Skip to content

Claim and evidence ledger

This ledger keeps high-risk publication claims and canonical scene claims attached to an evidence class, source location, public surface, and limitation. Paper reported means the claim belongs to Kimi K3 arXiv:2607.24653v2; it is not independently reproduced here.

Publication claims

Claim ID Evidence Claim Source Public locations Boundary
model-scale Paper Reported Kimi K3 has 2.8 trillion total parameters, 104 billion activated parameters, and a one-million-token context window. §1, paper p. 2; Table 1 README.md, docs/00_thesis.md, docs/06_cases_conclusion.md, docs/blog/kimi-k3-building-blocks.md These are paper-reported model properties, not repository reproductions.
hybrid-layer-cadence Paper Reported The 93-layer attention stack contains 69 KDA and 24 Gated MLA layers in a repeated 3:1 cadence, ending with MLA. §2; Fig. 2; Table 1 docs/01_architecture.md, docs/blog/kimi-k3-building-blocks.md The local miniature demonstrates only a small 3:1 stack and does not reproduce the full model.
routed-experts Paper Reported Stable LatentMoE reports 896 routed experts with 16 selected per token, alongside two shared experts. §2.3; Table 1 docs/01_architecture.md, docs/blog/kimi-k3-building-blocks.md The repository does not reproduce paper-scale routing, balance, or expert parallelism.
vision-pathway-scale Paper Reported MoonViT-V2 is reported as a 27-layer, approximately 401M-parameter encoder supporting inputs up to 3584×3584 pixels. §2.4; Table 1 docs/01_architecture.md The local vision module only demonstrates patchification.
scaling-efficiency Paper Reported K3 reports an approximately 2.5× scaling-efficiency improvement over K2 under the paper's fitted comparison. §3.2; Fig. 7 docs/02_pretraining.md, docs/blog/kimi-k3-building-blocks.md The local scaling notebook uses authored coefficients and does not refit or verify the paper's curve.
context-curriculum Paper Reported The reported context curriculum progresses from 8K to 64K during pretraining and from 256K to 1M during cooldown. §3.4 docs/02_pretraining.md, docs/blog/kimi-k3-building-blocks.md Context capacity and curriculum exposure do not prove perfect long-range retrieval.
posttraining-specialists Paper Reported Three domains crossed with low, high, and max reasoning effort produce nine specialist policies before MOPD consolidation. §4.1.2–§4.1.3 docs/03_posttraining.md, docs/blog/kimi-k3-building-blocks.md The nine paper models and their training runs are not available locally.
evaluation-context-management Paper Reported The primary BrowseComp result uses context compaction at 300K tokens; the report separately includes a 1M-context result without context management. §6.1.3 docs/05_evaluation.md The repository does not reproduce either evaluation protocol.
nano-kpu-case Paper Reported The nano-KPU case reports timing closure at 100 MHz, more than 8,700 decoded tokens/s in RTL simulation, 1.46M standard cells, and 0.277 MiB SRAM. §7 docs/06_cases_conclusion.md These are reported EDA and simulation outputs, not fabricated-silicon measurements or local reproductions.
public-benchmark-tables Paper Reported Selected reasoning, coding, agentic, and vision values are transcribed from the paper and compared only within their original benchmark rows. §6.1.4; Table 2 docs/05_evaluation.md The heterogeneous metrics cannot be averaged into a valid universal score, and this repository does not rerun the harnesses.
vision-python-lifts Paper Reported The paired Python condition raises K3's reported scores by 1.8 on MMMU-Pro, 6.5 on CharXiv RQ, 3.5 on Math-Vision, and 18.0 on ZeroBench-main pass@5. §6.1.4; Table 2 docs/05_evaluation.md The intervention changes the evaluated system but does not identify which tool action caused each gain.
internal-evaluation-profile Paper Reported The paper reports K3 at 76.3 on Swarm Bench, 90.0 on Deep Research Bench, and a +31.0 win-minus-lose margin against Opus 4.8 on Kimi Webdev Bench. §6.2.1; Tables 3–4 docs/05_evaluation.md The underlying private tasks, trajectories, and judge calibration are unavailable for independent audit.
