Repository navigation
[RF][HS3] Follow the HS3 0.3 specification fixes (HS3 #154) - #24201
Conversation
3512e71 to
1824118
Compare
456278c to
27fbb8d
Compare
8b38c66 to
fa40c73
Compare
|
I can still reproduce auxiliary-region import/export failures with ROOT 6.43.01, commit The application is an actual auxiliary measurement whose coordinate is declared in The region layout has an empty nonextended event-data component and one separate auxiliary observation. The group is reachable from the sampling PDF, while its measured values establish the global-observable roles. It restores inference, but exposes the following serialization and validation defects.
The combined-distribution rules distinguish an absent region, an empty nonextended sample, and an empty extended sample. Reference reachability alone does not establish how many likelihood factors contribute. The self-contained reproducer below runs no fits or toy ensemble. It reports four product/array round-trip cases and four HistFactory contribution-counting cases. Expected behaviour:
On the unpatched build, all four round-trip cases fail; empty/missing regions are incorrectly rejected and the missing observation is incorrectly accepted. Self-contained Python reproducer"""Small HS3 auxiliary-region reproducer
Tests import plus two exports/reimports for product/array auxiliary regions,
and checks that empty/missing regions and real duplicate observations are distinguished.
"""
import os,resource,json,copy,sys
from pathlib import Path
import ROOT as R
R.gROOT.SetBatch(True);R.DisableImplicitMT()
R.RooMsgService.instance().setGlobalKillBelow(R.RooFit.WARNING)
def document(kind='array',hf=False):
aux={'name':'aux','type':'array_dist','component_type':'gaussian_dist','default_parameters':{'sigma':1.},'components':[{'x':'g1','mean':'theta'},{'x':'g2','mean':'eta'}]}
physics={'name':'physics','type':'gaussian_dist','x':'x','mean':'mean','sigma':1.}
defs=[physics,aux,{'name':'model','type':'combined_dist','columns':['channel'],'components':[{'key':['physics'],'dist':'physics'},{'key':['auxiliary'],'dist':'aux'}]}]
if kind=='product':
aux.clear();aux.update({'name':'aux','type':'product_dist','factors':['c1','c2']})
defs += [{'name':'c1','type':'gaussian_dist','x':'g1','mean':'theta','sigma':1.},{'name':'c2','type':'gaussian_dist','x':'g2','mean':'eta','sigma':1.}]
axis={'name':'x','min':-5.,'max':5.}
physical_data={'name':'physics_data','type':'unbinned','axes':[axis],'entries':[[-.4],[.2],[.7]]}
if hf:
axis.update({'min':0.,'max':2.,'nbins':2})
physics.clear();physics.update({'name':'physics','type':'histfactory_dist','axes':[axis],'default_interpolation':{'type':'mult','in':'poly6','out':'exp'},'samples':[{'name':'signal','data':{'contents':[10.,15.]},'modifiers':[{'type':'normfactor','parameters':['mu']},{'name':'s1','type':'normsys','parameters':['theta'],'data':{'lo':.9,'hi':1.1},'constraints':['aux']},{'name':'s2','type':'normsys','parameters':['eta'],'data':{'lo':.8,'hi':1.2},'constraints':['aux']}]}]})
physical_data={'name':'physics_data','type':'binned','axes':[axis],'contents':[10.,15.]}
axes=[{'name':g,'min':-8.,'max':8.} for g in ['g1','g2']]
return {'metadata':{'hs3_version':'0.3'},'distributions':defs,'functions':[] if hf else [{'name':'mean','type':'generic','expression':'mu+theta+eta'}],
'data':[physical_data,{'name':'empty','type':'unbinned','axes':[],'entries':[]},{'name':'combData','type':'combined','columns':['channel'],'components':[{'key':['physics'],'dataset':'physics_data'},{'key':['auxiliary'],'dataset':'empty'}]},{'name':'measurement','type':'unbinned','axes':axes,'entries':[[.2,-.3]]}],
'likelihoods':[{'name':'likelihood','distributions':['model','aux'],'data':['combData','measurement']}],
'analyses':[{'name':'ModelConfig','likelihood':'likelihood','domains':['domain'],'parameters_of_interest':['mu']}],
'domains':[{'name':'domain','type':'product_domain','axes':[{'name':'channel','categories':['physics','auxiliary']},axis,{'name':'mu','min':0. if hf else -3.,'max':3.},{'name':'theta','min':-3.,'max':3.},{'name':'eta','min':-3.,'max':3.},*axes]}],
'parameter_points':[{'name':'default_values','parameters':[{'name':'mu','value':1.},{'name':'theta','value':0.},{'name':'eta','value':0.},{'name':'g1','value':.2,'const':True},{'name':'g2','value':-.3,'const':True}]}]}
def run_case(doc,roundtrip=False,explicit=False):
config=R.RooJSONFactoryWSTool.config();config.exportArrayDist=True;config.exportConstraintData=explicit
workspaces=[];result={'imported':False,'exported':0,'reimported':0}
try:
ws=R.RooWorkspace();workspaces.append(ws);assert R.RooJSONFactoryWSTool(ws).importJSONfromString(json.dumps(doc));result['imported']=True
if not roundtrip:return result
leaf=ws.pdf('c1') or ws.pdf('g1_constraint');leaf.setStringAttribute('aux_note','retained')
reference=[];previous=None
for generation in range(3):
mc=ws.obj('ModelConfig');assert mc and mc.GetPdf().getPdf('auxiliary')
assert len(mc.GetGlobalObservables())==2
assert not mc.GetExternalConstraints() or len(mc.GetExternalConstraints())==0
leaf=ws.pdf('c1') or ws.pdf('g1_constraint');assert leaf.getStringAttribute('aux_note')=='retained'
encoded=str(R.RooJSONFactoryWSTool(ws).exportJSONtoString()) if generation<2 else None
nll=mc.GetPdf().createNLL(ws.data('combData'),R.RooFit.GlobalObservables(mc.GetGlobalObservables()),R.RooFit.Offset(False))
vals=[]
for mu,theta,eta in [(1.,0.,0.),(.5,.4,-.5),(1.2,-.4,.5)]:
for name,value in [('mu',mu),('theta',theta),('eta',eta)]:ws.var(name).setVal(value)
vals.append(nll.getVal())
if reference:assert max(abs(a-b) for a,b in zip(vals,reference))<1e-9
else:reference=vals
for name,value in [('mu',1.),('theta',0.),('eta',0.)]:ws.var(name).setVal(value)
del nll
if encoded:
result['exported']+=1
if previous:assert json.loads(previous)==json.loads(encoded),'document changed after first export'
previous=encoded;ws=R.RooWorkspace();workspaces.append(ws)
assert R.RooJSONFactoryWSTool(ws).importJSONfromString(encoded);result['reimported']+=1
result['nll']=reference
except Exception as exc:result['error']=str(exc)
return result
results={}
for kind in ['product','array']:
for explicit in [False,True]:results[kind+('_data' if explicit else '_implicit')]=run_case(document(kind),True,explicit)
for mode in ['empty','missing','double','missing_observation']:
d=document(hf=True);data={x['name']:x for x in d['data']};lh=d['likelihoods'][0]
if mode=='missing':data['combData']['components'].pop()
if mode=='double':data['empty'].update({'axes':copy.deepcopy(data['measurement']['axes']),'entries':[[.2,-.3]]})
if mode=='missing_observation':
lh['distributions']=['model'];lh['data']=['combData'];d['data'].remove(data['measurement']);data['physics_data']['contents']=[0.,0.]
