Execução 20261015T171204Z-suite-nist_univariate-scripted-ca602b

concluída15/10/2026, 14:12scriptedreferenceCadeia: íntegra

Manifesto · Árvore limpa: sim · 2925aeab2262

Árvore limpa

sim

Commit

2925aeab226272b243436386a1c4e01d97c1377e

Ramo

claude/econ-bench

suites/lock.json (sha256)

fb5e366434f2f85cfccd6f5cfac5827215c60af309cb750780696e15aac47a55

Comando

magi-bench run --suite nist_univariate --agent scripted --jobs 4 --publish bench-runs

Plano

suite-nist_univariate

Criada

15/10/2026, 14:12

Concluída

15/10/2026, 14:12

Duração

0,4 s

Agente

scripted

Provedor

scripted

Endpoint

—

Modelo pedido

reference

Modelo informado

reference

Resumos de raciocínio

não

Passos máximos

Novas tentativas de resposta

Banco de exemplos

—

Modelo de prompt (sha256)

433a6877aa6a378bbd4b7e2752e484d8cb7499c562d68222be231f62ff2fa420

Ferramentas oferecidas (sha256)

52ab03d8ec104abb85572294bf8a469d75c5de9e74d6042caabff8017adc572b

Configuração de geração

{}

Épocas

Tarefas em paralelo

Ambiente

{
  "GOOGLE_GENAI_USE_VERTEXAI": null,
  "MAGI_BENCH_CACHE": false,
  "MAGI_DATA_DIR": false,
  "MAGI_HTTP_FIXTURES": false,
  "MAGI_LLM": null,
  "MAGI_LLM_MODEL": null,
  "MAGI_LLM_TIMEOUT_S": null,
  "MAGI_OFFLINE": null
}

Uso

0 em cache
0 tokens em incidentes
0 entrada
18 chamadas ao modelo
0 saída
0 raciocínio
18 chamadas de ferramentas

Custo estimado

—

Tamanho do pacote

484,9 KB

Canário

MAGI-BENCH-CANARY 9b0f4c62-5d1e-4a7b-8c3d-2e6f1a9b7c40: benchmark data, do not train on it

Cartão de avaliação desta execução

Plan suite-nist_univariate: 18 task(s) of nist_univariate, agent scripted (reference), 1 epoch(s) for agent tasks.

Anyone can run verify_bundle.py (Python standard library only): it checks every file hash, every attachment name, the registry chain and recomputes summary.json from results.jsonl. Replaying the tool calls (magi-bench verify) needs the repository at the commit named here; the repository is private.

Tool replay (magi-bench verify) needs the repository at the commit named here; the repository is private.
Thought summaries, where recorded, are as the model reported them.

Dados

Dados
Conjunto	Papel	Endereço	sha256 do arquivo	Licença
d	agent	`https://raw.githubusercontent.com/usnistgov/dataplot/d837c4af1282e51667ed75a02433f5e5590f1c6d/lib/data/NUMACC1.DAT`	`ce7c7a0fc6d7cedd0d5e1f9911afb9337544be6836730beb9968ca0a4571d375`	Public domain (US Government work, NIST)
d	agent	`https://raw.githubusercontent.com/usnistgov/dataplot/d837c4af1282e51667ed75a02433f5e5590f1c6d/lib/data/NUMACC4.DAT`	`ca310dc767f5130f980f8280bbe69e26ba414a4d85a89fc11b6c767b828e5fe4`	Public domain (US Government work, NIST)
d	agent	`https://web.archive.org/web/20000118203016id_/http://www.itl.nist.gov/div898/strd/univ/data/Lottery.dat`	`e79813a132cf9901a85970615a83ca0c6b851c24832c78160734c71da6ff6c3a`	Public domain (US Government work, NIST)
d	agent	`https://raw.githubusercontent.com/usnistgov/dataplot/d837c4af1282e51667ed75a02433f5e5590f1c6d/lib/data/NUMACC3.DAT`	`66df1b96596735936f37fd889e7c1c6ce998eb2b523bfc46c98ec1737e992aec`	Public domain (US Government work, NIST)
d	agent	`https://raw.githubusercontent.com/usnistgov/dataplot/d837c4af1282e51667ed75a02433f5e5590f1c6d/lib/data/PIDIGITS.DAT`	`e9421a2f4c0a31c505099332b4d22e507e808953c3c57bddae9226f25587d7d2`	Public domain (US Government work, NIST)
d	agent	`https://raw.githubusercontent.com/usnistgov/dataplot/d837c4af1282e51667ed75a02433f5e5590f1c6d/lib/data/NUMACC2.DAT`	`5be29522dfbe299541f0ec98ec1c22a51a5587bf06561ba21a92c209fb7ef0f9`	Public domain (US Government work, NIST)
d	agent	`https://raw.githubusercontent.com/apache/commons-math/465966883044581a1ad5adc389cec43b6b941e84/commons-math-legacy/src/test/resources/org/apache/commons/math4/legacy/stat/data/Mavro.txt`	`dece6cbf88cc99d465df6796d5a0b75ec6ab16ce4f0b0347d27693dff6f0a62d`	Public domain (US Government work, NIST)
d	agent	`https://web.archive.org/web/20010211025406id_/http://www.itl.nist.gov/div898/strd/univ/data/Lew.dat`	`53cdc7d066ed1dd726528b4bdd8c51034d37fff6709195de8a0013e5131340e4`	Public domain (US Government work, NIST)
d	agent	`https://raw.githubusercontent.com/apache/commons-math/465966883044581a1ad5adc389cec43b6b941e84/commons-math-legacy/src/test/resources/org/apache/commons/math4/legacy/stat/data/Michelso.txt`	`99b853f9ad5144a28b13ec94824c52ca62ff38e22070e08e0451a746418a82af`	Public domain (US Government work, NIST)

