the molecular components that each bouton needs to maintain its active zone integrity, replenish its vesicle pools, and sustain its release capacity. A bouton that is not adequately supplied drifts toward lower structural states regardless of its tagging history, because maintenance requires a continuous resource allocation just as spine maintenance does.
 ### Occupancy vs Capacity for the Axon
 **DAY occupancy** — how effectively the axon is currently performing its three functions, driven by `axon_fast_trace`:
 - Current propagation reliability — the fraction of APs that successfully reach all boutons, degrading under high-frequency firing as sodium channels at branch points enter relative refractoriness
 - Current transport rate — how fast structural components are being delivered to boutons right now, fluctuating with local ATP availability and motor protein engagement
 - Current bouton supply level — whether individual boutons have sufficient molecular components for sustained release at this moment
 **NIGHT capacity** — the ceiling on DAY occupancy, set by `axon_structure`:
 - Myelination density — determines AP propagation speed and the frequency at which propagation failure begins to occur
 - Transport machinery capacity — motor protein density and microtubule integrity, determining the maximum rate of anterograde delivery to boutons
 - Axonal mitochondrial density — local ATP supply for both propagation and transport along the axon shaft, determining the energy ceiling on axonal function independent of astrocytic lactate delivery
 ---
 ## Astrosynapse
 ### What Does the Astrosynapse Actually Do?
 The astrosynapse has three distinct functions:
 **Glutamate clearance** — it removes glutamate from the cleft via EAAT transporters, terminating the signal and preventing spillover to neighboring synapses. This is the astrosynapse's primary fast function.
 **D-serine supply** — it releases D-serine as the NMDA co-agonist, gating whether the postsynapse can open its NMDA channels. Without D-serine, NMDA cannot open regardless of depolarization. The astrosynapse is therefore a permissive gate on postsynaptic LTP induction.
 **Diffusion geometry control** — by physically moving closer to or further from the cleft, it controls how concentrated glutamate remains in the cleft and how quickly it escapes to the extrasynaptic space. This is the perisynaptic distance variable — the structural variable that amplifies both LTP and LTD directions.
 ### Occupancy vs Capacity for the Astrosynapse
 **DAY occupancy** — how the astrosynapse is currently performing its three functions, driven by `astro_fast_trace`:
 - Current clearance rate — how fast glutamate is being removed right now, fluctuates with transporter availability and local ATP
 - Current D-serine release rate — how much co-agonist is being supplied right now, proportional to astro_fast_trace magnitude
 - Current diffusion geometry — the instantaneous physical position of the process relative to the cleft
 **NIGHT capacity** — the ceiling on DAY functions, set by `astro_structure`:
 - EAAT transporter density — determines maximum clearance rate
 - Serine racemase enzyme density — determines maximum D-serine synthesis rate
 - Perisynaptic distance — the resting position of the process walls around the cleft
 - ECM integrity — the extracellular matrix scaffold that stabilizes the process position
@@ -0,0 +1,423 @@
 # The Abstract Pattern
 A component operates within two ceilings set by the previous NIGHT: a **structure** that bounds how strongly each behavior can act, and a **budget capacity** that bounds how much fuel the component can hold. Both ceilings bound an active, competitive DAY process — structure bounds how far behavior strength can be filled toward its maximum, budget capacity bounds how far fuel can be replenished toward its maximum — and in both cases the filling competes against other components for a shared resource. During DAY, in each context, the component executes behaviors that draw on budget and deposit fast traces. Two kinds of evidence accumulate: a **tag**, when a local eligibility signal coincides with non-local validation, driving *strength*; and an **endurance need**, when budget depletion interrupts a behavior on a successful trajectory, driving *endurance*. At NIGHT, tags raise structure and endurance needs raise budget capacity, both proportional to available material and energy, both drawing from the same finite pool, so that strength and endurance compete. What is not committed decays for lack of maintenance, and the resources freed partially fund what was.
 ---
 ## DAY — The General Form
 Every DAY behavior runs within two ceilings and competes for two shared resources.
