Pular para o conteúdo
Voltar aos benchmarks

Execução 20261015T171234Z-suite-nist_anova-baseline-71784e

concluída15/10/2026, 14:12baselinerules-1Cadeia: 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_anova --agent baseline --jobs 4 --publish bench-runs
Plano
suite-nist_anova
Criada
15/10/2026, 14:12
Concluída
15/10/2026, 14:12
Duração
0,6 s
Agente
baseline
Provedor
baseline
Endpoint
—
Modelo pedido
rules-1
Modelo informado
rules-1
Resumos de raciocínio
não
Passos máximos
12
Novas tentativas de resposta
1
Banco de exemplos
—
Modelo de prompt (sha256)
433a6877aa6a378bbd4b7e2752e484d8cb7499c562d68222be231f62ff2fa420
Ferramentas oferecidas (sha256)
52ab03d8ec104abb85572294bf8a469d75c5de9e74d6042caabff8017adc572b
Configuração de geração
{}
Épocas
1
Tarefas em paralelo
4
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
  • 11 chamadas ao modelo
  • 0 saída
  • 0 raciocínio
  • 11 chamadas de ferramentas
Custo estimado
—
Tamanho do pacote
706,4 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_anova: 22 task(s) of nist_anova, agent baseline (rules-1), 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
ConjuntoPapelEndereçosha256 do arquivoLicença
dagenthttps://raw.githubusercontent.com/scipy/scipy/92d2a8592782ee19a1161d0bf3fc2241ba78bb63/scipy/stats/tests/data/nist_anova/SmLs03.dateb23c78904a4d0a238a144503a4f7db7eb849be21937ef1e20f1dbff2d264355Public domain (US Government work, NIST)
dagenthttps://raw.githubusercontent.com/scipy/scipy/92d2a8592782ee19a1161d0bf3fc2241ba78bb63/scipy/stats/tests/data/nist_anova/SmLs02.dat9c23f2c51935740a123d6882ee41b874b697b3618bdfe2915d1b76370817a080Public domain (US Government work, NIST)
dagenthttps://raw.githubusercontent.com/scipy/scipy/92d2a8592782ee19a1161d0bf3fc2241ba78bb63/scipy/stats/tests/data/nist_anova/SmLs07.dat42d492d7577ebe456fa9a204789ea8370c844f508aa3242a8e57c1976b133890Public domain (US Government work, NIST)
dagenthttps://raw.githubusercontent.com/scipy/scipy/92d2a8592782ee19a1161d0bf3fc2241ba78bb63/scipy/stats/tests/data/nist_anova/SmLs09.dataa610b390c8d947ec258e32df0f43467fcb1820f47c5ce25a993ae1d9c715ae7Public domain (US Government work, NIST)
dagenthttps://raw.githubusercontent.com/scipy/scipy/92d2a8592782ee19a1161d0bf3fc2241ba78bb63/scipy/stats/tests/data/nist_anova/SmLs08.dataabc5043423a82786b79fca02b04f8f31f9bcfef25683f15a67edcf359c84d18Public domain (US Government work, NIST)
dagenthttps://raw.githubusercontent.com/scipy/scipy/92d2a8592782ee19a1161d0bf3fc2241ba78bb63/scipy/stats/tests/data/nist_anova/SmLs05.dat8894da0165059fb0cf2d377d6d087f10c2842b50cf1b47e737cc64ec14253d11Public domain (US Government work, NIST)
dagenthttps://raw.githubusercontent.com/scipy/scipy/92d2a8592782ee19a1161d0bf3fc2241ba78bb63/scipy/stats/tests/data/nist_anova/AtmWtAg.dat41d7748bb1f870d8400017c53993eea65862ffd482aae1693be84d93245c303fPublic domain (US Government work, NIST)
dagenthttps://raw.githubusercontent.com/scipy/scipy/92d2a8592782ee19a1161d0bf3fc2241ba78bb63/scipy/stats/tests/data/nist_anova/SiRstv.datc7dc09da0d6a9f37f80caff0f45fd688e883303120e2d776cfab94efb1b4ef13Public domain (US Government work, NIST)
dagenthttps://raw.githubusercontent.com/scipy/scipy/92d2a8592782ee19a1161d0bf3fc2241ba78bb63/scipy/stats/tests/data/nist_anova/SmLs01.dat29d9c979d46d845ed72c0fb0ed79083c8313833bbcf72040326640d87e2e40e4Public domain (US Government work, NIST)
dagenthttps://raw.githubusercontent.com/scipy/scipy/92d2a8592782ee19a1161d0bf3fc2241ba78bb63/scipy/stats/tests/data/nist_anova/SmLs06.datae23a4613f8b46098984fa422b7db1ef16270f7f20c2787f128d57f0e2b778dfPublic domain (US Government work, NIST)
dagenthttps://raw.githubusercontent.com/scipy/scipy/92d2a8592782ee19a1161d0bf3fc2241ba78bb63/scipy/stats/tests/data/nist_anova/SmLs04.dat7c8f87a60245f5c7467418a7725855cce71608273964966e5da954c22ad5fa57Public domain (US Government work, NIST)