results['histfactory_'+mode]=run_case(d)
output=Path(sys.argv[1]) if len(sys.argv)>1 else Path('reproducer_results.json')
output.write_text(json.dumps({'root':R.gROOT.GetVersion(),'commit':str(R.gROOT.GetGitCommit()),'results':results},indent=2)+'\n')
for name,result in results.items():print(name,json.dumps(result),flush=True)AI assistance: Codex assisted with the reproducer, proposed implementation and numerical comparison. This draft and the patch need the author's technical review before posting/submission. |
|
Two issues remain in the RooFit/XRooFit workflow after the latest auxiliary-region changes. The new grouped-region and contribution-counting tests pass. The following failures concern sampling-PDF preservation and a separate scalar-export ordering problem. 1. The default import still changes the expected p-value. With The unchanged application call is: w = ROOT.Experimental.XRooFit.xRooNode("119.json")
w.loadSnapshot("nominalGlobs")
nll = w["models/ModelConfig"].nll("combData", [ROOT.RooFit.Binned(1)])
hp = nll.hypoPoint(value=0, alt_value=1)
print(hp.pNull_asymp(nSigma=0).value())The small reproducer below isolates the loss of PDF reachability without needing the Higgs files or running any fits. It prints: Reproducer 1: auxiliary globals leave the sampling PDF"""A valid NLL round trip can remove auxiliary globals from the sampling PDF."""
import os,resource
os.environ['OMP_NUM_THREADS']='1'
resource.setrlimit(resource.RLIMIT_AS,(8*1024**3,8*1024**3))
import ROOT as R
R.gROOT.SetBatch(True)
w=R.RooWorkspace('original')
for definition in [
'sum::mean(mu[1,0,3],theta[0,-3,3],eta[0,-3,3])',
'Gaussian::physics(x[0,-5,5],mean,1)',
'Gaussian::c1(g1[0.2,-8,8],theta,1)',
'Gaussian::c2(g2[-0.3,-8,8],eta,1)',
'PROD::aux(c1,c2)',
'SIMUL::model(channel[physics,auxiliary],physics=physics,auxiliary=aux)',
]:
assert w.factory(definition)
for name in ['g1','g2']:w.var(name).setConstant(True)
columns=R.RooArgSet(w.var('x'),w.cat('channel'))
data=R.RooDataSet('data','data',columns)
w.cat('channel').setLabel('physics')
for value in [-.4,.2,.7]:w.var('x').setVal(value);data.add(columns)
getattr(w,'import')(data)
mc=R.RooStats.ModelConfig('ModelConfig',w)
mc.SetPdf(w.pdf('model'));mc.SetObservables(columns)
mc.SetParametersOfInterest(R.RooArgSet(w.var('mu')))
mc.SetNuisanceParameters(R.RooArgSet(w.var('theta'),w.var('eta')))
mc.SetGlobalObservables(R.RooArgSet(w.var('g1'),w.var('g2')))
getattr(w,'import')(mc)
cfg=R.RooJSONFactoryWSTool.config()
cfg.exportArrayDist=True;cfg.exportConstraintData=True
cfg.importConstraintsAsChannels=False
encoded=str(R.RooJSONFactoryWSTool(w).exportJSONtoString())
v=R.RooWorkspace('roundtrip')
assert R.RooJSONFactoryWSTool(v).importJSONfromString(encoded)
for label,ws in [('original',w),('roundtrip',v)]:
m=ws.obj('ModelConfig');g=m.GetGlobalObservables();external=m.GetExternalConstraints()
print(label,'globals=',len(g),'PDF contains globals=',[bool(m.GetPdf().dependsOn(ws.var(n))) for n in ['g1','g2']], 'external=',[p.GetName() for p in external] if external else [],flush=True)These are actual auxiliary measurements declared as global observables. The needed behaviour is to retain a sampling model that includes them, or make the consuming generation workflow explicitly include external auxiliary measurements. This does not require treating fixed regularizers as fluctuating observations. 2. A scalar Gaussian can be emitted before its observed-coordinate hint is registered. The later point dataset then uses a different axis from the Gaussian's exported Reimport fails with: This also occurs in the original 119 GeV export for The second reproducer fails as written. Changing only Reproducer 2: scalar Gaussian export depends on object traversal orderRun as """Reproduce the scalar-Gaussian point-data axis mismatch, without Higgs files.
An otherwise unused product keeps this HF constraint scalar even with arrays
on, as happens for shared constraints in the Higgs workspace.
