mlboydaisuke
GLiClass-Edge v3.0 for LiteRT: S128 and S256 graphs (fp32 and fp16 weights), float16 token table, tokenizer, Python host, Android sample, conversion scripts, fixtures and card
88c9095 verified 23 days ago
Raw History Blame Contribute Delete
164 kB
{"set":"gliclass_app_gate","rows":152,"threshold":0.5,"windows":{"s128":152,"s256":0},"source":"official gliclass 0.1.20 pipeline on CPU fp32 (batch 1): captured input_ids, raw logits and the single-label / multi-label results; redistributable subset: SemIf authored144 (MIT), the model card's two examples, six invented requests","fixtures":[{"id":"semif_000","source":"semif","text":"The optician ordered replacement lenses. The workshop confirms they have not yet been fitted to the customer's glasses.","prompt":"Assess the claim: the replacement lenses have been fitted.","labels":["The evidence establishes the claim","The evidence does not establish either","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,253,5407,22881,452,644,14662,15,510,1478,6876,6960,5407,22881,15,380,22586,23849,597,452,417,2568,644,14662,281,253,7731,434,17543,15,50282],"label_positions":[1,7,14],"window":128,"logits":[4.308628559112549,3.846890449523926,0.7567108869552612],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.6028247475624084}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9867266416549683},{"label":"The evidence does not establish either","score":0.9791001677513123},{"label":"The evidence establishes the opposite","score":0.6806392073631287}]},{"id":"semif_001","source":"semif","text":"The optician ordered replacement lenses. The workshop confirms they have not yet been fitted to the customer's glasses.","prompt":"Assess the claim: replacement lenses were ordered.","labels":["The evidence establishes the claim","The evidence does not establish either","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,5407,22881,497,6960,15,510,1478,6876,6960,5407,22881,15,380,22586,23849,597,452,417,2568,644,14662,281,253,7731,434,17543,15,50282],"label_positions":[1,7,14],"window":128,"logits":[5.050986289978027,0.4260352551937103,-0.034054215997457504],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9842590093612671}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.99363774061203},{"label":"The evidence does not establish either","score":0.6049265265464783}]},{"id":"semif_002","source":"semif","text":"The workshop confirms it fitted the replacement lenses to the customer's glasses.","prompt":"Assess the claim: the replacement lenses have been fitted.","labels":["The evidence does not establish either","The evidence establishes the claim","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,253,5407,22881,452,644,14662,15,510,22586,23849,352,14662,253,5407,22881,281,253,7731,434,17543,15,50282],"label_positions":[1,8,14],"window":128,"logits":[-9.126107215881348,7.078324317932129,-5.453106880187988],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9999963045120239}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9991575479507446}]},{"id":"semif_003","source":"semif","text":"The optician records a glasses prescription but no order or fitting status.","prompt":"Assess the claim: the replacement lenses have been fitted.","labels":["The evidence does not establish either","The evidence establishes the claim","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,253,5407,22881,452,644,14662,15,510,1478,6876,5861,247,17543,17632,533,642,1340,390,13532,3708,15,50282],"label_positions":[1,8,14],"window":128,"logits":[5.295374393463135,0.6928500533103943,2.5949838161468506],"pipeline_single":[{"label":"The evidence does not establish either","score":0.928327739238739}],"pipeline_multi":[{"label":"The evidence does not establish either","score":0.995010256767273},{"label":"The evidence establishes the claim","score":0.6666006445884705},{"label":"The evidence establishes the opposite","score":0.9305380582809448}]},{"id":"semif_004","source":"semif","text":"The guest writes, \"The listing says towels are supplied. I agree: fresh towels were provided during my stay.\"","prompt":"Assess the claim: the guest endorses the listing's towel statement.","labels":["The evidence establishes the claim","The evidence establishes the opposite","The evidence does not establish either"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50369,2903,405,253,1750,27,253,12141,990,11092,253,16485,434,29861,3908,15,510,12141,12013,13,346,510,16485,2296,41204,403,12164,15,309,5194,27,5352,41204,497,2530,1309,619,3297,449,50282],"label_positions":[1,7,13],"window":128,"logits":[4.761003017425537,-3.7188048362731934,-7.732299327850342],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9997887015342712}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9915155172348022}]},{"id":"semif_005","source":"semif","text":"The guest writes, \"The listing says towels are supplied. I agree: fresh towels were provided during my stay.\"","prompt":"Assess the claim: the guest disputes the towel statement.","labels":["The evidence does not establish either","The evidence establishes the claim","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,253,12141,24598,253,29861,3908,15,510,12141,12013,13,346,510,16485,2296,41204,403,12164,15,309,5194,27,5352,41204,497,2530,1309,619,3297,449,50282],"label_positions":[1,8,14],"window":128,"logits":[-7.114278793334961,4.76469612121582,-3.6232025623321533],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9997655749320984}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9915465712547302}]},{"id":"semif_006","source":"semif","text":"The guest writes, \"The listing says towels are supplied, but none were provided. I dispute that statement.\"","prompt":"Assess the claim: the guest endorses the listing's towel statement.","labels":["The evidence establishes the opposite","The evidence does not establish either","The evidence establishes the claim"],"ids":[50281,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,253,12141,990,11092,253,16485,434,29861,3908,15,510,12141,12013,13,346,510,16485,2296,41204,403,12164,13,533,5293,497,2530,15,309,12027,326,3908,449,50282],"label_positions":[1,7,14],"window":128,"logits":[3.6526925563812256,4.9305291175842285,0.6474969983100891],"pipeline_single":[{"label":"The evidence does not establish either","score":0.7737302184104919}],"pipeline_multi":[{"label":"The evidence establishes the opposite","score":0.9747337102890015},{"label":"The evidence does not establish either","score":0.9928291440010071},{"label":"The evidence establishes the claim","score":0.6564462184906006}]},{"id":"semif_007","source":"semif","text":"The guest forwards the listing but provides no comment about towels or the stay.","prompt":"Assess the claim: the guest endorses the listing's towel statement.","labels":["The evidence establishes the claim","The evidence establishes the opposite","The evidence does not establish either"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50369,2903,405,253,1750,27,253,12141,990,11092,253,16485,434,29861,3908,15,510,12141,32856,253,16485,533,3400,642,4385,670,41204,390,253,3297,15,50282],"label_positions":[1,7,13],"window":128,"logits":[-0.1559862345457077,2.4671223163604736,4.356616973876953],"pipeline_single":[{"label":"The evidence does not establish either","score":0.860497772693634}],"pipeline_multi":[{"label":"The evidence establishes the opposite","score":0.9218046069145203},{"label":"The evidence does not establish either","score":0.9873406291007996}]},{"id":"semif_008","source":"semif","text":"The technician says terminal Cedar is online. Terminal Maple is explicitly offline.","prompt":"Assess the claim: terminal Maple is online.","labels":["The evidence establishes the claim","The evidence does not establish either","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,8351,44575,310,3909,15,510,40048,2296,8351,330,31679,310,3909,15,37060,44575,310,11120,28841,15,50282],"label_positions":[1,7,14],"window":128,"logits":[4.334864139556885,1.4138274192810059,1.0253863334655762],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9170836210250854}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.987065851688385},{"label":"The evidence does not establish either","score":0.8043689131736755},{"label":"The evidence establishes the opposite","score":0.7360205054283142}]},{"id":"semif_009","source":"semif","text":"The technician says terminal Cedar is online. Terminal Maple is explicitly offline.","prompt":"Assess the claim: terminal Cedar is online.","labels":["The evidence establishes the claim","The evidence does not establish either","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,8351,330,31679,310,3909,15,510,40048,2296,8351,330,31679,310,3909,15,37060,44575,310,11120,28841,15,50282],"label_positions":[1,7,14],"window":128,"logits":[5.065106391906738,-1.7189934253692627,-0.34554505348205566],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9944308400154114}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.993726372718811}]},{"id":"semif_010","source":"semif","text":"The technician confirms terminal Maple is online and terminal Cedar is offline.","prompt":"Assess the claim: terminal Maple is online.","labels":["The evidence establishes the claim","The evidence does not establish either","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,8351,44575,310,3909,15,510,40048,23849,8351,44575,310,3909,285,8351,330,31679,310,28841,15,50282],"label_positions":[1,7,14],"window":128,"logits":[6.980473041534424,-5.663201808929443,0.3609679639339447],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9986644983291626}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9990710020065308},{"label":"The evidence establishes the opposite","score":0.5892747044563293}]},{"id":"semif_011","source":"semif","text":"The technician lists both terminals but omits their connection status.","prompt":"Assess the claim: terminal Maple is online.","labels":["The evidence establishes the opposite","The evidence does not establish either","The evidence establishes the claim"],"ids":[50281,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,8351,44575,310,3909,15,510,40048,10894,1097,20737,533,7005,953,616,4602,3708,15,50282],"label_positions":[1,7,14],"window":128,"logits":[0.43967875838279724,4.128590106964111,1.0991016626358032],"pipeline_single":[{"label":"The evidence does not establish either","score":0.931671679019928}],"pipeline_multi":[{"label":"The evidence establishes the opposite","score":0.6081824898719788},{"label":"The evidence does not establish either","score":0.9841497540473938},{"label":"The evidence establishes the claim","score":0.7500917911529541}]},{"id":"semif_012","source":"semif","text":"The catalogue originally dated the letter to June. Its author issued a correction stating July was correct and June was mistaken.","prompt":"Assess the claim: the corrected date is in July.","labels":["The evidence does not establish either","The evidence establishes the opposite","The evidence establishes the claim"],"ids":[50281,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,7285,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,253,15045,3522,310,275,4163,15,510,33733,8927,15483,253,4857,281,3978,15,7850,2488,6808,247,10618,14851,4163,369,3451,285,3978,369,20854,15,50282],"label_positions":[1,8,14],"window":128,"logits":[3.131744146347046,3.365994691848755,0.20870362222194672],"pipeline_single":[{"label":"The evidence establishes the opposite","score":0.5453441739082336}],"pipeline_multi":[{"label":"The evidence does not establish either","score":0.9581833481788635},{"label":"The evidence establishes the opposite","score":0.9666247367858887},{"label":"The evidence establishes the claim","score":0.55198734998703}]},{"id":"semif_013","source":"semif","text":"The catalogue originally dated the letter to June. Its author issued a correction stating July was correct and June was mistaken.","prompt":"Assess the claim: the corrected date is in June.","labels":["The evidence establishes the claim","The evidence does not establish either","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,253,15045,3522,310,275,3978,15,510,33733,8927,15483,253,4857,281,3978,15,7850,2488,6808,247,10618,14851,4163,369,3451,285,3978,369,20854,15,50282],"label_positions":[1,7,14],"window":128,"logits":[2.8479504585266113,3.1749954223632812,2.798828363418579],"pipeline_single":[{"label":"The evidence does not establish either","score":0.4153619408607483}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9452126026153564},{"label":"The evidence does not establish either","score":0.959882378578186},{"label":"The evidence establishes the opposite","score":0.9426124691963196}]},{"id":"semif_014","source":"semif","text":"The catalogue author corrects the date to June and expressly rejects the earlier July date.","prompt":"Assess the claim: the corrected date is in July.","labels":["The evidence establishes the claim","The evidence does not establish either","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,253,15045,3522,310,275,4163,15,510,33733,2488,3451,84,253,3522,281,3978,285,20251,41471,253,4321,4163,3522,15,50282],"label_positions":[1,7,14],"window":128,"logits":[3.89770245552063,1.6670348644256592,1.0891040563583374],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.8563505411148071}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9801149964332581},{"label":"The evidence does not establish either","score":0.8411800861358643},{"label":"The evidence establishes the opposite","score":0.748212993144989}]},{"id":"semif_015","source":"semif","text":"The catalogue mentions a date correction but gives no corrected date.","prompt":"Assess the claim: the corrected date is in July.","labels":["The evidence does not establish either","The evidence establishes the claim","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,253,15045,3522,310,275,4163,15,510,33733,25957,247,3522,10618,533,4245,642,15045,3522,15,50282],"label_positions":[1,8,14],"window":128,"logits":[5.322050094604492,0.7801234126091003,2.5665271282196045],"pipeline_single":[{"label":"The evidence does not establish either","score":0.930900514125824}],"pipeline_multi":[{"label":"The evidence does not establish either","score":0.9951410293579102},{"label":"The evidence establishes the claim","score":0.6857066750526428},{"label":"The evidence establishes the opposite","score":0.9286760091781616}]},{"id":"semif_016","source":"semif","text":"The intern attached instructions for weighing the parcel and explicitly says no weighing has been performed.","prompt":"Assess the claim: the parcel has been weighed.","labels":["The evidence establishes the opposite","The evidence does not establish either","The evidence establishes the claim"],"ids":[50281,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,253,32975,556,644,24398,15,510,4184,7660,7997,323,27466,253,32975,285,11120,2296,642,27466,556,644,2684,15,50282],"label_positions":[1,7,14],"window":128,"logits":[1.768953561782837,3.65108585357666,-0.04599286988377571],"pipeline_single":[{"label":"The evidence does not establish either","score":0.8495736718177795}],"pipeline_multi":[{"label":"The evidence establishes the opposite","score":0.8543274402618408},{"label":"The evidence does not establish either","score":0.9746940732002258}]},{"id":"semif_017","source":"semif","text":"The intern attached instructions for weighing the parcel and explicitly says no weighing has been performed.","prompt":"Assess the claim: the document contains weighing instructions.","labels":["The evidence establishes the opposite","The evidence establishes the claim","The evidence does not establish either"],"ids":[50281,50368,380,1941,25097,253,7285,50368,380,1941,25097,253,1750,50368,380,1941,1057,417,5100,2057,50369,2903,405,253,1750,27,253,3389,4428,27466,7997,15,510,4184,7660,7997,323,27466,253,32975,285,11120,2296,642,27466,556,644,2684,15,50282],"label_positions":[1,7,13],"window":128,"logits":[1.8232589960098267,0.9351064562797546,4.38356351852417],"pipeline_single":[{"label":"The evidence does not establish either","score":0.9016516208648682}],"pipeline_multi":[{"label":"The evidence establishes the opposite","score":0.8609567284584045},{"label":"The evidence establishes the claim","score":0.7181101441383362},{"label":"The evidence does not establish either","score":0.9876729846000671}]},{"id":"semif_018","source":"semif","text":"The intern performed the weighing and recorded the parcel's measured weight.","prompt":"Assess the claim: the parcel has been weighed.","labels":["The evidence establishes the opposite","The evidence establishes the claim","The evidence does not establish either"],"ids":[50281,50368,380,1941,25097,253,7285,50368,380,1941,25097,253,1750,50368,380,1941,1057,417,5100,2057,50369,2903,405,253,1750,27,253,32975,556,644,24398,15,510,4184,2684,253,27466,285,5950,253,32975,434,4080,2801,15,50282],"label_positions":[1,7,13],"window":128,"logits":[-3.5777182579040527,2.4311752319335938,-7.915648937225342],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9975173473358154}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9191738963127136}]},{"id":"semif_019","source":"semif","text":"The intern supplies a parcel identifier but no procedure or measurement information.","prompt":"Assess the claim: the parcel has been weighed.","labels":["The evidence establishes the claim","The evidence establishes the opposite","The evidence does not establish either"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50369,2903,405,253,1750,27,253,32975,556,644,24398,15,510,4184,13191,247,32975,21674,533,642,5199,390,6814,1491,15,50282],"label_positions":[1,7,13],"window":128,"logits":[-2.324983596801758,3.0180089473724365,4.973719596862793],"pipeline_single":[{"label":"The evidence does not establish either","score":0.8755491971969604}],"pipeline_multi":[{"label":"The evidence establishes the opposite","score":0.9533811211585999},{"label":"The evidence does not establish either","score":0.9931301474571228}]},{"id":"semif_020","source":"semif","text":"During a puppet show, a character announces the discovery of a dragon egg. The production note states this is fictional and no real egg was discovered.","prompt":"Assess the claim: the egg discovery was fictional.","labels":["The evidence establishes the opposite","The evidence does not establish either","The evidence establishes the claim"],"ids":[50281,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,253,7238,8900,369,29934,15,10457,247,47717,921,13,247,1894,43076,253,8900,273,247,22159,7238,15,380,3275,3877,3054,436,310,29934,285,642,1524,7238,369,6888,15,50282],"label_positions":[1,7,14],"window":128,"logits":[2.032954454421997,4.675543785095215,0.6975498199462891],"pipeline_single":[{"label":"The