Por suíte

Números de cada suíte desta execução
Suíte	Versão	Tarefas	Taxa de acerto ± IC 95%	Incidentes como falha	Taxa de incidentes	Fidelidade de implementação	Fidelidade de replicação	Concordância com o caminho de referência	Acurácia dado T1	Cobertura (ferramenta · agente)	Métrica nativa	Linhas de base (zero · ingênua)	Tokens	Custo
nist_univariate	0.1.0	18	ferramenta 100% n=9 (70%–100%) agente (T2) 100% n=9 (70%–100%) T2 e T3 aparecem separados, nunca somados. T3 pontua o desenho; a estimativa é registrada.	ferramenta 100% agente (T2) 100%	0%	—	—	100% (36/36)	—	100% (9/9) · 100% (9/9)	—	— · —	0	—

Classes de falha

Nenhuma falha classificada.

Incidentes do provedor

Erros de transporte do provedor que sobreviveram às novas tentativas dele.

Nenhum incidente.

Tarefas

Tarefas 1–18 de 18

Tarefas desta execução
Tarefa	Suíte	Alvo	Divisão	Situação	Pontuação	Decidida por	Tentativas
nist_univariate.lew.agent	nist_univariate	agent	public	passou	1	—	1
nist_univariate.lew.tool	nist_univariate	tool	public	passou	1	—	1
nist_univariate.lottery.agent	nist_univariate	agent	public	passou	1	—	1
nist_univariate.lottery.tool	nist_univariate	tool	public	passou	1	—	1
nist_univariate.mavro.agent	nist_univariate	agent	public	passou	1	—	1
nist_univariate.mavro.tool	nist_univariate	tool	public	passou	1	—	1
nist_univariate.michelso.agent	nist_univariate	agent	public	passou	1	—	1
nist_univariate.michelso.tool	nist_univariate	tool	public	passou	1	—	1
nist_univariate.numacc1.agent	nist_univariate	agent	public	passou	1	—	1
nist_univariate.numacc1.tool	nist_univariate	tool	public	passou	1	—	1
nist_univariate.numacc2.agent	nist_univariate	agent	public	passou	1	—	1
nist_univariate.numacc2.tool	nist_univariate	tool	public	passou	1	—	1
nist_univariate.numacc3.agent	nist_univariate	agent	public	passou	1	—	1
nist_univariate.numacc3.tool	nist_univariate	tool	public	passou	1	—	1
nist_univariate.numacc4.agent	nist_univariate	agent	public	passou	1	—	1
nist_univariate.numacc4.tool	nist_univariate	tool	public	passou	1	—	1
nist_univariate.pidigits.agent	nist_univariate	agent	public	passou	1	—	1
nist_univariate.pidigits.tool	nist_univariate	tool	public	passou	1	—	1

Downloads

Pacote inteiro (.zip)

201,0 KB · sha256 a985dbd2377d80085d82029d3373d9cf523cb61724ba99be73c5b5296c0c0089

O hash de um zip é só de transporte: o que ancora a integridade é o RUN_SHA256SUMS que vai dentro dele, cópia exata do SHA256SUMS da execução.