"""
import os,resource,json,sys
from pathlib import Path
os.environ['OMP_NUM_THREADS']='1';resource.setrlimit(resource.RLIMIT_AS,(8*1024**3,8*1024**3))
import ROOT as R
R.gROOT.SetBatch(True);R.DisableImplicitMT()
doc={'metadata':{'hs3_version':'0.3'},'distributions':[
{'name':'physics','type':'histfactory_dist','axes':[{'name':'x','min':0.,'max':2.,'nbins':2}],
'default_interpolation':{'type':'mult','in':'poly6','out':'exp'},
'samples':[{'name':'signal','data':{'contents':[10.,15.]},'modifiers':[
{'type':'normfactor','parameters':['mu']},{'name':'s','type':'normsys','parameters':['theta'],'data':{'lo':.9,'hi':1.1},'constraints':['constraint']}]}]},
{'name':'constraint','type':'gaussian_dist','x':'theta','mean':'g','sigma':1.}],
'data':[{'name':'data','type':'binned','axes':[{'name':'x','min':0.,'max':2.,'nbins':2}],'contents':[10.,15.]}],
'likelihoods':[{'name':'likelihood','distributions':['physics'],'data':['data'],'aux_distributions':['constraint']}],
'analyses':[{'name':'ModelConfig','likelihood':'likelihood','domains':['domain'],'parameters_of_interest':['mu']}],
'domains':[{'name':'domain','type':'product_domain','axes':[{'name':'x','min':0.,'max':2.,'nbins':2},{'name':'mu','min':0.,'max':3.},{'name':'theta','min':-3.,'max':3.},{'name':'g','min':-5.,'max':5.}]}],
'parameter_points':[{'name':'default_values','parameters':[{'name':'mu','value':1.},{'name':'theta','value':0.},{'name':'g','value':0.,'const':True}]}]}
w=R.RooWorkspace('w');assert R.RooJSONFactoryWSTool(w).importJSONfromString(json.dumps(doc))
w.factory('PROD::keep_scalar(constraint)')
mc=w.obj('ModelConfig');mc.SetGlobalObservables(R.RooArgSet(w.var('g')))
c=R.RooJSONFactoryWSTool.config();c.exportArrayDist=True;c.exportConstraintData=True
encoded=str(R.RooJSONFactoryWSTool(w).exportJSONtoString());d=json.loads(encoded)
Path(sys.argv[1]).write_text(encoded+'\n')
print('constraint:',next(x for x in d['distributions'] if x['name']=='constraint'),flush=True)
print('measurement:',next(x for x in d['data'] if x['name']=='constraint_data'),flush=True)
v=R.RooWorkspace('roundtrip');assert R.RooJSONFactoryWSTool(v).importJSONfromString(encoded)
print('REIMPORT SUCCEEDED',flush=True)The experimental AI assistance: Codex assisted with the reproducers and validation summary. Please review the technical details before posting. |
|
Here's a quick summary of my last 2 commits:
|
Test Results 13 files 13 suites 2d 6h 33m 11s ⏱️ For more details on these failures, see this check. Results for commit dd6905a. ♻️ This comment has been updated with latest results. |
HS3 0.3 (HS3 PR root-project#154, decision on HS3 root-project#156) allows a continuous data axis to omit `min` or `max`, which means that the axis is unbounded there, and leaves JSON `null` undefined for bounds. RooFit wrote `null` for an infinite bound of the axes of unbinned data, and the largest representable number for the axes of constraint data. Both now leave the bound out, like for domain axes. On import, an axis with only one bound sets that bound and leaves the other side unbounded; before, the range was only set if both bounds were given. `null` is still read for older documents. Binned axes keep finite bounds; the validator now reports a binned axis with an infinite bound. Assisted-by: claude-code:claude-opus-5-5
HS3 0.3 (HS3 PR root-project#154) renames the key of the location parameter of landau_dist from `mean` to `mu`, since it is neither the mean, which doesn't exist, nor the most probable value of the distribution. RooLandau is now written with `mu`. Documents before 0.3 used `mean`, which is still read; in a document of version 0.3 or later it is read with a warning. Assisted-by: claude-code:claude-opus-5-5
HS3 0.3 (HS3 PR root-project#154, decision on HS3 root-project#156) makes the `extended` flag of `mixture_dist` required: * With one coefficient per summand, the flag alone decides whether the mixture has a Poisson term, and a document without it is invalid. Such documents of version 0.3 or later are now rejected; older documents are read as before, as an extendable RooAddPdf. * An explicit `"extended": false` with one coefficient per summand was read as an extendable RooAddPdf with a warning, since a RooAddPdf with one coefficient per summand can always be extended. It is now honoured: the RooAddPdf is built from the normalized coefficients c_i / sum(c), written as RooFormulaVars "<name>_fraction_<i>", of which the last one follows from the others. This is the same shape and can't be extended. * With one coefficient fewer than summands, a missing flag is still accepted, as the standard allows. * A mixture without coefficients, which RooFit reads as the sum of its extended summands, is not defined in HS3 0.3. It is still read and written, with a warning for documents of version 0.3 or later and on export. The MixtureDistExtendedFlag test is extended accordingly; its last case, which expected the warning for an explicit "false", now checks that the mixture is not extendable and has the normalized shape. Assisted-by: claude-code:claude-opus-5-5
The HS3 expression language has the boolean literals `TRUE` and `FALSE` and the exact comparisons `===` and `!==`. RooFit translated only `PI`, `EULER` and `ifelse()` for TFormula, so the others were looked up as objects or failed to parse. They are now translated to `1`, `0`, `==` and `!=`; the comparisons of TFormula are exact. HS3 PR root-project#154 also makes these names reserved (decision on HS3 root-project#156). Assisted-by: claude-code:claude-opus-5-5
HS3 0.3 (HS3 PR root-project#154, decision on HS3 root-project#156) reserves the names of the expression language, i.e. PI, EULER, TRUE, FALSE, ifelse and its functions, which no distribution, function or parameter may carry. A reference in an expression evaluates to the value of a parameter, variable or function; a reference to a distribution is invalid. * The validator reports objects with a reserved name: an error for documents of version 0.3 or later, a warning otherwise and on export, like the other checks of the documents RooFit writes. * A generic expression of a document of version 0.3 or later that refers to a distribution is rejected on import; older documents are read as before. * The export fails for anything that would be written as an expression that refers to a pdf, since it can't be a valid document: a RooFormulaVar or RooGenericPdf that depends on a pdf, a RooTFnBinding with a pdf as observable or parameter, and the helper functions that transform a parameter of a RooLognormal or RooExponential if that parameter is a pdf. Whether a later version should allow generic_dist expressions that operate on distributions is discussed in HS3 root-project#159. Assisted-by: claude-code:claude-opus-5-5
HS3 point data is the observation of a single variable. With its axis, it is the same as unbinned data with a single entry (HS3 PR root-project#154). RooFit rejected it on import. It is now read as a RooDataSet with one entry of one variable, and such a data set (one real variable, one unweighted entry) is written as point data with its axis. The observed values of single constraint observables, which config().exportConstraintData writes, are also point data now. The "uncertainty" of point data is ignored with a warning, since HS3 doesn't define how it enters a likelihood. Point data without an axis gets its variable from the paired distribution, which follows in a separate commit. Assisted-by: claude-code:claude-opus-5-5
…ution HS3 0.3 (HS3 PR root-project#154, decision on HS3 root-project#156) states how a number given in-line in the "data" of a likelihood, or a point data set without axes, is bound to a variable: it is the value of the single variate of the paired distribution. If the variate can't be determined, the document is rejected. RooFit parsed in-line numbers but never used them, and rejected point data. * A point data set without axes that a likelihood pairs with a distribution with a single variate is read as a RooDataSet with one entry of that variable. If it is paired with distributions of different variates, or the variate can't be determined, the document is rejected. * An in-line number becomes a point data set "<distribution>_data" (with a suffix if the name is taken) of the variate of its distribution, which is then used like a data set the term refers to, e.g. as the observed value of a constraint term. The variate is determined like for the check of distinct variates; a distribution for which it is not a single name, like a product of distributions, is rejected. RooFit writes "data": [0] for a ModelConfig without data, with the number 0 as the only entry, which is not an observation. In this exact form it stays that in documents before 0.3 (HS3 PR root-project#154), and for now also in documents that carry RooFit's information about the ModelConfig of the analysis, since that is what RooFit still writes. A 0 in a longer array is a value like any other. Assisted-by: claude-code:claude-opus-5-5