 ```
 given:   STRUCTURE         // bounds behavior strength (ceiling from NIGHT)
         BUDGET_CEILING    // bounds fuel capacity (ceiling from NIGHT)
 in:      CONTEXT           // local or global triggering condition
 if:      BUDGET >= cost    // operational fuel available
 then:    behavior executes, strength bounded by STRUCTURE
         BUDGET     -= cost
         FAST_TRACE += f(behavior)               // local record deposited
 else:    behavior suppressed                     // fuel was the limit
         if behavior was ON A SUCCESSFUL TRAJECTORY:
             ENDURANCE_NEED += g(trajectory)      // fuel interrupted a forming success
 ```
 Two competitive DAY processes fill the two ceilings:
 **Strength filling (bounded by STRUCTURE).** Behavior strength rises toward the structural ceiling by competing for local occupancy resources — receptors at the postsynapse, vesicles at the presynapse. A behavior cannot act more strongly than its structure permits, because the occupancy it draws on is itself bounded by the structure.
 **Fuel replenishment (bounded by BUDGET_CEILING).** Fuel rises toward the budget ceiling by competing for shared upstream supply — astrocyte lactate, soma shipment. Each component's claim is the gap between its current budget and its ceiling; the shared supply is rationed by these claims:
 ```
 // competitive replenishment — the ceiling bounds the process via the demand
 c_demand          = BUDGET_CEILING - BUDGET           // gap below ceiling = claim on supply
 total_demand      = sum(c_demand for components on shared supply S)
 allocation_factor = min(1, S / (total_demand + ε))
 replenishment     = c_demand × allocation_factor      // rationed share
 BUDGET           += replenishment                      // never exceeds ceiling (demand was the gap)
 S                -= replenishment
 ```
 Neither ceiling is applied as a clamp. Each bounds its process from within: structure is the thing being filled with occupancy, budget_ceiling is the target the replenishment demand reaches toward. A high budget_ceiling is not free even during DAY — it makes a large standing claim on shared fuel, and the component reaches it only if the supply can satisfy that claim against competing claims.
 The fast trace drives two parallel processes; depletion drives a third.
 **Within the same context** — the fast trace biases the next execution of the same behavior. Short-term modulation. Local, no external signal.
 **Across contexts** — the fast trace accumulates into `possible_tagging` above the eligibility threshold. The bridge toward strength. Requires the trace to survive into a NOT/CONTINUOUS context.
 **On depletion** — when budget gates a behavior that was succeeding, `endurance_need` accumulates. The bridge toward endurance. Requires the depletion to have interrupted something valuable, not merely to have occurred.
 ---
 ### Tag Formation — Non-Local Coincidence (drives STRENGTH)
 Strength is associative. The tag requires local eligibility plus non-local validation, the number of coincidences set by the component's spatial scale.
 **PRE, DEND, SOMA, AXON, ASTRO — one non-local coincidence:**
 ```
 if FAST_TRACE > eligibility and dopamine > threshold:
    TAG += dopamine × possible_tagging
 ```
 **POST — three coincidences (astrosynapse, soma, organism):**
 ```
 // 1. NOT_bAP: local Ca²⁺ + astrosynapse D-serine → CANDIDATE
 if FAST_TRACE > Ca_TAG_threshold and D-serine > threshold:
    post_possible_tagging += FAST_TRACE
 // 2. bAP: CANDIDATE + soma fired → amplified above Ca_HIGH
 if post_possible_tagging > threshold and bAP arrives:
    FAST_TRACE += bAP_boost
 // 3. any context: CANDIDATE + dopamine → STABLE
 if post_possible_tagging > threshold and dopamine > threshold:
    TAG += dopamine × post_possible_tagging
 ```
 ---
 ### Endurance Formation — Interrupted Success (drives ENDURANCE)
 Endurance is homeostatic, not associative. It requires depletion plus a successful trajectory, the meaning of "successful" set by the component's local function. **No dopamine.**
 ```
 if BUDGET < cost and trajectory_was_succeeding:
    ENDURANCE_NEED += g(trajectory)    // graded by closeness to success
 ```
 Per-component definition of *succeeding*:
 - **PRE** — release was driving rising postsynaptic engagement
 - **POST** — calcium was climbing toward the tagging threshold
 - **DEND** — active spines existed distal to where propagation died
 - **SOMA** — nuclear calcium was approaching CREB, or firing was recruiting downstream
 - **AXON** — propagation failed to engaged boutons, not idle ones
 - **ASTRO** — the postsynapse was depolarized and waiting for D-serine when synthesis ran out
 The signal shape is identical everywhere — fuel ran out at the verge of a valuable outcome — only the local definition of "verge" varies.