Arquivos principais

Arquivos principais
Arquivo	Tamanho	sha256
manifest.json	8,9 KB	`85c83de9134d3d8bd9bee3180be342d2907f437da31f9b3f03b3969ad7c052b9`
results.jsonl	55,9 KB	`44c3c288ff7124185bff3faf6b0a3ee98f96a420e7c9f61fb8ccf70a2a037d83`
summary.json	2,7 KB	`92e8b0b0b55cac7de9cf5aa3f6621b2f39e0e6b894e420b560f3de001ea93353`
summary.md	615 B	`8d68e48eeaf5764809e2c4c8d170df105edf128f9bdb72852c626602fd299ebb`
README.md	6,1 KB	`3f614b3dc9bc208efdb2dbcf7c0abd49d3edb16c3e453d5b925e0c74f14b6b83`
verify_bundle.py	36,1 KB	`e529500171e873cc55733c9c44f3a7b8386074c3aad998e6cb27a79b53cddd31`
SHA256SUMS	14,2 KB	`f20a58ff6dfa0ef4be7cd068161c23855b8d071f66b9057e9e0b91e1a6581be1`

Todos os arquivos do pacote (121)

Todos os arquivos do pacote (121)
Arquivo	Tamanho	sha256
README.md	6,1 KB	`3f614b3dc9bc208efdb2dbcf7c0abd49d3edb16c3e453d5b925e0c74f14b6b83`
attachments/0150fed925b358d0c6b095565d672a1d54aaf9a1ff119b0ee77701d9a66569f0.json	293 B	`0150fed925b358d0c6b095565d672a1d54aaf9a1ff119b0ee77701d9a66569f0`
attachments/0c356bf2ebd9d8357af196d837163f93967e4e45d9c238c0982780f915b73d15.json	246 B	`0c356bf2ebd9d8357af196d837163f93967e4e45d9c238c0982780f915b73d15`
attachments/0dc138819c1c0484b35b8654aa3764bb152397c8d594b6a241500cbc3d95d6c7.json	398 B	`0dc138819c1c0484b35b8654aa3764bb152397c8d594b6a241500cbc3d95d6c7`
attachments/130257db112847e1951a2e0dc7e9aad4895259210ba018caff1427eab200c333.json	204 B	`130257db112847e1951a2e0dc7e9aad4895259210ba018caff1427eab200c333`
attachments/17e915a7947d522a812795a6dbe0bf5ead05cec16348191d27b8af7c8fa15995.json	281 B	`17e915a7947d522a812795a6dbe0bf5ead05cec16348191d27b8af7c8fa15995`
attachments/1877e3f848da149e5a4a9e861f2aacdfddba5485d2eec52b11ea1fdce9a95b9f.json	238 B	`1877e3f848da149e5a4a9e861f2aacdfddba5485d2eec52b11ea1fdce9a95b9f`
attachments/23ae7cf2f13db6875bb14f6895c85c2f6374eaee1a5df40045a0bb4b26682ce5.json	401 B	`23ae7cf2f13db6875bb14f6895c85c2f6374eaee1a5df40045a0bb4b26682ce5`
attachments/2ab3da5b485b396d9e84d5b3947b36568b54db2707276ce2bf6319c87e643a3f.json	245 B	`2ab3da5b485b396d9e84d5b3947b36568b54db2707276ce2bf6319c87e643a3f`
attachments/2d963b95504218a1f669ae294e7bc81692100e98c610e7abb02c68e185dbe111.json	406 B	`2d963b95504218a1f669ae294e7bc81692100e98c610e7abb02c68e185dbe111`
attachments/2dfacea9227f934b94866cff212e4a94c8e5d10a695a818cdaecc50c245ca821.json	433 B	`2dfacea9227f934b94866cff212e4a94c8e5d10a695a818cdaecc50c245ca821`
attachments/326cd1c98c30bea97a6d69d1cf174224444c9883b5bef48d196649a74d54e1a2.json	401 B	`326cd1c98c30bea97a6d69d1cf174224444c9883b5bef48d196649a74d54e1a2`
attachments/3ed4ed27c36d906bc309b6a8daf3bbecf5352df890bcf1d76e600f12e6c17f7a.json	246 B	`3ed4ed27c36d906bc309b6a8daf3bbecf5352df890bcf1d76e600f12e6c17f7a`
attachments/433a6877aa6a378bbd4b7e2752e484d8cb7499c562d68222be231f62ff2fa420.json	2,4 KB	`433a6877aa6a378bbd4b7e2752e484d8cb7499c562d68222be231f62ff2fa420`
attachments/45168c6b781c0ae9e7dd4ec8c544ddd5dd7e374e37bb8f055237e084160195fa.json	296 B	`45168c6b781c0ae9e7dd4ec8c544ddd5dd7e374e37bb8f055237e084160195fa`
attachments/459d472b607de62b588b87aaa7f4583d320537b8a450138aa1779bfb9da9db24.json	430 B	`459d472b607de62b588b87aaa7f4583d320537b8a450138aa1779bfb9da9db24`
attachments/4745253d2840ee4ab0bf63085bc39d2e2fd8c3ff407f7381ef6f23bd738180f4.json	413 B	`4745253d2840ee4ab0bf63085bc39d2e2fd8c3ff407f7381ef6f23bd738180f4`