HS3 0.3 (HS3 PR root-project#154, decisions on HS3 root-project#156 and root-project#157) adds rules for the axes of data sets: * A fixed axis (with "value") is only allowed in domains. A data axis with "value" is rejected. * The axis of point data is named like the variate of the paired distribution. A point data set whose axis is not that variate is rejected. * A variate is normalized over the axis of the paired data set, or else over its axis in the domains of the analysis. If both exist, they must give the same range; an absent bound is equal only to an absent bound. The validator reports a difference: an error for documents of version 0.3 or later, a warning for older ones. RooFit itself keeps taking ranges from the default domain, or from the first domain that lists a variable, for all analyses of a workspace; with the new check, a document of version 0.3 can't contradict that for the observables of its data sets. Assisted-by: claude-code:claude-opus-5-5
…elihood In HS3 0.3 (HS3 PR root-project#154, decision on HS3 root-project#156), a likelihood consists of exactly the terms it lists, and the `constraints` of a HistFactory modifier are a requirement that adds no term: every likelihood that contains the channel must have each named distribution contribute exactly once, through `distributions` or `aux_distributions`, or as a factor of a `product_dist` or a component of a `combined_dist` reached from them. For documents of version 0.3 or later, a likelihood that lists a named constraint never, or more than once, is now rejected. RooFit's own export already lists these terms in `aux_distributions`. For older documents, nothing changes: RooFit still adds the constraints named by the modifiers itself (likelihoodTerms()). That code stays, both for older documents and for constraint types that might be able to infer their terms from the channel in the future. The rf515_hfJSON tutorial and the hand-written documents of version 0.3 of the tests HistFactoryArrayDistConstraints, HistFactoryArrayDistExport, HistFactoryConstraintTermsInLikelihood (twoChannelHistFactoryJSON()) and HistFactoryConstraintAlsoExternal relied on the constraints being added implicitly; their likelihoods now list them in "aux_distributions". Assisted-by: claude-code:claude-opus-5-5
In HS3 0.3 (HS3 PR root-project#154, decision on HS3 root-project#156), the constraints that a `staterror` modifier names are authoritative: a reader evaluates it like a `shapefactor` and derives neither the constraint nor whether a gamma is fixed from the `errors` of the samples. The relative uncertainty computed from the errors is guidance for writers only. RooFit computed the relative uncertainties from the samples and used them to set the range, the error and the constness of the gammas with named constraints. For documents of version 0.3 or later, this is no longer done: the gammas keep the range from the domains and the constness from the parameter points, and only get the uncertainty that their constraint encodes as initial error. The derivation is kept for older documents, and for the legacy constraint types, which create their constraint terms from it. Gammas without a constraint are left free in any version. RooFit's export writes a fixed gamma, e.g. in a bin without uncertainty, as constant with a null constraint, and the ranges of the gammas in the domains, so the configuration survives a round trip. The new test StatErrorFromDocument checks both. Assisted-by: claude-code:claude-opus-5-5
A ModelConfig with a pdf, but without any data set in the workspace, is a "pure model": it can be used to generate toys or an Asimov data set, but there is no likelihood to evaluate before that. RooFit wrote it as a likelihood with the number 0 in "data", which HS3 0.3 reads as an observation of value 0 for the single variate of the distribution (HS3 PR root-project#154). Following HS3 PR root-project#154 (commit c67e621), a likelihood with "data": null now marks such a pure model: it groups the distributions of a model so that an analysis, and thus a ModelConfig, can refer to them, and it can't be used as a likelihood before a data set is created. * The typed document gets a term without data (std::monostate) and a flag for a pure-model likelihood; the parser reads and the writer writes "data": null. * A ModelConfig without data is exported as a pure model. * On import, a pure model gives a ModelConfig without data, like the number 0 did. The number 0 is still read as "no data" in documents before 0.3 in the exact form "data": [0], which is the only one older versions of RooFit wrote; a 0 in a longer array, or in documents of version 0.3 or later, is an observation like any other number. A pure model has no data at all, so the constraint terms of its channels are always written to "aux_distributions", with their observed values as constant parameters, also with config().exportConstraintData, which pairs them with data sets only in a likelihood with data. Test changes: a hand-written document of the ObservablesWithoutData test, which used the number 0 like RooFit, now uses "data": null. The HistFactoryConstraintTermsInLikelihood test, which covers the data sets of the constraint terms, had a ModelConfig without matching data; it now imports a combined data set for its RooSimultaneous, so that the likelihood has data, and its expected data names are adjusted. Assisted-by: claude-code:claude-opus-5-5
…ents A RooLognormal is by default parametrized by its median and shape parameter, and is written as a lognormal_dist of the functions "<median>_lognormal_log" and "<shape>_lognormal_log". Such a pdf could not be a component of an array distribution, with two consequences for the log-normal constraints of HistFactory models: - config().exportArrayDist had no effect on them: they were always written on their own, so there was no array per type of constraint; - config().exportConstraintData had no effect on them either, because the observable of a constraint is found by the same function: they stayed in "aux_distributions" instead of being paired with data. The HS3 standard lets the components of an array distribution name functions, so they are now written as components. On import, the components already go through the importer of lognormal_dist, which restores the parametrization of RooFit. The convention of the suffix is now in two functions next to each other, lognormalLogName() and lognormalParameters(), which the exporter and importer of lognormal_dist and the array distribution all use. Assisted-by: claude-code:claude-fable-5-2
A parameter of a RooFit class that is parametrized differently than its
HS3 distribution (RooLognormal, RooExponential) is written as a function
named after the parameter, e.g. "k_lognormal_log" for log(k). For a
literal constant, this gave names like "1.2_lognormal_log" or
"-0.1_exponential_inverted", which are no identifiers: HS3 requires the
names of functions to match [A-Za-z_][A-Za-z0-9_]*.
The value of a literal constant is now spelled as an identifier:
"const_1p2_lognormal_log", "const_m0p1_exponential_inverted",
"const_1em05_...". It is written with as many digits as it takes to read
it back unchanged. Before, the name of the RooConstVar was used, which
has six significant digits, so that the value changed in a round trip.
A negative value is put in parentheses in the expression ("-(-0.1)"
instead of "--0.1").
Names of the form "const_<number>" are thereby reserved: a function of a
parameter with such a name can't be written, because it could not be
told apart when reading. The names that older versions wrote are still
read.
