The whole point of conditioning="physical" is generalizing to a
species/material outside the training menu, but two independent code
paths still hard-required training-vocab membership:
- giant/data/transforms.py: build_cond_features unconditionally raised
KeyError on an out-of-vocab pdg/material. _vectorized_map_lookup
gains a strict=False mode (dummy index instead of raising), used only
under conditioning="physical" where ConditionEncoder never reads
cond_cat anyway; "embedding" mode is untouched and still raises,
since cond_cat IS the conditioning signal there.
- giant/rollout.py: the known_pdg termination gate still killed a track
on step 1 for any pdg outside pdg_map, regardless of conditioning
mode. Now skipped entirely under conditioning="physical".
- giant/model/network.py: PdgRouter/ProcessRouter always build their
own training-vocab nn.Embedding independent of conditioning, silently
reintroducing the same limitation at the routing layer. build_models
now raises loudly if conditioning="physical" is paired with either
router type, rather than silently building a model that can't
generalize the way it claims to.
This unblocks the held-out-species/material generalization experiment
against the multi-material dataset (see CLAUDE.md roadmap). Each fix
has a regression test, including an end-to-end rollout test seeded
with a resolvable-but-out-of-vocab PDG code.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
- log_transform / _validate_unit_pre_dir now raise on non-finite input
instead of letting a NaN row silently poison the persisted normalizer
cache (norm < 1e-6 was always False for NaN, so the existing guard
never caught it).
- encode_secondaries warns when a row's secondary energies cumulatively
exceed e_sec, instead of silently saturating the overflowing slot's
stick-breaking logit via the _EPS floor.
- EVENT_ID_FILE_STRIDE overflow now raises instead of silently colliding
two files' event ids together (reintroducing train/val leakage).
- make_event_split(val_fraction=0.0) now actually holds out nothing,
instead of always forcing at least 1 validation event.
- setup_cache.save() is now serialized with a flock, since two
concurrent writers (a real scenario on this repo's shared
portal/condor machines) could otherwise race and silently drop one
writer's freshly-computed cache section.
- Documented (no behavior change) the pre_dir ≈ -ẑ antipodal rotation
singularity in _rodrigues_axis, which is real but inherent to any
single-valued local-frame convention.
Each fix has a regression test.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Router-only knobs (lambda_balance/lambda_proc/lambda_entropy/
gumbel_tau_start/_end) and WGAN-only knobs (n_critic/gp_weight) were
being logged to wandb's top-level run config unconditionally, even for
runs where routing or WGAN mode is off, implying hyperparameters from
an inactive code path. Extract _wandb_run_config and only include each
group when its gate is actually true (router.enabled / mode=="wgan");
the full model_config (with its router sub-dict) is still always
logged in full, so no information is lost.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Extends default_out_dir_name's non-default-field convention to the
router's new gumbel combine-weight flag and its learnable-knob toggles,
so gumbel sweep configs (learn_centers on/off, learn_width,
learn_temperature) resolve to distinguishable checkpoint directory
names instead of colliding on the same r-<type><n> token.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Trains the routed trunk's forward combination as a hard one-hot sample
(matching eval-time top-1 dispatch exactly) while keeping a smooth gradient
on the backward pass, targeting the train/eval mismatch identified as a
likely contributor to experts overlapping instead of partitioning in the
first energy-router rollout benchmark. Off by default (model.router.gumbel);
existing routed configs/checkpoints are unaffected.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
EnergyRouter's gate sharpness was a single fixed temperature shared by
every expert, with no way for an expert to independently learn how much
of the energy axis it covers. Adds two mutually exclusive, default-off
modes: learn_width (per-expert learnable width) and learn_temperature
(single learnable shared scalar), both bounded via a sigmoid
interpolation warm-started to reproduce today's fixed-temperature gate
exactly at init, to compare against each other without risking the
unbounded-width collapse failure mode. Also promotes gate_stats's
entropy into a generic, optional Router.entropy_loss (lambda_entropy) as
a secondary guard against all experts' widths co-inflating together.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
NormalizerEntry.energy_reservoir_sample kept 100k raw energy values purely
to seed EnergyRouter centers via np.quantile at load time, which alone
accounted for most of the setup cache sidecar's ~2MB size (float32 values
round-tripped through Python floats serialize at full double precision).