 ---
 ### Trace Recession — The Temporal Behavior
 In every NOT/CONTINUOUS context, all traces decay:
 ```
 FAST_TRACE       *= decay(τ_fast)      // ms–s   — closes eligibility window
 possible_tagging *= decay(τ_mid)       // s–min  — closes tagging window
 ENDURANCE_NEED   *= decay(τ_mid)       // s–min  — closes endurance window
 TAG              *= decay(τ_slow)      // hours  — closes commitment window
 ```
 Decay is not a separate behavior — it is the passive consequence of molecular processes. It enforces time windows without any clock: a coincidence must complete, and a depletion must interrupt a success, while the relevant trace is still elevated. Timing is the competition between accumulation and decay.
 ---
 ## NIGHT — The General Form
 NIGHT raises two ceilings from two kinds of evidence, both drawing on the same finite material and energy.
 **Strength commit — driven by tag (validated coincidence):**
 ```
 if TAG > threshold:
    Δstructure = min(expansion_cost, MATERIAL, ENERGY × fraction)
    STRUCTURE += Δstructure × coherence_bonus    // raises the strength ceiling
    MATERIAL  -= Δstructure                       // RECOVERABLE
    ENERGY    -= Δstructure × ATP_cost             // NOT recoverable
 ```
 Coherence bonus when pre, post, and astro tags are all set together — the three synaptic components independently gathered evidence for the same change.
 **Endurance commit — driven by endurance need (interrupted success):**
 ```
 if ENDURANCE_NEED > threshold:
    Δcap = min(capacity_cost, MATERIAL, ENERGY × fraction)
    BUDGET_CEILING += Δcap                         // raises the endurance ceiling
    MATERIAL       -= Δcap                          // RECOVERABLE (mitochondria recyclable)
    ENERGY         -= Δcap × biogenesis_cost         // NOT recoverable
 // no coherence bonus, no dopamine — endurance is per-component homeostatic
 ```
 The two commits compete for the same material and energy: building endurance somewhere cannot strengthen elsewhere. A component both significant and fuel-limited demands both and is the strongest claimant, potentially forcing decay elsewhere.
 **What is not committed decays — by neglect, for both ceilings:**
 ```
 STRUCTURE      -= decay_rate × Δt_night
 STRUCTURE      += min(structure_maintenance, maintenance_cost)
 BUDGET_CEILING -= capacity_decay_rate × Δt_night
 BUDGET_CEILING += min(capacity_maintenance, capacity_cost)
 // if maintenance < decay: the ceiling drifts down
 //   structure → depotentiation by neglect
 //   budget_ceiling → loss of endurance (mitophagy of idle capacity)
 // recovered material partially funds the commits above
 ```
 ---
 ## The Pattern in One View
 ```
 TWO CEILINGS, each bounding a competitive DAY process and raised by NIGHT evidence:
  STRUCTURE (strength)         bounds behavior strength;
                               filled in DAY by competing for occupancy;
                               raised in NIGHT by TAG (validated coincidence)
  BUDGET_CEILING (endurance)   bounds fuel capacity;
                               filled in DAY by competing for shared supply;
                               raised in NIGHT by ENDURANCE_NEED (interrupted success)
 DAY   behavior runs within both ceilings, both filled competitively
      consumes budget, deposits fast trace
      fast trace + non-local coincidence → TAG            (evidence for strength)
      depletion + interrupted success    → ENDURANCE_NEED  (evidence for endurance)
      traces decay in NOT/CONTINUOUS contexts — windows close
 NIGHT TAG            → raise STRUCTURE       (per-event power)
      ENDURANCE_NEED → raise BUDGET_CEILING  (sustainable duration)
      both draw the SAME material + energy → strength and endurance compete
      unmaintained ceilings of either kind decay → freed material funds the rest
 A high ceiling of either kind is never free: structure must be filled by winning
 occupancy, budget capacity must be filled by winning shared fuel — both against
 competing components, every DAY. The system invests STRENGTH where a valuable
 coincidence completed and was validated, and ENDURANCE where fuel — not structure,
 not significance — was what stood between activity and success. To be both effective
 and sustainable, a connection must win on both, at both timescales, against all
 others drawing from the same finite pools.
