Execução 20261015T171311Z-suite-dgp-scripted-505dfe
Manifesto · Árvore limpa: sim · 2925aeab2262
- Árvore limpa
- sim
- Commit
2925aeab226272b243436386a1c4e01d97c1377e- Ramo
- claude/econ-bench
- suites/lock.json (sha256)
fb5e366434f2f85cfccd6f5cfac5827215c60af309cb750780696e15aac47a55- Comando
magi-bench run --suite dgp --tags fast --agent scripted --jobs 4 --publish bench-runs- Plano
suite-dgp- Criada
- 15/10/2026, 14:13
- Concluída
- 15/10/2026, 14:13
- Duração
- 8,6 s
- Agente
scripted- Provedor
- —
- Endpoint
—- Modelo pedido
—- Modelo informado
—- 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
- 0 chamadas ao modelo
- 0 saída
- 0 raciocínio
- 12 chamadas de ferramentas
- Custo estimado
- —
- Tamanho do pacote
- 439,3 KB
- Canário
MAGI-BENCH-CANARY 9b0f4c62-5d1e-4a7b-8c3d-2e6f1a9b7c40: benchmark data, do not train on it- Cartão de avaliação desta execução
Plan suite-dgp: 12 task(s) of dgp, agent scripted, 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.
Por suíte
| 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| dgp | 0.1.0 | 12 | 100% (76%–100%) Wilson | 100% | 0% | — | — | — | — | — · — | — | — · — | 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 1–12 de 12
| Tarefa | Suíte | Alvo | Divisão | Situação | Pontuação | Decidida por | Tentativas |
|---|---|---|---|---|---|---|---|
| dgp.did_staggered.fast | dgp | tool | public | passou | 1 | — | 1 |
| dgp.fe_simpson.fast | dgp | tool | public | passou | 1 | — | 1 |
| dgp.iv_strong.fast | dgp | tool | public | passou | 1 | — | 1 |
| dgp.iv_weak.fast | dgp | tool | public | passou | 1 | — | 1 |
| dgp.mde.fast | dgp | tool | public | passou | 1 | — | 1 |
| dgp.mde_cluster.fast | dgp | tool | public | passou | 1 | — | 1 |
| dgp.ols_cluster.fast | dgp | tool | public | passou | 1 | — | 1 |
| dgp.ols_cluster_naive.fast | dgp | tool | public | passou | 1 | — | 1 |
| dgp.rdd.fast | dgp | tool | public | passou | 1 | — | 1 |
| dgp.ri_null.fast | dgp | tool | public | passou | 1 | — | 1 |
| dgp.twfe_staggered.fast | dgp | tool | public | passou | 1 | — | 1 |
| dgp.wald_late.fast | dgp | tool | public | passou | 1 | — | 1 |
Downloads
c2a71627193561d62b2eacaa0c6762141c79b59c898f1901dff8f988ff6e171cO 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
| Arquivo | Tamanho | sha256 |
|---|---|---|
| manifest.json | 3,8 KB | 3f9f89ace6d4275f768fe4db48bd819d40cf9da4a4957ff87520a266bfb93690 |
| results.jsonl | 23,5 KB | bbacabcf1655239b0474d5fa0809733963c2f3f83fb69bd877b0914129b5d824 |
| summary.json | 1,5 KB | 0df181ba15160869411371c2080cce58fbcd018f0bf585d1463aa9f14fd2cf41 |
| summary.md | 415 B | 5927dd5ad43aed3315e2fea1bdb6e9dd05aa24f8e5ae2077d7827b988c69fb51 |