evidence does not establish either","score":0.9175154566764832}],"pipeline_multi":[{"label":"The evidence establishes the opposite","score":0.884213924407959},{"label":"The evidence does not establish either","score":0.9907655715942383},{"label":"The evidence establishes the claim","score":0.6676443219184875}]},{"id":"semif_021","source":"semif","text":"During a puppet show, a character announces the discovery of a dragon egg. The production note states this is fictional and no real egg was discovered.","prompt":"Assess the claim: a real egg was discovered.","labels":["The evidence establishes the claim","The evidence establishes the opposite","The evidence does not establish either"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50369,2903,405,253,1750,27,247,1524,7238,369,6888,15,10457,247,47717,921,13,247,1894,43076,253,8900,273,247,22159,7238,15,380,3275,3877,3054,436,310,29934,285,642,1524,7238,369,6888,15,50282],"label_positions":[1,7,13],"window":128,"logits":[-2.061401128768921,1.391658067703247,2.916720151901245],"pipeline_single":[{"label":"The evidence does not establish either","score":0.8166635036468506}],"pipeline_multi":[{"label":"The evidence establishes the opposite","score":0.8008567690849304},{"label":"The evidence does not establish either","score":0.9486668109893799}]},{"id":"semif_022","source":"semif","text":"The note describes a real bird egg discovered outside a performance and expressly says the discovery was not fictional.","prompt":"Assess the claim: the egg discovery was fictional.","labels":["The evidence establishes the claim","The evidence establishes the opposite","The evidence does not establish either"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50369,2903,405,253,1750,27,253,7238,8900,369,29934,15,510,3877,8631,247,1524,12621,7238,6888,3345,247,3045,285,20251,2296,253,8900,369,417,29934,15,50282],"label_positions":[1,7,13],"window":128,"logits":[3.0581066608428955,-0.45177605748176575,1.4598743915557861],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.8115867972373962}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9551312327384949},{"label":"The evidence does not establish either","score":0.8115134239196777}]},{"id":"semif_023","source":"semif","text":"A note mentions an egg without describing a discovery or whether the account is fictional.","prompt":"Assess the claim: the egg discovery was fictional.","labels":["The evidence does not establish either","The evidence establishes the claim","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,253,7238,8900,369,29934,15,34,3877,25957,271,7238,1293,12930,247,8900,390,1880,253,2395,310,29934,15,50282],"label_positions":[1,8,14],"window":128,"logits":[0.6688317656517029,1.2208884954452515,-0.8068892359733582],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.5856885313987732}],"pipeline_multi":[{"label":"The evidence does not establish either","score":0.6612415313720703},{"label":"The evidence establishes the claim","score":0.7722198367118835}]},{"id":"semif_024","source":"semif","text":"The architect permits reproducing a plan in an internal training booklet and expressly forbids selling copies.","prompt":"Sell copies only with the architect's sales permission. May copies be sold?","labels":["The supplied information does not settle whether the rule permits the action","The stated rule prohibits the action","The stated rule permits the action"],"ids":[50281,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50369,322,437,10125,760,342,253,6805,434,6224,9214,15,2552,10125,320,4211,32,510,6805,16000,39306,247,2098,275,271,4812,3733,1984,1059,285,20251,17163,2352,10156,10125,15,50282],"label_positions":[1,14,21],"window":128,"logits":[1.378990888595581,4.383742332458496,-2.889841318130493],"pipeline_single":[{"label":"The stated rule prohibits the action","score":0.95215904712677}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.7988288998603821},{"label":"The stated rule prohibits the action","score":0.9876751899719238}]},{"id":"semif_025","source":"semif","text":"The architect permits reproducing a plan in an internal training booklet and expressly forbids selling copies.","prompt":"Internal training reproduction is allowed when the architect permits that use. May the plan appear in the training booklet?","labels":["The stated rule prohibits the action","The stated rule permits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,21074,3733,21068,310,4136,672,253,6805,16000,326,897,15,2552,253,2098,3176,275,253,3733,1984,1059,32,510,6805,16000,39306,247,2098,275,271,4812,3733,1984,1059,285,20251,17163,2352,10156,10125,15,50282],"label_positions":[1,8,15],"window":128,"logits":[0.6873278021812439,3.4085030555725098,-1.2106269598007202],"pipeline_single":[{"label":"The stated rule permits the action","score":0.9296629428863525}],"pipeline_multi":[{"label":"The stated rule prohibits the action","score":0.6653721928596497},{"label":"The stated rule permits the action","score":0.9679692387580872}]},{"id":"semif_026","source":"semif","text":"The architect expressly permits selling copies of the plan.","prompt":"Sell copies only with the architect's sales permission. May copies be sold?","labels":["The stated rule prohibits the action","The supplied information does not settle whether the rule permits the action","The stated rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,16000,253,2250,50369,322,437,10125,760,342,253,6805,434,6224,9214,15,2552,10125,320,4211,32,510,6805,20251,16000,10156,10125,273,253,2098,15,50282],"label_positions":[1,8,21],"window":128,"logits":[-2.5814249515533447,-3.395770311355591,2.501614809036255],"pipeline_single":[{"label":"The stated rule permits the action","score":0.9911317229270935}],"pipeline_multi":[{"label":"The stated rule permits the action","score":0.9242549538612366}]},{"id":"semif_027","source":"semif","text":"An architect's permission letter exists, but the uses it allows are omitted.","prompt":"Sell copies only with the architect's sales permission. May copies be sold?","labels":["The supplied information does not settle whether the rule permits the action","The stated rule permits the action","The stated rule prohibits the action"],"ids":[50281,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50369,322,437,10125,760,342,253,6805,434,6224,9214,15,2552,10125,320,4211,32,1145,6805,434,9214,4857,4961,13,533,253,4648,352,4483,403,11035,15,50282],"label_positions":[1,14,21],"window":128,"logits":[7.377035617828369,-4.477917194366455,1.2323999404907227],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9978525638580322}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9993749260902405},{"label":"The stated rule prohibits the action","score":0.7742383480072021}]},{"id":"semif_028","source":"semif","text":"The guide completed first-aid training but not mountain-navigation training.","prompt":"The first-aid badge requires only first-aid training. May this guide receive it?","labels":["The stated rule permits the action","The supplied information does not settle whether the rule permits the action","The stated rule prohibits the action"],"ids":[50281,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50369,380,806,14,13774,32741,4419,760,806,14,13774,3733,15,2552,436,7102,4763,352,32,510,7102,6312,806,14,13774,3733,533,417,11129,14,37336,3733,15,50282],"label_positions":[1,8,21],"window":128,"logits":[-6.1405181884765625,5.657013893127441,0.6606237292289734],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9932757616043091}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9965192079544067},{"label":"The stated rule prohibits the action","score":0.659400463104248}]},{"id":"semif_029","source":"semif","text":"The guide completed first-aid training but not mountain-navigation training.","prompt":"Under the alternative rule, the badge requires both first-aid and mountain-navigation training. May this guide receive it?","labels":["The stated rule permits the action","The stated rule prohibits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,6166,253,5795,4086,13,253,32741,4419,1097,806,14,13774,285,11129,14,37336,3733,15,2552,436,7102,4763,352,32,510,7102,6312,806,14,13774,3733,533,417,11129,14,37336,3733,15,50282],"label_positions":[1,8,15],"window":128,"logits":[-7.949103355407715,0.13502924144268036,5.12271785736084],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.993222713470459}],"pipeline_multi":[{"label":"The stated rule prohibits the action","score":0.5337061285972595},{"label":"The supplied information does not settle whether the rule permits the action","score":0.9940755367279053}]},{"id":"semif_030","source":"semif","text":"The guide completed mountain-navigation training but not first-aid training.","prompt":"The first-aid badge requires only first-aid training. May this guide receive it?","labels":["The stated rule prohibits the action","The supplied information does not settle whether the rule permits the action","The stated rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,16000,253,2250,50369,380,806,14,13774,32741,4419,760,806,14,13774,3733,15,2552,436,7102,4763,352,32,510,7102,6312,11129,14,37336,3733,533,417,806,14,13774,3733,15,50282],"label_positions":[1,8,21],"window":128,"logits":[2.971574068069458,5.806873321533203,-6.782646656036377],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9445507526397705}],"pipeline_multi":[{"label":"The stated rule prohibits the action","score":0.9512733221054077},{"label":"The supplied information does not settle whether the rule permits the action","score":0.9970021843910217}]},{"id":"semif_031","source":"semif","text":"The guide registered for training, but completion information is not supplied.","prompt":"The first-aid badge requires only first-aid training. May this guide receive it?","labels":["The stated rule prohibits the action","The supplied information does not settle whether the rule permits the action","The stated rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,16000,253,2250,50369,380,806,14,13774,32741,4419,760,806,14,13774,3733,15,2552,436,7102,4763,352,32,510,7102,9856,323,3733,13,533,12240,1491,310,417,12164,15,50282],"label_positions":[1,8,21],"window":128,"logits":[2.134492874145508,6.612058639526367,-2.4193670749664307],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9886497259140015}],"pipeline_multi":[{"label":"The stated rule prohibits the action","score":0.8942107558250427},{"label":"The supplied information does not settle whether the rule permits the action","score":0.9986577033996582}]},{"id":"semif_032","source":"semif","text":"The designer approves making a sample badge but expressly withholds approval for mass production.","prompt":"Mass production is allowed only after mass-production approval. May it begin?","labels":["The stated rule permits the action","The supplied information does not settle whether the rule permits the action","The stated rule prohibits the action"],"ids":[50281,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50369,7532,3275,310,4136,760,846,2280,14,25307,9612,15,2552,352,3135,32,510,17039,1192,1634,2403,247,3410,32741,533,20251,342,15532,9612,323,2280,3275,15,50282],"label_positions":[1,8,21],"window":128,"logits":[-3.62551212310791,4.405926704406738,-0.5778872966766357],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9928781390190125}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9879423975944519}]},{"id":"semif_033","source":"semif","text":"The designer approves making a sample badge but expressly withholds approval for mass production.","prompt":"A sample may be made when sample production is approved. May the sample be made?","labels":["The stated rule permits the action","The supplied information does not settle whether the rule permits the action","The stated rule prohibits the action"],"ids":[50281,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50369,329,3410,778,320,1160,672,3410,3275,310,7012,15,2552,253,3410,320,1160,32,510,17039,1192,1634,2403,247,3410,32741,533,20251,342,15532,9612,323,2280,3275,15,50282],"label_positions":[1,8,21],"window":128,"logits":[-3.1763699054718018,3.504011869430542,-1.0536904335021973],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9883948564529419}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9708016514778137}]},{"id":"semif_034","source":"semif","text":"The designer explicitly approves mass production of the badge.","prompt":"Mass production is allowed only after mass-production approval. May it begin?","labels":["The stated rule prohibits the action","The supplied information does not settle whether the rule permits the action","The stated rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,16000,253,2250,50369,7532,3275,310,4136,760,846,2280,14,25307,9612,15,2552,352,3135,32,510,17039,11120,1192,1634,2280,3275,273,253,32741,15,50282],"label_positions":[1,8,21],"window":128,"logits":[-0.6428121328353882,2.5843141078948975,-1.1865311861038208],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9409959316253662}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9298452138900757}]},{"id":"semif_035","source":"semif","text":"The designer issued a decision but its production scope is unavailable.","prompt":"Mass production is allowed only after mass-production approval. May it begin?","labels":["The supplied information does not settle whether the rule permits the action","The stated rule permits the action","The stated rule prohibits the action"],"ids":[50281,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50369,7532,3275,310,4136,760,846,2280,14,25307,9612,15,2552,352,3135,32,510,17039,6808,247,3061,533,697,3275,7990,310,29356,15,50282],"label_positions":[1,14,21],"window":128,"logits":[6.592842102050781,-3.9263999462127686,1.9331576824188232],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9905927777290344}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9986316561698914},{"label":"The stated rule prohibits the action","score":0.8735984563827515}]},{"id":"semif_036","source":"semif","text":"The visitor's wristband covers the sculpture garden and expressly excludes the rooftop terrace.","prompt":"A wristband permits entry exactly to the areas it covers. May the visitor enter the sculpture garden?","labels":["The stated rule prohibits the action","The supplied information does not settle whether the rule permits the action","The stated rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,16000,253,2250,50369,329,20051,4152,16000,5857,4555,281,253,3672,352,10949,15,2552,253,23218,4901,253,34486,10329,32,510,23218,434,20051,4152,10949,253,34486,10329,285,20251,43337,253,43271,412,36118,15,50282],"label_positions":[1,8,21],"window":128,"logits":[-3.2673285007476807,2.0901215076446533,0.0415189154446125],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.8821236491203308}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.8899393081665039},{"label":"The stated rule permits the action","score":0.5103782415390015}]},{"id":"semif_037","source":"semif","text":"The visitor's wristband covers the sculpture garden and expressly excludes the rooftop terrace.","prompt":"A wristband permits entry exactly to the areas it covers. May the visitor enter the rooftop terrace?","labels":["The supplied information does not settle whether the rule permits the action","The stated rule prohibits the action","The stated rule permits the action"],"ids":[50281,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50369,329,20051,4152,16000,5857,4555,281,253,3672,352,10949,15,2552,253,23218,4901,253,43271,412,36118,32,510,23218,434,20051,4152,10949,253,34486,10329,285,20251,43337,253,43271,412,36118,15,50282],"label_positions":[1,14,21],"window":128,"logits":[1.699424386024475,0.6422805786132812,-1.8512396812438965],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.7266637086868286}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.845459520816803},{"label":"The stated rule prohibits the action","score":0.6552687883377075}]},{"id":"semif_038","source":"semif","text":"The wristband expressly excludes the sculpture garden and covers only the rooftop terrace.","prompt":"A wristband permits entry exactly to the areas it covers. May the visitor enter the sculpture garden?","labels":["The stated rule prohibits the action","The stated rule permits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,329,20051,4152,16000,5857,4555,281,253,3672,352,10949,15,2552,253,23218,4901,253,34486,10329,32,510,20051,4152,20251,43337,253,34486,10329,285,10949,760,253,43271,412,36118,15,50282],"label_positions":[1,8,15],"window":128,"logits":[-0.8321740031242371,-1.537496566772461,4.1966447830200195],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9903145432472229}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9851770401000977}]},{"id":"semif_039","source":"semif","text":"The visitor has a wristband but its covered areas are not supplied.","prompt":"A wristband permits entry exactly to the areas it covers. May the visitor enter the sculpture garden?","labels":["The supplied information does not settle whether the rule permits the action","The stated rule permits the action","The stated rule prohibits the action"],"ids":[50281,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50369,329,20051,4152,16000,5857,4555,281,253,3672,352,10949,15,2552,253,23218,4901,253,34486,10329,32,510,23218,556,247,20051,4152,533,697,6107,3672,403,417,12164,15,50282],"label_positions":[1,14,21],"window":128,"logits":[6.758432865142822,-0.5863232016563416,-2.202714204788208],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9992263317108154}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9988402724266052}]},{"id":"semif_040","source":"semif","text":"The account owner permits changing the display name but expressly forbids changing the recovery email.","prompt":"Change an account field only when the owner authorizes changing that field. May the recovery email be changed?","labels":["The stated rule prohibits the action","The stated rule permits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,15836,271,2395,1673,760,672,253,7302,2488,4219,6890,326,1673,15,2552,253,7355,4579,320,4391,32,510,2395,7302,16000,6890,253,3148,1416,533,20251,17163,2352,6890,253,7355,4579,15,50282],"label_positions":[1,8,15],"window":128,"logits":[3.2905328273773193,-2.650879383087158,4.811682224273682],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.8203211426734924}],"pipeline_multi":[{"label":"The