 ```
 # More details
 ## SOMA
 ### The Abstract Pattern Applied to Soma Timing
 The abstract pattern says: a behavior deposits a trace, the trace decays, and the trace biases the next behavior. For the soma, the AP is the behavior, and **the refractory period and threshold elevation should both be consequences of a single trace deposited by the AP, decaying back toward baseline**. Neither should be a hardcoded duration — both should emerge from the return of the trace to resting conditions.
 ---
 Yes, this is much more consistent with the rest of the architecture. The soma should not compute an explicit rhythm estimate and predict the next input — that is top-down. Instead, the **mismatch itself leaves a trace**, and that trace adjusts the refractory dynamics. Let me think through this carefully.
 ---
 ### The Bottom-Up Mechanism
 The key event is: **a dendritic input arrives strong enough to fire the soma, but the soma is still refractory.** This is a missed opportunity — the input wanted to fire the cell, but the cell was not ready. This mismatch is the signal.
 Each time this happens, it should leave a trace that biases the refractory dynamics toward recovering faster in that timing window — so that next time an input arrives at that phase, the soma is ready. This is potentiation of the refractory recovery, occurring within DAY, driven entirely by the local coincidence of "input wanted to fire" and "soma was not ready."
 ```
 scope DAY | context NOT_AP (within refractory):
    // Detect the mismatch: suprathreshold input during refractory
    if branch_Vm > effective_threshold and soma_Na_inactivation > inactivation_threshold:
        // Input arrived but soma could not fire — missed coincidence
        refractory_alignment_trace += (branch_Vm - effective_threshold)
                                       × soma_Na_inactivation
        // graded: stronger input + deeper refractory → larger trace
        // this is the "potentiation" signal for faster recovery
 ```
 The `refractory_alignment_trace` then biases the recovery rate of the inactivation trace:
 ```
    // Recovery rate biased by accumulated alignment trace
    recovery_rate = base_recovery_rate × (1 + refractory_alignment_trace)
    soma_Na_inactivation *= decay(τ_Na / recovery_rate)
    // more alignment trace → faster recovery → soma ready sooner next time
 ```
 ---
 ### Why This Is Bottom-Up
 There is no rhythm estimation, no prediction of the next input time, no computed inter-input interval. The soma does not model its input. It simply notices, locally and reactively, that an input arrived when it was not ready, and leaves a trace that makes it recover faster. Over many such mismatches at the same phase, the recovery speeds up at that phase specifically — and the soma ends up aligned with its input rhythm **without ever representing that rhythm**.
 The alignment is an emergent statistical consequence of many local mismatch events, exactly as a potentiated synapse becomes tuned to its input without representing what it is tuned to. The phase-coupling appears, but nothing in the soma computed it.
 ---
 ### Depotentiation as Neglect — Not Explicit
 Now the crucial part you raised: the depotentiation of refractory alignment must occur as a **consequence of not potentiating**, not as an explicit opposing mechanism.
 The `refractory_alignment_trace` decays continuously. If mismatches keep happening at a particular phase, the trace is continuously replenished and the fast recovery is maintained. If mismatches stop happening — because the input rhythm changed, or because the alignment succeeded and inputs now arrive when the soma is ready — then the trace is no longer replenished and **decays back toward baseline on its own**.