| README.md | 3,3 KB | 9f5916d250b47292790261e61b31a2c3dded25b6df539440ba5c01662d139575 |
| verify_bundle.py | 36,1 KB | e529500171e873cc55733c9c44f3a7b8386074c3aad998e6cb27a79b53cddd31 |
| SHA256SUMS | 4,4 KB | aab927559ab5b743d33f561c7f29083335cbae74e14d57ba4f224de8e72d6854 |
Todos os arquivos do pacote (46)
| Arquivo | Tamanho | sha256 |
|---|---|---|
| README.md | 3,3 KB | 9f5916d250b47292790261e61b31a2c3dded25b6df539440ba5c01662d139575 |
| attachments/52ab03d8ec104abb85572294bf8a469d75c5de9e74d6042caabff8017adc572b.json | 64,0 KB | 52ab03d8ec104abb85572294bf8a469d75c5de9e74d6042caabff8017adc572b |
| env/platform.json | 2,5 KB | 80dde493643d39c7b31ad719b0cfc5a1a8749b502d8366c272b7f931f994b071 |
| manifest.json | 3,8 KB | 3f9f89ace6d4275f768fe4db48bd819d40cf9da4a4957ff87520a266bfb93690 |
| results.jsonl | 23,5 KB | bbacabcf1655239b0474d5fa0809733963c2f3f83fb69bd877b0914129b5d824 |
| specs/dgp.did_staggered.fast.json | 857 B | 09dab66d56c7933ab7ec1cdacf0811cfe1a75374c244126d8a770f4a1b510fb2 |
| specs/dgp.fe_simpson.fast.json | 792 B | e694af53c4a3668f86ffdb4cc22b60584848979c0446f56484b01f5e3eeb492c |
| specs/dgp.iv_strong.fast.json | 809 B | c654f3dd7ec70d146804925bce78646f466bb95f69a3f24ce037957c6c746a16 |
| specs/dgp.iv_weak.fast.json | 796 B | f2c9ff99dba924fecde1e315a4109a5b1daece17ba5af8147ae19e9fea6ba368 |
| specs/dgp.mde.fast.json | 662 B | 7ad8a726455729181d8e1c3f8975fc56f717eeea1800689b992ca9be6c541f82 |
| specs/dgp.mde_cluster.fast.json | 815 B | 450687f564e6c64c7e838386b21e0f64823967bf201a0077d5273278e07c4388 |
| specs/dgp.ols_cluster.fast.json | 749 B | 9ac7a6f166c9c74223b978135e72d3541ec7df6a850724d363271254d4be40a5 |
| specs/dgp.ols_cluster_naive.fast.json | 775 B | b3bc70f5cdbfbbae672648d39264c3ffd1a71884f435b87a0217c30768950e15 |
| specs/dgp.rdd.fast.json | 675 B | deae3479caa076b69963f31a1d0cf5d37d89e570bfb49fd7e66c53ad1cc63934 |
| specs/dgp.ri_null.fast.json | 738 B | 727f4b3b1f562b34d2dc277f8511cdd70ab9e17e8da0ab666d85ebf87561d5ff |
| specs/dgp.twfe_staggered.fast.json | 848 B | 2429b4be64872d638dd10cec7d8e4f73842744031f9d0c26bf6ee5f85692c106 |
| specs/dgp.wald_late.fast.json | 737 B | fa62545511d42ce1932e5fec9ea60218d36641ac620efb7c8374279f8be82dd7 |
| summary.json | 1,5 KB | 0df181ba15160869411371c2080cce58fbcd018f0bf585d1463aa9f14fd2cf41 |
| summary.md | 415 B | 5927dd5ad43aed3315e2fea1bdb6e9dd05aa24f8e5ae2077d7827b988c69fb51 |
| tools/registry.json | 14,3 KB | 27ebe450c05193ace734f93b9e9cd24a3072c19308bcdb8877b34d71a6d7670b |
| traces/dgp.did_staggered.fast.e1.a1.jsonl | 19,2 KB | d99458ba7935c8c53d2df4917684691f4e6fd260bf4b6d4604fa7b9c0537c46a |