Por suíte

Números de cada suíte desta execução
SuíteVersãoTarefasTaxa de acerto ± IC 95%Incidentes como falhaTaxa de incidentesFidelidade de implementaçãoFidelidade de replicaçãoConcordância com o caminho de referênciaAcurácia dado T1Cobertura (ferramenta · agente)Métrica nativaLinhas de base (zero · ingênua)TokensCusto
nist_anova0.1.122
  • ferramenta 73% n=11 (43%–90%)
  • agente (T2) 0% n=11 (0%–26%)
T2 e T3 aparecem separados, nunca somados. T3 pontua o desenho; a estimativa é registrada.
  • ferramenta 73%
  • agente (T2) 0%
0%——73% (8/11)—100% (11/11) · 100% (11/11)—— · —0—

Classes de falha

Quantas tarefas cada classe de falha decidiu, por suíte
SuíteClasses de falhaTarefas
nist_anovanenhuma estimativa citada no_estimate_cited11
nist_anovafora da tolerância out_of_tolerance3

Incidentes do provedor

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

Nenhum incidente.

Tarefas

Tarefas 1–22 de 22

Tarefas desta execução
TarefaSuíteAlvoDivisãoSituaçãoPontuaçãoDecidida porTentativas
nist_anova.atmwtag.agentnist_anovaagentpublicfalhou0,142857nenhuma estimativa citada (#1)1
nist_anova.atmwtag.toolnist_anovatoolpublicpassou1—1
nist_anova.sirstv.agentnist_anovaagentpublicfalhou0,142857nenhuma estimativa citada (#1)1
nist_anova.sirstv.toolnist_anovatoolpublicpassou1—1
nist_anova.smls01.agentnist_anovaagentpublicfalhou0,142857nenhuma estimativa citada (#1)1
nist_anova.smls01.toolnist_anovatoolpublicpassou1—1
nist_anova.smls02.agentnist_anovaagentpublicfalhou0,142857nenhuma estimativa citada (#1)1
nist_anova.smls02.toolnist_anovatoolpublicpassou1—1
nist_anova.smls03.agentnist_anovaagentpublicfalhou0,142857nenhuma estimativa citada (#1)1
nist_anova.smls03.toolnist_anovatoolpublicpassou1—1
nist_anova.smls04.agentnist_anovaagentpublicfalhou0,142857nenhuma estimativa citada (#1)1
nist_anova.smls04.toolnist_anovatoolpublicpassou1—1
nist_anova.smls05.agentnist_anovaagentpublicfalhou0,142857nenhuma estimativa citada (#1)1
nist_anova.smls05.toolnist_anovatoolpublicpassou1—1
nist_anova.smls06.agentnist_anovaagentpublicfalhou0,142857nenhuma estimativa citada (#1)1
nist_anova.smls06.toolnist_anovatoolpublicpassou1—1
nist_anova.smls07.agentnist_anovaagentpublicfalhou0,142857nenhuma estimativa citada (#1)1
nist_anova.smls07.toolnist_anovatoolpublicfalhou0,75fora da tolerância (#3)1
nist_anova.smls08.agentnist_anovaagentpublicfalhou0,142857nenhuma estimativa citada (#1)1
nist_anova.smls08.toolnist_anovatoolpublicfalhou0,75fora da tolerância (#3)1
nist_anova.smls09.agentnist_anovaagentpublicfalhou0,142857nenhuma estimativa citada (#1)1
nist_anova.smls09.toolnist_anovatoolpublicfalhou0,75fora da tolerância (#3)1