Assisted-by: claude-code:claude-fable-5-2
RooFit has no class for an array distribution. When a document is read, the components become individual pdfs, and a RooProdPdf holds them together so that the array can be written again. HistFactory channels use the components directly; the product is not part of any model. If such a workspace was written without array distributions (config().exportArrayDist = false), the product was written as a product_dist that no likelihood contains, only because it is a pdf of the workspace that nothing uses. Read back, it is an ordinary product that refers to every constraint by name, so the constraints could never be collected into arrays again: the flag had no effect anymore on any later export. The objects that RooFit creates to represent something of a document that it has no class for are now marked with the attribute "hs3_helper". A helper is no statement of the user about the model: - it is only written if another object that is written refers to it, if a ModelConfig names it, or if the HS3 object that it stands for is written (the array distribution), but not just because it is in the workspace; - a helper that is not written is ignored where the export looks at the users of an object: its components are top-level objects, which are written on their own, and it does not keep a constraint from being a component of an array. The attribute is set by the importer of array_dist and is not written. It is not specific to array distributions: other importers that build composite structures can mark their parts in the same way. Objects of users, also a product that a user marked as array distribution, are written as before. Assisted-by: claude-code:claude-fable-5-2
A HistFactory workspace built by MakeModelAndMeasurementFast() is written to HS3 in every layout of the auxiliary measurements that config().exportArrayDist and config().exportConstraintData select: the constraint terms in "aux_distributions" or paired with data, on their own or collected into one array distribution per type. The model has three channels whose sets of constrained parameters overlap partially, with Gaussian and Poisson constraints; two variants add a log-normal constraint in either parametrization of RooLognormal. For every model and layout, the test checks that - the document has the layout that the flags select, with exactly one array distribution per type of constraint, and every constraint term once in each likelihood; - the workspace that is read back has the same ModelConfig, data, variables and constraints, and gives the same document when written again; - a likelihood scan gives the same values, with the nuisance parameters fixed and profiled; - toys are identical for all layouts, a toy of either model gives the same likelihood in the original and the imported model, and the sampled distributions agree over many toys; - the global observables stay constant RooRealVars, the likelihood stays the same, and the layout is the one that was asked for, when the layout changes between two exports, for every pair of layouts. The names of the constraint pdfs and which of x and mean of a Gaussian is the global observable are not part of the model and not compared. Assisted-by: claude-code:claude-fable-5-2
Since "Leave infinite bounds of data axes out instead of writing null", no axis writes an infinite bound as null anymore, and writeBound() in HS3Writer.cxx has no caller. Builds with -Werror (dev=ON) fail with -Wunused-function. Assisted-by: claude-code:claude-fable-5-2
HS3 0.3 allows a fixed axis (with "value") only in domains, and the parser rejected a data axis with "value" in documents of any version. ROOT 6.34 wrote the observable of a data set like this, e.g. in the likelihood of the ATLAS top-quark mass measurement on HEPData (INSPIRE 2894561, HS3 0.2), which could no longer be imported. The parser now only records that the axis has a "value", and the validation reports it: as an error for documents of version 0.3 or later, and as a warning for older ones, like the other rules that came with 0.3. As before the check was added, the value itself is not used. Assisted-by: claude-code:claude-fable-5-2
…ore 0.3 The validation rejects a sample with two histosys modifiers of the same name, because their histograms are named after the modifier. ROOT wrote such documents, though: a parameter that interpolates a sample more than once became several histosys modifiers of the same name. Two of the likelihoods of the ATLAS VH measurement on HEPData (INSPIRE 2905253, HS3 0.2, written by ROOT 6.37) are like this and could no longer be imported. For documents before HS3 0.3, this is now a warning instead of an error, and the import tells the histograms of the repeated modifiers apart by a counter. Each modifier becomes one entry of the PiecewiseInterpolation, as written. The export already combines several histosys modifiers of one parameter into one, so writing the model again gives a document that is valid in the current version. Documents of version 0.3 or later with such modifiers are rejected as before. Assisted-by: claude-code:claude-fable-5-2
…nel invalid The HistFactory export writes a RooFormulaVar among the factors of a sample that is a product as one modifier per factor: a bare parameter becomes a normfactor. A parameter that occurs twice in the formula, e.g. in "b*b", became two normfactors of the same name, which can't be combined into one, so the export failed. The same happens if the sample already has a normfactor of that parameter. The likelihoods of the ATLAS ttbar/Z cross-section measurement on HEPData (INSPIRE 2689657), which use the square of a b-tagging efficiency like this, could be imported but not written again. The export now checks the channel after splitting formulas, with the checks of a HistFactory distribution and the combination of duplicate modifiers. If it is invalid for any reason, and valid when the formulas of the channel are written as custom modifiers like other functions, they are written as custom modifiers. A channel that is invalid either way is reported as before. Assisted-by: claude-code:claude-fable-5-2
The check that every constraint named by a HistFactory modifier contributes exactly once to a likelihood (HS3 0.3) counted how often the constraint is listed, also as a component of a combined distribution. But a distribution contributes one factor per entry of the data it is paired with. A constraint that is a region of the model, so that it is part of the sampling distribution, and also a term of its own paired with the measurement, was rejected as contributing twice, although the region has no data. Before the check was added, such documents were read. Conversely, a constraint that is only a region without data was accepted as one contribution, although nothing is observed. The contributions are now counted with the paired data: a term counts once per entry of its data set, and a component of a combined distribution through the component of the paired combined data set with the same key, i.e. not at all if that is missing or has no entries. * A region without data plus the measurement as a separate term is one contribution. Since listing a constraint in the model and again on its own is probably not intended, there is a warning. * A component of a combined distribution without any data component gives a warning. * The measurement both as the data of the region and as a separate term is still rejected, as two contributions. * A region without data and no measurement is now rejected: it is no observation. Reported on the pull request, with a reproducer whose four HistFactory cases are the new test HistFactoryConstraintContributionsCountData. Assisted-by: claude-code:claude-fable-5-2
…ution An auxiliary measurement that is part of the model, a region whose pdf consists of constraint terms, could not be written: for a product, the group and its factors were both listed in the likelihood, and the export stopped at the shared variates; for an array, the likelihood named the components of the array, which have no name in the document, and the document could not be read back. Reported on the pull request. Export: * With config().exportConstraintData, an array of constraints of a model that is a RooSimultaneous is written as a component of the combined distribution, and the data set with its observed values as a component of the combined data set, instead of as a separate term of the likelihood. The two are the same likelihood, but the combined distribution is then the sampling distribution of all measurements. Each combined data set gets a data set of its own, named like its other components. Single constraints stay terms of the likelihood, as do the constraints of models with several index columns. * A channel of the model that consists of constraint terms only is written once, as that channel. If its data set has no entries, the observed values are taken from its global observables. * A component of an array is never referred to by its own name, whatever kind of channel its constraint belongs to. * The components that are auxiliary measurements are marked in misc.ROOT_internal.auxiliary_channels. Import: * By default, marked components are read as before: as constraint terms with global observables. Without the mark, RooFit can't tell an auxiliary measurement from a channel with one event. * EXPERIMENTAL, with the new config().importConstraintsAsChannels: they stay components of the RooSimultaneous, with their data set of one entry in the combined data set. HistFactory channels are then built without the constraints that are measurements of their own. A workspace read like this is written without the "constraints" of its modifiers; the likelihood is the same. * A distribution that is a component without data and also a term with data contributes once. RooFit left such a term out of the likelihood, because a component without data is no constraint term for it. It is now read as the term (or, with the option, as the component with the data of the term), with a warning. The layout tests are adapted, check the constraint terms of every channel after a round trip, and have a case for the experimental import. The new test AuxiliaryMeasurementAsRegionOfTheModel has the reported round trips, with the likelihood compared to its analytic value in every generation. Assisted-by: claude-code:claude-fable-5-2