 ```
    // No explicit depotentiation — just decay when not reinforced
    refractory_alignment_trace *= decay(τ_alignment)
    // if mismatches continue → trace replenished → fast recovery maintained
    // if mismatches stop → trace decays → recovery returns to baseline
 ```
 This is exactly parallel to synaptic depotentiation by neglect. The soma does not actively slow its recovery when alignment is no longer needed. It simply stops receiving the mismatch signal that was keeping the recovery fast, and the recovery drifts back to baseline because the trace that accelerated it is no longer reinforced.
 There is an elegant self-limiting property here. Once the soma is well-aligned, inputs arrive when it is ready, so there are no more mismatches, so the alignment trace stops being replenished and begins to decay. This would slowly de-align the soma — until inputs start arriving during refractory again, regenerating the mismatch and re-potentiating the alignment. The system settles into a dynamic equilibrium where just enough mismatch occurs to maintain just enough alignment. The soma hovers at the edge of alignment, continuously corrected by the residual mismatches that its imperfect alignment produces.
 ---
 ### The Full Bottom-Up Soma Timing
 ```
 scope DAY | context AP:
    effective_threshold = soma_structure.baseline_threshold
                          × (1 + soma_adaptation)
                          × neuromod_factor(NE_level, ACh_level)
    can_fire = (soma_Na_inactivation < inactivation_threshold)
    if branch_Vm > effective_threshold and can_fire:
        AP_fired = True
        soma_budget -= AP_generation_cost
        // Deposit traces from the AP
        soma_Na_inactivation += AP_amplitude       // fast — refractory
        soma_adaptation      += AP_contribution     // slow — spike train threshold
        soma_fast_trace      += nuclear_Ca_influx() // slow — plasticity tagging
 scope DAY | context NOT_AP:
    // MISMATCH DETECTION — bottom-up alignment signal
    if branch_Vm > effective_threshold and soma_Na_inactivation > inactivation_threshold:
        // input wanted to fire but soma was refractory — missed coincidence
        refractory_alignment_trace += (branch_Vm - effective_threshold)
                                       × soma_Na_inactivation
        // local potentiation of recovery — no prediction, no rhythm model
    // Recovery biased by alignment trace
    recovery_rate = base_recovery_rate × (1 + refractory_alignment_trace)
    soma_Na_inactivation *= decay(τ_Na / recovery_rate)    // faster if aligned
    soma_adaptation      *= decay(τ_adaptation)
    soma_fast_trace      *= decay(τ_nuclear)
    // Alignment trace decays — depotentiation by neglect, not explicit
    refractory_alignment_trace *= decay(τ_alignment)
    // maintained only while mismatches continue
    // self-limiting: good alignment → fewer mismatches → trace decays →
    //                slight de-alignment → mismatches return → re-potentiation
    // ... budget replenishment, shipments, tagging as before ...
 ```
 ---
 ### The Conceptual Payoff
 This makes the soma's temporal alignment obey exactly the same principles as everything else in the system:
 A behavior leaves a trace — here the missed coincidence leaves the alignment trace.
 The trace biases future behavior — here it accelerates recovery so the next input at that phase succeeds.
 Potentiation is the active drive — the soma actively speeds up recovery in response to mismatch.
 Depotentiation is neglect — the alignment trace decays when mismatches stop, with no explicit opposing process.
 The system finds equilibrium through the residual of its own imperfection — just enough mismatch persists to maintain just enough alignment.
 And critically, the soma achieves temporal prediction — firing in phase with its input rhythm — **without ever representing the rhythm**. The prediction is implicit in the structure of the recovery dynamics, built up from purely local, reactive, bottom-up trace deposits. This is the same way a potentiated synapse "predicts" that its input will be significant without representing the prediction: the prediction is the physical bias left by past experience, not a computed expectation. The soma's phase-coupling is the temporal version of the synapse's weight — both are implicit predictions encoded as physical bias, both built bottom-up from local coincidence, both maintained by reinforcement and lost by neglect.
 ## Energy depletion in Presynapse
 how does the budget and energy influence the model. If for example a presynapse has no more energy variuos times during day, what happens?
 Good question. Let me trace through exactly what happens when energy is repeatedly depleted, following the mechanics already in the pseudocode.