Only a handful of quantile levels are ever read back, so collapse the
sample to a fixed 1001-point quantile grid at save time and interpolate
arbitrary levels from it at use time instead — about 100x smaller with
negligible (<0.001) error on the levels that matter. Bumps the cache
format version since old sidecars have no such grid to fall back on.
Pulled forward from the not-yet-mergeable condor-gpu-train-rollout branch:
`new-run` resolves CLI hyperparameter overrides into a full config.toml and
run dir (reusing the existing default_out_dir_name collision-avoidance and a
newly factored-out router-override helper shared with `train`), so a run can
be prepared and reviewed before `giant train` actually kicks off. Also
brings README up to date with the model/CLI as it actually stands
(physical/embedding conditioning, WGAN/MoE-router modes, giant analyze,
W&B, setup-stage caching), which had drifted back to describing the
Phase-1 proof-of-concept.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Each input parquet file is one Geant4 job (scripts/steps_to_parquet.py),
and a job's event_id numbering always restarts from 0 — so loading
multiple files together (a directory or .manifest) let same-numbered
events from different files collapse into one during the event index
scan and train/val split, corrupting both. Every per-file event_id now
gets offset by file index * EVENT_ID_FILE_STRIDE (giant/data/loader.py),
threaded through the setup-cache event index, the streaming dataset,
and predict/rollout seeding. Bumps the setup-cache format version so
stale sidecars computed pre-fix are invalidated.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Lets the vocab maps, event-id split index, and normalizer stats be
warmed once for a dataset (right after `dwarf convert`, or before a
`dwarf hparam-scan` sweep) without needing to also start training.
Extracts the setup-stage logic out of giant/pipeline.py:run_train_job
into a standalone run_setup_stage() (returning a SetupStageResult),
reused by both run_train_job and the new dwarf command's
scripts/warm_setup_cache.py — a behavior-preserving refactor, covered
by the existing test_pipeline.py suite.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Building the pdg/material vocab maps, the process map, and fitting the
Stage-1/Stage-2 normalizers all require scanning the training dataset
before a single epoch runs, which is wasted work whenever the same
data path is reused across runs (hyperparameter sweeps via `dwarf
hparam-scan`, repeated manual training attempts, ...). Persist those
setup-stage outputs to a JSON sidecar next to the input data
(giant/data/setup_cache.py), validated by a file fingerprint plus
fixed dimension constants and a manually-bumped format version before
reuse, with a soft warning (not a hard invalidation) on a git-hash
mismatch alone.
Also derives n_train_steps instantly from cached per-event row counts
instead of accumulating it during the normalizer scan, and always
collects the energy-router reservoir sample while the cache is being
populated (not only when the current run's router is energy-typed) so
a later run enabling --router-type energy never needs to rescan just
to seed expert centers.
New --cache-setup/--no-cache-setup (default on) and
--rebuild-setup-cache/--no-rebuild-setup-cache flags on `giant train`.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
The streaming update re-derived two full (B, F) arrays from the
running mean (once before updating it, once after) plus an elementwise
product — five passes over each chunk and three temporary arrays, to
maintain a mean/variance that's tiny in width (COND_DIM=15 at most).
Reformulate as Chan/Golub/LeVeque's parallel-variance algorithm:
compute the chunk's own local mean/M2 (independent of the running
state) and merge it in with an O(F) combination formula. Same
streaming interface and output (identical to ~1e-14, float64 rounding
noise), ~40% faster per update() call on a benchmark chunk.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
build_index_maps, build_index_maps_from_files, and (mostly)
build_process_map_from_files had no test pinning their sort order,
tie-breaking, or cross-file union behavior — all load-bearing for a
trained checkpoint's vocabulary, and all at risk of silently changing
under a future single-pass (pyarrow/polars) rewrite of the setup-stage
scan. Add tests for numeric-vs-lexicographic PDG sort (nuclear/ion
codes), negative PDG codes, dedup/bijective indices, file-order
independence, and process-map tie-breaking/boundary conditions
(n_experts=1, fewer processes than experts, 3-file partial overlap).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Fits normalizers over multi-hundred-million-row datasets, so the setup
pass's per-row Python overhead compounds fast: encode_secondaries
recomputed an O(K) prefix sum from scratch on every one of its 15
stick-breaking iterations, np.isin re-sorted the full train-event-id
array on every chunk, and pdg/material/process index lookups ran a
Python dict lookup per row. The normalizer-fit pass also computed
encode_secondaries's stick-logit and direction-rotation blocks in full
even though it only ever reads the mass/charge columns.