The comment of config().exportConstraintData still described the layout before the previous commit. Assisted-by: claude-code:claude-fable-5-2
Follow-up to the auxiliary measurements, from a second report on the pull request with a published workspace (ATLAS Higgs combination). * On import, a constraint term with a global observable becomes a factor of every channel that is a product and depends on one of its other parameters, instead of an external constraint of the ModelConfig. The export takes the constraints out of the channel products, since a likelihood lists each term once; the import now puts them back, as HistFactory builds its models. The pdf of the model is then the sampling distribution of the auxiliary measurements again. In the reported workspace, 19 of 517 global observables were no longer reachable from the pdf after a round trip, which changed expected p-values from Asimov data sets generated from it. Terms without a global observable, e.g. the regularization of an unfolding, and the constraints of channels that are not products stay external constraints. * A Gaussian constraint is written with its global observable as "x". Which of x and mean that is was recorded when the channel that names the constraint was written, which could be after the constraint itself: the document then paired the constraint with a data set of another axis and could not be read. It is now determined from the global observables of the ModelConfigs before any pdf is written. * EXPERIMENTAL import of constraints as channels: an observation that is a term of two likelihoods gets a data set for each of their combined data sets, since a data set can only be a component of one. ConstraintDataOfProductConstraints expected the constraint to be an external constraint after a round trip; it now expects it in the model. New tests: GaussianConstraintObservableBeforeItsChannel and AuxiliaryObservationSharedByTwoLikelihoods. Assisted-by: claude-code:claude-fable-5-2
…n import The previous commit puts the constraint terms of a model back into its channels on import, but only into channels that are products. A channel of another kind, e.g. a single Gaussian, kept its constraints as external constraints of the ModelConfig, so that the pdf of the model was still not the sampling distribution of the auxiliary measurements (the first reproducer of the report on the pull request). A component of a combined distribution that is no product is now wrapped in a RooProdPdf "<channel>_with_constraints" with the constraint terms of its parameters, which are the other terms of the likelihoods that have the combined distribution. This is done when the combined distribution is read, since the components of a RooSimultaneous can't be replaced later. RooFit takes the constraints out of such a product when it builds a likelihood, as for a HistFactory channel; the new test ConstraintsStayInTheSamplingDistribution compares that likelihood, built from the pdf and the global observables alone, with its analytic value. Written again, the wrapper is a product_dist of its channel, so the name of the component changes once, in the first round trip. A global observable of a constraint is now recognized by nothing else in the model depending on it, not by being constant: its value can come from the data set of the constraint, which is read later. An array of constraints goes into a channel as a whole, since its components have no names in a document. Assisted-by: claude-code:claude-fable-5-2
1a1d59a to
dd6905a
Compare
HS3 root-project#161 was revised: the likelihood is the plain product of its terms, and union composition applies only within a listed distribution (combined and array distributions). Distributions that share factors, e.g. the models of a combination with common constraint terms, are joined in a combined distribution, which may contain combined distributions itself. * Distinct variates: each term of a likelihood is the union of its parts (components of combined distributions, recursively, and of array distributions), in which identical parts count once; a variate of two terms is shared, also by identical parts. Components of a combined distribution whose sub-data set is missing or empty contribute nothing and are left out. The axes of identical factors may occur in several sub-data sets of the paired combined data set. A violation is reported together with the violations of the "constraints" of HistFactory modifiers, and the error says how to join such distributions. * External arrays are no longer split into their components: two arrays that share components can't both be terms of a likelihood any more. * Combined data sets may have combined data sets as components; their columns become columns of the outer data set, with the label "" in the rows of the other components. * The import of a likelihood flattens its model into one RooSimultaneous over a RooSuperCategory, also for a single term with nested combined distributions, with "" in the columns that don't apply to a channel. Array channels of one component type, each with one data entry, are merged into one array with the union of their components, and their entries into one; differing observed values of a shared variate are an error. The replaced combined distributions are helpers, which the export only writes if something else uses them. * Skipping helpers on export is weakly transitive: an object that only skipped helpers use is not written either (e.g. the arrays that were merged), except that a skipped array dissolves into its components, which are then written on their own. HistFactory modifiers name an array that is written. * The HistFactory checks of root-project#24201 descend into nested combined distributions, and a nested combined distribution is not wrapped with constraints like other channels that are no products. Tests: identical array components within a combined distribution give the likelihood of one array; as two terms of a likelihood they are rejected. Two HistFactory models written with exportConstraintData are joined in a nested combined distribution, flattened, and give the likelihood of the single model of both channels; as two terms, they are rejected. Assisted-by: claude-code:claude-opus-5-5 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
HS3 root-project#161 was revised: the likelihood is the plain product of its terms, and union composition applies only within a listed distribution (combined and array distributions). Distributions that share factors, e.g. the models of a combination with common constraint terms, are joined in a combined distribution, which may contain combined distributions itself. * Distinct variates: each term of a likelihood is the union of its parts (components of combined distributions, recursively, and of array distributions), in which identical parts count once; a variate of two terms is shared, also by identical parts. Components of a combined distribution whose sub-data set is missing or empty contribute nothing and are left out. The axes of identical factors may occur in several sub-data sets of the paired combined data set. A violation is reported together with the violations of the "constraints" of HistFactory modifiers, and the error says how to join such distributions. * External arrays are no longer split into their components: two arrays that share components can't both be terms of a likelihood any more. * Combined data sets may have combined data sets as components; their columns become columns of the outer data set, with the label "" in the rows of the other components. * The import of a likelihood flattens its model into one RooSimultaneous over a RooSuperCategory, also for a single term with nested combined distributions, with "" in the columns that don't apply to a channel. Array channels of one component type, each with one data entry, are merged into one array with the union of their components, and their entries into one; differing observed values of a shared variate are an error. The replaced combined distributions are helpers, which the export only writes if something else uses them. * Skipping helpers on export is weakly transitive: an object that only skipped helpers use is not written either (e.g. the arrays that were merged), except that a skipped array dissolves into its components, which are then written on their own. HistFactory modifiers name an array that is written. * The HistFactory checks of root-project#24201 descend into nested combined distributions, and a nested combined distribution is not wrapped with constraints like other channels that are no products. Tests: identical array components within a combined distribution give the likelihood of one array; as two terms of a likelihood they are rejected. Two HistFactory models written with exportConstraintData are joined in a nested combined distribution, flattened, and give the likelihood of the single model of both channels; as two terms, they are rejected. Assisted-by: claude-code:claude-opus-5-5 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This Pull request:
Brings RooFit's HS3 import and export in line with HS3 PR
#154
("Fixes before v0.3"). That PR implements the decisions on HS3
#156
and the fixes of
#157.
Each commit is one change, with a test.
Commits 12–15 are a separate topic on top: the layouts in which the auxiliary measurements
(constraint terms) of HistFactory models are written. They don't depend on HS3 #154. Commits 17–19 keep documents
before 0.3 that are published on HEPData importable and writable.
Where HS3 0.3 now forbids or changes something that older documents rely on, the new behaviour applies to
documents with
hs3_version0.3 or later, and older documents are read as before, usually with a warning. The codefor the old behaviour (implicit HistFactory constraint terms, staterror gammas configured from the sample errors) is
kept, not removed: older documents need it, and it may be reactivated for constraint types that infer their strength
from the channel.