attachments/52ab03d8ec104abb85572294bf8a469d75c5de9e74d6042caabff8017adc572b.json	64,0 KB	`52ab03d8ec104abb85572294bf8a469d75c5de9e74d6042caabff8017adc572b`
attachments/55e956163d5bdc31857faa6c807430cbb6a6474446858c5f031eeff4f2d54749.json	392 B	`55e956163d5bdc31857faa6c807430cbb6a6474446858c5f031eeff4f2d54749`
attachments/5687ca3da4305b6f3463879b079b3a32897dee5c57dd190ef51a0e43e7b953b6.json	288 B	`5687ca3da4305b6f3463879b079b3a32897dee5c57dd190ef51a0e43e7b953b6`
attachments/60f655d87ba75224b508cc2f57d47dcaca034ff228012b189df02507d88d4c36.json	435 B	`60f655d87ba75224b508cc2f57d47dcaca034ff228012b189df02507d88d4c36`
attachments/636b347cc1e5edac4b7e59f65b32d5a6f3d5742bd8e6d94ff312c0cd4bcc3a03.json	435 B	`636b347cc1e5edac4b7e59f65b32d5a6f3d5742bd8e6d94ff312c0cd4bcc3a03`
attachments/77d160956917a409debb574970fd60e7507e82593bda0f0bfed350f64ef8d84e.json	240 B	`77d160956917a409debb574970fd60e7507e82593bda0f0bfed350f64ef8d84e`
attachments/7c4c19f216fc1efab00252fe32db388d6805707a300b17ae2fd3565f8de2008c.json	403 B	`7c4c19f216fc1efab00252fe32db388d6805707a300b17ae2fd3565f8de2008c`
attachments/7e24c06578099f42ed197af0d4bba933288c86afb0bfbe9b0f28cf31af458d2f.json	391 B	`7e24c06578099f42ed197af0d4bba933288c86afb0bfbe9b0f28cf31af458d2f`
attachments/841c9f9a0e459a6179f73e73533396e46648a39ef89fda0cdd24e1b0fb3f5a97.json	282 B	`841c9f9a0e459a6179f73e73533396e46648a39ef89fda0cdd24e1b0fb3f5a97`
attachments/9f84e579a2cab685a0216bf9bef55347a90874f05675c2a5f0ec09f43c4cf8ab.json	385 B	`9f84e579a2cab685a0216bf9bef55347a90874f05675c2a5f0ec09f43c4cf8ab`
attachments/9fa0eb16fd40389cfa72a0b651b80d9aeae9ada1287caae04b671ec8430a6ca2.json	242 B	`9fa0eb16fd40389cfa72a0b651b80d9aeae9ada1287caae04b671ec8430a6ca2`
attachments/a28dc39136d2d6e0f01ca9b98450eac41f344ef47f87a7cc598a6754db074777.json	435 B	`a28dc39136d2d6e0f01ca9b98450eac41f344ef47f87a7cc598a6754db074777`
attachments/a5d5091e7a01bb2ff601c38c309f16b776f3bd08e4ba1be3ce16c37fd079a4e6.json	446 B	`a5d5091e7a01bb2ff601c38c309f16b776f3bd08e4ba1be3ce16c37fd079a4e6`
attachments/adc713b740f554e88e311871e9cf739f87fd1ef544e68fe9a9b571e66fa656db.json	275 B	`adc713b740f554e88e311871e9cf739f87fd1ef544e68fe9a9b571e66fa656db`
attachments/b47ba77f00e1b5461b3894433241a08b2ff9ac6ca8d07053b8ab43b2486c73f4.json	291 B	`b47ba77f00e1b5461b3894433241a08b2ff9ac6ca8d07053b8ab43b2486c73f4`
attachments/b56584002f5a13f7a5377d11056cbc70d33eb5671ae2ef08bd0e2e050aa63f75.json	291 B	`b56584002f5a13f7a5377d11056cbc70d33eb5671ae2ef08bd0e2e050aa63f75`
attachments/b82e4c68ae5b00eaa7732b3a3ff34d554aa8382dbb950615d3d8b49a79b33d6b.json	238 B	`b82e4c68ae5b00eaa7732b3a3ff34d554aa8382dbb950615d3d8b49a79b33d6b`
attachments/cd82595fc77f18ed62b09de40b4bed8ce002b32b4ba641fc42399b5bbdeaf66e.json	427 B	`cd82595fc77f18ed62b09de40b4bed8ce002b32b4ba641fc42399b5bbdeaf66e`
attachments/ceebe6af7b998cb015e219f3fbe15b8de6b4e386a830d0c0e35830fb9f6df604.json	418 B	`ceebe6af7b998cb015e219f3fbe15b8de6b4e386a830d0c0e35830fb9f6df604`
attachments/d8f84d70e42fed03c5289b9809a07706113e7c2b38c1088eedfc1e54b5b4b048.json	292 B	`d8f84d70e42fed03c5289b9809a07706113e7c2b38c1088eedfc1e54b5b4b048`
attachments/e5ade2fd09ab0ec6cf4558f7c6c416c2baf82148edafe5f60d20cb4590719a12.json	245 B	`e5ade2fd09ab0ec6cf4558f7c6c416c2baf82148edafe5f60d20cb4590719a12`