cyber-evaluation-profile Paper Reported The paper reports approximately 70% confirmation among reviewed Tier-1 candidates and 14 of 36 solved Tier-2 tasks for K3 versus 8 of 36 for GLM-5.2. §6.2.2 docs/05_evaluation.md Selective review, private targets, baseline refusals, and the paper's lower-bound warning constrain interpretation.
third-party-snapshot Paper Reported The July 23, 2026 third-party snapshot reports K3 fourth on Artificial Analysis, second on Vals Index, first on WebDev Arena, eighth on Text Arena, and fourth on Agent Arena. §6.3; Table 5 docs/05_evaluation.md Rankings and Elo-style values are time-dependent and measure different constructs.
cost-frontier-examples Paper Reported The paper places K3 on or near task-specific score-cost frontiers and reports selected relative costs for Kimi Code Bench, BrowseComp, GDPval, and AA-Briefcase. §6.4; Fig. 13 docs/05_evaluation.md Costs combine internal measurements and cited provider prices under different task-specific harnesses.
kernel-case-results Paper Reported The selected kernel case reports AttnRes latency falling from 283.6 ms to 114.4 ms and DSA and KDA runtime reductions of 55.1% and 73.6%. §7 docs/06_cases_conclusion.md These selected paper measurements do not establish success rates or generalize to unseen kernels.
science-case-scale Paper Reported The selected astrophysics case reports more than 20 papers, about 300 equations of state, and roughly 3,000 lines of code produced in two hours. §7 docs/06_cases_conclusion.md Speed and code volume do not establish scientific correctness; no independent domain audit was performed here.

Canonical visual-scene claims

Course · chapter · beat Evidence Claim Source Boundary
architecture · design-space · three-axes Animated Interpretation A single hidden state must carry history, retrieve useful depth, and select specialized capacity. §2 This organizing frame is a teaching synthesis, not a decomposition named by the paper.
architecture · native-multimodality · patch-project-merge Animated Interpretation Pixels become patches, visual features, projected embeddings, and finally members of the same sequence as text. §2.4 Local evidence validates patch and shape flow, not MoonViT-V2 training or multimodal quality.
architecture · hybrid-cadence · execute-and-replicate-motif Paper Reported One token traverses three recurrent updates and one global read; twenty-three motifs plus a final MLA produce 69 KDA and 24 MLA layers. §2.1 The animation explains layer cadence; it does not measure the quality or cost contribution of the ratio.
architecture · kda · recurrence Executed Here KDA replaces a growing list with a fixed state, then decays, probes, corrects, writes, reads, and resolves into the notebook trace. §2.1.1, Eqs. 1–6 The sequential miniature verifies the recurrence and chunk handoff, not FlashKDA or million-token retention.
architecture · gated-mla · compress-read-and-gate Animated Interpretation Compact latents persist; a global query reconstructs head-specific keys and values on demand and gates the result back into the residual stream. §2.1.2 The miniature checks dimensions and cadence but does not reproduce K3's trained cache-quality tradeoff.
architecture · attnres · retrieve-over-depth Executed Here Ordinary addition collapses depth history; AttnRes scores addressable block summaries and forms a depth-selective blend. §2.2, Eqs. 8–10 Local tests verify normalized depth weights, not full-model optimization or Block AttnRes memory savings.
architecture · stable-latent-moe · route-stabilize-and-balance Animated Interpretation The paper combines 896/top-16 latent routing, a shared full-width path, bounded SiTU-GLU, and score-margin Quantile Balancing. §2.3–§2.3.3 The local 8-expert/top-2 path omits latent/shared branches and uses count-EMA rather than paper Quantile Balancing.
architecture · per-head-muon · split-orthogonalize-and-repack Executed Here Split the fused gradient into head-local matrices, apply five polynomial Newton-Schulz steps independently, and repack the original shape. §2.5 Small-matrix singular-value traces validate mechanics only; rectangular targets are shape-aware semi-orthogonal factors.