Downloads

Pacote inteiro (.zip)
237,4 KB · sha256 8caa739c9fcf8b172f051424d3b61726d73f543ef238b27df227ba4f8261d607

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
ArquivoTamanhosha256
manifest.json9,8 KBa45199d27cf04484011e5e877d1deea1f06a9f34bc1758816d4f95dc9cac0637
results.jsonl103,7 KBfb410040370cbed822c4fc86b7a418cd5a87b60312ab1bd236b6de95ce13c909
summary.json3,0 KBa675117bdc734eef722529da18cb2f878985ad1cb03a985af33ebcf608850290
summary.md656 Bfa6dc99f02f6be96ce45272571a9392432c345acd253f464d090636355088678
README.md6,7 KBfb944adca8353ebb8bc45cf6c14bbef128d68ac68bc3e3e45ae6d05770845e86
verify_bundle.py36,1 KBe529500171e873cc55733c9c44f3a7b8386074c3aad998e6cb27a79b53cddd31
SHA256SUMS12,1 KB4d086120920fa8328d3fa04f999833d3702e04cd0e7815a8a6d2fdbf7c3624cc
Todos os arquivos do pacote (110)
Todos os arquivos do pacote (110)
ArquivoTamanhosha256
README.md6,7 KBfb944adca8353ebb8bc45cf6c14bbef128d68ac68bc3e3e45ae6d05770845e86
attachments/0c102fd5acc443f1811649c0b90dea80adeff3befc5bda208043aef3787789af.json679 B0c102fd5acc443f1811649c0b90dea80adeff3befc5bda208043aef3787789af
attachments/0e301ed3af0ef17536c53475e22ec24b40e112f716409516c36cc788dc3e07f7.json623 B0e301ed3af0ef17536c53475e22ec24b40e112f716409516c36cc788dc3e07f7
attachments/0f7dcb669869c69d9c86c521075f49e679546c4800fa6cf737aaeab3bbd2b00a.json440 B0f7dcb669869c69d9c86c521075f49e679546c4800fa6cf737aaeab3bbd2b00a
attachments/1edf672eb0e2d370794ac0239f2070db7deb764823ede3dfbbf3dcfc6152e906.json655 B1edf672eb0e2d370794ac0239f2070db7deb764823ede3dfbbf3dcfc6152e906
attachments/1f99f36ee436b4adef1f4ef2806080532383d9de4d815fa11951bffc9c4153e9.json683 B1f99f36ee436b4adef1f4ef2806080532383d9de4d815fa11951bffc9c4153e9
attachments/2067a9a59b5531f1c95228862190141e088490ae88a96fdb6a94369e40dc9900.json567 B2067a9a59b5531f1c95228862190141e088490ae88a96fdb6a94369e40dc9900
attachments/4176e046d8b1507b577753171db7343f29408fbd4c82328905efcbc297d73849.json683 B4176e046d8b1507b577753171db7343f29408fbd4c82328905efcbc297d73849
attachments/433a6877aa6a378bbd4b7e2752e484d8cb7499c562d68222be231f62ff2fa420.json2,4 KB433a6877aa6a378bbd4b7e2752e484d8cb7499c562d68222be231f62ff2fa420
attachments/4f24c5cd2598c347e6daa325e0045b0e389ddcd2c5aca33da0c6ec11d5becb20.json621 B4f24c5cd2598c347e6daa325e0045b0e389ddcd2c5aca33da0c6ec11d5becb20
attachments/52ab03d8ec104abb85572294bf8a469d75c5de9e74d6042caabff8017adc572b.json64,0 KB52ab03d8ec104abb85572294bf8a469d75c5de9e74d6042caabff8017adc572b