Note
HS3 #154 was merged on 2026-11-18 (merge commit
5570053).
All commits follow #154, including
"data": nullfor pure models (HS3 commitc67e621,
with the reading of the old placeholder restricted to
"data": [0]in0109565).
Changes or fixes:
nullundefined); RooFit wrotenull, or the largest double for constraint data. Import: an axis with one bound sets that bound only. The validator rejects infinite bounds on binned axes.UnboundedDataAxesmean→mu. Export writesmu;meanis still read (with a warning in ≥ 0.3 documents).LandauLocationKeyfalsewith one coefficient per summand: honoured (built from the normalized coefficientsc_i/Σc, not extendable) instead of a warning. Missing flag with n−1 coefficients: still accepted. No coefficients: read and written with a warning (undefined in 0.3).MixtureDistExtendedFlag(extended)1,0,==,!=for TFormula.ExpressionBuiltinsPI,EULER,TRUE,FALSE,ifelseor a function of the language: validator error for ≥ 0.3, warning otherwise and on export. A generic expression referring to a distribution: rejected on import (≥ 0.3). The export fails for anything that would be written as such an expression (RooFormulaVar/RooGenericPdfdepending on a pdf,RooTFnBindingwith a pdf, the transformation helpers ofRooLognormal/RooExponential). Whether to allowgeneric_distexpressions on distributions later is discussed in HS3 #159.ReservedNamesAndDistributionReferencespointdata (rejected so far) becomes a one-entry 1DRooDataSet; such a data set (one real variable, one unweighted entry) is written aspointdata with its axis, also for the constraint data ofconfig().exportConstraintData. The provisionaluncertaintyis ignored with a warning.PointDatadata, or point data without axes, is the value of the single variate of the paired distribution; rejected if that can't be determined. In-line numbers become a point data set<distribution>_data."data": [0], RooFit's old "no data" placeholder, keeps that meaning in documents before 0.3 in exactly this form (and, until the last commit, in documents RooFit wrote); a 0 in a longer array is a value.DataWithoutAxesvalue) axes in data sets; the axis of point data must be the variate of the paired distribution; a paired data axis and an analysis-domain axis for the same variate must give the same range (validator: error for ≥ 0.3, warning otherwise).DataAxesAgainstDomainsconstraintsof a modifier add no term in 0.3: each named distribution must contribute exactly once to every likelihood with the channel; ≥ 0.3 documents that don't are rejected. RooFit's export already lists them. Older documents: constraints are still added implicitly.HistFactoryConstraintsListedOnce25dc4e91aa6). RooFit's export writes fixed gammas as constant with anullconstraint.StatErrorFromDocument"data": null, instead of"data": [0], and read back as a ModelConfig without data."data": [0]is still read as "no data" in documents before 0.3; any other 0 is a value. A pure model writes its constraint terms toaux_distributionsalso withconfig().exportConstraintData.PureModelLikelihoodRooLognormalin RooFit's default parametrization (median, shape) is written withmu/sigmanaming the functionslog(median)/log(shape). It could not be a component of anarray_dist, soconfig().exportArrayDistandconfig().exportConstraintDatahad no effect on such constraints. It now can; the suffix convention is in two functions that the standalone and the array code share.ArrayDistOfLognormalsInRooFitParametrization1.2_lognormal_logor-0.1_exponential_inverted, which are not identifiers. The value is now spelled as one (const_1p2_lognormal_log,const_m0p1_exponential_inverted), with all digits needed to read it back unchanged (before: six). Names of the formconst_<number>are reserved for this. The old names are still read.FunctionsOfLiteralConstantsHaveValidNamesRooProdPdfthat holds the components of an importedarray_disttogether was written as aproduct_distwhen arrays were switched off; read back, it kept the constraints from ever being collected into arrays again. Objects that RooFit creates to represent something it has no class for now carry the attributehs3_helper: they are only written if something refers to them (or the HS3 object they stand for is written), and are otherwise ignored by the export. Not specific to arrays.HelperObjectstestHS3AuxiliaryMeasurements: a three-channel HistFactory workspace with partially overlapping constraints (Gaussian, Poisson, and log-normal in two variants) is written in all four combinations ofexportArrayDist×exportConstraintDataand read back. Checks the layout, one array per constraint type, the workspace, a likelihood scan (fixed and profiled), toys, and every pair of layouts in sequence.testHS3AuxiliaryMeasurements(51 tests)writeBound()inHS3Writer.cxxbut left the definition, which fails builds with-Werror(dev=ON) on-Wunused-function. Fix on top instead of in commit 1, to avoid rewriting the history; commits 1–15 therefore don't build on their own withdev=ON.dev=ONvaluein documents of any version, but ROOT 6.34 wrote the observable of a data set like this (e.g. the top-quark mass likelihood on HEPData, INSPIRE 2894561). The parser now records it and the validator reports it: error for ≥ 0.3, warning otherwise. The value is not used, as before commit 8.DataAxesAgainstDomains(extended)histosysmodifiers of the same name in a sample. ROOT wrote these for a parameter that interpolates a sample more than once (e.g. two VH likelihoods on HEPData, INSPIRE 2905253, ROOT 6.37). Now a warning before 0.3. They are read as one parameter with stacked effects: the parameter enters the interpolation once per modifier (only the histogram objects of the repeated modifier get a counter in their names). The export combines them into one modifier as before. Still an error for ≥ 0.3.HistFactoryHistoSysOfTheSameNameInOlderDocumentsRooFormulaVarfactor of a sample that is a product as one modifier per factor. A parameter that occurs twice (b*b), or that the sample already has as anormfactor, became twonormfactors of the same name, and the export failed (e.g. the ttbar/Z likelihoods on HEPData, INSPIRE 2689657, which could be imported but not written again). The export now checks the channel after splitting; if it is invalid for any reason and valid with the formulas of the channel as custom modifiers, they are written as custom modifiers.FormulaIsNotSplitIfThatMakesTheChannelInvalidcombined_distthrough the component of the paired combined data with the same key (nothing if that is missing or empty). A region without data plus the measurement as its own term is one contribution (with a warning); a region without data and no measurement is rejected. Reported in the comments of this PR.HistFactoryConstraintContributionsCountDataexportConstraintData, an array of constraints of a model that is aRooSimultaneousis a component of thecombined_dist, with its data set as a component of the combined data set (before: a separate likelihood term). A channel that consists of constraint terms only is written once, as that channel, with the observed values from its global observables if its data is empty. A component of an array is never referred to by its own name. Marked inmisc.ROOT_internal.auxiliary_channels. Import: by default, marked components are read as constraint terms with global observables, as before. EXPERIMENTALconfig().importConstraintsAsChannels: they stay components of theRooSimultaneouswith a one-entry data set, and HistFactory channels are built without them. A distribution that is a component without data and a term with data is read as the term (RooFit left it out of the likelihood before), with a warning.AuxiliaryMeasurementAsRegionOfTheModel,ConstraintsAsChannels, layout tests adaptedconfig().exportConstraintData.x/meanin the other order than its data set). Experimental import: an observation shared by two likelihoods gets one data set per combined data set.GaussianConstraintObservableBeforeItsChannel,AuxiliaryObservationSharedByTwoLikelihoods;ConstraintDataOfProductConstraintschangedcombined_distthat is no product (e.g. a single Gaussian) is wrapped in aRooProdPdf<channel>_with_constraintswith the constraint terms of its parameters, so that the pdf of the model is the sampling distribution of its auxiliary measurements for such models too; RooFit takes the constraints out of the product when it builds a likelihood, as for a HistFactory channel. The name of the component changes once, in the first round trip. A global observable is recognized by nothing else in the model depending on it; an array of constraints goes into a channel as a whole.ConstraintsStayInTheSamplingDistributionNot changed, by decision: the interpolation combinations that
FlexibleInterpVarcan't evaluate(
add/poly6/poly1,mult/poly6/poly1fornormsys) are still rejected, which HS3 0.3 requires of a reader thatcan't evaluate them.