Replace the prefix-sum recompute with a single np.cumsum, add a
sorted_membership helper (searchsorted-based) in place of np.isin at
both the setup-pass and per-epoch call sites, vectorize the index
lookups via _vectorized_map_lookup, and add an opt-in phys_only path
so the setup pass skips the stick-breaking/rotation work it discards
anyway. All four changes are output-identical performance refactors,
backed by new unit tests plus the existing suite.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Previously the same fixed 7 fields (mode/hidden_dim/n_blocks/emb_dim/
conditioning/lr/batch_size) were always baked into the name, even for a
vanilla run, and router config wasn't represented at all. Now
default_out_dir_name only includes fields that differ from
DEFAULT_CONFIG, adds router/seed/epochs as candidates, and caps at 6
shown fields with a hashed overflow suffix for heavily-swept configs.
Covers the default-config 0-sentinel inheritance path (the exact bug
fixed by 969c5c6, previously untested since every router test in
test_router.py passes expert_hidden_dim/expert_n_blocks explicitly),
plus missing-key inheritance, full override, and partial override.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
The 2026-07-22 rollout benchmark's router_gating diagnostic showed the
10-expert EnergyRouter's default linspace(-2, 2, n_experts) init assumes a
roughly uniform z-normalized energy distribution, leaving experts heavily
overlapping instead of partitioning the range. Add an optional
centers_init kwarg (backward compatible, defaults to the old linspace) and
have giant train estimate it from a reservoir sample of the real energy
column, collected during the existing normalizer-fitting pass.
giant analyze prep/submit previously defaulted the run directory to
next to the rollout parquet on /ceph. Default it instead to
<cwd>/analysis_runs/analysis_<id> so it lands inside the portal repo
checkout (/work) — gitignored, --run-dir still overrides it.
derive_run_dir/prep gained a default_base param; library callers that
don't pass one keep the old parquet-relative fallback.
Checkpoints trained before commit 68fb99b (physical-property
conditioning, COND_DIM 8->15) saved a COND_DIM_BASE-wide cond
normalizer, fit before build_cond_features grew the extra physical
columns. Any inference against such a checkpoint under current code
(predict/rollout/router_gating) crashed broadcasting a 15-wide
cond_cont against an 8-wide mean/std.
In "embedding" mode those physical columns are never read by
ConditionEncoder, so padding the missing entries with mean=0/std=1 is
a safe no-op. "physical" mode reads them directly, so a mismatch there
still raises instead of silently normalizing garbage.
mschnepf/slc7-condocker's ancient glibc/libstdc++ can't load current
numpy/polars wheels from a uv-synced .venv (ImportError: CXXABI_1.3.9
not found). Switch the default to cverstege/alma9-gridjob, a modern
EL9-based image.
uv isn't installed on the HTCondor worker docker image, so `uv run`
fails there. giant is already an installed console script in the
repo's uv-synced .venv, so exec it directly instead. write_submit now
fails fast with a clear message if .venv/bin/giant is missing.
Each condor job's +RequestWalltime used to be one flat 3600s default
for every (plot, chunk), regardless of how much data it actually
streams over. `prep` now records each chunk's rollout+reference row
count, and `giant/analysis/runtime_estimate.py` turns that into a
per-job estimate: a per-spec (intercept, seconds/row) cost model fit
by `scripts/profile_analysis_costs.py` against synthetic mock data on
this machine, plus a fixed overhead placeholder (docker/uv/shared-fs
startup — unmeasurable here, no /ceph access) and a single
RUNTIME_SAFETY_MARGIN multiplier. jobs.txt gains a walltime column and
the submit description references it via $(walltime) instead of a
constant.
Add a second parallelism axis to giant analyze: each plot's data can now
be split into a configurable number of event_id-disjoint chunks, each
computed as its own HTCondor job, bounding per-job walltime and scan cost
on large rollout/reference files instead of one job re-scanning the
whole file per plot.