stated rule prohibits the action","score":0.9641026258468628},{"label":"The supplied information does not settle whether the rule permits the action","score":0.9919314980506897}]},{"id":"semif_041","source":"semif","text":"The account owner permits changing the display name but expressly forbids changing the recovery email.","prompt":"Change an account field only when the owner authorizes changing that field. May the display name be changed?","labels":["The supplied information does not settle whether the rule permits the action","The stated rule permits the action","The stated rule prohibits the action"],"ids":[50281,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50369,15836,271,2395,1673,760,672,253,7302,2488,4219,6890,326,1673,15,2552,253,3148,1416,320,4391,32,510,2395,7302,16000,6890,253,3148,1416,533,20251,17163,2352,6890,253,7355,4579,15,50282],"label_positions":[1,14,21],"window":128,"logits":[4.694452285766602,-1.1570820808410645,1.2212326526641846],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9672186374664307}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9909370541572571},{"label":"The stated rule prohibits the action","score":0.7722803950309753}]},{"id":"semif_042","source":"semif","text":"The owner expressly permits changing the recovery email.","prompt":"Change an account field only when the owner authorizes changing that field. May the recovery email be changed?","labels":["The supplied information does not settle whether the rule permits the action","The stated rule prohibits the action","The stated rule permits the action"],"ids":[50281,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50369,15836,271,2395,1673,760,672,253,7302,2488,4219,6890,326,1673,15,2552,253,7355,4579,320,4391,32,510,7302,20251,16000,6890,253,7355,4579,15,50282],"label_positions":[1,14,21],"window":128,"logits":[-1.468812108039856,-2.998877763748169,0.843748152256012],"pipeline_single":[{"label":"The stated rule permits the action","score":0.8925027847290039}],"pipeline_multi":[{"label":"The stated rule permits the action","score":0.699254035949707}]},{"id":"semif_043","source":"semif","text":"The owner requested an account update, but the fields to be changed are omitted.","prompt":"Change an account field only when the owner authorizes changing that field. May the recovery email be changed?","labels":["The stated rule permits the action","The stated rule prohibits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,15836,271,2395,1673,760,672,253,7302,2488,4219,6890,326,1673,15,2552,253,7355,4579,320,4391,32,510,7302,9521,271,2395,5731,13,533,253,4910,281,320,4391,403,11035,15,50282],"label_positions":[1,8,15],"window":128,"logits":[-6.27384090423584,1.2875490188598633,6.262434959411621],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9931344985961914}],"pipeline_multi":[{"label":"The stated rule prohibits the action","score":0.7837320566177368},{"label":"The supplied information does not settle whether the rule permits the action","score":0.9980970025062561}]},{"id":"semif_044","source":"semif","text":"The applicant lives in the valley but works outside it.","prompt":"A resident's pass requires living in the valley and has no workplace restriction. May it be issued?","labels":["The stated rule prohibits the action","The stated rule permits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,329,14544,434,1509,4419,3811,275,253,17836,285,556,642,21853,12400,15,2552,352,320,6808,32,510,22123,4852,275,253,17836,533,2987,3345,352,15,50282],"label_positions":[1,8,15],"window":128,"logits":[-2.147202491760254,-3.2518999576568604,2.1427559852600098],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9820806980133057}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.8949899077415466}]},{"id":"semif_045","source":"semif","text":"The applicant lives in the valley but works outside it.","prompt":"Under the alternative rule, a pass requires working in the valley; residence alone is insufficient. May it be issued?","labels":["The stated rule prohibits the action","The stated rule permits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,6166,253,5795,4086,13,247,1509,4419,2444,275,253,17836,28,12913,3815,310,12497,15,2552,352,320,6808,32,510,22123,4852,275,253,17836,533,2987,3345,352,15,50282],"label_positions":[1,8,15],"window":128,"logits":[0.7889171242713928,-3.937140941619873,4.685628890991211],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9799228310585022}],"pipeline_multi":[{"label":"The stated rule prohibits the action","score":0.6875987648963928},{"label":"The supplied information does not settle whether the rule permits the action","score":0.9908574223518372}]},{"id":"semif_046","source":"semif","text":"The applicant lives outside the valley and works inside it.","prompt":"A resident's pass requires living in the valley and has no workplace restriction. May it be issued?","labels":["The stated rule permits the action","The stated rule prohibits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,329,14544,434,1509,4419,3811,275,253,17836,285,556,642,21853,12400,15,2552,352,320,6808,32,510,22123,4852,3345,253,17836,285,2987,3304,352,15,50282],"label_positions":[1,8,15],"window":128,"logits":[-2.564985752105713,-2.281026840209961,0.5710764527320862],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9081197381019592}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.6390115022659302}]},{"id":"semif_047","source":"semif","text":"The applicant supplies a name but no home or work location.","prompt":"A resident's pass requires living in the valley and has no workplace restriction. May it be issued?","labels":["The stated rule prohibits the action","The stated rule permits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,329,14544,434,1509,4419,3811,275,253,17836,285,556,642,21853,12400,15,2552,352,320,6808,32,510,22123,13191,247,1416,533,642,1728,390,789,4328,15,50282],"label_positions":[1,8,15],"window":128,"logits":[-1.493224024772644,-3.725137233734131,3.3287315368652344],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9911637306213379}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9654014706611633}]},{"id":"semif_048","source":"semif","text":"Candidate A: The florist confirms that the wreath was delivered. Candidate B: The florist offers to deliver a wreath tomorrow.","prompt":"Choose the candidate reporting completed delivery.","labels":["Candidate B","Candidate A","Neither candidate supplies the requested evidence"],"ids":[50281,50368,330,33524,378,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50369,28890,253,7431,9610,6312,6742,15,36,33524,329,27,380,49716,382,23849,326,253,39137,506,369,8549,15,330,33524,378,27,380,49716,382,6131,281,7257,247,39137,506,10873,15,50282],"label_positions":[1,5,9],"window":128,"logits":[4.883325576782227,4.256973743438721,-8.744479179382324],"pipeline_single":[{"label":"Candidate B","score":0.6516613364219666}],"pipeline_multi":[{"label":"Candidate B","score":0.9924851059913635},{"label":"Candidate A","score":0.9860326647758484}]},{"id":"semif_049","source":"semif","text":"Candidate A: The florist confirms that the wreath was delivered. Candidate B: The florist offers to deliver a wreath tomorrow.","prompt":"Choose the candidate offering a future delivery.","labels":["Candidate B","Neither candidate supplies the requested evidence","Candidate A"],"ids":[50281,50368,330,33524,378,50368,17106,7431,13191,253,9521,1941,50368,330,33524,329,50369,28890,253,7431,9159,247,2852,6742,15,36,33524,329,27,380,49716,382,23849,326,253,39137,506,369,8549,15,330,33524,378,27,380,49716,382,6131,281,7257,247,39137,506,10873,15,50282],"label_positions":[1,5,12],"window":128,"logits":[3.8036396503448486,-9.786094665527344,4.502560138702393],"pipeline_single":[{"label":"Candidate A","score":0.6679481267929077}],"pipeline_multi":[{"label":"Candidate B","score":0.9781965017318726},{"label":"Candidate A","score":0.9890407919883728}]},{"id":"semif_050","source":"semif","text":"Candidate A: I can deliver a wreath tomorrow. Candidate B: The wreath was delivered.","prompt":"Choose the candidate reporting completed delivery.","labels":["Neither candidate supplies the requested evidence","Candidate B","Candidate A"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,378,50368,330,33524,329,50369,28890,253,7431,9610,6312,6742,15,36,33524,329,27,309,476,7257,247,39137,506,10873,15,330,33524,378,27,380,39137,506,369,8549,15,50282],"label_positions":[1,8,12],"window":128,"logits":[-8.772307395935059,6.455751419067383,4.233672142028809],"pipeline_single":[{"label":"Candidate B","score":0.9022145867347717}],"pipeline_multi":[{"label":"Candidate B","score":0.9984310269355774},{"label":"Candidate A","score":0.9857081770896912}]},{"id":"semif_051","source":"semif","text":"Candidate A: The florist gives an address. Candidate B: The wreath contains lilies.","prompt":"Choose the candidate reporting completed delivery.","labels":["Candidate B","Candidate A","Neither candidate supplies the requested evidence"],"ids":[50281,50368,330,33524,378,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50369,28890,253,7431,9610,6312,6742,15,36,33524,329,27,380,49716,382,4245,271,2953,15,330,33524,378,27,380,39137,506,4428,298,5348,15,50282],"label_positions":[1,5,9],"window":128,"logits":[4.784646511077881,3.351621389389038,-7.5651679039001465],"pipeline_single":[{"label":"Candidate B","score":0.8073694109916687}],"pipeline_multi":[{"label":"Candidate B","score":0.991712212562561},{"label":"Candidate A","score":0.9661579132080078}]},{"id":"semif_052","source":"semif","text":"Candidate A: The customer asks how an engraving would look but explicitly declines having it engraved yet. Candidate B: The customer instructs the shop to engrave the ring.","prompt":"Choose the candidate authorizing engraving.","labels":["Neither candidate supplies the requested evidence","Candidate B","Candidate A"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,378,50368,330,33524,329,50369,28890,253,7431,49931,38683,1382,15,36,33524,329,27,380,7731,12325,849,271,38683,1382,651,1007,533,11120,34044,1907,352,38683,1272,2568,15,330,33524,378,27,380,7731,9618,84,253,8979,281,38683,306,253,5818,15,50282],"label_positions":[1,8,12],"window":128,"logits":[-5.479363441467285,2.705578088760376,3.3174326419830322],"pipeline_single":[{"label":"Candidate A","score":0.6483001708984375}],"pipeline_multi":[{"label":"Candidate B","score":0.9373549818992615},{"label":"Candidate A","score":0.9650219678878784}]},{"id":"semif_053","source":"semif","text":"Candidate A: The customer asks how an engraving would look but explicitly declines having it engraved yet. Candidate B: The customer instructs the shop to engrave the ring.","prompt":"Choose the candidate asking only for information while withholding authorization.","labels":["Neither candidate supplies the requested evidence","Candidate A","Candidate B"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,329,50368,330,33524,378,50369,28890,253,7431,7004,760,323,1491,1223,40271,26239,15,36,33524,329,27,380,7731,12325,849,271,38683,1382,651,1007,533,11120,34044,1907,352,38683,1272,2568,15,330,33524,378,27,380,7731,9618,84,253,8979,281,38683,306,253,5818,15,50282],"label_positions":[1,8,12],"window":128,"logits":[-4.933750152587891,3.0496621131896973,3.768536329269409],"pipeline_single":[{"label":"Candidate B","score":0.6722838878631592}],"pipeline_multi":[{"label":"Candidate A","score":0.9547678828239441},{"label":"Candidate B","score":0.9774351119995117}]},{"id":"semif_054","source":"semif","text":"Candidate A: Please engrave the ring. Candidate B: Show me how it would look, but do not engrave it yet.","prompt":"Choose the candidate authorizing engraving.","labels":["Neither candidate supplies the requested evidence","Candidate B","Candidate A"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,378,50368,330,33524,329,50369,28890,253,7431,49931,38683,1382,15,36,33524,329,27,7764,38683,306,253,5818,15,330,33524,378,27,10684,479,849,352,651,1007,13,533,513,417,38683,306,352,2568,15,50282],"label_positions":[1,8,12],"window":128,"logits":[6.199556827545166,-0.39292606711387634,1.9108555316925049],"pipeline_single":[{"label":"Neither candidate supplies the requested evidence","score":0.9851309657096863}],"pipeline_multi":[{"label":"Neither candidate supplies the requested evidence","score":0.9979737401008606},{"label":"Candidate A","score":0.8711152076721191}]},{"id":"semif_055","source":"semif","text":"Candidate A: The customer gives a name. Candidate B: The ring is silver.","prompt":"Choose the candidate authorizing engraving.","labels":["Candidate B","Candidate A","Neither candidate supplies the requested evidence"],"ids":[50281,50368,330,33524,378,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50369,28890,253,7431,49931,38683,1382,15,36,33524,329,27,380,7731,4245,247,1416,15,330,33524,378,27,380,5818,310,9711,15,50282],"label_positions":[1,5,9],"window":128,"logits":[5.022441864013672,2.2736854553222656,-8.355561256408691],"pipeline_single":[{"label":"Candidate B","score":0.9398416876792908}],"pipeline_multi":[{"label":"Candidate B","score":0.99345463514328},{"label":"Candidate A","score":0.9066741466522217}]},{"id":"semif_056","source":"semif","text":"Candidate A: The note records that the completed insulation test passed. Candidate B: The note lists insulation-test steps but says no test was run.","prompt":"Choose the candidate reporting an observed test result.","labels":["Neither candidate supplies the requested evidence","Candidate A","Candidate B"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,329,50368,330,33524,378,50369,28890,253,7431,9610,271,2540,1071,906,15,36,33524,329,27,380,3877,5861,326,253,6312,29491,1071,4817,15,330,33524,378,27,380,3877,10894,29491,14,2566,5018,533,2296,642,1071,369,1408,15,50282],"label_positions":[1,8,12],"window":128,"logits":[6.487376689910889,2.3970603942871094,1.4234811067581177],"pipeline_single":[{"label":"Neither candidate supplies the requested evidence","score":0.9774647951126099}],"pipeline_multi":[{"label":"Neither candidate supplies the requested evidence","score":0.9984797835350037},{"label":"Candidate A","score":0.9166028499603271},{"label":"Candidate B","score":0.8058835864067078}]},{"id":"semif_057","source":"semif","text":"Candidate A: The note records that the completed insulation test passed. Candidate B: The note lists insulation-test steps but says no test was run.","prompt":"Choose the candidate containing only an unexecuted test procedure.","labels":["Candidate B","Candidate A","Neither candidate supplies the requested evidence"],"ids":[50281,50368,330,33524,378,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50369,28890,253,7431,4508,760,271,440,9993,4525,1071,5199,15,36,33524,329,27,380,3877,5861,326,253,6312,29491,1071,4817,15,330,33524,378,27,380,3877,10894,29491,14,2566,5018,533,2296,642,1071,369,1408,15,50282],"label_positions":[1,5,9],"window":128,"logits":[2.235140323638916,2.794227123260498,5.667917251586914],"pipeline_single":[{"label":"Neither candidate supplies the requested evidence","score":0.9184530973434448}],"pipeline_multi":[{"label":"Candidate B","score":0.9033610224723816},{"label":"Candidate A","score":0.9423630833625793},{"label":"Neither candidate supplies the requested evidence","score":0.9965568780899048}]},{"id":"semif_058","source":"semif","text":"Candidate A: Here are insulation-test steps; no test was run. Candidate B: The completed insulation test passed.","prompt":"Choose the candidate reporting an observed test result.","labels":["Neither candidate supplies the requested evidence","Candidate B","Candidate A"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,378,50368,330,33524,329,50369,28890,253,7431,9610,271,2540,1071,906,15,36,33524,329,27,3856,403,29491,14,2566,5018,28,642,1071,369,1408,15,330,33524,378,27,380,6312,29491,1071,4817,15,50282],"label_positions":[1,8,12],"window":128,"logits":[-0.9742915034294128,3.784067392349243,3.189027786254883],"pipeline_single":[{"label":"Candidate B","score":0.6409761309623718}],"pipeline_multi":[{"label":"Candidate B","score":0.9777751564979553},{"label":"Candidate A","score":0.960419237613678}]},{"id":"semif_059","source":"semif","text":"Candidate A: The cable is red. Candidate B: The tester is in a drawer.","prompt":"Choose the candidate reporting an observed test result.","labels":["Neither candidate supplies the requested evidence","Candidate A","Candidate B"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,329,50368,330,33524,378,50369,28890,253,7431,9610,271,2540,1071,906,15,36,33524,329,27,380,10856,310,2502,15,330,33524,378,27,380,49568,310,275,247,31579,15,50282],"label_positions":[1,8,12],"window":128,"logits":[-6.961508750915527,3.9417707920074463,4.5318922996521],"pipeline_single":[{"label":"Candidate B","score":0.6433888077735901}],"pipeline_multi":[{"label":"Candidate A","score":0.9809558987617493},{"label":"Candidate B","score":0.9893542528152466}]},{"id":"semif_060","source":"semif","text":"Candidate A: The editor quotes a proposal for a paywall only to argue against it. Candidate B: The editor endorses introducing a paywall.","prompt":"Choose the candidate supporting a paywall.","labels":["Candidate B","Candidate A","Neither candidate supplies the requested evidence"],"ids":[50281,50368,330,33524,378,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50369,28890,253,7431,8109,247,2075,12081,15,36,33524,329,27,380,8121,19101,247,10419,323,247,2075,12081,760,281,9059,1411,352,15,330,33524,378,27,380,8121,990,11092,16984,247,2075,12081,15,50282],"label_positions":[1,5,9],"window":128,"logits":[4.741189956665039,3.2190299034118652,-7.740980625152588],"pipeline_single":[{"label":"Candidate B","score":0.8208537101745605}],"pipeline_multi":[{"label":"Candidate B","score":0.9913472533226013},{"label":"Candidate A","score":0.9615440964698792}]},{"id":"semif_061","source":"semif","text":"Candidate A: The editor quotes a proposal for a paywall only to argue against it. Candidate B: The editor endorses introducing a paywall.","prompt":"Choose the candidate opposing a paywall.","labels":["Candidate A","Neither candidate supplies the requested evidence","Candidate B"],"ids":[50281,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50368,330,33524,378,50369,28890,253,7431,18327,247,2075,12081,15,36,33524,329,27,380,8121,19101,247,10419,323,247,2075,12081,760,281,9059,1411,352,15,330,33524,378,27,380,8121,990,11092,16984,247,2075,12081,15,50282],"label_positions":[1,5,12],"window":128,"logits":[1.3529258966445923,-7.704680442810059,4.69805908203125],"pipeline_single":[{"label":"Candidate