Behaviour changes users may notice
hs3_version0.3 or later are checked more strictly. They are rejected for:mixture_distwithoutextendedbut with one coefficient per summand;#159
for allowing it in
generic_distlater);mixture_distwith"extended": falseand one coefficient per summand is now not extendable.landau_distwritesmu;pointdata;"data": null(commit 11);array_distand followconfig().exportConstraintData(commit 12);const_<number>_<suffix>(commit 13); a parameter namedconst_<number>that needs such a function can't be exported;config().exportConstraintData, arrays of constraints are components of the model'scombined_dist, andtheir data sets (now named
<combined data>_<array>) components of the combined data set (commit 21);config().exportArrayDist = false, the product that held an importedarray_disttogether is no longerwritten as a
product_dist, unless something uses it; its components are written on their own (commit 14).Changed tests and reference data
MixtureDistExtendedFlag(commit 3): its last case expected a warning for"extended": false; it now checks thatthe mixture is not extendable and has the normalized shape. New cases for the missing flag.
Commit 9:
tutorials/roofit/roofit/rf515_hfJSON.json, and the hand-written 0.3 documents ofHistFactoryArrayDistConstraints,HistFactoryArrayDistExport,HistFactoryConstraintTermsInLikelihood(
twoChannelHistFactoryJSON()) andHistFactoryConstraintAlsoExternal: their likelihoods now list theconstraints in
aux_distributions.Commit 11:
ObservablesWithoutDatauses"data": nullinstead of[0];HistFactoryConstraintTermsInLikelihoodimports a combined data set for itsRooSimultaneous, so that thelikelihood has data and the test still covers the data sets of constraint terms; expected data names adjusted.
StatErrorFromDocument(commit 10), changed in the rebase onto master3aa99aad3f4: it expected the unconstrainedgamma of a bin without uncertainty to be fixed in a document before 0.3. Master
25dc4e91aa6leaves unconstrainedgammas free in any version, so the test now expects that, and fixes the gamma by hand before the round trip that
checks that a fixed gamma is written as fixed.
ConstraintDataOfProductConstraints(commit 23): it expected a constraint of a product to be an external constraintof the ModelConfig after a round trip. It now expects it to be a factor of the model again, and no external
constraint.
Commits 12–15 change no existing test. Known limitation, unchanged: a workspace with
Measurement::AddLogNormSyst()can't be exported (NormSysWithFunctionAsParameter).Checklist:
Rebased again onto master
3aa99aad3f4, which includes25dc4e91aa6("Fix HistFactory constraints, gammas andolder-document import"). Commit 10 conflicted with its new configuration of the gammas and was merged as described
in the table; the other conflicts were mechanical. At the tip,
testRooFitHS3(194 tests) andtestHS3AuxiliaryMeasurements(51 tests) pass, again with the HS3 library compiled from the branch against anexisting ROOT build, not through CMake: the new
hs3cppobject library of master is not exercised by this. The 283HS3 documents of the 17 records that HEPData lists under
analysis:hs3(all written by ROOT, HS3 0.1.90 and 0.2)were surveyed: none has a staterror without a constraint type, so none is affected by the gamma changes. 44 of them
(at least one per resource) were imported before and after the rebase with identical variables; the three that
failed to import are fixed by commits 17–18. With commit 19, all 283 documents are imported, exported and imported
again without error, checked with the elective test of #24228 (run against the HS3 library of this branch); that
test lists four of them as expected failures on master, which have to be removed there or here, whichever is merged
second.
Commits 20–24 (auxiliary measurements as regions, reported in the comments): at the tip,
testRooFitHS3199 testsand
testHS3AuxiliaryMeasurements63 tests pass (same private build), and all 283 HS3 documents from HEPData areimported, exported and imported again without error. Limitations: a workspace read with
importConstraintsAsChannelsis written without theconstraintsof its modifiers (same likelihood); without themark in
misc, a component with one entry is always read as a channel;RooSimultaneous::generate()can't samplesuch a model in one call, each component can be sampled by itself.
Before that, rebased onto master
7cc3f1b4474("Remove JSON I/O through export keys and factory expressions"): commit 2 nowchanges the C++ importer and exporter of
landau_distthat this master commit introduced, instead of the removedexport keys and factory expressions. After the rebase,
testRooFitHS3was built and run on each of the 15 commits(158 tests at commit 1, 170 at the tip, all passing) and
testHS3AuxiliaryMeasurementsat the tip (51 passing), withthe HS3 library compiled from the branch against an existing ROOT build, not through CMake. The numbers below are
from before the rebase.
Tests run (Linux, GCC 13, RelWithDebInfo,
-Droofit=ON -Dtesting=ON) on top of master27fbb8dd02a:testRooFitHS3157 → 167 tests (10 new),testHistFactory44, all passing. Every commit was built and tested on itsown (
testRooFitHS3andtestHistFactory). clang-format clean.Commits 12–15:
testRooFitHS3167 → 170 tests and the newtestHS3AuxiliaryMeasurements(51 tests), all passing;testRooFitHS3was run on each of the commits 12–14. These were tested with the HS3 library and the two testprograms compiled from the branch against an existing ROOT build of this PR, not through CMake: the new
ROOT_ADD_GTESTline and a full build of commits 12–15 are untested.testHistFactorydoesn't use the HS3 libraryand was not rerun.
Not run: the PyROOT tests, the
rf515_hfJSON.pytutorial (its JSON is covered byTutorialRF515RoundTrip), and theoptional HS3 test suite.
AI assistance: Claude Code (claude-opus-5-5) implemented the changes, the tests and this description from a list of
required changes that the author reviewed, under review of the author. The commits carry
Assisted-by: claude-code:claude-opus-5-5. Commits 12–24 were written by Claude Code (claude-fable-5-2) from anaudit of the export layouts and a check of the documents on HEPData that the author directed, and carry
Assisted-by: claude-code:claude-fable-5-2. It also did the rebases and their conflict resolutions.🤖 Generated with Claude Code