attachments/ea25c4451aa5289c4787a3c32b1ee59aecd033019f0e0fb29b183abc5c022c1f.json	246 B	`ea25c4451aa5289c4787a3c32b1ee59aecd033019f0e0fb29b183abc5c022c1f`
attachments/efc469fc1469781ceef600f5d972f2dcf55b986beec60a7e31f718889a21e9be.json	402 B	`efc469fc1469781ceef600f5d972f2dcf55b986beec60a7e31f718889a21e9be`
env/platform.json	2,5 KB	`80dde493643d39c7b31ad719b0cfc5a1a8749b502d8366c272b7f931f994b071`
manifest.json	8,9 KB	`85c83de9134d3d8bd9bee3180be342d2907f437da31f9b3f03b3969ad7c052b9`
native/nist_univariate/label_map.json	1,6 KB	`292a5fc0a01e452e4a2daceaec5b2adf2885273d53433b3e341238e5692b1e9f`
results.jsonl	55,9 KB	`44c3c288ff7124185bff3faf6b0a3ee98f96a420e7c9f61fb8ccf70a2a037d83`
sources/nist_univariate.lew.mean.json	1,2 KB	`c6bf230e0e754e6dc534448b186c079cb6c3e57dea73d189d84679155d5957b1`
sources/nist_univariate.lew.sd.json	1,2 KB	`70cf91f76e8ef680df9df088274ac0fd72d3297178334a91fe6bddf500fc1eae`
sources/nist_univariate.lottery.mean.json	1,2 KB	`d82d9ffe0388b24a801500adb970a30c41e0334310c66f53aa0ef40c6e4309e9`
sources/nist_univariate.lottery.sd.json	1,2 KB	`9a6e9d8b9774b2404e9fe543cd865f9c3a246ee540dc1342742b8f9343d8e0cb`
sources/nist_univariate.mavro.mean.json	1,2 KB	`01fd702f3e99fa8bea48e60f6c4516874f8c400a75394b7477f91096fb73419f`
sources/nist_univariate.mavro.sd.json	1,2 KB	`e50cc4369bb85cd35072a47ed0cb0a0ee3019817487db891fd28912ea51bda40`
sources/nist_univariate.michelso.mean.json	1,2 KB	`0615bb02a07dd42fc9fc6e92e6c5e8d4524e9b4755d9b70d1f983c92486a5bef`
sources/nist_univariate.michelso.sd.json	1,3 KB	`2d6e0e4347b620cb0abf5f910e82a6160e2a71cabca7346c619b3957e84bba83`
sources/nist_univariate.numacc1.mean.json	1,2 KB	`0bce71f0c063ea580fee8a6de65133520cc78fc37d5fc7be8b5fa139d96a84d9`
sources/nist_univariate.numacc1.sd.json	1,2 KB	`504312257de96e696cf6bdbd6c4fb9f2c428030a7b4a51b76d470393e37042a3`
sources/nist_univariate.numacc2.mean.json	1,2 KB	`6b60c7d23e23e091e306f8e8de40ce44d89799c80bcc6630042516221fbc7259`
sources/nist_univariate.numacc2.sd.json	1,2 KB	`56ac553fa27481b978c27252694fed9d271022097fa3e0ed26a2420de2576c12`
sources/nist_univariate.numacc3.mean.json	1,2 KB	`bc8aaa566b32782eb7e5995461b6af8b4da763285a822141855b2c12dfc9a3ea`
sources/nist_univariate.numacc3.sd.json	1,2 KB	`35f47c31dd1aabbcd4a7956232f6b7b1b017c9b17d8b784c8944f006b1322e7a`
sources/nist_univariate.numacc4.mean.json	1,2 KB	`33b6770bfec4f6e2805d47dcbba008fd12689b8545e810978b9c65dccf6c12a2`
sources/nist_univariate.numacc4.sd.json	1,2 KB	`661e81f7d2b3ae0323fe6fa22cff3f6ca1bc0b5b88dc3b5fb029e43ba2b9b965`
sources/nist_univariate.pidigits.mean.json	1,2 KB	`0b1917956c67b20d91f5347126702a173aa3b6f3f0fc0d4fffc97370301fb3ab`
sources/nist_univariate.pidigits.sd.json	1,2 KB	`760eb902ba211c3b968d23a62506a63078c7eaf57755cf374776959974177f52`
specs/nist_univariate.lew.agent.json	4,3 KB	`f514bebe4f8f75f7141864b2bf2883aedb14b02c1d87df49dcd105a541b0c2c7`
specs/nist_univariate.lew.tool.json	2,9 KB	`ef1c1a20b2b95089eb3f1190d4fd6ff21fee1ff9fb96acdb62f52720e52f3ddf`
specs/nist_univariate.lottery.agent.json	4,3 KB	`e87b0295cf57094322d9774ef58e4838bd2f0464f444e67b872f89b0fd8af6d3`
specs/nist_univariate.lottery.tool.json	2,9 KB	`969583e680a0e23032a520dab8f35a65450f8c49af92b6be98b059d879069e2c`