architecture · synthesis · rapid-replay Animated Interpretation One token passes through multimodal entry, hybrid sequence mixing, depth routing, sparse capacity, and the output head. §2 The synthesis composes mechanisms conceptually and is not an executed end-to-end K3 model.
evaluation · measurement-contract · evaluation-thesis Animated Interpretation A score is the final link in a measurement chain—not a property floating above its protocol. §6 The chain is an authored evaluation-literacy framework.
evaluation · measurement-contract · four-axes Paper Reported Reasoning, coding, agency, and vision are different lenses; none is a universal intelligence scalar. §6.1.1 Coverage breadth does not prove complete construct coverage or independence among benchmarks.
evaluation · measurement-contract · baseline-contract Paper Reported Maximum effort is aligned where possible, but fallback, cyberguard, and xhigh qualifications remain part of the comparison. §6.1.2 The paper notes fallback and cyberguard behavior; identical model-side conditions are not guaranteed.
evaluation · measurement-contract · protocol Paper Reported Model × effort × harness × tools × sampling × task version produces the observed result. §6.1.3 The report provides substantial configuration detail but not a complete local reproduction package.
evaluation · measurement-contract · metric-literacy Animated Interpretation Percentage, F1, Elo, criterion pass rate, and pass@5 answer different questions. Table 2 The metric taxonomy explains the table; it is not an additional paper result.
evaluation · public-results · reasoning-profile Paper Reported Competitive graduate reasoning does not erase the measured research-reasoning gap. §6.1.4; Table 2 The paper identifies the gap but does not establish a causal mechanism for it.
evaluation · public-results · coding-profile Paper Reported Coding performance is strong but task-dependent: K3 leads ProgramBench and SWE-Marathon, while Fable 5 leads FrontierSWE. §6.1.4; Table 2 Harness selection, H20 task calibration, fallbacks, and benchmark versions are material context.
evaluation · public-results · agentic-profile Paper Reported K3 leads several verifiable task suites yet trails the strongest model on Elo-rated knowledge work and harder computer use. §6.1.4; Table 2 The verified-versus-judged grouping is explanatory; benchmark construction differs in more than one dimension.
evaluation · public-results · vision-tools Paper Reported Python changes the evaluated system—and the paired lift reveals where tool-mediated inspection helps. §6.1.4; Table 2 Paired score lift shows association under the tool protocol, not which internal reasoning step caused it.
evaluation · public-results · fingerprint Paper Reported The honest summary is a vector of relative strengths—not 'third overall' or a count of wins. §6.1.4 The report does not publish a single cross-benchmark aggregate from which a universal overall rank can be computed.
evaluation · internal-and-cyber · internal-loop Paper Reported Public benchmarks compare; refreshed internal suites diagnose and steer iteration. §6.2.1 Private tasks, rubrics, and raw outputs are not independently auditable from this repository.
evaluation · internal-and-cyber · internal-profile Paper Reported Internal results sharpen both sides of the profile: orchestration and research strengths; behavior, MIRA, continuous assistants, and agentic vision gaps. §6.2.1; Tables 3–4 These developer-run benchmarks should be read with their harness assignments, refusals, and private-method caveats.
evaluation · internal-and-cyber · cyber-tiers Paper Reported Discovery and end-to-end exploitation are distinct capability tiers with different risk and completion demands. §6.2.2 Selective human review, excluded refusing baselines, private targets, and the paper's lower-bound warning constrain interpretation.
evaluation · internal-and-cyber · cyber-failures Paper Reported The remaining gap is not one number: final-chain completion, strategy under mitigations, debugging loops, and weak verification recur. §6.2.2 These failure attributions come from the paper's internal trajectory analysis, not this repository.
evaluation · triangulation-and-value · third-party Paper Reported Intelligence index, industry tasks, and human-preference arenas are three different external lenses. §6.3; Table 5 The report cites these third-party snapshots; rankings and Elo-style values drift over time.