B","score":0.965941309928894}],"pipeline_multi":[{"label":"Candidate A","score":0.7946075201034546},{"label":"Candidate B","score":0.9909693598747253}]},{"id":"semif_062","source":"semif","text":"Candidate A: I endorse introducing a paywall. Candidate B: I reject introducing a paywall.","prompt":"Choose the candidate supporting a paywall.","labels":["Neither candidate supplies the requested evidence","Candidate A","Candidate B"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,329,50368,330,33524,378,50369,28890,253,7431,8109,247,2075,12081,15,36,33524,329,27,309,18883,16984,247,2075,12081,15,330,33524,378,27,309,12009,16984,247,2075,12081,15,50282],"label_positions":[1,8,12],"window":128,"logits":[1.4619450569152832,2.2437217235565186,3.486752986907959],"pipeline_single":[{"label":"Candidate B","score":0.7039638161659241}],"pipeline_multi":[{"label":"Neither candidate supplies the requested evidence","score":0.8118299245834351},{"label":"Candidate A","score":0.9041076302528381},{"label":"Candidate B","score":0.9703084826469421}]},{"id":"semif_063","source":"semif","text":"Candidate A: The editor names the magazine. Candidate B: The website has a blue header.","prompt":"Choose the candidate supporting a paywall.","labels":["Candidate B","Candidate A","Neither candidate supplies the requested evidence"],"ids":[50281,50368,330,33524,378,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50369,28890,253,7431,8109,247,2075,12081,15,36,33524,329,27,380,8121,4454,253,11338,15,330,33524,378,27,380,4422,556,247,4797,10478,15,50282],"label_positions":[1,5,9],"window":128,"logits":[4.426358222961426,2.703251361846924,-6.654264450073242],"pipeline_single":[{"label":"Candidate B","score":0.8485175371170044}],"pipeline_multi":[{"label":"Candidate B","score":0.988183319568634},{"label":"Candidate A","score":0.937218189239502}]},{"id":"semif_064","source":"semif","text":"Candidate A: The owner asks to reseal the existing window while keeping its frame. Candidate B: The owner asks to remove the window and fit a complete replacement.","prompt":"Choose the candidate asking to repair the existing window.","labels":["Neither candidate supplies the requested evidence","Candidate A","Candidate B"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,329,50368,330,33524,378,50369,28890,253,7431,7004,281,8706,253,5368,3497,15,36,33524,329,27,380,7302,12325,281,1927,267,253,5368,3497,1223,7562,697,3665,15,330,33524,378,27,380,7302,12325,281,5386,253,3497,285,4944,247,3426,5407,15,50282],"label_positions":[1,8,12],"window":128,"logits":[-8.056711196899414,2.881953477859497,4.3380327224731445],"pipeline_single":[{"label":"Candidate B","score":0.810929536819458}],"pipeline_multi":[{"label":"Candidate A","score":0.9469470381736755},{"label":"Candidate B","score":0.987106204032898}]},{"id":"semif_065","source":"semif","text":"Candidate A: The owner asks to reseal the existing window while keeping its frame. Candidate B: The owner asks to remove the window and fit a complete replacement.","prompt":"Choose the candidate asking for complete replacement.","labels":["Neither candidate supplies the requested evidence","Candidate A","Candidate B"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,329,50368,330,33524,378,50369,28890,253,7431,7004,323,3426,5407,15,36,33524,329,27,380,7302,12325,281,1927,267,253,5368,3497,1223,7562,697,3665,15,330,33524,378,27,380,7302,12325,281,5386,253,3497,285,4944,247,3426,5407,15,50282],"label_positions":[1,8,12],"window":128,"logits":[-7.81072473526001,3.5161819458007812,4.9680962562561035],"pipeline_single":[{"label":"Candidate B","score":0.8102909922599792}],"pipeline_multi":[{"label":"Candidate A","score":0.9711446762084961},{"label":"Candidate B","score":0.9930917024612427}]},{"id":"semif_066","source":"semif","text":"Candidate A: Remove the window and install a replacement. Candidate B: Reseal the existing window and keep its frame.","prompt":"Choose the candidate asking to repair the existing window.","labels":["Neither candidate supplies the requested evidence","Candidate A","Candidate B"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,329,50368,330,33524,378,50369,28890,253,7431,7004,281,8706,253,5368,3497,15,36,33524,329,27,20004,253,3497,285,3334,247,5407,15,330,33524,378,27,2213,70,267,253,5368,3497,285,1978,697,3665,15,50282],"label_positions":[1,8,12],"window":128,"logits":[-7.5698957443237305,4.368438720703125,6.510221481323242],"pipeline_single":[{"label":"Candidate B","score":0.8948977589607239}],"pipeline_multi":[{"label":"Candidate A","score":0.9874875545501709},{"label":"Candidate B","score":0.9985139966011047}]},{"id":"semif_067","source":"semif","text":"Candidate A: The window faces a courtyard. Candidate B: The owner gives a postcode.","prompt":"Choose the candidate asking to repair the existing window.","labels":["Neither candidate supplies the requested evidence","Candidate B","Candidate A"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,378,50368,330,33524,329,50369,28890,253,7431,7004,281,8706,253,5368,3497,15,36,33524,329,27,380,3497,9365,247,33924,15,330,33524,378,27,380,7302,4245,247,1501,3211,15,50282],"label_positions":[1,8,12],"window":128,"logits":[-8.024839401245117,5.119321823120117,4.839545249938965],"pipeline_single":[{"label":"Candidate B","score":0.5694908499717712}],"pipeline_multi":[{"label":"Candidate B","score":0.9940553903579712},{"label":"Candidate A","score":0.9921514987945557}]},{"id":"semif_068","source":"semif","text":"Candidate A: The sponsor confirms receipt of a grant application but explicitly says no award decision has been made. Candidate B: The sponsor confirms that the grant was awarded.","prompt":"Choose the candidate reporting an awarded grant.","labels":["Candidate B","Candidate A","Neither candidate supplies the requested evidence"],"ids":[50281,50368,330,33524,378,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50369,28890,253,7431,9610,271,11941,4098,15,36,33524,329,27,380,28924,23849,17191,273,247,4098,2898,533,11120,2296,642,5722,3061,556,644,1160,15,330,33524,378,27,380,28924,23849,326,253,4098,369,11941,15,50282],"label_positions":[1,5,9],"window":128,"logits":[3.1644740104675293,1.8449101448059082,-8.467486381530762],"pipeline_single":[{"label":"Candidate B","score":0.789103627204895}],"pipeline_multi":[{"label":"Candidate B","score":0.9594752788543701},{"label":"Candidate A","score":0.8635283708572388}]},{"id":"semif_069","source":"semif","text":"Candidate A: The sponsor confirms receipt of a grant application but explicitly says no award decision has been made. Candidate B: The sponsor confirms that the grant was awarded.","prompt":"Choose the candidate reporting receipt with the award still undecided.","labels":["Neither candidate supplies the requested evidence","Candidate A","Candidate B"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,329,50368,330,33524,378,50369,28890,253,7431,9610,17191,342,253,5722,1335,440,31572,15,36,33524,329,27,380,28924,23849,17191,273,247,4098,2898,533,11120,2296,642,5722,3061,556,644,1160,15,330,33524,378,27,380,28924,23849,326,253,4098,369,11941,15,50282],"label_positions":[1,8,12],"window":128,"logits":[-8.33001708984375,3.4104788303375244,4.437898635864258],"pipeline_single":[{"label":"Candidate B","score":0.736413836479187}],"pipeline_multi":[{"label":"Candidate A","score":0.9680304527282715},{"label":"Candidate B","score":0.9883173108100891}]},{"id":"semif_070","source":"semif","text":"Candidate A: The grant was awarded. Candidate B: The application was received; the award remains undecided.","prompt":"Choose the candidate reporting an awarded grant.","labels":["Candidate A","Candidate B","Neither candidate supplies the requested evidence"],"ids":[50281,50368,330,33524,329,50368,330,33524,378,50368,17106,7431,13191,253,9521,1941,50369,28890,253,7431,9610,271,11941,4098,15,36,33524,329,27,380,4098,369,11941,15,330,33524,378,27,380,2898,369,2959,28,253,5722,4558,440,31572,15,50282],"label_positions":[1,5,9],"window":128,"logits":[4.739170074462891,3.694275140762329,-7.17503023147583],"pipeline_single":[{"label":"Candidate A","score":0.7397897243499756}],"pipeline_multi":[{"label":"Candidate A","score":0.9913299083709717},{"label":"Candidate B","score":0.9757378101348877}]},{"id":"semif_071","source":"semif","text":"Candidate A: The sponsor gives its name. Candidate B: The application has a reference number.","prompt":"Choose the candidate reporting an awarded grant.","labels":["Neither candidate supplies the requested evidence","Candidate A","Candidate B"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,329,50368,330,33524,378,50369,28890,253,7431,9610,271,11941,4098,15,36,33524,329,27,380,28924,4245,697,1416,15,330,33524,378,27,380,2898,556,247,3806,1180,15,50282],"label_positions":[1,8,12],"window":128,"logits":[-8.13697338104248,3.2054238319396973,5.680432319641113],"pipeline_single":[{"label":"Candidate B","score":0.9223702549934387}],"pipeline_multi":[{"label":"Candidate A","score":0.961037814617157},{"label":"Candidate B","score":0.9965994954109192}]},{"id":"semif_072","source":"semif","text":"On Monday the owner authorized scanning her notebook. On Tuesday she explicitly withdrew that authorization. The record says withdrawals cancel earlier permission, and no later permission was given.","prompt":"Assess the claim: permission to scan the notebook is currently valid.","labels":["The evidence establishes the opposite","The evidence establishes the claim","The evidence does not establish either"],"ids":[50281,50368,380,1941,25097,253,7285,50368,380,1941,25097,253,1750,50368,380,1941,1057,417,5100,2057,50369,2903,405,253,1750,27,9214,281,11017,253,24849,310,4390,3588,15,2374,7216,253,7302,14047,13733,617,24849,15,1623,7948,703,11120,29504,326,26239,15,380,1924,2296,10687,932,14002,4321,9214,13,285,642,1996,9214,369,1677,15,50282],"label_positions":[1,7,13],"window":128,"logits":[0.09187203645706177,1.7230756282806396,0.4343990981578827],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.679657518863678}],"pipeline_multi":[{"label":"The evidence establishes the opposite","score":0.5229518413543701},{"label":"The evidence establishes the claim","score":0.8485245704650879},{"label":"The evidence does not establish either","score":0.6069236397743225}]},{"id":"semif_073","source":"semif","text":"On Monday the owner authorized scanning her notebook. On Tuesday she explicitly withdrew that authorization. The record says withdrawals cancel earlier permission, and no later permission was given.","prompt":"Assess the claim: the owner gave permission on Monday.","labels":["The evidence does not establish either","The evidence establishes the opposite","The evidence establishes the claim"],"ids":[50281,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,7285,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,253,7302,3534,9214,327,7216,15,2374,7216,253,7302,14047,13733,617,24849,15,1623,7948,703,11120,29504,326,26239,15,380,1924,2296,10687,932,14002,4321,9214,13,285,642,1996,9214,369,1677,15,50282],"label_positions":[1,8,14],"window":128,"logits":[1.0607389211654663,0.7423920035362244,1.2521039247512817],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.41211622953414917}],"pipeline_multi":[{"label":"The evidence does not establish either","score":0.7428317666053772},{"label":"The evidence establishes the opposite","score":0.6775186657905579},{"label":"The evidence establishes the claim","score":0.7776638865470886}]},{"id":"semif_074","source":"semif","text":"The owner authorized scanning the notebook on Monday. The complete permission record confirms that she has not withdrawn it and it remains valid.","prompt":"Assess the claim: permission to scan the notebook is currently valid.","labels":["The evidence establishes the claim","The evidence establishes the opposite","The evidence does not establish either"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50369,2903,405,253,1750,27,9214,281,11017,253,24849,310,4390,3588,15,510,7302,14047,13733,253,24849,327,7216,15,380,3426,9214,1924,23849,326,703,556,417,26924,352,285,352,4558,3588,15,50282],"label_positions":[1,7,13],"window":128,"logits":[6.175728797912598,-3.8544304370880127,-5.906485557556152],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9999502897262573}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9979250431060791}]},{"id":"semif_075","source":"semif","text":"The owner authorized scanning on Monday. The supplied record omits all later permission changes and does not establish current validity.","prompt":"Assess the claim: permission to scan the notebook is currently valid.","labels":["The evidence establishes the claim","The evidence does not establish either","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,9214,281,11017,253,24849,310,4390,3588,15,510,7302,14047,13733,327,7216,15,380,12164,1924,7005,953,512,1996,9214,2544,285,1057,417,5100,1655,13091,15,50282],"label_positions":[1,7,14],"window":128,"logits":[1.7580947875976562,5.360621452331543,1.145432710647583],"pipeline_single":[{"label":"The evidence does not establish either","score":0.9596704244613647}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.8529708981513977},{"label":"The evidence does not establish either","score":0.9953239560127258},{"label":"The evidence establishes the opposite","score":0.7586756944656372}]},{"id":"semif_076","source":"semif","text":"The homeowner first allowed a surveyor to enter the attic. Before the visit she explicitly withdrew that permission. No later decision exists.","prompt":"Use the homeowner's latest permission decision; a withdrawal cancels the earlier grant. May the surveyor enter the attic?","labels":["The stated rule permits the action","The stated rule prohibits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,7890,253,1728,18602,434,6323,9214,3061,28,247,18185,476,35430,253,4321,4098,15,2552,253,6630,263,4901,253,49254,32,510,1728,18602,806,4136,247,6630,263,281,4901,253,49254,15,9613,253,4143,703,11120,29504,326,9214,15,1621,1996,3061,4961,15,50282],"label_positions":[1,8,15],"window":128,"logits":[-2.4012835025787354,0.5512642860412598,5.716588973999023],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9940265417098999}],"pipeline_multi":[{"label":"The stated rule prohibits the action","score":0.634428858757019},{"label":"The supplied information does not settle whether the rule permits the action","score":0.9967198967933655}]},{"id":"semif_077","source":"semif","text":"The homeowner first allowed a surveyor to enter the attic. Before the visit she explicitly withdrew that permission. No later decision exists.","prompt":"For this fictional protocol, the first recorded decision is binding and later withdrawals are ignored. May the surveyor enter the attic?","labels":["The stated rule permits the action","The stated rule prohibits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,1198,436,29934,7241,13,253,806,5950,3061,310,4865,285,1996,10687,932,403,12841,15,2552,253,6630,263,4901,253,49254,32,510,1728,18602,806,4136,247,6630,263,281,4901,253,49254,15,9613,253,4143,703,11120,29504,326,9214,15,1621,1996,3061,4961,15,50282],"label_positions":[1,8,15],"window":128,"logits":[-3.433546304702759,1.0313503742218018,5.129694938659668],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9834861755371094}],"pipeline_multi":[{"label":"The stated rule prohibits the action","score":0.7371776103973389},{"label":"The supplied information does not settle whether the rule permits the action","score":0.9941164255142212}]},{"id":"semif_078","source":"semif","text":"The homeowner first refused attic entry, then explicitly granted it before the visit. No later decision exists.","prompt":"Use the homeowner's latest permission decision; a withdrawal cancels the earlier grant. May the surveyor enter the attic?","labels":["The stated rule prohibits the action","The supplied information does not settle whether the rule permits the action","The stated rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,16000,253,2250,50369,7890,253,1728,18602,434,6323,9214,3061,28,247,18185,476,35430,253,4321,4098,15,2552,253,6630,263,4901,253,49254,32,510,1728,18602,806,9284,49254,5857,13,840,11120,7169,352,1078,253,4143,15,1621,1996,3061,4961,15,50282],"label_positions":[1,8,21],"window":128,"logits":[1.8468544483184814,5.617836952209473,-3.634965658187866],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9773973822593689}],"pipeline_multi":[{"label":"The stated rule prohibits the action","score":0.8637573719024658},{"label":"The supplied information does not settle whether the rule permits the action","score":0.996380627155304}]},{"id":"semif_079","source":"semif","text":"The homeowner gave an early permission decision, but neither its content nor any later decisions are available.","prompt":"Use the homeowner's latest permission decision; a withdrawal cancels the earlier grant. May the surveyor enter the attic?","labels":["The supplied information does not settle whether the rule permits the action","The stated rule prohibits the action","The stated rule permits the action"],"ids":[50281,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50369,7890,253,1728,18602,434,6323,9214,3061,28,247,18185,476,35430,253,4321,4098,15,2552,253,6630,263,4901,253,49254,32,510,1728,18602,3534,271,2393,9214,3061,13,533,6747,697,2600,4543,667,1996,7089,403,2130,15,50282],"label_positions":[1,14,21],"window":128,"logits":[6.386381149291992,0.6290313601493835,-3.424959421157837],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9967959523200989}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9983185529708862},{"label":"The stated rule prohibits the action","score":0.6522697806358337}]},{"id":"semif_080","source":"semif","text":"Candidate A: The speaker authorized streaming, then explicitly withdrew the authorization before the event. Candidate B: The speaker authorized streaming and the complete record confirms it remains in force.","prompt":"Select the candidate with currently valid streaming permission; a withdrawal cancels an earlier grant.","labels":["Neither candidate supplies the requested evidence","Candidate B","Candidate A"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,378,50368,330,33524,329,50369,16551,253,7431,342,4390,3588,18361,9214,28,247,18185,476,35430,271,4321,4098,15,36,33524,329,27,380,14925,14047,18361,13,840,11120,29504,253,26239,1078,253,2362,15,330,33524,378,27,380,14925,14047,18361,285,253,3426,1924,23849,352,4558,275,3490,15,50282],"label_positions":[1,8,12],"window":128,"logits":[-6.757970809936523,5.0852742195129395,2.0758841037750244],"pipeline_single":[{"label":"Candidate