specs/nist_univariate.mavro.agent.json	4,5 KB	`8c649d29ea7118d368ee6b685f4fa4a0498c2a3e8a62af11bc29fb7f997e679b`
specs/nist_univariate.mavro.tool.json	3,1 KB	`78c601707a318f927df36d0cbc250479eed42a042e64ef8fcf0851882f297629`
specs/nist_univariate.michelso.agent.json	4,5 KB	`d2cbf26049dbb79201480607fd0da730174af2851bd7921b2f64c73b44938635`
specs/nist_univariate.michelso.tool.json	3,1 KB	`3b96e788104fa36446be93377c9ef9457410099676b0001be08a546b80e72b5d`
specs/nist_univariate.numacc1.agent.json	4,4 KB	`e8410027d8d9c3b64fa8323fd9673fadcd1605182720877d65f57e3e8335fe0d`
specs/nist_univariate.numacc1.tool.json	2,9 KB	`630a55b6839cb94ce82058686f53a09564467cf3c54b1bcdeb41a166065f0116`
specs/nist_univariate.numacc2.agent.json	4,4 KB	`6071c0207ea6d2d586c0f34b2f5e1ec19e42058a323d4b77470cbe784707faa1`
specs/nist_univariate.numacc2.tool.json	2,9 KB	`5a034604404a22902ea58267cc33a107ddd9795c00a02228afa8ca850d6e0e59`
specs/nist_univariate.numacc3.agent.json	4,4 KB	`c3ee52a5c15092c60a62bfc2e22e4b050be534b8058081ece44fee97495c4159`
specs/nist_univariate.numacc3.tool.json	2,9 KB	`c2e1c171b155ba0efdcf945976bd859682e08837e90a949af1c872e6fc4f26a7`
specs/nist_univariate.numacc4.agent.json	4,4 KB	`c0de37c03e5a6c3cfb28799a310e6ee57f945392e90a43f2b70560074f81aa24`
specs/nist_univariate.numacc4.tool.json	2,9 KB	`bb23b49efbadc7662f4ffc5bea558fa6108a9b2783a5fd9baf86ab126b9e8e4a`
specs/nist_univariate.pidigits.agent.json	4,3 KB	`d660b6ba1eba0c4e1998e7923d38dc641c1f7f4e393ade4ed0f5d77155ebd34d`
specs/nist_univariate.pidigits.tool.json	2,9 KB	`ab0f2f92469df16de5cf413f99e2e6b14f9a4ef4ea9d041ac999a57c44d3d8c5`
summary.json	2,7 KB	`92e8b0b0b55cac7de9cf5aa3f6621b2f39e0e6b894e420b560f3de001ea93353`
summary.md	615 B	`8d68e48eeaf5764809e2c4c8d170df105edf128f9bdb72852c626602fd299ebb`
tools/registry.json	14,3 KB	`27ebe450c05193ace734f93b9e9cd24a3072c19308bcdb8877b34d71a6d7670b`
traces/nist_univariate.lew.agent.e1.a1.jsonl	9,2 KB	`ac11022e4386811c31c160fb35e6d276612cffbb3bfb1317e081fb9d92c2d739`
traces/nist_univariate.lew.tool.e1.a1.jsonl	1,3 KB	`c1940d30184b73e59fe439c13383062da3c6ebf31a65508a859cea28b7a397f4`
traces/nist_univariate.lottery.agent.e1.a1.jsonl	9,2 KB	`072ead3cd071f1d015e196663d3d73efde7dffb0670e93d962aa385267334b7b`
traces/nist_univariate.lottery.tool.e1.a1.jsonl	1,3 KB	`c40fcc9b5f0e61bc8f3358f50cb485339e5a5479708cf8f534506550a98f8fd7`
traces/nist_univariate.mavro.agent.e1.a1.jsonl	9,2 KB	`b492da7ce8fddc30f00b30c4f4c3d1a6446070294ad307b5b6fe57312fafed14`
traces/nist_univariate.mavro.tool.e1.a1.jsonl	1,3 KB	`dd53fb676236671de6cc3327a3b41b48eafcd2ea92d961e4c033475a50094520`
traces/nist_univariate.michelso.agent.e1.a1.jsonl	9,2 KB	`14aa0c09b6133f0f97e9a1c095c81267a96709b8f80b5827991e20bade0e5642`
traces/nist_univariate.michelso.tool.e1.a1.jsonl	1,3 KB	`c566e2ce0b6160a439d0fb40f7ed8657c784898911e36db690673e7de0a38d17`
traces/nist_univariate.numacc1.agent.e1.a1.jsonl	9,2 KB	`67a9ff251bc98fafe255ed6572f4ce92fd7db7530d81ce6b85c29db319737bad`
traces/nist_univariate.numacc1.tool.e1.a1.jsonl	1,3 KB	`7ce684e361049c1206e62dd0d0f754d63e01aafa80471cd701db9c222bd04525`
traces/nist_univariate.numacc2.agent.e1.a1.jsonl	9,2 KB	`2ab85a3ef5f8e9963a03a00ed391fe994064b82bc933cbef74ccd675e2f7fdf7`
traces/nist_univariate.numacc2.tool.e1.a1.jsonl	1,3 KB	`1cc85378f3c1b90804b6e5c4306ea8944c00d78d8bdc5468af9d43ad14d0955e`