 ---
 ### The Immediate Effect — Behavior Suppression
 When `pre_budget < AP_release_cost`, the pseudocode does:
 ```
 if pre_budget < AP_release_cost:
    suppress(NT_flux)
    exit context
 ```
 So the immediate consequence of an energy-depleted bouton is **silence** — it does not release neurotransmitter for that AP, regardless of how strong the incoming spike was. The AP arrives, but nothing comes out the other side. This is biologically real: ATP-depleted boutons fail to release because the VATPase cannot refill vesicles and the calcium pumps cannot maintain the gradients that drive release.
 ---
 ### The Cascade of Consequences Within DAY
 A single depletion is recoverable — the bouton refuels from astrocyte lactate in the next NOT_AP context and resumes. But **repeated depletion during DAY** sets off a cascade that runs through the entire trace and tagging machinery.
 **No release means no glutamate means no downstream trace.** When the bouton is silent, no glutamate reaches the cleft. The postsynapse receives no AMPA current, its NMDA channels do not open, and `post_fast_trace` does not rise. The astrosynapse detects no spillover, so `astro_fast_trace` does not rise and no D-serine pulse is released. The entire synaptic event simply does not happen. A bouton that is energy-depleted at the moment a significant pattern arrives causes that pattern to be invisible to the postsynapse — the synapse fails to participate in whatever the network is doing.
 **No participation means no eligibility.** Because the bouton did not release, `pre_fast_trace` is not elevated by a release event (it still rises from calcium influx, but without the reinforcing facilitation of successful release). More importantly, the postsynapse, having received no input, accumulates no `post_possible_tagging`. When dopamine arrives to validate the moment, there is nothing to validate at this synapse — the eligibility window is empty. The synapse misses the tagging opportunity entirely.
 **Missing the tag means missing the NIGHT commit.** Since no tag was set during DAY, the synapse has nothing to draw structural resources with during NIGHT. It does not potentiate. And because the system's depotentiation is by neglect, **a synapse that fails to potentiate is automatically on the path to depotentiation** — it receives only maintenance allocation, and if other synapses potentiated and drew down the shared pool, even maintenance may be insufficient.
 ---
 ### The Deeper Consequence — Energy Depletion Becomes Structural Depression
 Here is the important emergent property: **repeated energy depletion at a bouton during DAY leads to its structural depression during NIGHT, even though no depression signal was ever sent.**
 The chain is entirely passive:
 ```
 repeated pre_budget depletion in DAY
    → bouton silent during significant events
    → no glutamate release
    → no post_fast_trace, no post_possible_tagging
    → no tag set (pre or post)
    → no NIGHT structural commit at this synapse
    → only maintenance allocation received
    → if pool depleted by other synapses' potentiation:
        maintenance insufficient
    → pre_structure and post_structure decay
    → DEPOTENTIATION
 ```
 The energy-starved synapse is outcompeted not because it was marked for depression but because it could not generate the activity needed to claim resources. Energy availability during DAY therefore directly determines which synapses can even enter the competition for NIGHT potentiation.
 ---
 ### The Feedback Loop — Depression Reduces Future Energy Demand
 There is a stabilizing feedback here. A depotentiated synapse has smaller `pre_structure` — a smaller active zone, fewer docking slots, lower release probability. This means it costs **less energy to operate**. So a synapse that was energy-starved and consequently depotentiated now has lower energy demands, making it less likely to be energy-starved in the future.
 ```
 energy depletion → depotentiation → smaller structure → lower energy demand
    → less likely to deplete → stabilizes at a low-activity equilibrium
 ```
 The synapse settles into a low-energy, low-structure, low-activity state. It is not dead — it still operates at baseline — but it has been demoted from the pool of synapses competing for potentiation. Energy scarcity has selected it out.
 ---
 ### Why This Is Functionally Important
 This is not a bug — it is a resource-allocation mechanism with real computational value.
 **Energy availability acts as a second gate on plasticity, parallel to the neuromodulatory gate.** Dopamine asks "was this worth saving?" Energy asks "can this synapse afford to participate?" A synapse must pass both gates to be potentiated. This means the system preferentially potentiates synapses that are both behaviorally significant AND metabolically sustainable. A synapse that cannot sustain its own activity is not a good candidate for strengthening, because strengthening it would only increase its energy demand and make it fail more often.