B","score":0.9529900550842285}],"pipeline_multi":[{"label":"Candidate B","score":0.993850827217102},{"label":"Candidate A","score":0.8885370492935181}]},{"id":"semif_081","source":"semif","text":"Candidate A: The speaker authorized streaming, then explicitly withdrew the authorization before the event. Candidate B: The speaker authorized streaming and the complete record confirms it remains in force.","prompt":"Select the candidate documenting an authorization that was later withdrawn.","labels":["Candidate B","Candidate A","Neither candidate supplies the requested evidence"],"ids":[50281,50368,330,33524,378,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50369,16551,253,7431,48447,271,26239,326,369,1996,26924,15,36,33524,329,27,380,14925,14047,18361,13,840,11120,29504,253,26239,1078,253,2362,15,330,33524,378,27,380,14925,14047,18361,285,253,3426,1924,23849,352,4558,275,3490,15,50282],"label_positions":[1,5,9],"window":128,"logits":[5.46785306930542,2.1702332496643066,-7.252732753753662],"pipeline_single":[{"label":"Candidate B","score":0.9643442630767822}],"pipeline_multi":[{"label":"Candidate B","score":0.9957975149154663},{"label":"Candidate A","score":0.8975443840026855}]},{"id":"semif_082","source":"semif","text":"Candidate A: Streaming was authorized and the complete record says permission remains in force. Candidate B: Streaming was authorized, then explicitly withdrawn.","prompt":"Select the candidate with currently valid streaming permission; a withdrawal cancels an earlier grant.","labels":["Candidate B","Neither candidate supplies the requested evidence","Candidate A"],"ids":[50281,50368,330,33524,378,50368,17106,7431,13191,253,9521,1941,50368,330,33524,329,50369,16551,253,7431,342,4390,3588,18361,9214,28,247,18185,476,35430,271,4321,4098,15,36,33524,329,27,22364,272,369,14047,285,253,3426,1924,2296,9214,4558,275,3490,15,330,33524,378,27,22364,272,369,14047,13,840,11120,26924,15,50282],"label_positions":[1,5,12],"window":128,"logits":[4.962830543518066,-7.716492176055908,2.3683953285217285],"pipeline_single":[{"label":"Candidate B","score":0.9304998517036438}],"pipeline_multi":[{"label":"Candidate B","score":0.993055522441864},{"label":"Candidate A","score":0.9143853783607483}]},{"id":"semif_083","source":"semif","text":"Candidate A: A permission form is mentioned but its terms and later changes are missing. Candidate B: The event name is supplied without permission history.","prompt":"Select the candidate with currently valid streaming permission; a withdrawal cancels an earlier grant.","labels":["Candidate B","Candidate A","Neither candidate supplies the requested evidence"],"ids":[50281,50368,330,33524,378,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50369,16551,253,7431,342,4390,3588,18361,9214,28,247,18185,476,35430,271,4321,4098,15,36,33524,329,27,329,9214,830,310,5393,533,697,2426,285,1996,2544,403,5816,15,330,33524,378,27,380,2362,1416,310,12164,1293,9214,2892,15,50282],"label_positions":[1,5,9],"window":128,"logits":[3.0589563846588135,3.4154860973358154,-0.32272830605506897],"pipeline_single":[{"label":"Candidate A","score":0.5800806879997253}],"pipeline_multi":[{"label":"Candidate B","score":0.9551676511764526},{"label":"Candidate A","score":0.9681850671768188}]},{"id":"semif_084","source":"semif","text":"The director gave Lina authority to approve exhibit labels and explicitly forbade further delegation. Lina then told Mo to approve them. The rule states an attempted forbidden delegation grants no authority; Mo has no other grant.","prompt":"Assess the claim: Mo has authority to approve exhibit labels.","labels":["The evidence establishes the opposite","The evidence does not establish either","The evidence establishes the claim"],"ids":[50281,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,6956,556,6265,281,23255,10738,13301,15,510,6423,3534,418,1758,6265,281,23255,10738,13301,285,11120,17163,796,2007,31896,15,418,1758,840,2183,6956,281,23255,731,15,380,4086,3054,271,9919,25415,31896,16311,642,6265,28,6956,556,642,643,4098,15,50282],"label_positions":[1,7,14],"window":128,"logits":[2.682481050491333,3.643869161605835,1.7785658836364746],"pipeline_single":[{"label":"The evidence does not establish either","score":0.6505287289619446}],"pipeline_multi":[{"label":"The evidence establishes the opposite","score":0.9359849691390991},{"label":"The evidence does not establish either","score":0.9745154976844788},{"label":"The evidence establishes the claim","score":0.8555196523666382}]},{"id":"semif_085","source":"semif","text":"The director gave Lina authority to approve exhibit labels and explicitly forbade further delegation. Lina then told Mo to approve them. The rule states an attempted forbidden delegation grants no authority; Mo has no other grant.","prompt":"Assess the claim: Lina has authority to approve exhibit labels.","labels":["The evidence establishes the opposite","The evidence does not establish either","The evidence establishes the claim"],"ids":[50281,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,418,1758,556,6265,281,23255,10738,13301,15,510,6423,3534,418,1758,6265,281,23255,10738,13301,285,11120,17163,796,2007,31896,15,418,1758,840,2183,6956,281,23255,731,15,380,4086,3054,271,9919,25415,31896,16311,642,6265,28,6956,556,642,643,4098,15,50282],"label_positions":[1,7,14],"window":128,"logits":[2.8649613857269287,3.6936538219451904,1.8385326862335205],"pipeline_single":[{"label":"The evidence does not establish either","score":0.6277251839637756}],"pipeline_multi":[{"label":"The evidence establishes the opposite","score":0.9460868835449219},{"label":"The evidence does not establish either","score":0.975723147392273},{"label":"The evidence establishes the claim","score":0.8627750873565674}]},{"id":"semif_086","source":"semif","text":"The director gives Mo direct authority to approve exhibit labels; the record confirms this grant is valid.","prompt":"Assess the claim: Mo has authority to approve exhibit labels.","labels":["The evidence establishes the claim","The evidence does not establish either","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,6956,556,6265,281,23255,10738,13301,15,510,6423,4245,6956,1480,6265,281,23255,10738,13301,28,253,1924,23849,436,4098,310,3588,15,50282],"label_positions":[1,7,14],"window":128,"logits":[6.108570575714111,-7.647773742675781,-4.455903053283691],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9999730587005615}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9977812170982361}]},{"id":"semif_087","source":"semif","text":"Mo is named in correspondence about labels, but no authority grants or delegation terms are supplied.","prompt":"Assess the claim: Mo has authority to approve exhibit labels.","labels":["The evidence does not establish either","The evidence establishes the opposite","The evidence establishes the claim"],"ids":[50281,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,7285,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,6956,556,6265,281,23255,10738,13301,15,15155,310,4907,275,17668,670,13301,13,533,642,6265,16311,390,31896,2426,403,12164,15,50282],"label_positions":[1,8,14],"window":128,"logits":[4.751944541931152,2.6029531955718994,-0.9722192287445068],"pipeline_single":[{"label":"The evidence does not establish either","score":0.8929625153541565}],"pipeline_multi":[{"label":"The evidence does not establish either","score":0.9914389848709106},{"label":"The evidence establishes the opposite","score":0.9310513734817505}]},{"id":"semif_088","source":"semif","text":"The producer authorizes the stage manager to approve props. The stage manager passes the task to an assistant, who has no other approval authority.","prompt":"The stage manager may approve props but may not delegate that authority. Only authorized approvers may approve. May the assistant approve a prop?","labels":["The stated rule prohibits the action","The supplied information does not settle whether the rule permits the action","The stated rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,16000,253,2250,50369,380,3924,7205,778,23255,29060,533,778,417,24565,326,6265,15,7214,14047,1192,735,778,23255,15,2552,253,13372,23255,247,4198,32,510,14281,2488,4219,253,3924,7205,281,23255,29060,15,380,3924,7205,11999,253,4836,281,271,13372,13,665,556,642,643,9612,6265,15,50282],"label_positions":[1,8,21],"window":128,"logits":[-1.1133811473846436,4.885058879852295,-1.0667699575424194],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9949420094490051}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.992497980594635}]},{"id":"semif_089","source":"semif","text":"The producer authorizes the stage manager to approve props. The stage manager passes the task to an assistant, who has no other approval authority.","prompt":"The stage manager may delegate prop approval to an assistant, and doing so grants the assistant approval authority. May this assistant approve?","labels":["The stated rule permits the action","The stated rule prohibits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,380,3924,7205,778,24565,4198,9612,281,271,13372,13,285,2509,594,16311,253,13372,9612,6265,15,2552,436,13372,23255,32,510,14281,2488,4219,253,3924,7205,281,23255,29060,15,380,3924,7205,11999,253,4836,281,271,13372,13,665,556,642,643,9612,6265,15,50282],"label_positions":[1,8,15],"window":128,"logits":[-2.0644261837005615,-0.5279870629310608,3.4136452674865723],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.97694993019104}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9681282639503479}]},{"id":"semif_090","source":"semif","text":"The producer directly authorizes the assistant to approve props.","prompt":"The stage manager may approve props but may not delegate that authority. Only authorized approvers may approve. May the assistant approve a prop?","labels":["The supplied information does not settle whether the rule permits the action","The stated rule prohibits the action","The stated rule permits the action"],"ids":[50281,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50369,380,3924,7205,778,23255,29060,533,778,417,24565,326,6265,15,7214,14047,1192,735,778,23255,15,2552,253,13372,23255,247,4198,32,510,14281,3587,2488,4219,253,13372,281,23255,29060,15,50282],"label_positions":[1,14,21],"window":128,"logits":[3.3883278369903564,-1.1693835258483887,-2.0325028896331787],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9853095412254333}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9673377871513367}]},{"id":"semif_091","source":"semif","text":"An assistant works on the production, but no approval grants or delegation history are provided.","prompt":"The stage manager may approve props but may not delegate that authority. Only authorized approvers may approve. May the assistant approve a prop?","labels":["The stated rule prohibits the action","The supplied information does not settle whether the rule permits the action","The stated rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,16000,253,2250,50369,380,3924,7205,778,23255,29060,533,778,417,24565,326,6265,15,7214,14047,1192,735,778,23255,15,2552,253,13372,23255,247,4198,32,1145,13372,2987,327,253,3275,13,533,642,9612,16311,390,31896,2892,403,2530,15,50282],"label_positions":[1,8,21],"window":128,"logits":[0.9993076920509338,5.670736312866211,-2.3352508544921875],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9904007315635681}],"pipeline_multi":[{"label":"The stated rule prohibits the action","score":0.7309224009513855},{"label":"The supplied information does not settle whether the rule permits the action","score":0.9965664148330688}]},{"id":"semif_092","source":"semif","text":"The rule permits direct delegation by the director but forbids any further delegation. Candidate A: I received prop approval authority directly from the director. Candidate B: I received it only from A, and have no other grant.","prompt":"Select the candidate holding valid prop approval authority under the stated delegation rule.","labels":["Candidate B","Candidate A","Neither candidate supplies the requested evidence"],"ids":[50281,50368,330,33524,378,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50369,16551,253,7431,5877,3588,4198,9612,6265,762,253,4767,31896,4086,15,510,4086,16000,1480,31896,407,253,6423,533,17163,2352,667,2007,31896,15,330,33524,329,27,309,2959,4198,9612,6265,3587,432,253,6423,15,330,33524,378,27,309,2959,352,760,432,329,13,285,452,642,643,4098,15,50282],"label_positions":[1,5,9],"window":128,"logits":[3.199317455291748,4.130931377410889,4.203580856323242],"pipeline_single":[{"label":"Neither candidate supplies the requested evidence","score":0.4354943633079529}],"pipeline_multi":[{"label":"Candidate B","score":0.960808515548706},{"label":"Candidate A","score":0.9841862320899963},{"label":"Neither candidate supplies the requested evidence","score":0.9852780699729919}]},{"id":"semif_093","source":"semif","text":"The rule permits direct delegation by the director but forbids any further delegation. Candidate A: I received prop approval authority directly from the director. Candidate B: I received it only from A, and have no other grant.","prompt":"Select the candidate whose claimed authority comes only through a prohibited second delegation.","labels":["Neither candidate supplies the requested evidence","Candidate A","Candidate B"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,329,50368,330,33524,378,50369,16551,253,7431,3692,7558,6265,3249,760,949,247,19772,1273,31896,15,510,4086,16000,1480,31896,407,253,6423,533,17163,2352,667,2007,31896,15,330,33524,329,27,309,2959,4198,9612,6265,3587,432,253,6423,15,330,33524,378,27,309,2959,352,760,432,329,13,285,452,642,643,4098,15,50282],"label_positions":[1,8,12],"window":128,"logits":[4.823884963989258,3.6612112522125244,3.4569003582000732],"pipeline_single":[{"label":"Neither candidate supplies the requested evidence","score":0.6379489898681641}],"pipeline_multi":[{"label":"Neither candidate supplies the requested evidence","score":0.992028534412384},{"label":"Candidate A","score":0.9749426245689392},{"label":"Candidate B","score":0.9694362878799438}]},{"id":"semif_094","source":"semif","text":"The rule permits direct delegation by the director but forbids further delegation. Candidate A: My only claimed authority came from B. Candidate B: The director directly granted me prop approval authority.","prompt":"Select the candidate holding valid prop approval authority under the stated delegation rule.","labels":["Candidate A","Neither candidate supplies the requested evidence","Candidate B"],"ids":[50281,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50368,330,33524,378,50369,16551,253,7431,5877,3588,4198,9612,6265,762,253,4767,31896,4086,15,510,4086,16000,1480,31896,407,253,6423,533,17163,2352,2007,31896,15,330,33524,329,27,2752,760,7558,6265,2210,432,378,15,330,33524,378,27,380,6423,3587,7169,479,4198,9612,6265,15,50282],"label_positions":[1,5,12],"window":128,"logits":[0.6392349004745483,-4.771458625793457,5.025021553039551],"pipeline_single":[{"label":"Candidate B","score":0.9876458048820496}],"pipeline_multi":[{"label":"Candidate A","score":0.6545804738998413},{"label":"Candidate B","score":0.9934715032577515}]},{"id":"semif_095","source":"semif","text":"The director's delegation rule is supplied, but Candidate A and Candidate B provide only their names and no authority histories.","prompt":"Select the candidate holding valid prop approval authority under the stated delegation rule.","labels":["Candidate B","Candidate A","Neither candidate supplies the requested evidence"],"ids":[50281,50368,330,33524,378,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50369,16551,253,7431,5877,3588,4198,9612,6265,762,253,4767,31896,4086,15,510,6423,434,31896,4086,310,12164,13,533,330,33524,329,285,330,33524,378,2085,760,616,4454,285,642,6265,29892,15,50282],"label_positions":[1,5,9],"window":128,"logits":[5.027191638946533,4.763424396514893,5.705301284790039],"pipeline_single":[{"label":"Neither candidate supplies the requested evidence","score":0.5270172953605652}],"pipeline_multi":[{"label":"Candidate B","score":0.9934855103492737},{"label":"Candidate A","score":0.9915359020233154},{"label":"Neither candidate supplies the requested evidence","score":0.9966827034950256}]},{"id":"semif_096","source":"semif","text":"The return policy accepts faulty lamps despite opened packaging, but explicitly excludes water damage even when the lamp is faulty. This opened lamp is faulty because water entered it. No other cause is present.","prompt":"Assess the claim: this lamp qualifies for return under the stated policy.","labels":["The evidence establishes the opposite","The evidence does not establish either","The evidence establishes the claim"],"ids":[50281,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,436,18067,4426,7790,323,1091,762,253,4767,3646,15,510,1091,3646,25026,40249,30161,5747,5485,18420,13,533,11120,43337,1824,4723,1014,672,253,18067,310,40249,15,831,5485,18067,310,40249,984,1824,5966,352,15,1621,643,2847,310,1246,15,50282],"label_positions":[1,7,14],"window":128,"logits":[-0.4514804780483246,0.10926010459661484,2.884939193725586],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9108536839485168}],"pipeline_multi":[{"label":"The evidence does not establish either","score":0.5272879004478455},{"label":"The evidence establishes the claim","score":0.9470969438552856}]},{"id":"semif_097","source":"semif","text":"The return policy accepts faulty lamps despite opened packaging, but explicitly excludes water damage even when the lamp is faulty. This opened lamp is faulty because water entered it. No other cause is present.","prompt":"Assess the claim: the lamp has a fault.","labels":["The evidence establishes the claim","The evidence does not establish either","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,253,18067,556,247,9331,15,510,1091,3646,25026,40249,30161,5747,5485,18420,13,533,11120,43337,1824,4723,1014,672,253,18067,310,40249,15,831,5485,18067,310,40249,984,1824,5966,352,15,1621,643,2847,310,1246,15,50282],"label_positions":[1,7,14],"window":128,"logits":[4.166996955871582,1.5540106296539307,0.21922579407691956],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9152371287345886}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9847378134727478},{"label":"The evidence does not establish either","score":0.8254922032356262},{"label":"The evidence establishes the opposite","score":0.5545879602432251}]},{"id":"semif_098","source":"semif","text":"The return policy accepts faulty lamps despite opened packaging, but excludes water damage even when faulty. This