evaluation · triangulation-and-value · pareto Paper Reported A model is cost-efficient when no alternative is both cheaper and better for the same evaluated workload. §6.4; Figure 13 Costs combine internal measurements and cited API prices under task-specific harnesses as of July 2026.
evaluation · triangulation-and-value · why-gaps Animated Interpretation Observed gap → paper-stated factor → plausible mechanism → speculation: do not collapse these levels. §4; §6 Cross-section causal explanations are hypotheses unless the paper reports an ablation or direct trajectory analysis.
evaluation · triangulation-and-value · evaluation-synthesis Animated Interpretation Measure precisely, compare locally, triangulate independently, explain cautiously, and stop where the evidence stops. §6 synthesis This final discipline is an authored synthesis of the section's evidence structure.
evaluation · case-studies · case-method Animated Interpretation A case becomes evidence only while its task, trajectory, artifact, verification, and boundary remain attached. §7 synthesis The trajectory schema is an authored case-study reading method.
evaluation · case-studies · kernel-case Paper Reported Kernel optimization closes on correctness and latency under the same workload and sandbox. §7 The measurements and implementation are not reproduced in this repository.
evaluation · case-studies · compiler-case Paper Reported MiniTriton matters because frontend, lowering, runtime, autograd, distributed execution, and workload validation compose. §7 Source, rooflines, and GPT parity are paper-reported and not audited here.
evaluation · case-studies · chip-case Paper Reported The nano-KPU case propagates a design through RTL and an open EDA flow to timing, area, and throughput outputs. §7 The 48-hour case and EDA outputs are not independently reproduced.
evaluation · case-studies · science-case Paper Reported Scientific coding remains trustworthy only when sources, assumptions, equations, numerical checks, and interpretation stay linked. §7 Speed and code volume do not establish scientific correctness; no independent domain audit was performed here.
evaluation · case-studies · knowledge-case Paper Reported Knowledge work ends at a reviewable artifact, not at fluent synthesis. §7 Selected artifacts do not estimate reliability or source completeness.
evaluation · case-studies · creative-case Paper Reported The architecture explainer and the teaser assembled from 56 source clips are pipelines of planning, code, rendering, inspection, and revision—not one-prompt films. §7 The reported artifacts and production trajectories are not reproduced in this repository.
evaluation · conclusion · supported-conclusion Animated Interpretation Preserve what is reported, what this repository executes, and what remains an open question. §8 The synthesis is evidence-bounded; full-scale training and evaluation are not independently reproduced here.
infrastructure · thesis · four-regimes Animated Interpretation Training, prefill, rollout, and serving stress different boundaries of the same architecture. §5 The four-regime framing is an authored synthesis.
infrastructure · distributed-primer · parallelism-axes Animated Interpretation DP splits samples, PP splits depth, EP splits experts, and CP splits one sequence. Background required by §5.2 This coordinate-system diagram is an authored prerequisite synthesis, not a published K3 topology.
infrastructure · distributed-primer · zero-pipeline-schedule Animated Interpretation Virtual stages reduce bubbles; 1F1B changes activation lifetimes; ZeRO partitions model-state ownership. Prerequisite synthesis for §5.2 and paper-reported configuration The visual teaches semantics and memory ownership; it does not reproduce K3's full device mesh or communication schedule.
infrastructure · kda-systems · flash-kda-regimes Paper Reported One recurrence requires different schedules in training, long prefill, and token-by-token decoding. §5.1.1 No local GPU kernel or performance benchmark reproduces FlashKDA.
infrastructure · kda-systems · kcp-prefix-scan Paper Reported Each segment becomes an affine map; associative composition reveals every rank's incoming state. §5.1.2 The notebook verifies local affine composition; it does not implement distributed prefix-scan communication or KCP.
infrastructure · three-trillion-pretraining · three-bottlenecks Animated Interpretation Expert skew, activation residency, and variable vision compute are independent bottlenecks. §5.2 The causal grouping is a teaching synthesis of the paper's three subsections.
infrastructure · three-trillion-pretraining · moonep Paper Reported Bounded redundant experts turn variable routing into equal token counts and static launch shapes. §5.2.1 The notebook verifies equal-capacity overflow arithmetic; it does not implement MoonEP replica placement, dispatch, or zero-copy networking.