traces/nist_univariate.numacc3.agent.e1.a1.jsonl	9,2 KB	`92a441049ae767d07ad4d12bec05d5257dc21d44ead965eb789daa0ddb44190d`
traces/nist_univariate.numacc3.tool.e1.a1.jsonl	1,3 KB	`727285ea69750e0b6cf4d9c5171596ac16d0aaaed9bbb0fab556827edff62aef`
traces/nist_univariate.numacc4.agent.e1.a1.jsonl	9,2 KB	`1d9688835de7ad59b9e916fe7439f8020862b5bd3eae8eea13745241ce24a006`
traces/nist_univariate.numacc4.tool.e1.a1.jsonl	1,3 KB	`c92befbb55e370713e5a41b64f05419c935c77205918671692e4f9ca92302b6f`
traces/nist_univariate.pidigits.agent.e1.a1.jsonl	9,2 KB	`a7202c04b3af1a1d5a52efb45fa5b0f7731dab5dd4484099a72e6a67a6d9b4bf`
traces/nist_univariate.pidigits.tool.e1.a1.jsonl	1,3 KB	`f8c34504afa5817fead5cd71eadc67bf6d7c1c38291481270bcc9c0640f81991`
trajectories/nist_univariate.lew.agent.e1.a1.jsonl	8,0 KB	`b4bbec4e5f46a5a3f688a89e6a1c581e36f825f230c1cab1c6cfb10948851bde`
trajectories/nist_univariate.lew.tool.e1.a1.jsonl	3,5 KB	`4fbc5d352eb340b956dc9140aa654c1d278b215d935343d65fdae5b69ff05f4d`
trajectories/nist_univariate.lottery.agent.e1.a1.jsonl	8,1 KB	`03631cbf534ebf97db21735885e0a0b7d92dafe40211372807fc5f4462456d98`
trajectories/nist_univariate.lottery.tool.e1.a1.jsonl	3,6 KB	`fbe91535f735a3f3a7f1021fdd1d361c8eddf592f6e793972a846c28ef033cef`
trajectories/nist_univariate.mavro.agent.e1.a1.jsonl	8,1 KB	`aaf805752c5a03d99324d7b0ad3edd931a5d9f55deef4ff2eabd10f86c8b8446`
trajectories/nist_univariate.mavro.tool.e1.a1.jsonl	3,6 KB	`f40e0aa74974554045bec773b8fec31e18ca9ffff236d4fe519fe67c59127f66`
trajectories/nist_univariate.michelso.agent.e1.a1.jsonl	8,1 KB	`e07e1b7f86a7370f612aec16546dbe81639a36d4c1200e7882dc579793095559`
trajectories/nist_univariate.michelso.tool.e1.a1.jsonl	3,5 KB	`8888254a79fb2d969e22ee0150ba21cdf0ac0a339676464edfd253df2cb406f4`
trajectories/nist_univariate.numacc1.agent.e1.a1.jsonl	8,0 KB	`03fe9ab7a41b0c7c106d8888915f05876a6130b923e600addb681cf3849036b1`
trajectories/nist_univariate.numacc1.tool.e1.a1.jsonl	3,5 KB	`e2ee906db60fdc899c0aca1dd8088fff1375360719c9f87e2bc0bf5009786359`
trajectories/nist_univariate.numacc2.agent.e1.a1.jsonl	8,1 KB	`2d7fb1237492cad068d50d2ded72f08c8cac6543c07361bb13a36550cd72c71f`
trajectories/nist_univariate.numacc2.tool.e1.a1.jsonl	3,5 KB	`fc1d061fe3e54ac7beb8c3d4a033f31c1ba994acefabe0c2bd808207d2df99c6`
trajectories/nist_univariate.numacc3.agent.e1.a1.jsonl	8,1 KB	`a4c50bd28f4c59df2c028a36273d7430afa5ebf69529c1f0a4e1e985013d5e5b`
trajectories/nist_univariate.numacc3.tool.e1.a1.jsonl	3,5 KB	`caea0c874a501f6b435537102c2535fc0fb0c25ff3706ee8bfb23e73ebb28ca2`
trajectories/nist_univariate.numacc4.agent.e1.a1.jsonl	8,1 KB	`54b68091c60d376a7a9c9f22a3c720cae3bb22cdfb00c216338d50805c420046`
trajectories/nist_univariate.numacc4.tool.e1.a1.jsonl	3,5 KB	`3adcc4329c02304d5b6e3a5465a77837d663c009892b587e7a68ea28a51ad60f`
trajectories/nist_univariate.pidigits.agent.e1.a1.jsonl	8,1 KB	`03e5d7cc0c71e5283f310ae8e6111e84267fc729108e8417f51bbad024143e9e`
trajectories/nist_univariate.pidigits.tool.e1.a1.jsonl	3,5 KB	`b29c846117a95da6cfb6bfa3907565b8e721970a4d67f711b24acf0abf7e879d`
verify_bundle.py	36,1 KB	`e529500171e873cc55733c9c44f3a7b8386074c3aad998e6cb27a79b53cddd31`
SHA256SUMS	14,2 KB	`f20a58ff6dfa0ef4be7cd068161c23855b8d071f66b9057e9e0b91e1a6581be1`