opened lamp has a manufacturing wiring fault, with no water damage or other exclusion.","prompt":"Assess the claim: this lamp qualifies for return under the stated policy.","labels":["The evidence establishes the opposite","The evidence does not establish either","The evidence establishes the claim"],"ids":[50281,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,436,18067,4426,7790,323,1091,762,253,4767,3646,15,510,1091,3646,25026,40249,30161,5747,5485,18420,13,533,43337,1824,4723,1014,672,40249,15,831,5485,18067,556,247,10264,24927,9331,13,342,642,1824,4723,390,643,14978,15,50282],"label_positions":[1,7,14],"window":128,"logits":[-0.37514960765838623,0.7507978081703186,3.064763069152832],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.8842234015464783}],"pipeline_multi":[{"label":"The evidence does not establish either","score":0.6793525218963623},{"label":"The evidence establishes the claim","score":0.9554156064987183}]},{"id":"semif_099","source":"semif","text":"The return policy accepts faulty lamps despite opened packaging but excludes water damage even when faulty. The lamp is faulty, but the cause and presence of water damage are omitted.","prompt":"Assess the claim: this lamp qualifies for return under the stated policy.","labels":["The evidence does not establish either","The evidence establishes the claim","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,436,18067,4426,7790,323,1091,762,253,4767,3646,15,510,1091,3646,25026,40249,30161,5747,5485,18420,533,43337,1824,4723,1014,672,40249,15,380,18067,310,40249,13,533,253,2847,285,3361,273,1824,4723,403,11035,15,50282],"label_positions":[1,8,14],"window":128,"logits":[5.051133632659912,1.8887587785720825,3.5172600746154785],"pipeline_single":[{"label":"The evidence does not establish either","score":0.7948976159095764}],"pipeline_multi":[{"label":"The evidence does not establish either","score":0.9936386942863464},{"label":"The evidence establishes the claim","score":0.8686139583587646},{"label":"The evidence establishes the opposite","score":0.971174955368042}]},{"id":"semif_100","source":"semif","text":"The opened paint tin has a manufacturing defect and also contains added solvent. Both facts are confirmed.","prompt":"Normally reject opened paint. Accept it for a manufacturing defect, except that added solvent always makes it ineligible. May this return be accepted?","labels":["The stated rule permits the action","The supplied information does not settle whether the rule permits the action","The stated rule prohibits the action"],"ids":[50281,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50369,40474,12009,5485,6848,15,31884,352,323,247,10264,7071,13,3707,326,2879,15465,1900,2789,352,275,43851,15,2552,436,1091,320,7607,32,510,5485,6848,20596,556,247,10264,7071,285,671,4428,2879,15465,15,6295,5441,403,5783,15,50282],"label_positions":[1,8,21],"window":128,"logits":[-3.2733943462371826,-0.4943391978740692,0.7815320491790771],"pipeline_single":[{"label":"The stated rule prohibits the action","score":0.7712928652763367}],"pipeline_multi":[{"label":"The stated rule prohibits the action","score":0.6860101819038391}]},{"id":"semif_101","source":"semif","text":"The opened paint tin has a manufacturing defect and also contains added solvent. Both facts are confirmed.","prompt":"Accept defective paint even if opened or mixed with solvent; neither condition overrides the defect exception. May this return be accepted?","labels":["The stated rule permits the action","The supplied information does not settle whether the rule permits the action","The stated rule prohibits the action"],"ids":[50281,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50369,31884,22327,6848,1014,604,5485,390,6804,342,15465,28,6747,1617,17797,1487,253,7071,6517,15,2552,436,1091,320,7607,32,510,5485,6848,20596,556,247,10264,7071,285,671,4428,2879,15465,15,6295,5441,403,5783,15,50282],"label_positions":[1,8,21],"window":128,"logits":[-2.031137704849243,-0.02298540435731411,0.24557200074195862],"pipeline_single":[{"label":"The stated rule prohibits the action","score":0.5355891585350037}],"pipeline_multi":[{"label":"The stated rule prohibits the action","score":0.5610862970352173}]},{"id":"semif_102","source":"semif","text":"The opened tin has a manufacturing defect and the inspection confirms no solvent was added.","prompt":"Normally reject opened paint. Accept it for a manufacturing defect, except that added solvent always makes it ineligible. May this return be accepted?","labels":["The stated rule permits the action","The supplied information does not settle whether the rule permits the action","The stated rule prohibits the action"],"ids":[50281,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50369,40474,12009,5485,6848,15,31884,352,323,247,10264,7071,13,3707,326,2879,15465,1900,2789,352,275,43851,15,2552,436,1091,320,7607,32,510,5485,20596,556,247,10264,7071,285,253,15981,23849,642,15465,369,2879,15,50282],"label_positions":[1,8,21],"window":128,"logits":[-5.912365436553955,5.010038375854492,0.42656856775283813],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9898663759231567}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9933736324310303},{"label":"The stated rule prohibits the action","score":0.6050539612770081}]},{"id":"semif_103","source":"semif","text":"The opened tin is defective, but whether solvent was added is not known.","prompt":"Normally reject opened paint. Accept it for a manufacturing defect, except that added solvent always makes it ineligible. May this return be accepted?","labels":["The stated rule permits the action","The supplied information does not settle whether the rule permits the action","The stated rule prohibits the action"],"ids":[50281,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50369,40474,12009,5485,6848,15,31884,352,323,247,10264,7071,13,3707,326,2879,15465,1900,2789,352,275,43851,15,2552,436,1091,320,7607,32,510,5485,20596,310,22327,13,533,1880,15465,369,2879,310,417,1929,15,50282],"label_positions":[1,8,21],"window":128,"logits":[-5.023099899291992,5.889843940734863,0.751326858997345],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9941498041152954}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9972401857376099},{"label":"The stated rule prohibits the action","score":0.6794677376747131}]},{"id":"semif_104","source":"semif","text":"Accept late submissions for documented outages, except that missing signatures always disqualify. Candidate A: My submission was late because of a documented outage and includes the required signature. Candidate B: Mine was late because of a documented outage but lacks the signature.","prompt":"Select the submission qualifying under the stated exception and exclusion.","labels":["Candidate B","Candidate A","Neither candidate supplies the requested evidence"],"ids":[50281,50368,330,33524,378,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50369,16551,253,19529,28661,762,253,4767,6517,285,14978,15,29011,3563,35103,323,14290,562,1131,13,3707,326,5816,20076,1900,42069,1419,15,330,33524,329,27,2752,19529,369,3563,984,273,247,14290,562,486,285,3797,253,2424,11118,15,330,33524,378,27,27288,369,3563,984,273,247,14290,562,486,533,19756,253,11118,15,50282],"label_positions":[1,5,9],"window":128,"logits":[3.9595227241516113,0.264253169298172,4.101851463317871],"pipeline_single":[{"label":"Neither candidate supplies the requested evidence","score":0.5294138789176941}],"pipeline_multi":[{"label":"Candidate B","score":0.9812847375869751},{"label":"Candidate A","score":0.565681517124176},{"label":"Neither candidate supplies the requested evidence","score":0.9837270975112915}]},{"id":"semif_105","source":"semif","text":"Accept late submissions for documented outages, except that missing signatures always disqualify. Candidate A: My submission was late because of a documented outage and includes the required signature. Candidate B: Mine was late because of a documented outage but lacks the signature.","prompt":"Select the submission disqualified specifically by the signature exclusion despite the outage exception.","labels":["Neither candidate supplies the requested evidence","Candidate B","Candidate A"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,378,50368,330,33524,329,50369,16551,253,19529,557,28758,5742,407,253,11118,14978,5747,253,562,486,6517,15,29011,3563,35103,323,14290,562,1131,13,3707,326,5816,20076,1900,42069,1419,15,330,33524,329,27,2752,19529,369,3563,984,273,247,14290,562,486,285,3797,253,2424,11118,15,330,33524,378,27,27288,369,3563,984,273,247,14290,562,486,533,19756,253,11118,15,50282],"label_positions":[1,8,12],"window":128,"logits":[0.4922393262386322,4.165761947631836,0.9259591102600098],"pipeline_single":[{"label":"Candidate B","score":0.9393565654754639}],"pipeline_multi":[{"label":"Neither candidate supplies the requested evidence","score":0.6206337809562683},{"label":"Candidate B","score":0.9847192764282227},{"label":"Candidate A","score":0.7162547707557678}]},{"id":"semif_106","source":"semif","text":"Accept late submissions for documented outages, except that missing signatures always disqualify. Candidate A: My late outage-related submission lacks the signature. Candidate B: My late outage-related submission has the signature. Both outages are documented.","prompt":"Select the submission qualifying under the stated exception and exclusion.","labels":["Neither candidate supplies the requested evidence","Candidate B","Candidate A"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,378,50368,330,33524,329,50369,16551,253,19529,28661,762,253,4767,6517,285,14978,15,29011,3563,35103,323,14290,562,1131,13,3707,326,5816,20076,1900,42069,1419,15,330,33524,329,27,2752,3563,562,486,14,4919,19529,19756,253,11118,15,330,33524,378,27,2752,3563,562,486,14,4919,19529,556,253,11118,15,6295,562,1131,403,14290,15,50282],"label_positions":[1,8,12],"window":128,"logits":[-9.2096529006958,4.294315338134766,3.090137481689453],"pipeline_single":[{"label":"Candidate B","score":0.7692663669586182}],"pipeline_multi":[{"label":"Candidate B","score":0.9865378141403198},{"label":"Candidate A","score":0.9564840197563171}]},{"id":"semif_107","source":"semif","text":"Accept late submissions for documented outages, except that missing signatures always disqualify. Candidate A and Candidate B report late submissions but provide neither outage documentation nor signature information.","prompt":"Select the submission qualifying under the stated exception and exclusion.","labels":["Candidate A","Neither candidate supplies the requested evidence","Candidate B"],"ids":[50281,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50368,330,33524,378,50369,16551,253,19529,28661,762,253,4767,6517,285,14978,15,29011,3563,35103,323,14290,562,1131,13,3707,326,5816,20076,1900,42069,1419,15,330,33524,329,285,330,33524,378,1304,3563,35103,533,2085,6747,562,486,10097,4543,11118,1491,15,50282],"label_positions":[1,5,12],"window":128,"logits":[4.469883918762207,5.591819763183594,3.461747407913208],"pipeline_single":[{"label":"Neither candidate supplies the requested evidence","score":0.6922918558120728}],"pipeline_multi":[{"label":"Candidate A","score":0.9886809587478638},{"label":"Neither candidate supplies the requested evidence","score":0.9962855577468872},{"label":"Candidate B","score":0.9695795178413391}]},{"id":"semif_108","source":"semif","text":"The desk log says the crate is in storage. The warehouse inventory says it has left storage. Both reports are current. The supplied protocol says the warehouse inventory controls location decisions whenever these two sources conflict.","prompt":"Assess the claim: under the supplied protocol, the crate is currently in storage.","labels":["The evidence establishes the opposite","The evidence does not establish either","The evidence establishes the claim"],"ids":[50281,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,762,253,12164,7241,13,253,47143,310,4390,275,5718,15,510,8597,2412,2296,253,47143,310,275,5718,15,380,27134,19543,2296,352,556,1669,5718,15,6295,5012,403,1655,15,380,12164,7241,2296,253,27134,19543,5760,4328,7089,10793,841,767,4973,7344,15,50282],"label_positions":[1,7,14],"window":128,"logits":[-2.595266103744507,-7.027514934539795,3.6641106605529785],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.998068630695343}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9750134348869324}]},{"id":"semif_109","source":"semif","text":"The desk log says the crate is in storage. The warehouse inventory says it has left storage. Both reports are current. The supplied protocol says the warehouse inventory controls location decisions whenever these two sources conflict.","prompt":"Assess the claim: the desk log reports the crate in storage.","labels":["The evidence establishes the opposite","The evidence does not establish either","The evidence establishes the claim"],"ids":[50281,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,253,8597,2412,5012,253,47143,275,5718,15,510,8597,2412,2296,253,47143,310,275,5718,15,380,27134,19543,2296,352,556,1669,5718,15,6295,5012,403,1655,15,380,12164,7241,2296,253,27134,19543,5760,4328,7089,10793,841,767,4973,7344,15,50282],"label_positions":[1,7,14],"window":128,"logits":[-2.492398738861084,-6.742766857147217,3.3110575675964355],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9969492554664612}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9648061990737915}]},{"id":"semif_110","source":"semif","text":"The desk log says the crate has left storage; the warehouse inventory says it is in storage. Both reports are current, and the inventory controls conflicts under the protocol.","prompt":"Assess the claim: under the supplied protocol, the crate is currently in storage.","labels":["The evidence establishes the opposite","The evidence does not establish either","The evidence establishes the claim"],"ids":[50281,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,762,253,12164,7241,13,253,47143,310,4390,275,5718,15,510,8597,2412,2296,253,47143,556,1669,5718,28,253,27134,19543,2296,352,310,275,5718,15,6295,5012,403,1655,13,285,253,19543,5760,15272,762,253,7241,15,50282],"label_positions":[1,7,14],"window":128,"logits":[-2.1086020469665527,-5.815290927886963,2.9235212802886963],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9933592677116394}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9489970207214355}]},{"id":"semif_111","source":"semif","text":"The protocol gives the inventory priority, but the current inventory and desk-log entries for the crate are omitted.","prompt":"Assess the claim: under the supplied protocol, the crate is currently in storage.","labels":["The evidence establishes the claim","The evidence establishes the opposite","The evidence does not establish either"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50369,2903,405,253,1750,27,762,253,12164,7241,13,253,47143,310,4390,275,5718,15,510,7241,4245,253,19543,11674,13,533,253,1655,19543,285,8597,14,2808,12028,323,253,47143,403,11035,15,50282],"label_positions":[1,7,13],"window":128,"logits":[-0.006200299598276615,3.122286081314087,3.743008852005005],"pipeline_single":[{"label":"The evidence does not establish either","score":0.6405771970748901}],"pipeline_multi":[{"label":"The evidence establishes the opposite","score":0.9578027725219727},{"label":"The evidence does not establish either","score":0.9768651723861694}]},{"id":"semif_112","source":"semif","text":"The desk clerk reports the equipment deposit as paid. The signed ledger reports it as unpaid. Both reports are current.","prompt":"Release equipment exactly when the deposit is recorded paid; in conflicts, the signed ledger overrides the desk clerk. May it be released?","labels":["The supplied information does not settle whether the rule permits the action","The stated rule prohibits the action","The stated rule permits the action"],"ids":[50281,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50369,20002,6500,4555,672,253,18831,310,5950,5087,28,275,15272,13,253,6704,3977,1063,17797,1487,253,8597,21334,15,2552,352,320,4439,32,510,8597,21334,5012,253,6500,18831,347,5087,15,380,6704,3977,1063,5012,352,347,35778,15,6295,5012,403,1655,15,50282],"label_positions":[1,14,21],"window":128,"logits":[-2.6795506477355957,-2.4653899669647217,-2.1170952320098877],"pipeline_single":[{"label":"The stated rule permits the action","score":0.43942540884017944}],"pipeline_multi":[]},{"id":"semif_113","source":"semif","text":"The desk clerk reports the equipment deposit as paid. The signed ledger reports it as unpaid. Both reports are current.","prompt":"Release equipment exactly when the deposit is recorded paid; under this alternative protocol, the desk clerk overrides the ledger. May it be released?","labels":["The supplied information does not settle whether the rule permits the action","The stated rule prohibits the action","The stated rule permits the action"],"ids":[50281,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50369,20002,6500,4555,672,253,18831,310,5950,5087,28,762,436,5795,7241,13,253,8597,21334,17797,1487,253,3977,1063,15,2552,352,320,4439,32,510,8597,21334,5012,253,6500,18831,347,5087,15,380,6704,3977,1063,5012,352,347,35778,15,6295,5012,403,1655,15,50282],"label_positions":[1,14,21],"window":128,"logits":[-2.7602968215942383,-2.479029893875122,-1.4014904499053955],"pipeline_single":[{"label":"The stated rule permits the action","score":0.6260175108909607}],"pipeline_multi":[]},{"id":"semif_114","source":"semif","text":"The desk clerk reports the deposit unpaid, while the signed ledger reports it paid. Both reports are current.","prompt":"Release equipment exactly when the deposit is recorded paid; in conflicts, the signed ledger overrides the desk clerk. May it be released?","labels":["The stated rule permits the action","The stated rule prohibits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,20002,6500,4555,672,253,18831,310,5950,5087,28,275,15272,13,253,6704,3977,1063,17797,1487,253,8597,21334,15,2552,352,320,4439,32,510,8597,21334,5012,253,18831,35778,13,1223,253,6704,3977,1063,5012,352,5087,15,6295,5012,403,1655,15,50282],"label_positions":[1,8,15],"window":128,"logits":[-0.8225588202476501,-2.2846639156341553,-0.07117392867803574],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.632498562335968}],"pipeline_multi":[]},{"id":"semif_115","source":"semif","text":"The record mentions the desk clerk and ledger but supplies neither deposit status.","prompt":"Release equipment exactly when the deposit is recorded paid; in conflicts, the signed ledger overrides the desk clerk. May it be released?","labels":["The