infrastructure · three-trillion-pretraining · memory-ledger Paper Reported Memory is a lifetime-scheduling problem, not one monolithic allocation. §5.2.2 The notebook computes a local lifetime ledger; it does not perform recomputation, pooling, offload, gradient transformation, or communication.
infrastructure · three-trillion-pretraining · overlap-and-reuse Paper Reported Known expert offsets enable direct placement and GEMM overlap; non-overlapping lifetimes enable safe buffer reuse. §5.2.1–§5.2.2 The timeline is explanatory; no local multi-GPU transport, allocator aliasing, or P2P Muon benchmark is executed.
infrastructure · three-trillion-pretraining · vision-critical-path Paper Reported Dynamic context groups shorten large-image work; pipeline decomposition hides it outside the critical path. §5.2.3 No local distributed vision pipeline reproduces the reported optimization.
infrastructure · three-trillion-pretraining · decoupled-encoder Paper Reported DEP lets variable vision work advance independently, then joins the language path at an explicit feature boundary. §5.2.3 No local encoder service, queue, or distributed critical-path measurement reproduces DEP.
infrastructure · million-token-rl · rollout-state-pool Paper Reported Rollout scheduling can pause trajectories only if KV and KDA state survive outside the active worker. §5.3.1 The repository has no external cache pool or distributed RL runtime.
infrastructure · million-token-rl · rollout-control-loop Paper Reported Memory and queue pressure reduce active decode; exact state preservation makes that control action reversible. §5.3.1 The feedback equation is explanatory; the paper runtime's controller parameters and production traces are not reproduced.
infrastructure · million-token-rl · agentenv Paper Reported AgentENV treats an environment as durable world state with isolation and lifecycle operations. §5.3.2 The local Python dictionary stores caller data; it is not a microVM or copy-on-write system.
infrastructure · million-token-rl · overlaybd-storage Paper Reported OverlayBD separates a shared immutable base from small trajectory-specific changes. §5.3.2 The repository does not integrate OverlayBD, a block device, or microVM snapshots.
infrastructure · online-serving · hybrid-prefix-cache Paper Reported Fine MLA hashes and coarse physical pages remain consistent with sparse KDA checkpoints. §5.4.1 The notebook checks exact boundary agreement; it does not implement the joint physical cache or state reconstruction.
infrastructure · online-serving · prefix-reuse-walkthrough Animated Interpretation A request hits a fine hash, loads coarse pages, restores the nearest KDA checkpoint, and replays only the suffix. Mechanism synthesis for §5.4.1 The packing and replay diagram explains the reported design without claiming the paper's undisclosed byte layout or hit-rate policy.
infrastructure · online-serving · serving-kernels Paper Reported Production serving optimizes the whole hybrid path, including state reconstruction after speculative verification. §5.4.2 Local code contains no production GPU kernels or measured serving speedup.
infrastructure · online-serving · kernel-toolchain Animated Interpretation DSA sparsifies token interactions; KDA recurrently compresses history; cuBLAS and MiniTriton solve different kernel layers. Prerequisite comparison for §5.4.2 and §7.1 No local DSA, MiniTriton compiler, custom CUDA kernel, or comparative GPU benchmark is executed.
infrastructure · online-serving · fleet-scheduling Paper Reported The scheduler weighs locality, memory pressure, latency budget, and fairness before admitting work. §5.4.3 The notebook filters and scores two fixture nodes; it does not reproduce the distributed fleet scheduler or its measured policy.
infrastructure · synthesis · infrastructure-synthesis Animated Interpretation The through-line is control over where state lives, when work runs, and how boundaries remain consistent. §5 synthesis The systems-level causal chain is an authored synthesis.
posttraining · pipeline · thesis Animated Interpretation Post-training changes how capability is elicited, verified, budgeted, and deployed. §4 The causal framing is an authored synthesis.