attachments/64dafc339f5a91e73db345541b83c329e73c0bb33ace22972cece72c303dea8a.json681 B64dafc339f5a91e73db345541b83c329e73c0bb33ace22972cece72c303dea8a
attachments/6c5ebf5edb18ce2a66bbb9eb5fa99f326c43b8f9657aee85bab2dd62582b6b98.json624 B6c5ebf5edb18ce2a66bbb9eb5fa99f326c43b8f9657aee85bab2dd62582b6b98
attachments/7c5a1060ea78f57b6e5e311278f2d0d2ebc40319f05ec940305043d08c9ccb72.json622 B7c5a1060ea78f57b6e5e311278f2d0d2ebc40319f05ec940305043d08c9ccb72
attachments/7ff22857fdfc78abec02cac245299defc0894002536c1283147e87f6d04bf78a.json679 B7ff22857fdfc78abec02cac245299defc0894002536c1283147e87f6d04bf78a
attachments/8e3f2e9bfa7bae3a646541c9714d4c8543aa3c291570095e43b00eb7123064aa.json681 B8e3f2e9bfa7bae3a646541c9714d4c8543aa3c291570095e43b00eb7123064aa
attachments/9277bb4d86b40aa659e1c0b7ebf85ca63569228dcf99cd9c8908a391ccb802b3.json679 B9277bb4d86b40aa659e1c0b7ebf85ca63569228dcf99cd9c8908a391ccb802b3
attachments/aadeb977d60c8e4aca76275ea9e8433f05fcb0a99f8ad5331ab03f648ebe741f.json683 Baadeb977d60c8e4aca76275ea9e8433f05fcb0a99f8ad5331ab03f648ebe741f
attachments/abc3d4859f96d4af20668ae1bc5719b3d71a73558e6b4571c7007cad69dec1b8.json681 Babc3d4859f96d4af20668ae1bc5719b3d71a73558e6b4571c7007cad69dec1b8
attachments/b2583ec1de10d91e7032e70925b0c69f730866a8ea03d9be6af7ff5f8746155a.json621 Bb2583ec1de10d91e7032e70925b0c69f730866a8ea03d9be6af7ff5f8746155a
attachments/c9e12a4fad84731cfa6886a57a2472697cddbb7037777fce51020784d588ae33.json623 Bc9e12a4fad84731cfa6886a57a2472697cddbb7037777fce51020784d588ae33
attachments/cd3253465d6761cc9505175a5189f1b9665c6d7dc01031fb7f7b84876774b518.json623 Bcd3253465d6761cc9505175a5189f1b9665c6d7dc01031fb7f7b84876774b518
attachments/d31dd13b45095fbc71a3c9216c5eb92ac726d3df06edc56d5da76a51c8c3d023.json622 Bd31dd13b45095fbc71a3c9216c5eb92ac726d3df06edc56d5da76a51c8c3d023
attachments/dfb9851cc07f8a9c67e105acae6e6c3e36240741df69936e11b3d632b4acdd7e.json622 Bdfb9851cc07f8a9c67e105acae6e6c3e36240741df69936e11b3d632b4acdd7e
attachments/ef7e7412e67c8e0d1fbecb44b3287ff41466d1bf058bdcee277fd655251ccc0f.json637 Bef7e7412e67c8e0d1fbecb44b3287ff41466d1bf058bdcee277fd655251ccc0f
env/platform.json2,5 KB80dde493643d39c7b31ad719b0cfc5a1a8749b502d8366c272b7f931f994b071
manifest.json9,8 KBa45199d27cf04484011e5e877d1deea1f06a9f34bc1758816d4f95dc9cac0637
results.jsonl103,7 KBfb410040370cbed822c4fc86b7a418cd5a87b60312ab1bd236b6de95ce13c909