stated rule prohibits the action","The stated rule permits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,20002,6500,4555,672,253,18831,310,5950,5087,28,275,15272,13,253,6704,3977,1063,17797,1487,253,8597,21334,15,2552,352,320,4439,32,510,1924,25957,253,8597,21334,285,3977,1063,533,13191,6747,18831,3708,15,50282],"label_positions":[1,8,15],"window":128,"logits":[2.547910690307617,-4.727472305297852,6.274618625640869],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9764779806137085}],"pipeline_multi":[{"label":"The stated rule prohibits the action","score":0.9274330735206604},{"label":"The supplied information does not settle whether the rule permits the action","score":0.9981200098991394}]},{"id":"semif_116","source":"semif","text":"For this task, the current signed checklist controls readiness when it conflicts with chat. Candidate A: Chat says ready, but the signed checklist says not ready. Candidate B: Chat says not ready, but the signed checklist says ready.","prompt":"Select the candidate ready according to the controlling signed checklist.","labels":["Candidate A","Neither candidate supplies the requested evidence","Candidate B"],"ids":[50281,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50368,330,33524,378,50369,16551,253,7431,4704,2556,281,253,10938,6704,44282,15,2214,436,4836,13,253,1655,6704,44282,5760,40628,672,352,15272,342,12939,15,330,33524,329,27,24180,2296,4704,13,533,253,6704,44282,2296,417,4704,15,330,33524,378,27,24180,2296,417,4704,13,533,253,6704,44282,2296,4704,15,50282],"label_positions":[1,5,12],"window":128,"logits":[0.3743223249912262,-2.8670337200164795,3.652118444442749],"pipeline_single":[{"label":"Candidate B","score":0.962291419506073}],"pipeline_multi":[{"label":"Candidate A","score":0.592503011226654},{"label":"Candidate B","score":0.9747195243835449}]},{"id":"semif_117","source":"semif","text":"For this task, the current signed checklist controls readiness when it conflicts with chat. Candidate A: Chat says ready, but the signed checklist says not ready. Candidate B: Chat says not ready, but the signed checklist says ready.","prompt":"Under the alternative protocol, chat controls conflicts. Select the candidate ready according to chat.","labels":["Neither candidate supplies the requested evidence","Candidate A","Candidate B"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,329,50368,330,33524,378,50369,6166,253,5795,7241,13,12939,5760,15272,15,16551,253,7431,4704,2556,281,12939,15,2214,436,4836,13,253,1655,6704,44282,5760,40628,672,352,15272,342,12939,15,330,33524,329,27,24180,2296,4704,13,533,253,6704,44282,2296,417,4704,15,330,33524,378,27,24180,2296,417,4704,13,533,253,6704,44282,2296,4704,15,50282],"label_positions":[1,8,12],"window":128,"logits":[2.564119815826416,1.2643368244171143,2.871490955352783],"pipeline_single":[{"label":"Candidate B","score":0.5165730118751526}],"pipeline_multi":[{"label":"Neither candidate supplies the requested evidence","score":0.9285163879394531},{"label":"Candidate A","score":0.7797717452049255},{"label":"Candidate B","score":0.9464190602302551}]},{"id":"semif_118","source":"semif","text":"The signed checklist controls conflicts. Candidate A: The checklist says ready and chat says not ready. Candidate B: The checklist says not ready and chat says ready.","prompt":"Select the candidate ready according to the controlling signed checklist.","labels":["Candidate A","Candidate B","Neither candidate supplies the requested evidence"],"ids":[50281,50368,330,33524,329,50368,330,33524,378,50368,17106,7431,13191,253,9521,1941,50369,16551,253,7431,4704,2556,281,253,10938,6704,44282,15,510,6704,44282,5760,15272,15,330,33524,329,27,380,44282,2296,4704,285,12939,2296,417,4704,15,330,33524,378,27,380,44282,2296,417,4704,285,12939,2296,4704,15,50282],"label_positions":[1,5,9],"window":128,"logits":[3.5709564685821533,3.1400911808013916,1.702272653579712],"pipeline_single":[{"label":"Candidate A","score":0.554239809513092}],"pipeline_multi":[{"label":"Candidate A","score":0.9726406335830688},{"label":"Candidate B","score":0.958516538143158},{"label":"Neither candidate supplies the requested evidence","score":0.8458312749862671}]},{"id":"semif_119","source":"semif","text":"The signed checklist controls conflicts, but Candidate A and Candidate B provide only project names without checklist or chat status.","prompt":"Select the candidate ready according to the controlling signed checklist.","labels":["Neither candidate supplies the requested evidence","Candidate B","Candidate A"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,378,50368,330,33524,329,50369,16551,253,7431,4704,2556,281,253,10938,6704,44282,15,510,6704,44282,5760,15272,13,533,330,33524,329,285,330,33524,378,2085,760,2199,4454,1293,44282,390,12939,3708,15,50282],"label_positions":[1,8,12],"window":128,"logits":[4.4641313552856445,4.132500648498535,4.441253662109375],"pipeline_single":[{"label":"Neither candidate supplies the requested evidence","score":0.3710390031337738}],"pipeline_multi":[{"label":"Neither candidate supplies the requested evidence","score":0.988616406917572},{"label":"Candidate B","score":0.9842106103897095},{"label":"Candidate A","score":0.9883559942245483}]},{"id":"semif_120","source":"semif","text":"The agreed handover requires both the source files and the user guide. The delivery record confirms the source files arrived and explicitly says the guide was not delivered.","prompt":"Assess the claim: the agreed handover is complete.","labels":["The evidence establishes the opposite","The evidence does not establish either","The evidence establishes the claim"],"ids":[50281,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,253,5821,1133,1189,310,3426,15,510,5821,1133,1189,4419,1097,253,2603,4367,285,253,2608,7102,15,380,6742,1924,23849,253,2603,4367,7244,285,11120,2296,253,7102,369,417,8549,15,50282],"label_positions":[1,7,14],"window":128,"logits":[-2.0583131313323975,-0.9072809815406799,4.5263190269470215],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9942840933799744}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9892954230308533}]},{"id":"semif_121","source":"semif","text":"The agreed handover requires both the source files and the user guide. The delivery record confirms the source files arrived and explicitly says the guide was not delivered.","prompt":"Assess the claim: the source files were delivered.","labels":["The evidence does not establish either","The evidence establishes the opposite","The evidence establishes the claim"],"ids":[50281,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,7285,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,253,2603,4367,497,8549,15,510,5821,1133,1189,4419,1097,253,2603,4367,285,253,2608,7102,15,380,6742,1924,23849,253,2603,4367,7244,285,11120,2296,253,7102,369,417,8549,15,50282],"label_positions":[1,8,14],"window":128,"logits":[-1.5593183040618896,2.3195595741271973,2.7809031009674072],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.608468770980835}],"pipeline_multi":[{"label":"The evidence establishes the opposite","score":0.9104840159416199},{"label":"The evidence establishes the claim","score":0.9416350722312927}]},{"id":"semif_122","source":"semif","text":"The agreed handover requires the source files and user guide. The delivery record confirms that both arrived.","prompt":"Assess the claim: the agreed handover is complete.","labels":["The evidence establishes the claim","The evidence does not establish either","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,253,5821,1133,1189,310,3426,15,510,5821,1133,1189,4419,253,2603,4367,285,2608,7102,15,380,6742,1924,23849,326,1097,7244,15,50282],"label_positions":[1,7,14],"window":128,"logits":[6.7414045333862305,-7.9707417488098145,-5.570198059082031],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9999951124191284}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9988203644752502}]},{"id":"semif_123","source":"semif","text":"The agreement requires source files and a user guide, but the delivery record gives no information about either item.","prompt":"Assess the claim: the agreed handover is complete.","labels":["The evidence establishes the opposite","The evidence establishes the claim","The evidence does not establish either"],"ids":[50281,50368,380,1941,25097,253,7285,50368,380,1941,25097,253,1750,50368,380,1941,1057,417,5100,2057,50369,2903,405,253,1750,27,253,5821,1133,1189,310,3426,15,510,4345,4419,2603,4367,285,247,2608,7102,13,533,253,6742,1924,4245,642,1491,670,2057,5382,15,50282],"label_positions":[1,7,13],"window":128,"logits":[2.9477810859680176,0.4106271266937256,5.408679008483887],"pipeline_single":[{"label":"The evidence does not establish either","score":0.9156592488288879}],"pipeline_multi":[{"label":"The evidence establishes the opposite","score":0.9501584768295288},{"label":"The evidence establishes the claim","score":0.6012382507324219},{"label":"The evidence does not establish either","score":0.9955424666404724}]},{"id":"semif_124","source":"semif","text":"The contractor supplied the translated manual but explicitly did not supply the glossary.","prompt":"Approve final handover exactly when both the translated manual and glossary have been supplied. May final handover be approved?","labels":["The stated rule prohibits the action","The stated rule permits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,17274,306,2457,1133,1189,4555,672,1097,253,15786,11595,285,27392,552,452,644,12164,15,2552,2457,1133,1189,320,7012,32,510,22350,12164,253,15786,11595,533,11120,858,417,6186,253,27392,552,15,50282],"label_positions":[1,8,15],"window":128,"logits":[1.5167218446731567,-5.43327522277832,7.122102737426758],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9963319897651672}],"pipeline_multi":[{"label":"The stated rule prohibits the action","score":0.8200553059577942},{"label":"The supplied information does not settle whether the rule permits the action","score":0.9991936087608337}]},{"id":"semif_125","source":"semif","text":"The contractor supplied the translated manual but explicitly did not supply the glossary.","prompt":"Approve the translation milestone when the manual has been supplied; the glossary is not required for this milestone. May this milestone be approved?","labels":["The stated rule prohibits the action","The stated rule permits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,17274,306,253,10234,41457,672,253,11595,556,644,12164,28,253,27392,552,310,417,2424,323,436,41457,15,2552,436,41457,320,7012,32,510,22350,12164,253,15786,11595,533,11120,858,417,6186,253,27392,552,15,50282],"label_positions":[1,8,15],"window":128,"logits":[1.1336109638214111,-5.500843048095703,6.592101573944092],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9957525730133057}],"pipeline_multi":[{"label":"The stated rule prohibits the action","score":0.7565046548843384},{"label":"The supplied information does not settle whether the rule permits the action","score":0.998630702495575}]},{"id":"semif_126","source":"semif","text":"The contractor supplied both the translated manual and the glossary.","prompt":"Approve final handover exactly when both the translated manual and glossary have been supplied. May final handover be approved?","labels":["The stated rule permits the action","The stated rule prohibits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,17274,306,2457,1133,1189,4555,672,1097,253,15786,11595,285,27392,552,452,644,12164,15,2552,2457,1133,1189,320,7012,32,510,22350,12164,1097,253,15786,11595,285,253,27392,552,15,50282],"label_positions":[1,8,15],"window":128,"logits":[-0.3768692910671234,-3.226304531097412,0.6571550965309143],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.7266635894775391}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.6586210131645203}]},{"id":"semif_127","source":"semif","text":"The contractor reports working on the handover but supplies no delivery record for either item.","prompt":"Approve final handover exactly when both the translated manual and glossary have been supplied. May final handover be approved?","labels":["The stated rule permits the action","The supplied information does not settle whether the rule permits the action","The stated rule prohibits the action"],"ids":[50281,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50369,17274,306,2457,1133,1189,4555,672,1097,253,15786,11595,285,27392,552,452,644,12164,15,2552,2457,1133,1189,320,7012,32,510,22350,5012,2444,327,253,1133,1189,533,13191,642,6742,1924,323,2057,5382,15,50282],"label_positions":[1,8,21],"window":128,"logits":[-3.480537176132202,6.72838020324707,-1.5565944910049438],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9997109770774841}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9988049268722534}]},{"id":"semif_128","source":"semif","text":"A complete incident package requires both a timeline and a remedy report. Candidate A: Both documents are attached. Candidate B: Only the timeline is attached; the remedy report is absent.","prompt":"Select the complete incident package.","labels":["Candidate B","Neither candidate supplies the requested evidence","Candidate A"],"ids":[50281,50368,330,33524,378,50368,17106,7431,13191,253,9521,1941,50368,330,33524,329,50369,16551,253,3426,7119,5522,15,34,3426,7119,5522,4419,1097,247,28563,285,247,16748,1304,15,330,33524,329,27,6295,7177,403,7660,15,330,33524,378,27,7214,253,28563,310,7660,28,253,16748,1304,310,12125,15,50282],"label_positions":[1,5,12],"window":128,"logits":[4.797384262084961,4.057397365570068,3.274618625640869],"pipeline_single":[{"label":"Candidate B","score":0.5898911356925964}],"pipeline_multi":[{"label":"Candidate B","score":0.9918162226676941},{"label":"Neither candidate supplies the requested evidence","score":0.9830000400543213},{"label":"Candidate A","score":0.9635477066040039}]},{"id":"semif_129","source":"semif","text":"A complete incident package requires both a timeline and a remedy report. Candidate A: Both documents are attached. Candidate B: Only the timeline is attached; the remedy report is absent.","prompt":"Select the package containing the timeline but missing the remedy report.","labels":["Candidate B","Candidate A","Neither candidate supplies the requested evidence"],"ids":[50281,50368,330,33524,378,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50369,16551,253,5522,4508,253,28563,533,5816,253,16748,1304,15,34,3426,7119,5522,4419,1097,247,28563,285,247,16748,1304,15,330,33524,329,27,6295,7177,403,7660,15,330,33524,378,27,7214,253,28563,310,7660,28,253,16748,1304,310,12125,15,50282],"label_positions":[1,5,9],"window":128,"logits":[4.042050361633301,2.8605682849884033,2.996619462966919],"pipeline_single":[{"label":"Candidate B","score":0.6030039191246033}],"pipeline_multi":[{"label":"Candidate B","score":0.98274165391922},{"label":"Candidate A","score":0.9458624124526978},{"label":"Neither candidate supplies the requested evidence","score":0.952421247959137}]},{"id":"semif_130","source":"semif","text":"A complete package requires both documents. Candidate A: The timeline is attached but the remedy report is absent. Candidate B: Both the timeline and remedy report are attached.","prompt":"Select the complete incident package.","labels":["Candidate B","Candidate A","Neither candidate supplies the requested evidence"],"ids":[50281,50368,330,33524,378,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50369,16551,253,3426,7119,5522,15,34,3426,5522,4419,1097,7177,15,330,33524,329,27,380,28563,310,7660,533,253,16748,1304,310,12125,15,330,33524,378,27,6295,253,28563,285,16748,1304,403,7660,15,50282],"label_positions":[1,5,9],"window":128,"logits":[5.7600860595703125,3.551547050476074,-7.778270721435547],"pipeline_single":[{"label":"Candidate B","score":0.901012659072876}],"pipeline_multi":[{"label":"Candidate B","score":0.996859073638916},{"label":"Candidate A","score":0.9721193909645081}]},{"id":"semif_131","source":"semif","text":"A complete package requires both documents. Candidate A and Candidate B give only package titles and no attachment information.","prompt":"Select the complete incident package.","labels":["Candidate B","Neither candidate supplies the requested evidence","Candidate A"],"ids":[50281,50368,330,33524,378,50368,17106,7431,13191,253,9521,1941,50368,330,33524,329,50369,16551,253,3426,7119,5522,15,34,3426,5522,4419,1097,7177,15,330,33524,329,285,330,33524,378,1918,760,5522,14505,285,642,14170,1491,15,50282],"label_positions":[1,5,12],"window":128,"logits":[6.537266254425049,3.925546884536743,4.3316731452941895],"pipeline_single":[{"label":"Candidate B","score":0.8448847532272339}],"pipeline_multi":[{"label":"Candidate B","score":0.9985536932945251},{"label":"Neither candidate supplies the requested evidence","score":0.9806504845619202},{"label":"Candidate A","score":0.9870250225067139}]},{"id":"semif_132","source":"semif","text":"The routing rule assigns repairs to the in-house workshop when it can perform the work; use the outside workshop only when the in-house workshop cannot. Both workshops confirm they can perform this repair.","prompt":"Assess the claim: the routing rule assigns this repair to the outside workshop.","labels":["The evidence establishes the claim","The evidence does not establish either","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,25097,253,1750,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,253,24749,4086,39360,436,8706,281,253,3345,22586,15,510,24749,4086,39360,25931,281,253,275,14,5967,22586,672,352,476,1347,253,789,28,897,253,3345,22586,760,672,253,275,14,5967,22586,2550,15,6295,29561,6583,597,476,1347,436,8706,15,50282],"label_positions":[1,7,14],"window":128,"logits":[4.92616605758667,-2.902198076248169,-1.049410343170166],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9970703125}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9927980303764343}]},{"id":"semif_133","source":"semif","text":"The routing rule assigns repairs to the in-house workshop when it can perform the work; use the outside workshop only when the in-house workshop cannot. Both workshops confirm they can perform this repair.","prompt":"Assess the claim: the outside workshop can perform this repair.","labels":["The evidence does not establish either","The evidence establishes the claim","The evidence establishes the opposite"],"ids":[50281,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50368,380,1941,25097,253,7285,50369,2903,405,253,1750,27,253,3345,22586,476,1347,436,8706,15,510,24749,4086,39360,25931,281,253,275,14,5967,22586,672,352,476,1347,253,789,28,897,253,3345,22586,760,672,253,275,14,5967,22586,2550,15,6295,29561,6583,597,476,1347,436,8706,15,50282],"label_positions":[1,8,14],"window":128,"logits":[-3.1207869052886963,4.052310943603516,-0.2740112841129303],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9862098097801208}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9829148054122925}]},{"id":"semif_134","source":"semif","text":"The