posttraining · pipeline · three-stage Paper Reported Demonstrate, improve through outcomes, then consolidate. §4.1 Full-scale training is not reproduced.
posttraining · sft · trajectories Paper Reported A demonstration is a verified sequence of reasoning, tools, observations, and outcomes. §4.1.1 Dataset scale and acceptance rates are not disclosed.
posttraining · sft · qat-start Paper Reported Deployment arithmetic enters before reinforcement learning begins. §4.1.1; §4.1.4 Local code does not emulate MX formats.
posttraining · rl · expert-grid Paper Reported Three domains times three effort levels yields nine teachers. §4.1.2 The paper does not publish fixed token counts for effort levels.
posttraining · rl · partial-rollout Executed Here Optimization begins when a fraction lambda completes; unfinished trajectories resume later. §4.1.2 The local queue demonstrates scheduling, not distributed RL.
posttraining · rl · effort-control Executed Here Effort is trained by penalizing trajectories that exceed a problem-relative budget. §4.1.2 Local budgets are illustrative; K3 values are not disclosed.
posttraining · rl · grm Paper Reported The judge must externalize its rubric before comparing candidates. §4.1.2 Judge accuracy is not reproduced.
posttraining · mopd · teacher-selection Paper Reported Each sampled domain and effort selects one matching teacher. §4.1.3 Nine paper models are not available locally.
posttraining · mopd · token-reward Executed Here Every student token receives a clipped teacher-versus-student log-ratio reward. §4.1.3; Eq. 15 The local tensor calculation does not reproduce convergence.
posttraining · deployment · qat Paper Reported Expert weights use MXFP4; activations use MXFP8; sensitive non-expert modules stay higher precision. §4.1.4 Memory savings depend on complete serving layout.
posttraining · deployment · eagle Paper Reported A pretrained MTP layer becomes a seven-step recurrent EAGLE-3 draft. §4.1.4 Draft speedup is not reproduced.
posttraining · deployment · lk-loss Executed Here LK directly optimizes the acceptance probability used by lossless speculative sampling. §4.1.4; Eq. 16 Local distributions are authored fixtures.
posttraining · environments · white-box Paper Reported Vary tools, prompts, memory, context, skills, and subagents by task group. §4.2.1 No local harness-composition runtime reproduces this mechanism.
posttraining · environments · knowledge-graph Executed Here Fine concepts guide source retrieval; related nodes create cross-concept tasks. §4.2.2 No web-scale expansion is reproduced.
posttraining · environments · verifiable Paper Reported Reward must depend on observable outcomes rather than persuasive self-report. §4.2.3 Evaluator reliability remains a separate concern.
posttraining · task-atlas · kernels Paper Reported Wrong kernels receive zero; correct kernels are scored against expert speed and the roofline. §4.2.4 No GPU benchmark executes in this course.
posttraining · task-atlas · assistants Paper Reported Persistent mock applications create interdependent events across simulated days. §4.2.5 The paper reports up to thousands of calls and millions of context tokens, not a typical case.
posttraining · task-atlas · autonomous Paper Reported The agent sees the objective and interfaces—not a reference procedure. §4.2.6 Verifier isolation reduces but cannot eliminate reward hacking.
posttraining · task-atlas · webdev Paper Reported A project that fails, errors, or fakes the artifact receives zero reward. §4.2.7 Internal reward-model quality is not reproduced.
posttraining · synthesis · synthesis Animated Interpretation A deployable agent is downstream of its demonstrations, rewards, budgets, teachers, and verifiers. §4 synthesis The causal chain is an authored synthesis.
pretraining · thesis · causal-program Animated Interpretation The final checkpoint is the residue of every upstream decision. §3 Causal framing is a teaching synthesis.
pretraining · corpus · source-domains Paper Reported Different domains teach different regularities; provenance survives curation. §3.1 Mixture values are not disclosed.
pretraining · corpus · filtering Executed Here A filter reshapes the gradient distribution. §3.1 Local thresholds are illustrative.
pretraining · corpus · deduplication Executed Here Frequency is influence; duplicates create repeated pressure. §3.1 Authored fixtures do not validate internet-scale recall.