sources/nist_anova.atmwtag.f.json1,2 KBb5a6c5c5287a671b1621401bd30326d0bc5fd35a814eb2bc445d3cc2e7c8ca83
sources/nist_anova.sirstv.f.json1,2 KBbf95547264806865e0fbac859e1a826b51ec3e962abf8c5c325440de1b629d15
sources/nist_anova.smls01.f.json1,2 KBe4bac31e384f00a16dc4f43b7af9ca2accd4eb6022a4bee54a335b4bbadb29b5
sources/nist_anova.smls02.f.json1,2 KB6242118874f8283982f44712457bfc42b1c32413bef7f45c8f1d0a8cba31e692
sources/nist_anova.smls03.f.json1,2 KB1291a925871f113ee2b09f2e5c740c4220ed2a455508d6be8ce579b9cde0f610
sources/nist_anova.smls04.f.json1,2 KB0099df50ab3624047eecdc2a05e24bb0cd3f6569bc2223440737d6aa5fd257c2
sources/nist_anova.smls05.f.json1,2 KB3fad3999338a84dabf3d585db7f25173185d9638fd19ba41245508ba56e3a8c6
sources/nist_anova.smls06.f.json1,2 KB01e9663e93374309c62f7cea1b86e2456b7c1353403253520b623180d60661f2
sources/nist_anova.smls07.f.json1,2 KB5628f56eac524a8645542e90f71e531a745fecc3dbb1edc919dd6ccf2905c6d7
sources/nist_anova.smls08.f.json1,2 KBeaed1f36bf86587d01263821f60819637461409770d8b1fbd599407a3d003230
sources/nist_anova.smls09.f.json1,2 KB897fffe0385a47ef6b29f012f641f9cc7010db6d480c5dcb49e14fe11be78b45
specs/nist_anova.atmwtag.agent.json6,5 KB1634b2494954c1e6cdfaf8876c305465914d365a92fe2c4ae727a2902fe911a7
specs/nist_anova.atmwtag.tool.json4,1 KBabc86088e487b2a0e4409603253fef549191769109832d8e642769d1b4482c9d
specs/nist_anova.sirstv.agent.json6,7 KB05fa753022e81031b7b6fd108da84031e7e04c7a8844d9bd98bc6f7823d8bf83
specs/nist_anova.sirstv.tool.json4,4 KB68a4f636d64d058982134a82dfe4cf043e82c7109baabd2571a6ed71fd74351d
specs/nist_anova.smls01.agent.json6,8 KBcc13a44eaad0340e25eb9e4fddfe6a6f14acfb4fe6464d3ef4b14b0cfa526c7c
specs/nist_anova.smls01.tool.json4,6 KBcf442b80a7e723a1f83d136cded03797091c2dcd41428108f505b52f9a780e05
specs/nist_anova.smls02.agent.json6,8 KB9ebcc0fa858d8b6cb30513ddeb2586bfefca083707fd8cce910f462848ab4834
specs/nist_anova.smls02.tool.json4,6 KB2db1d61c804bd51d16c2324b373a5c6f2e8329f629e1502874a59e281e1e6da0
specs/nist_anova.smls03.agent.json6,8 KBee54aa7517c43ba58b09ad6117e9e16ea94247a304e79392c89b685f8ba04cf2
specs/nist_anova.smls03.tool.json4,6 KB582c7f1abadce5bc72e31dc66fdf97e08ffccb9509035bfa671d88fc20e7624c
specs/nist_anova.smls04.agent.json6,8 KB28a7c71067611a94f501abd14320ec0b79adb884ed6a4e4ad5ef0a0cca1053f6
specs/nist_anova.smls04.tool.json4,6 KBa498d795a112bb7f1499c6d5879603ba1f482de9e8de63c289c32149e80ca37d
specs/nist_anova.smls05.agent.json6,9 KB489ba239e0a7036f013fd4f0b25b873bb91c5b8d87e0bde8261cc309d02f6bd1