routing rule assigns repairs to the in-house workshop when it can perform the work; use the outside workshop only when the in-house workshop cannot. The in-house workshop cannot perform this repair; the outside workshop can.","prompt":"Assess the claim: the routing rule assigns this repair to the outside workshop.","labels":["The evidence establishes the opposite","The evidence does not establish either","The evidence establishes the claim"],"ids":[50281,50368,380,1941,25097,253,7285,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,253,24749,4086,39360,436,8706,281,253,3345,22586,15,510,24749,4086,39360,25931,281,253,275,14,5967,22586,672,352,476,1347,253,789,28,897,253,3345,22586,760,672,253,275,14,5967,22586,2550,15,380,275,14,5967,22586,2550,1347,436,8706,28,253,3345,22586,476,15,50282],"label_positions":[1,7,14],"window":128,"logits":[-0.9744598269462585,-0.3550699055194855,2.8098742961883545],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.9390196204185486}],"pipeline_multi":[{"label":"The evidence establishes the claim","score":0.9432070255279541}]},{"id":"semif_135","source":"semif","text":"The routing rule assigns repairs to the in-house workshop when it can perform the work; use the outside workshop only when the in-house workshop cannot. Neither workshop's ability to perform this repair is supplied.","prompt":"Assess the claim: the routing rule assigns this repair to the outside workshop.","labels":["The evidence does not establish either","The evidence establishes the opposite","The evidence establishes the claim"],"ids":[50281,50368,380,1941,1057,417,5100,2057,50368,380,1941,25097,253,7285,50368,380,1941,25097,253,1750,50369,2903,405,253,1750,27,253,24749,4086,39360,436,8706,281,253,3345,22586,15,510,24749,4086,39360,25931,281,253,275,14,5967,22586,672,352,476,1347,253,789,28,897,253,3345,22586,760,672,253,275,14,5967,22586,2550,15,17106,22586,434,3745,281,1347,436,8706,310,12164,15,50282],"label_positions":[1,8,14],"window":128,"logits":[0.8792452216148376,1.3264240026474,1.6944670677185059],"pipeline_single":[{"label":"The evidence establishes the claim","score":0.4684655964374542}],"pipeline_multi":[{"label":"The evidence does not establish either","score":0.7066658139228821},{"label":"The evidence establishes the opposite","score":0.7902485132217407},{"label":"The evidence establishes the claim","score":0.8448107242584229}]},{"id":"semif_136","source":"semif","text":"The town hall and school both confirm they are available and suitable for the meeting.","prompt":"Book the school only as a fallback when the town hall is unavailable or unsuitable; otherwise book the town hall. May the school be booked under this policy?","labels":["The stated rule prohibits the action","The stated rule permits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,7225,253,2143,760,347,247,2965,2135,672,253,3874,7423,310,29356,390,49590,28,5010,1984,253,3874,7423,15,2552,253,2143,320,32346,762,436,3646,32,510,3874,7423,285,2143,1097,6583,597,403,2130,285,7470,323,253,4804,15,50282],"label_positions":[1,8,15],"window":128,"logits":[-2.2421529293060303,-1.5666526556015015,0.8390467762947083],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.8801991939544678}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.6982644200325012}]},{"id":"semif_137","source":"semif","text":"The town hall and school both confirm they are available and suitable for the meeting.","prompt":"Under the alternative policy, either suitable available venue may be booked without priority. May the school be booked?","labels":["The stated rule prohibits the action","The stated rule permits the action","The supplied information does not settle whether the rule permits the action"],"ids":[50281,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50369,6166,253,5795,3646,13,2057,7470,2130,18767,778,320,32346,1293,11674,15,2552,253,2143,320,32346,32,510,3874,7423,285,2143,1097,6583,597,403,2130,285,7470,323,253,4804,15,50282],"label_positions":[1,8,15],"window":128,"logits":[-1.4090884923934937,-1.889697790145874,2.1995935440063477],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.958002507686615}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9002130031585693}]},{"id":"semif_138","source":"semif","text":"The town hall is confirmed unavailable, while the school is available and suitable.","prompt":"Book the school only as a fallback when the town hall is unavailable or unsuitable; otherwise book the town hall. May the school be booked under this policy?","labels":["The supplied information does not settle whether the rule permits the action","The stated rule permits the action","The stated rule prohibits the action"],"ids":[50281,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50369,7225,253,2143,760,347,247,2965,2135,672,253,3874,7423,310,29356,390,49590,28,5010,1984,253,3874,7423,15,2552,253,2143,320,32346,762,436,3646,32,510,3874,7423,310,5783,29356,13,1223,253,2143,310,2130,285,7470,15,50282],"label_positions":[1,14,21],"window":128,"logits":[1.27017080783844,-2.154705286026001,-0.9663571715354919],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.8776686787605286}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.7807719707489014}]},{"id":"semif_139","source":"semif","text":"The two venues are named, but neither availability nor suitability is provided.","prompt":"Book the school only as a fallback when the town hall is unavailable or unsuitable; otherwise book the town hall. May the school be booked under this policy?","labels":["The supplied information does not settle whether the rule permits the action","The stated rule prohibits the action","The stated rule permits the action"],"ids":[50281,50368,380,12164,1491,1057,417,16359,1880,253,4086,16000,253,2250,50368,380,4767,4086,33093,253,2250,50368,380,4767,4086,16000,253,2250,50369,7225,253,2143,760,347,247,2965,2135,672,253,3874,7423,310,29356,390,49590,28,5010,1984,253,3874,7423,15,2552,253,2143,320,32346,762,436,3646,32,510,767,28966,403,4907,13,533,6747,11659,4543,45984,310,2530,15,50282],"label_positions":[1,14,21],"window":128,"logits":[6.126063346862793,0.18504072725772858,-4.864823341369629],"pipeline_single":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9973607659339905}],"pipeline_multi":[{"label":"The supplied information does not settle whether the rule permits the action","score":0.9978195428848267},{"label":"The stated rule prohibits the action","score":0.5461286306381226}]},{"id":"semif_140","source":"semif","text":"Candidate A is the preferred translator and is confirmed able to handle this language. Candidate B is the fallback translator and is also able to handle it.","prompt":"Choose A whenever A is able; choose B only when A is unable and B is able.","labels":["Candidate B","Candidate A","Neither candidate supplies the requested evidence"],"ids":[50281,50368,330,33524,378,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50369,28890,329,10793,329,310,2104,28,5206,378,760,672,329,310,7591,285,378,310,2104,15,36,33524,329,310,253,9013,42726,285,310,5783,2104,281,6016,436,3448,15,330,33524,378,310,253,2965,2135,42726,285,310,671,2104,281,6016,352,15,50282],"label_positions":[1,5,9],"window":128,"logits":[5.017245769500732,5.439719200134277,-8.163958549499512],"pipeline_single":[{"label":"Candidate A","score":0.6040745377540588}],"pipeline_multi":[{"label":"Candidate B","score":0.9934207797050476},{"label":"Candidate A","score":0.9956781268119812}]},{"id":"semif_141","source":"semif","text":"Candidate A is the preferred translator and is confirmed able to handle this language. Candidate B is the fallback translator and is also able to handle it.","prompt":"Under the alternative priority, choose B whenever B is able; choose A only when B is unable and A is able.","labels":["Neither candidate supplies the requested evidence","Candidate B","Candidate A"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,378,50368,330,33524,329,50369,6166,253,5795,11674,13,5206,378,10793,378,310,2104,28,5206,329,760,672,378,310,7591,285,329,310,2104,15,36,33524,329,310,253,9013,42726,285,310,5783,2104,281,6016,436,3448,15,330,33524,378,310,253,2965,2135,42726,285,310,671,2104,281,6016,352,15,50282],"label_positions":[1,8,12],"window":128,"logits":[-8.262385368347168,5.970678329467773,5.214794158935547],"pipeline_single":[{"label":"Candidate B","score":0.6804591417312622}],"pipeline_multi":[{"label":"Candidate B","score":0.9974539875984192},{"label":"Candidate A","score":0.9945937991142273}]},{"id":"semif_142","source":"semif","text":"Candidate A is the preferred translator but is confirmed unable to handle this language. Candidate B is the fallback and is confirmed able.","prompt":"Choose A whenever A is able; choose B only when A is unable and B is able.","labels":["Candidate A","Neither candidate supplies the requested evidence","Candidate B"],"ids":[50281,50368,330,33524,329,50368,17106,7431,13191,253,9521,1941,50368,330,33524,378,50369,28890,329,10793,329,310,2104,28,5206,378,760,672,329,310,7591,285,378,310,2104,15,36,33524,329,310,253,9013,42726,533,310,5783,7591,281,6016,436,3448,15,330,33524,378,310,253,2965,2135,285,310,5783,2104,15,50282],"label_positions":[1,5,12],"window":128,"logits":[3.5246827602386475,-6.521418571472168,5.433955192565918],"pipeline_single":[{"label":"Candidate B","score":0.8709325194358826}],"pipeline_multi":[{"label":"Candidate A","score":0.9713819622993469},{"label":"Candidate B","score":0.9956531524658203}]},{"id":"semif_143","source":"semif","text":"Candidate A is preferred and Candidate B is the fallback, but neither candidate's ability to handle the language is supplied.","prompt":"Choose A whenever A is able; choose B only when A is unable and B is able.","labels":["Neither candidate supplies the requested evidence","Candidate B","Candidate A"],"ids":[50281,50368,17106,7431,13191,253,9521,1941,50368,330,33524,378,50368,330,33524,329,50369,28890,329,10793,329,310,2104,28,5206,378,760,672,329,310,7591,285,378,310,2104,15,36,33524,329,310,9013,285,330,33524,378,310,253,2965,2135,13,533,6747,7431,434,3745,281,6016,253,3448,310,12164,15,50282],"label_positions":[1,8,12],"window":128,"logits":[5.91500186920166,-0.32432177662849426,1.180864930152893],"pipeline_single":[{"label":"Neither candidate supplies the requested evidence","score":0.9893729090690613}],"pipeline_multi":[{"label":"Neither candidate supplies the requested evidence","score":0.997308611869812},{"label":"Candidate A","score":0.7651033401489258}]},{"id":"card_01","source":"card","text":"One day I will see the world!","prompt":null,"labels":["travel","dreams","sport","science","politics"],"ids":[50281,50368,4288,50368,13702,50368,9678,50368,5859,50368,8672,50369,2596,1388,309,588,923,253,1533,2,50282],"label_positions":[1,3,5,7,9],"window":128,"logits":[0.8957796096801758,1.1802023649215698,-2.0749542713165283,-3.154866933822632,-1.8614181280136108],"pipeline_single":[{"label":"dreams","score":0.5399913191795349}],"pipeline_multi":[{"label":"travel","score":0.7100813984870911},{"label":"dreams","score":0.7649841904640198}]},{"id":"card_02","source":"card","text":"The cat slept on the windowsill all afternoon","prompt":null,"labels":["The cat was awake and playing outside."],"ids":[50281,50368,380,5798,369,22238,285,4882,3345,15,50369,380,5798,21567,327,253,8323,408,512,9055,50282],"label_positions":[1],"window":128,"logits":[0.36137598752975464],"pipeline_single":[{"label":"The cat was awake and playing outside.","score":1.0}],"pipeline_multi":[{"label":"The cat was awake and playing outside.","score":0.5893734693527222}]},{"id":"inv_01","source":"invented","text":"Hello, my name is Anwen Pritchley. I was charged twice for my Prandle Cloud Basic plan this month (invoice 2219-B). Please refund the duplicate charge; I already updated my card details last week.","prompt":null,"labels":["billing issue","refund request","technical problem","cancel subscription","praise","shipping delay"],"ids":[50281,50368,33484,2523,50368,23005,2748,50368,7681,1895,50368,14002,21729,50368,19916,50368,15076,5778,50369,24387,13,619,1416,310,743,15082,367,902,348,2205,15,309,369,6636,7019,323,619,2604,395,282,18189,20233,2098,436,1770,313,249,22619,3307,746,14,35,481,7764,23005,253,21036,4179,28,309,2168,9300,619,3120,4278,1390,2129,15,50282],"label_positions":[1,4,7,10,13,15],"window":128,"logits":[3.706204652786255,5.075766563415527,3.138960838317871,-1.7548538446426392,-3.812939405441284,-0.7556197643280029],"pipeline_single":[{"label":"refund request","score":0.712995171546936}],"pipeline_multi":[{"label":"billing issue","score":0.9760186672210693},{"label":"refund request","score":0.9937924742698669},{"label":"technical problem","score":0.9584715366363525}]},{"id":"inv_02","source":"invented","text":"The Zorvik X2 router from Tallowmere Networks keeps dropping the connection every evening around 9 pm. I have restarted it and reset it to factory settings, but the status light still blinks orange.","prompt":null,"labels":["connectivity problem","hardware defect","billing issue","feature request","installation help"],"ids":[50281,50368,17769,1895,50368,10309,7071,50368,33484,2523,50368,4735,2748,50368,12692,1361,50369,380,1503,263,30127,1594,19,23093,432,308,8912,37166,32492,11359,18752,253,4602,1046,7237,1475,898,12920,15,309,452,19855,264,352,285,14932,352,281,13250,7533,13,533,253,3708,1708,1335,787,3106,13735,15,50282],"label_positions":[1,4,7,10,13],"window":128,"logits":[5.232974052429199,2.948697328567505,2.0541250705718994,1.4580307006835938,-1.1246856451034546],"pipeline_single":[{"label":"connectivity problem","score":0.8560521006584167}],"pipeline_multi":[{"label":"connectivity problem","score":0.9946907162666321},{"label":"hardware defect","score":0.9502018690109253},{"label":"billing issue","score":0.8863638043403625},{"label":"feature request","score":0.8112313151359558}]},{"id":"inv_03","source":"invented","text":"I have used the Quellbrook kettle from Marrowby Home every morning for three months. It boils fast, stays quiet, and the handle never gets hot. Worth every penny.","prompt":null,"labels":["positive","negative","neutral","mentions price","mentions durability","mentions noise","mentions delivery"],"ids":[50281,50368,2762,50368,4016,50368,9238,50368,25957,4376,50368,25957,35091,50368,25957,6046,50368,25957,6742,50369,309,452,908,253,3277,437,30103,465,35189,432,2398,736,1615,9067,1046,4131,323,1264,2607,15,733,1766,3683,3809,13,19931,7107,13,285,253,6016,1620,4850,3511,15,32354,1046,36550,15,50282],"label_positions":[1,3,5,7,10,13,16],"window":128,"logits":[2.709301471710205,-2.552198648452759,0.6019762754440308,2.8154830932617188,3.5540754795074463,1.0051621198654175,2.9884097576141357],"pipeline_single":[{"label":"mentions durability","score":0.3834286034107208}],"pipeline_multi":[{"label":"positive","score":0.9375733137130737},{"label":"neutral","score":0.6461083292961121},{"label":"mentions price","score":0.9435068368911743},{"label":"mentions durability","score":0.9721878170967102},{"label":"mentions noise","score":0.7320722937583923},{"label":"mentions delivery","score":0.9520477652549744}]},{"id":"inv_04","source":"invented","text":"The Pembrake trail shoes looked great out of the box, but the sole started peeling after two short hikes and the support team at Gristvale Outdoor never answered my emails.","prompt":null,"labels":["positive","negative","product quality","customer service","price","sizing"],"ids":[50281,50368,2762,50368,4016,50368,1885,3290,50368,7731,2579,50368,4376,50368,256,3006,50369,380,367,358,4946,413,11693,12682,3261,1270,562,273,253,3817,13,533,253,7934,3053,759,8855,846,767,2159,288,13972,285,253,1329,2285,387,1997,382,87,1079,6282,11806,1620,9577,619,16530,15,50282],"label_positions":[1,3,5,8,11,13],"window":128,"logits":[-5.768506050109863,5.412256240844727,2.2759017944335938,3.2131454944610596,1.5247962474822998,1.2387256622314453],"pipeline_single":[{"label":"negative","score":0.8401584029197693}],"pipeline_multi":[{"label":"negative","score":0.9955582618713379},{"label":"product quality","score":0.906861424446106},{"label":"customer service","score":0.9613259434700012},{"label":"price","score":0.8212436437606812},{"label":"sizing","score":0.7753421068191528}]},{"id":"inv_05","source":"invented","text":"The town council of Brackenfold approved a plan on Monday to turn the old Thistlecombe rail depot into a public library, with construction expected to begin next spring.","prompt":null,"labels":["local government","transportation","education","sports","business","weather","crime","culture"],"ids":[50281,50368,1980,2208,50368,13120,50368,4730,50368,9001,50368,2136,50368,8588,50368,6617,50368,4466,50369,380,3874,12265,273,2652,471,257,8089,7012,247,2098,327,7216,281,1614,253,1711,596,19300,49766,8087,1305,302,715,247,1345,6335,13,342,5140,3264,281,3135,1735,7203,15,50282],"label_positions":[1,4,6,8,10,12,14,16],"window":128,"logits":[2.032649278640747,2.9681835174560547,-2.064822196960449,-2.9853570461273193,0.05589117482304573,-2.0493955612182617,-2.959576368331909,-3.6506121158599854],"pipeline_single":[{"label":"transportation","score":0.681912899017334}],"pipeline_multi":[{"label":"local government","score":0.8841826915740967},{"label":"transportation","score":0.9511158466339111},{"label":"business","score":0.5139691829681396}]},{"id":"inv_06","source":"invented","text":"Hi Corwin, could we move Thursday's design review with the Lindqvale team to Friday at 10 am? I also need the updated budget sheet before the meeting.","prompt":null,"labels":["meeting reschedule","document request","complaint","invoice","job application"],"ids":[50281,50368,4804,501,1962,8009,50368,3389,2748,50368,5833,50368,45156,50368,2628,2898,50369,17459,3094,6481,13,812,359,2118,8216,434,2216,2278,342,253,12529,82,87,1079,2285,281,6794,387,884,717,32,309,671,878,253,9300,7563,8335,1078,253,4804,15,50282],"label_positions":[1,6,9,11,13],"window":128,"logits":[1.301638126373291,3.1355655193328857,-0.06942925602197647,-0.8441410064697266,0.23284102976322174],"pipeline_single":[{"label":"document request","score":0.7849856615066528}],"pipeline_multi":[{"label":"meeting reschedule","score":0.7861105799674988},{"label":"document request","score":0.9583361744880676},{"label":"job application","score":0.5579487085342407}]}]}