pretraining · corpus · rephrasing Paper Reported Variation is useful only when meaning survives. §3.1 No local generator reproduces the pipeline.
pretraining · corpus · vision-taxonomy Paper Reported Seeing, reading, locating, and tracking are different learning problems. §3.1 Taxonomy is reported, not locally trained.
pretraining · corpus · programmatic-vision Paper Reported The code states intent; the render exposes consequence. §3.1 Render generation is not reproduced.
pretraining · corpus · mixture-policy Executed Here The sampler decides where the next unit of compute goes. §3.1 K3 mixture weights remain undisclosed.
pretraining · scaling · observations Animated Interpretation The curve is earned from measurements. §3.2 Local coefficients are synthetic.
pretraining · scaling · iso-compute Executed Here Finite compute cannot maximize model size and data simultaneously. §3.2 C approximately 6ND is a teaching approximation.
pretraining · scaling · coupled-knobs Paper Reported Change the model family and yesterday’s recipe stops being evidence. §3.2 Full-scale optima are not reproduced.
pretraining · scaling · fair-schedules Paper Reported Shared hyperparameters test compatibility, not method quality. §3.2 Schedule searches are not reproduced.
pretraining · scaling · efficiency Paper Reported Compare compute at equal loss, not raw parameter counts. §3.2; Fig. 7 The ratio is reported, not independently reproduced.
pretraining · recipe · native-objective Paper Reported One stream, one loss, one shared backbone. §3.3 Full training is not reproduced.
pretraining · recipe · control-stack Paper Reported No single mechanism owns stability. §3.3 Only schedule arithmetic executes locally.
pretraining · recipe · per-head-muon Paper Reported Normalize update scale where the architecture is modular. §2.5; §3.3 The full derivation belongs to Course 1.
pretraining · long-context · nope Paper Reported Removing positional rescaling removes one intervention, not the learning problem. §3.4 NoPE alone does not prove useful million-token retention.
pretraining · long-context · distant-evidence Paper Reported Padding creates distance; task design creates dependence. §3.4 Local chunk preservation is not semantic retention.
pretraining · long-context · curriculum Paper Reported Spend expensive long-sequence tokens late and deliberately. §3.4 Local progress boundaries are illustrative.
pretraining · synthesis · causal-synthesis Animated Interpretation Architecture supplies possibility; pretraining acquires behavior. §3 synthesis The causal chain is an authored synthesis.
thesis · two-scaling-axes · plot-two-axes Animated Interpretation Pretraining changes the policy you begin with; test-time scaling changes how much work that policy can spend on this problem. §1 The two-axis diagram is an authored organizing model; it is not a reported ablation.
thesis · model-facts · separate-scale-facts Paper Reported 2.8T total parameters, 104B active parameters, and a 1M-token context window are not one scalar called scale. §1 These are paper-reported model properties, not independently reproduced measurements.
thesis · contribution-map · pretraining-axis Animated Interpretation Architecture, data, compute allocation, optimization, and context curriculum create the starting policy. §1; §§2–3 This dependency chain is a teaching synthesis, not a component ablation.
thesis · contribution-map · test-time-axis Animated Interpretation Useful test-time scale requires learned effort, stateful environments, verification, and infrastructure. §1; §§4–5 The diagram combines reported mechanisms without assigning measured causal contribution.
thesis · contribution-map · assemble-paper-map Animated Interpretation Architecture creates the computation; pretraining shapes the foundation; post-training creates effortful agents; infrastructure makes both feasible; evaluation bounds the claim. §1; §§2–8 The dependency chain is a teaching synthesis and does not imply a measured causal contribution for every component.
thesis · evidence-contract · label-evidence-levels Animated Interpretation Reported by paper ≠ animated interpretation ≠ executed here. Course evidence policy This is the repository's learning contract, not a K3 paper result.
thesis · evidence-contract · learning-route Animated Interpretation Watch the causal picture, inspect retained evidence, recover the derivation, and state the limitation. Course learning contract The route is an authored pedagogy rather than a paper result.