specs/nist_anova.smls05.tool.json4,6 KBe941089507fa5453024ede63dfdc1bddc940d3042d7fe4753fed00938c86b465
specs/nist_anova.smls06.agent.json6,9 KB55cfd069a2b766283031b2ae4c48dbaa76bf0363d65c541bfc21d1a99fab04eb
specs/nist_anova.smls06.tool.json4,6 KBc48e07126112ed5b4450ca6c8db39d569f7b7e50de81b0eddc7030a595e6bd1e
specs/nist_anova.smls07.agent.json6,8 KB6611c03621e9640927009e2e46b31cbd129d77bb642482646e1f4d5a7eb4b709
specs/nist_anova.smls07.tool.json4,6 KBac8a44e39bdabdcf70f756bde87559a37917ed3ef192d05bd79be56951feef0c
specs/nist_anova.smls08.agent.json6,8 KB0329712a83b4d16bca85f7f4c3b69dbe3c3ea6fac0139c2445468a9e09426b8e
specs/nist_anova.smls08.tool.json4,6 KB92973255a6fd367ea5aa426d0c96a7ac2bcffe8f2b45f5495832944b0b7de584
specs/nist_anova.smls09.agent.json6,9 KB8d0e4ac5cae52a8b0f87d3233686a4b3df51b1b1c5f32f9f9297a45a659c1c58
specs/nist_anova.smls09.tool.json4,6 KBade586127410acbb014816796758dd037b6d7bf57895496afd2e7d911d1b4f61
summary.json3,0 KBa675117bdc734eef722529da18cb2f878985ad1cb03a985af33ebcf608850290
summary.md656 Bfa6dc99f02f6be96ce45272571a9392432c345acd253f464d090636355088678
tools/registry.json14,3 KB27ebe450c05193ace734f93b9e9cd24a3072c19308bcdb8877b34d71a6d7670b
traces/nist_anova.atmwtag.agent.e1.a1.jsonl7,4 KB5ebf2c3661ea45a9e52dc5133dd008d9b2bd2721b584937a5af7911775729686
traces/nist_anova.atmwtag.tool.e1.a1.jsonl4,0 KB3cbe6ab872149d29135f723fc18ddfa6e011b3514a4f9d413ca8ccb7d19f9bc8
traces/nist_anova.sirstv.agent.e1.a1.jsonl7,5 KB2bf37eb374a1f3debb743674652ef6c1722a57ede8adb1fec165ddd9cb0c6aa5
traces/nist_anova.sirstv.tool.e1.a1.jsonl5,0 KBa93a682125c50aa05d27e093c2e30c43e7468438895172703fa7503fb0c8780e
traces/nist_anova.smls01.agent.e1.a1.jsonl7,6 KB2e07e83f7b0592f366a7295efb1f0b62fefd07e96eeefc2e45c94084c2abda26
traces/nist_anova.smls01.tool.e1.a1.jsonl6,3 KB6c2d78cd6f417b7a00d2c4da62957f24866a53048a3b9258c0bdbf5b21543710
traces/nist_anova.smls02.agent.e1.a1.jsonl7,6 KB62682fa3bd432a0118e341da30ea23e5a109cf9b116b5512418d9694d88ad27c
traces/nist_anova.smls02.tool.e1.a1.jsonl6,3 KBb040404d3029e97800e9230855cddb4b8dc7352a08955d5a54defac05e3b75b0
traces/nist_anova.smls03.agent.e1.a1.jsonl7,6 KB55525a7392088f196487e6b344bdd0d99fb227d2324bc187517c9d7d7eb01e33
traces/nist_anova.smls03.tool.e1.a1.jsonl6,3 KBd6f5a27d5a868f160e10b2afab9ea9d9280dc0b128787c003c9bc1d4384831bf
traces/nist_anova.smls04.agent.e1.a1.jsonl7,6 KB97d08a7a58f54a7c95d5aea4a75f70eac01294a2d8af643dc367ac757e0896d1