Every PlotSpec now splits into compute_partial (runs per (plot, chunk)
job against a chunk-filtered Bundle) and finalize (merges chunks -
elementwise sum for fixed-edge histograms/species shares, concatenate
-then-recompute for specs that derive edges or mean/std from the full
per-event/per-secondary array). Router diagnostics stay chunkable=False
and always run as a single job. giant analyze render now joins every
plot's chunk partials (merge_all) before rendering, transparently.
New: --chunks on `analyze prep`/`analyze submit`, --chunk on
`analyze compute-one`, and a new `analyze merge-one` command.
New "model" family in the gallery: router_gating (mean soft gate weight
vs. pre-step energy, showing the router's soft decision boundaries) and
router_share_by_pdg/router_share_by_process (stacked top-1 dispatch share
by species / true physics process). Needs a live checkpoint's Router, so
it's a documented exception to the rest of the package's polars/numpy-only
contract; gracefully degrades to a placeholder for non-MoE checkpoints.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
ty correctly flagged this as unsound: _CTX's inferred dict[str, int]
type doesn't rule out a "run_dir" key, which would silently bind to
prep's own run_dir: str | Path | None parameter instead of falling
through to **ctx_kwargs. Passing the context kwargs by name in a
small test helper removes the ambiguity.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
`giant analyze prep` / `submit` now take the `giant rollout` YAML sidecar as
their only positional input instead of explicit --rollout/--reference/--out-dir.
The YAML's `output`/`dataset` keys name the rollout parquet and its seed file
(the reference truth), and the rest of the sidecar (checkpoint, geometry oracle,
cutoffs) flows into every plot's gallery metadata.
prep derives its own run directory next to the rollout parquet
(<...>/analysis_<id>/) holding shared.json, run_meta.json, reduced/, plots/.
compute-one and render now take just --run-dir / a run-dir argument and read the
resolved paths + metadata from run_meta.json, so the condor wrapper no longer
threads file paths. open_side scans a directory of reference shards via glob.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Replace the monolithic giant/analysis.py (predict-local + RolloutVsTruth
diagnostics) with a lean giant/analysis/ package that compares one
autoregressive `giant rollout` for a checkpoint against a held-out
miniCaloSim reference file, and generates publication-styled plots in
parallel on HTCondor.
Rollout output and a raw reference file share a world-frame physical
column subset under identical names, so the old ALR/local-frame decode
machinery is gone — everything is world-frame mm/MeV.
- sources.py: canonical LazyFrames, synthetic-termination-row filtering,
the secondary view (rollout generation>0 tracks vs reference sec_*_list).
- reduce.py: streaming primitives — a single hist1d group_by pass, per-event
scalars, edep-weighted depth/transverse profiles, species share, leakage.
- context.py/grouping.py: prep resolves fixed bin edges + energy/pdg/material
group sets once into shared.json, so each compute job is one pass, no range
scan (histogram efficiency).
- catalog.py: declarative PlotSpec registry — marginals x {overall,energy,pdg,
material}, per-event totals, shower profiles, species/leakage, secondaries.
- render.py: the only plotstyle/LaTeX importer; PDFs + gallery metadata.
- condor.py + `giant analyze` CLI (prep/compute-one/list/render/submit):
one job per plot, compute/render split (workers polars-only, no LaTeX).
Styling via ETPlot's plotstyle (added to the analysis extra). New tests cover
the reduce primitives, catalog id uniqueness + compute, condor submit, and a
guarded render smoke test. Delete the two predict-diagnostics notebooks.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Adds --mode wgan alongside flow/ddpm: both stages get a WGAN-GP
generator/critic pair (giant.model.wgan) instead of flow matching, so
inference is a single forward pass per stage rather than a 10-step ODE
integration — the fast-eval architecture noted in the roadmap.
predict/rollout auto-detect the mode from the checkpoint's model_config.
Best-checkpoint selection for wgan uses marginal-KL against the EMA
generators every epoch, since a critic loss isn't a monotone quality
signal. --router is not supported together with --mode wgan.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
- make_seed_frontier only resolves particle mass/charge in "physical"
mode, so "embedding"-mode rollouts no longer crash on a seed PDG code
giant.particles can't resolve (the TERM_UNKNOWN_PDG gate now handles it).