 **Local energy competition implements a form of spatial sparsification.** Boutons on the same axon share `axon_budget` and ultimately the same astrocytic lactate supply. When many boutons are active simultaneously, the shared energy is divided among them, and the weakest — those with the least efficient structure or the least reliable input — deplete first and fall silent. This automatically sparsifies activity: under energy pressure, only the most robust synapses keep firing, and they are the ones that get potentiated. The system concentrates its limited resources on its strongest connections.
 **The astrocyte's energy delivery becomes a control signal.** Because the astrocyte controls lactate distribution across its territory, it has indirect control over which synapses can sustain activity and therefore which can be potentiated. A region of the astrocyte territory that is well-perfused and well-fueled supports vigorous plasticity. A region that is metabolically stressed — perhaps because of high overall demand or reduced vascular supply — suppresses plasticity in its synapses regardless of their activity. This couples the metabolic state of the tissue directly to its capacity to learn.
 ---
 ### What Repeated Depletion Looks Like Over Days
 If a bouton is chronically energy-starved across multiple DAY cycles — perhaps because it is in a metabolically compromised region, or because it is competing with many highly active neighbors — the trajectory is:
 ```
 Day 1: depletes occasionally → misses some events → weak tag → partial commit
 Day 2: smaller structure → still depletes under load → weaker tag → less commit
 Day 3: structure decaying → maintenance insufficient → depotentiation accelerates
 ...
 Equilibrium: minimal structure, minimal energy demand, minimal participation
             synapse survives but is functionally silent
             resources it would have consumed now available to neighbors
 ```
 This is a reasonable model of what happens to synapses in metabolically stressed tissue — they do not die immediately, but they are progressively silenced and depotentiated, freeing their resources for synapses in healthier regions. It is also a model of how chronic metabolic limitation — aging, vascular disease, mitochondrial dysfunction — would manifest as a gradual loss of plasticity capacity: not through any depression signal, but through the simple inability of energy-starved synapses to participate in the activity that would let them claim resources.
 The energy budget is therefore not just a constraint that occasionally blocks behavior — it is a continuous selective pressure that shapes which synapses thrive and which fade, operating silently in parallel with the explicit activity-and-reward-driven plasticity, and ultimately determining the metabolic sustainability of whatever the system chooses to remember.
 ## Three parallel competitive resource economies
 The neuronal structural economy — soma produces material, distributed through dendrite to spines and through axon to boutons, competed for by tagged synapses during NIGHT.
 The astrocytic energy economy — astrocyte cell body produces lactate, distributed to perisynaptic processes, competed for by active synapses during DAY in proportion to their clearance demand.
 The soma's own energy economy — soma mitochondria fuel AP generation and shipping, competed for by the soma's own functions.
 All three share the same logic: a central producer with a capped output, distribution to peripheral consumers, demand-weighted allocation, and a self-reinforcing coupling where stronger consumers both demand and receive more. And all three ultimately bottom out at the same vascular glucose ceiling — the astrocyte directly, the soma through its own glucose uptake.
 The deep consequence is that a synapse must win on both economies to be potentiated. It must generate enough activity to pull lactate from the astrocyte (energy economy) AND accumulate enough tag to draw material during NIGHT (structural economy). A synapse that wins the structural competition but cannot pull energy will be unable to sustain the activity that justified its potentiation — it will be a large, expensive structure that keeps going silent. A synapse that pulls energy but never accumulates a tag stays metabolically supported but structurally weak. Only synapses that win both — active enough to be fueled, significant enough to be tagged — achieve and maintain full potentiation. The two economies together implement a stringent joint criterion: persistent significant activity that the metabolic infrastructure can sustain.
Author	SHA1	Message	Date
ocrampal	e4ef1dfb83	Delete 2026-06-10-what-the-organism-does.md	2026-06-19 11:19:42 +02:00
ocrampal	ce46bf3c39	Create 2026-06-19-abstract-pattern-expression.md	2026-06-19 11:18:52 +02:00