traces/nist_anova.smls04.tool.e1.a1.jsonl6,3 KB36a7b691a739e0319a2eb4bab03857a487c153828d21f6a1c53fdb96c9830082
traces/nist_anova.smls05.agent.e1.a1.jsonl7,6 KB88219fe0b5af609773d067dc83f2be712c7864bf89a33377b389f4f9c874e09d
traces/nist_anova.smls05.tool.e1.a1.jsonl6,3 KB10cc6ca48857a90054fe7e7103a7a5eab63c9c84f9156375abdd0fb7a27c22e4
traces/nist_anova.smls06.agent.e1.a1.jsonl7,6 KBf94334485ce78db8d0ca6423195c073c3c256efe1ef1af1ba72bfe2c9a0ba0d8
traces/nist_anova.smls06.tool.e1.a1.jsonl6,3 KB71c145b8d4f9336871e51119327754fbd316fae0fcde94de7719e691ddb18933
traces/nist_anova.smls07.agent.e1.a1.jsonl7,6 KB35be315130040f731aa72335c22275a866c6e303bf188bfe37fd4483050389dc
traces/nist_anova.smls07.tool.e1.a1.jsonl6,3 KB22dec168ed8e630907329068d9be952ebc76bdf5528455282674c11bed70f8dc
traces/nist_anova.smls08.agent.e1.a1.jsonl7,6 KB0887f3c6b192366ee455f5ed1edcf9664bc74fdccc976a770d389fab7c647240
traces/nist_anova.smls08.tool.e1.a1.jsonl6,3 KB8cfedd59f990858eb303c22ac7738ccc01965d1d302f48ba8f34c3a18459fa18
traces/nist_anova.smls09.agent.e1.a1.jsonl7,6 KB55f78f0580c76f181ff5fbd97b57eaeda2223bff4f396467f0fe7b3d5be2b231
traces/nist_anova.smls09.tool.e1.a1.jsonl6,3 KB537c0ee9cd09a61613f8b14cfb06415061c647d1bda1a7c53bd52f42e40092a4
trajectories/nist_anova.atmwtag.agent.e1.a1.jsonl7,2 KB4c0542090a120fd768cae1d8f6771d92b297b2ca7eea864313db727c439e7160
trajectories/nist_anova.atmwtag.tool.e1.a1.jsonl6,6 KB4b34808f07e46d4b1d8f9d8d7fe6d8ec28ab564b6c9aa9da392f33a45a9af1fa
trajectories/nist_anova.sirstv.agent.e1.a1.jsonl7,2 KBa3744a48d7cf17fa124311523e4f17e775c06a272936bade8d4979e6384e1358
trajectories/nist_anova.sirstv.tool.e1.a1.jsonl7,6 KBbc96ad3fe27c5522b20d8e2f4be701e80b5bf2768485efda0677308145ff859a
trajectories/nist_anova.smls01.agent.e1.a1.jsonl7,2 KB97bdd4ea8d1ef660a6496ea1d98f66d3e0a3998c498cc90378f881551344bb91
trajectories/nist_anova.smls01.tool.e1.a1.jsonl8,8 KB7812b04442b004a8e6f089d0071cda8cc6c354619882f03f8d6c68ff8d6e9015
trajectories/nist_anova.smls02.agent.e1.a1.jsonl7,2 KB97745e5daa730b44feb503f29a8f585003eb304bd11088bb8b58ce62d67e2850
trajectories/nist_anova.smls02.tool.e1.a1.jsonl8,8 KB0b2492707c5c94c8834f645631d86795956b9ff3a1bc6a9eb8a0f8ef879d9a19
trajectories/nist_anova.smls03.agent.e1.a1.jsonl7,2 KB9a5ead5cfd8a7ef9dcf77416971dd7a27f247cbde6e4f135d0e5c2284bcfeaf6
trajectories/nist_anova.smls03.tool.e1.a1.jsonl8,8 KB784ee814b7a5c0b0c0b61266447a289a7400ea4f39ed1564f91532bc89383043