- nearest_known_pdg skips unresolvable candidate PDG codes instead of
raising and killing the whole rollout/predict run.
- predict/rollout fail with a clear message when a checkpoint predates
the sec_phys normalizer, instead of a bare KeyError.
- validate_marginals' phys_kl degrades to NaN (matching the
energy_fraction_kl pattern) instead of crashing when a validated batch
has zero secondaries on either side.
- Correct CLAUDE.md's stale claim that the materials table is unfilled.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Adds model.conditioning = "physical" | "embedding": physical mode routes
particle mass/charge and material Z_eff/A_eff/density/X0/lambda_int through
small MLPs to replace the learned PDG/material embedding tables, so the
surrogate generalizes to PDG codes/materials outside the training vocab
instead of memorizing it. "embedding" stays available as the comparison
baseline (old checkpoints without the key default to it).
Stage 2 now regresses a secondary's mass/charge directly against a fixed
physics-derived target instead of a learned/snapped embedding, and uses no
snapping at inference — the model's raw predicted (mass, charge) is the
secondary's physical identity, including for its own further rollout steps.
A separate reporting-only nearest-known-PDG lookup (never fed back into the
model) populates output pdg columns / the embedding-mode rollout fallback.
giant/materials.py's table is populated with Geant4's own built-in NIST
constants (Z_eff, A_eff, density, X0, lambda_int), extracted directly from
the Geant4 11.4.1 build vendored in minicalosim via G4NistManager rather
than hand-typed literature values. G4_LYSO is left unfilled: confirmed (both
by runtime lookup and by searching minicalosim's history) that it's never
actually a constructed Geant4 material there, only documentation/UI color-map
text.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Merged in every non-analysis change from the MoE-prototype branch (routing,
training, data pipeline, streaming rollout output), keeping this branch's
lean streaming giant/analysis.py and rebuilding the rollout-vs-truth feature
natively on it instead of resurrecting the old numpy SampleCollection path.
- Add RolloutVsTruth, accepted anywhere Tier 1-3 functions take a predict-parquet
source: decodes a giant rollout file and a held-out truth file into
RAW_TARGET_NAMES space via a polars port of the forward local-frame rotation,
fully streaming (no SampleCollection, no eager materialization).
- Add compute_rollout_vs_truth_observables_pl for Tier 4, reusing
EventObservables (now backed by independent real_table/gen_table to support
unequal rollout/truth event counts) so every existing shower-observable plot
function works unchanged for both one-step and full-rollout comparisons.
- Update analysis/rollout_validation.ipynb to the new API and CLAUDE.md's
architecture description; add test coverage for the new source type.
- Fix a pre-existing return-type mismatch in giant.rollout.rollout() (found by
`ty check`): the on_chunk summary-dict branch didn't match the declared
dict[str, np.ndarray] return type, now expressed as a RolloutSummary TypedDict.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Route on several independent axes at once (e.g. energy x pdg), each with
its own expert count and hyperparameters. The joint gate is the outer
product of per-axis softmax gates, so it stays a partition of unity and
top1/balance_loss factor per-axis. Config uses flat axis{i}_{field} keys
in model.router (TOML/CLI friendly), also settable via repeatable
--router-axis flags.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
_Recorder previously accumulated every generated step across all events/
tracks/steps in Python lists, materialised once at the end and written
via a single pq.write_table — memory scaled with n_events * max_steps *
avg_tracks_per_event. rollout() now takes an optional on_chunk callback
that streams each non-empty batch immediately (fixed per-key dtypes via
_RECORD_DTYPES keep every chunk's table schema identical, which
pq.ParquetWriter requires across writes); giant rollout wires this to an
incrementally-written ParquetWriter, mirroring the row-group streaming
giant predict already does on its input side. Without on_chunk, rollout()
keeps its old buffered return for existing callers/tests.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Routes on the pre-step PDG code, which — unlike ProcessRouter's process
label — is already known at gate time (a conditioning input), so no
supervision is needed and classify_loss falls back to the zero default.
