Tracked external evidence
Every external product, model, platform, writeup, and case study that changed the PostTrainLLM learning map gets one canonical record. Each dossier keeps the local translation beside its evidence limits so a useful idea never turns into an unsupported claim.
Evidence index
Indexed from the tracked review ledger and industry learning map.
Failed-attempt accounting, slice metrics, trace review, candidate selection, batch-first post-training, policy lag, and LoRA update geometry make autoresearch inspectable instead of hiding the search process behind a final score.
Open evidence dossier →Candidate-selection framing can make a sparse task measurable when unconstrained generation is too difficult or too ambiguous to grade reliably.
Open evidence dossier →Batch rollouts, offline scoring, and compact updates can make a post-training loop easier to inspect, while policy lag can stabilize learning under some reward surfaces.
Open evidence dossier →Effective update geometry, layer placement, and controlled rank analysis can explain why two adapters with similar parameter counts behave differently.
Open evidence dossier →File-native and code-native harnesses may fit knowledge-work agents better than bespoke tool APIs because the environment already exposes durable state and familiar operations.
Open evidence dossier →Post-training is a system of custom data, reward shaping, performance work, infrastructure, evaluation, and packaging rather than a generic fine-tuning screen.
Open evidence dossier →Small public SQL models provide realistic baselines and expose how much benchmark, model size, and serving format affect apparently similar claims.
Open evidence dossier →Strong SQL systems report execution accuracy on substantial SQL benchmarks rather than relying on exact string match alone.
Open evidence dossier →Apple's system model is a free and private routing floor, but its context and action-grounding limits make it unsuitable as the core capability dependency for a realistic tool catalog.
Open evidence dossier →Composite rewards, trace-driven data loops, reasoning-depth classification, and explicit environment contracts make reinforcement-style fine-tuning more inspectable.
Open evidence dossier →Structured-output enforcement and an explicit context hierarchy can reduce ambiguous agent actions and make tool boundaries easier to inspect.
Open evidence dossier →SIMD and cache-heavy bulk BPE can make first-pass tokenization much faster on large corpora, including Qwen tokenizers on Apple Silicon.
Open evidence dossier →A compact call-only model combines top-five tool retrieval, constrained decoding, confidence escalation, bounded context, quantization, and a small packaged Mac artifact.
Open evidence dossier →Raw WebGPU plus SIMD-WASM can run Parakeet TDT browser inference with public kernels, a package format, cache behavior, a converter, and a benchmark harness.
Open evidence dossier →Curated domain data, filtered reasoning traces, supervised fine-tuning, model merging, and verifiable-reward reinforcement learning combine in a JEE mathematics specialist.
Open evidence dossier →Ternary representation, packing overhead, activation transforms, kernel support, artifact size, runtime memory, and capability retention can rank a model differently depending on the deployment constraint.
Open evidence dossier →Parameter-aware query optimization needs equal search budgets, fresh held-out measurement, SQL-equivalence checks, and a native-planner baseline before an offline plan search can claim value.
Open evidence dossier →Admission control, scheduling, paged KV allocation, prefill, decode, continuous batching, caching, and distributed execution explain why a serving engine behaves differently from a single-request model loop.
Open evidence dossier →Shape-specific Metal kernels, a model-specific speculative draft, packed weights, cache reuse, and a startup memory plan trade generic model support for Mac-local serving performance.
Open evidence dossier →