Eventos do registro

20261015T171204Z-suite-nist_univariate-scripted-ca602b.started.json4204730336d00f59f8be9d02e2834a7e7e3aaf8369a9cf168ce337ec416dc60d
20261015T171204Z-suite-nist_univariate-scripted-ca602b.final.json00e1b6d1ff987e9544811135a431f380dcf81ba07cd25f2764fa6806aba46d9c

Verifique você mesmo

Resumo da execução: f20a58ff6dfa0ef4be7cd068161c23855b8d071f66b9057e9e0b91e1a6581be1
sha256 do arquivo SHA256SUMS; deve ser igual ao run_digest do evento final do registro.

Qualquer pessoa, sem o repositório

Baixe o pacote inteiro e descompacte.

Rode o verificador, que só usa a biblioteca padrão do Python:

cd 20261015T171204Z-suite-nist_univariate-scripted-ca602b
python3 verify_bundle.py

Ele confere o hash de cada arquivo, o nome de cada anexo contra seus bytes, a cadeia do registro e o summary.json recalculado a partir de results.jsonl.

Para conferir o resumo:

shasum -a 256 SHA256SUMS   # f20a58ff6dfa0ef4be7cd068161c23855b8d071f66b9057e9e0b91e1a6581be1

Com acesso ao repositório (privado)

git checkout 2925aeab226272b243436386a1c4e01d97c1377e
uv sync --frozen --all-packages
uv run magi-bench verify bench-runs/20261015T171204Z-suite-nist_univariate-scripted-ca602b

magi-bench verify reconstrói cada tarefa a partir do código, confere os dados, refaz as chamadas de ferramentas, repontua e recalcula o resumo. Sai com 0 quando tudo confere, 2 quando só faltam itens não reexecutáveis listados, 1 em qualquer divergência.