Generalizes EnergyRouter's soft-turn-on-then-Voronoi trick from a 1-D
distance to a small learned PDG embedding space: its own embedding table
maps each PDG code to a point, and n_experts learnable centers partition
that space.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Brings in the rollout-validation fixes developed alongside Phase 2
(exact e_sec budget rescaling in decode_secondaries, filtering
synthetic termination rows out of load_rollout_vs_truth, Tier 4 truth
overlay, --energy-gev support in dwarf make-root) and reconciles them
with this branch's mixture-of-experts routing work: build_features/
build_models/dataset plumbing keep the ProcessRouter's proc_map/
proc_idx threading, and create_root_files.py's job_seed folds in both
the per-job seed derivation and the new energy_gev component.
run_pbwo4/run_sampling now accept a trailing energy_GeV positional arg;
thread it through plan/run/seed so datasets like pbwo4_10gev can be
generated at non-default beam energies.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
decode_secondaries's stick-breaking only guarantees valid secondary slots
sum to <= e_sec, leaving a shortfall that rollout.py silently dumped into
that step's edep. Rescale the valid slots by one common per-row factor
instead, so they sum to exactly e_sec whenever n_sec > 0: this spreads any
shortfall proportionally across all secondaries rather than concentrating
it in whichever slot is last by energy rank (which would let that one
low-energy secondary balloon and distort the shower's topology). Rows
where every valid slot decodes to ~zero fall back to an even split.
n_sec == 0 rows are unchanged (still nothing to carry the budget, so
rollout.py's edep top-up still applies there) — narrowed the related
caveat in load_rollout_vs_truth's docstring to just that case.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
load_rollout_vs_truth was including rollout.py's synthetic termination-
bookkeeping rows (escaped/unknown_pdg/energy_cutoff/max_steps) unfiltered:
these carry step_length=0 and edep=pre_E dumped in one row for shower-level
energy conservation, not a real per-step value, and nearly doubled the
apparent mean edep in a repro. _load_world_frame_side now drops them, keeping
only real generated steps (continuing or natural_end). Also documents the
remaining, unfixable difference: rollout's edep on real steps absorbs any
secondary-energy budget Stage 2 didn't allocate, which truth's edep never does.
Adds compute_truth_observables, the truth-schema counterpart to
compute_rollout_observables, so the Tier 4 event-level plots
(plot_rollout_longitudinal/transverse/total_energy) can overlay a real
reference computed directly from load_rollout_vs_truth's own truth file,
without needing a separate paired giant predict --coord local file. Shares
the depth/transverse binning core with compute_rollout_observables via a new
_event_axis_depth_transverse helper.
Updates rollout_validation.ipynb's Tier 4 section to use this reference and
points ROLLOUT_FILE/TRUTH_FILE at a real prediction/shard pair.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Extends the Tier 1-3 SampleCollection diagnostics (marginals, correlations,
pairwise, direction alignment, constraints) to work on a full autoregressive
giant rollout shower checked against an independent ground-truth steps file,
rather than only paired giant predict --coord local output. The two files
are unpaired (different lengths, own conditioning), so SampleCollection
gains optional *_gen fields and _group_labels/marginal_table/plot_marginals/
plot_pairwise build independent real/gen masks instead of assuming one.
Adds analysis/rollout_validation.ipynb, a sibling of validation.ipynb built
around this workflow.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Replace giant/analysis.py's dual numpy-SampleCollection + polars paths with a
single polars-streaming implementation that produces the validation notebook's
plots directly from a `giant predict --coord local` parquet, sized for files
larger than RAM.
- Drop the numpy SampleCollection path (load_predicted_local, marginal_table,
correlation_matrices, direction_alignment, constraint_report, plot_kl_bars)
and the rollout observables; the 5 remaining plotters now take a parquet
path / LazyFrame and stream internally.
- Rewrite compute_event_observables_pl to aggregate in parallel streaming
polars (post-pos reconstruction as expressions) instead of a serial
pyarrow-batch + numpy loop, fixing a pre-existing OOM (holistic median +
323M-row join in the bin-edge sizing). Medians are approximated from a
streaming log-bin histogram with within-bin interpolation.
- Keep every full-file scan narrow (few columns): on a file larger than RAM,
peak mmap memory, not scan count, is the binding constraint. Marginals run
one dim at a time (~15GB peak) rather than a combined all-dims pass (OOM).
- Update analysis/validation.ipynb to the path-based API; delete the
analysis/export_*.py and compare_ode_steps_*.py one-off scripts.