trajectories/nist_anova.smls04.agent.e1.a1.jsonl7,2 KBa8262f5b4741abb037ca35c50e2a9729d6369c5ee418ae47013081af0d179b09
trajectories/nist_anova.smls04.tool.e1.a1.jsonl8,8 KBabc424dc4228dc40d081d247a35a58043220a4cae6cea6a3e27e717204762af8
trajectories/nist_anova.smls05.agent.e1.a1.jsonl7,2 KBa95ea101bbc6b2bb7c3bcba991cdb17d5463ab5b6d3d81196f8869bd9e37b334
trajectories/nist_anova.smls05.tool.e1.a1.jsonl8,9 KB7d563098031a72596246c8cd1970b5bf6888594ad8a4d438cc6bd0a9fe2c3b6e
trajectories/nist_anova.smls06.agent.e1.a1.jsonl7,2 KBa11360cf96e042b5d95ca83733db2531b3e18cd637110ed8f9d9e2db84ef382e
trajectories/nist_anova.smls06.tool.e1.a1.jsonl8,8 KB57a807a36cccee14305a6c4d77e15a6d4afb48026cb0a3178132575a38ae3c5b
trajectories/nist_anova.smls07.agent.e1.a1.jsonl7,2 KB4f82645d8dcbe8bbee3d93eb68ef960cbadc1b1c095322dc61f3fbba8006b5e0
trajectories/nist_anova.smls07.tool.e1.a1.jsonl8,9 KB6a6b198ed8bf7d427d09488451b0aebbd49d4badad42a80febae4720620da4cd
trajectories/nist_anova.smls08.agent.e1.a1.jsonl7,2 KB509a517da887eb91eb2afad8b74910a49297bef258e68815926acbaab1f4c704
trajectories/nist_anova.smls08.tool.e1.a1.jsonl8,9 KBe713c0f85961f718b5661ffb409353660408bc3c7f1673f433a47a93f246074c
trajectories/nist_anova.smls09.agent.e1.a1.jsonl7,2 KB3d2a44403efdd6c710047589cf778743e029c28cead310e01ce71b2c04eba158
trajectories/nist_anova.smls09.tool.e1.a1.jsonl8,9 KBa40b2832cac790df09036bdf451447df72521a61b1de4727e37bdd6f8bc37f2a
verify_bundle.py36,1 KBe529500171e873cc55733c9c44f3a7b8386074c3aad998e6cb27a79b53cddd31
SHA256SUMS12,1 KB4d086120920fa8328d3fa04f999833d3702e04cd0e7815a8a6d2fdbf7c3624cc

Eventos do registro

Verifique você mesmo

Resumo da execução
4d086120920fa8328d3fa04f999833d3702e04cd0e7815a8a6d2fdbf7c3624cc
sha256 do arquivo SHA256SUMS; deve ser igual ao run_digest do evento final do registro.

Qualquer pessoa, sem o repositório

  1. Baixe o pacote inteiro e descompacte.
  2. Rode o verificador, que só usa a biblioteca padrão do Python:
    cd 20261015T171234Z-suite-nist_anova-baseline-71784e
    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   # 4d086120920fa8328d3fa04f999833d3702e04cd0e7815a8a6d2fdbf7c3624cc

Com acesso ao repositório (privado)

git checkout 2925aeab226272b243436386a1c4e01d97c1377e
uv sync --frozen --all-packages
uv run magi-bench verify bench-runs/20261015T171234Z-suite-nist_anova-baseline-71784e

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.