- Rewrite tests/test_analysis.py around parquet fixtures with an inline numpy
oracle; add correlation/streaming-plotter and approx-median coverage.
Verified end-to-end on the 32GB predict file: full notebook completes at
~25GB peak (no OOM); event rollup runs at ~13 cores.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
A listed child_track_id can fail to match any first-step row (e.g. a
secondary absorbed below the tracking threshold at birth). The
parent->child left join in _add_secondary_attributes left these as
nulls, which silently became NaN once the parquet round-tripped
through the loader's float32 padding — poisoning every later secondary
slot in that step via the cumulative "remaining budget" in
encode_secondaries, while e_sec quietly undercounted and n_sec (from
len(child_track_ids)) overcounted relative to the actual lists.
Drop orphans from both the per-secondary lists and child_track_ids
itself so downstream counts stay consistent, and thread the per-file
orphaned count back through convert_steps_to_parquet so both the
sequential and --jobs>1 batch paths in `dwarf convert` can report an
aggregate total instead of relying on grepping printed output.
Also floors encode_secondaries' slot-0 budget to _EPS (matching the
i>0 branch), fixing a harmless but noisy 0/0 divide warning on
zero-secondary steps.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
A listed child_track_id can fail to match any first-step row (e.g. a
secondary absorbed below the tracking threshold at birth). The
parent->child left join in _add_secondary_attributes left these as
nulls, which silently became NaN once the parquet round-tripped
through the loader's float32 padding — poisoning every later secondary
slot in that step via the cumulative "remaining budget" in
encode_secondaries, while e_sec quietly undercounted and n_sec (from
len(child_track_ids)) overcounted relative to the actual lists.
Drop orphans from both the per-secondary lists and child_track_ids
itself so downstream counts stay consistent, and thread the per-file
orphaned count back through convert_steps_to_parquet so both the
sequential and --jobs>1 batch paths in `dwarf convert` can report an
aggregate total instead of relying on grepping printed output.
Also floors encode_secondaries' slot-0 budget to _EPS (matching the
i>0 branch), fixing a harmless but noisy 0/0 divide warning on
zero-secondary steps.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Concurrent job launches in create_root_files.py can start within the
same wall-clock second, and minicalosim's default seed falls back to
time(NULL) in that case — so two "independent" shards could silently
get identical RNG state and produce byte-identical physics. Requires
the companion MINICALOSIM_SEED env-var support in the minicalosim repo.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Concurrent job launches in create_root_files.py can start within the
same wall-clock second, and minicalosim's default seed falls back to
time(NULL) in that case — so two "independent" shards could silently
get identical RNG state and produce byte-identical physics. Requires
the companion MINICALOSIM_SEED env-var support in the minicalosim repo.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
A parquet that carries child_track_ids/e_sec but was never run through the
parent->child join lacks the per-secondary columns (sec_E_list/sec_pdg_list/
sec_dir_list). build_features would fall back to all-zero sec_cont/sec_pdg_idx,
collapsing every secondary to PDG index 0 and a constant energy fraction — a
broken Stage 2 that trained with no error (single-species validation tables).
Add an opt-in require_secondaries flag that raises when n_sec > 0 but the lists
are absent, and enable it on the training paths (StreamingStepsDataset and the
normalizer-fit pass). giant predict keeps the default False for Stage-1-only use.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
A parquet that carries child_track_ids/e_sec but was never run through the
parent->child join lacks the per-secondary columns (sec_E_list/sec_pdg_list/
sec_dir_list). build_features would fall back to all-zero sec_cont/sec_pdg_idx,
collapsing every secondary to PDG index 0 and a constant energy fraction — a
broken Stage 2 that trained with no error (single-species validation tables).
Add an opt-in require_secondaries flag that raises when n_sec > 0 but the lists
are absent, and enable it on the training paths (StreamingStepsDataset and the
normalizer-fit pass). giant predict keeps the default False for Stage-1-only use.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Routes on the physics process (Compton, phot, brems, ...) that ends a
step, supervised by a small classifier since process is a post-step
outcome unobservable at gate time. Threads a process label end-to-end
through the data pipeline (loader, build_features, dataset batches,
training loss/checkpointing) alongside the existing EnergyRouter.
lars