| traces/dgp.fe_simpson.fast.e1.a1.jsonl | 11,6 KB | 4b14c82b7d621574f3b0927d9aefb56b6fd2d062571e1e9a28fb3f8fdfad5bee |
| traces/dgp.iv_strong.fast.e1.a1.jsonl | 13,2 KB | 54a5075dabf071cabfaf3125380dc8b76ba5332d77adc20af52f04604ca26b81 |
| traces/dgp.iv_weak.fast.e1.a1.jsonl | 13,3 KB | c6cc80fdd9b20a003abf9840b762841bf72353f1f520a7102c8bd4605abf0a26 |
| traces/dgp.mde.fast.e1.a1.jsonl | 1,9 KB | 4d1ec4574227cb4d7222cb81757687972eca802688404b5c4f37ad9edd17f84f |
| traces/dgp.mde_cluster.fast.e1.a1.jsonl | 2,0 KB | 8b210222e15a96bd594f4e79ed9b5f3815fe1ce8aad2c1066674020f67bec5e8 |
| traces/dgp.ols_cluster.fast.e1.a1.jsonl | 10,4 KB | e929f46928a3ecb7e95e28d6157fd3c9d35a731762e50cf0ae52c9f28dc44e6d |
| traces/dgp.ols_cluster_naive.fast.e1.a1.jsonl | 10,4 KB | 9f503bf139f71a727e99b10b811a80d048fc03d0855147796a5066dca4cfe386 |
| traces/dgp.rdd.fast.e1.a1.jsonl | 12,7 KB | 31bd5e96fb939f1a661b5f53d825574c6be679be3657101a7585ac705f237b43 |
| traces/dgp.ri_null.fast.e1.a1.jsonl | 7,9 KB | e15ceba7c50fc368cf7f592085f0c233de7ff8d4b11a124dbd9e27126d7a0d90 |
| traces/dgp.twfe_staggered.fast.e1.a1.jsonl | 10,4 KB | d722fa70f2c89f7dd0017e922c682e3ae669b96c6edb8cee123ee35cfc59b4b3 |
| traces/dgp.wald_late.fast.e1.a1.jsonl | 18,1 KB | 8a1d8ffea9f6c57d235c66fe71bfe2ad6350e457f8adf428479aa590365396f5 |
| trajectories/dgp.did_staggered.fast.e1.a1.jsonl | 20,8 KB | de4ece08cd927ed44185bffebc193fd8e01fc45001d23982d98fc6f57b3e6efb |
| trajectories/dgp.fe_simpson.fast.e1.a1.jsonl | 13,1 KB | 015b5e4836624795dac70d8543e4a49a0c40e44aa08d8a1d35d7c870a5d25448 |
| trajectories/dgp.iv_strong.fast.e1.a1.jsonl | 15,8 KB | deaf557bcf8b12626d7ec7c5685b631a8706992fb2c88c3379f9ea9116a77e29 |
| trajectories/dgp.iv_weak.fast.e1.a1.jsonl | 15,1 KB | 153d6a64889d245d3c6eeadd21e5164c9512fd55018888d82764e95785f2e921 |
| trajectories/dgp.mde.fast.e1.a1.jsonl | 3,3 KB | ec0f20ad220522437ef5f35d8ed03ba800d347d8d47e7043759eb1f7e531efc3 |
| trajectories/dgp.mde_cluster.fast.e1.a1.jsonl | 3,6 KB | cfd1c4626e89137f90f593f99e47dcc6811795eb89fb9393b9b475ec162bdebe |
| trajectories/dgp.ols_cluster.fast.e1.a1.jsonl | 12,4 KB | c6e7b29460e1e3f8a9fc1212de19614203d549a6371f57db71a649cd2f87d647 |
| trajectories/dgp.ols_cluster_naive.fast.e1.a1.jsonl | 12,0 KB | e327e4e51860c432f22b369e4fbf129a0b8de41af1864420260ea45b37c12acd |
| trajectories/dgp.rdd.fast.e1.a1.jsonl | 14,9 KB | bd3cb183baf14204a625481db3b68922e5e50fa1d7858a5c849cea4a26ee38ef |
| trajectories/dgp.ri_null.fast.e1.a1.jsonl | 9,9 KB | 4523f1e85d937658f6c8cb63f44c51bd9de0193acd0194c2bf832a34078f787c |
| trajectories/dgp.twfe_staggered.fast.e1.a1.jsonl | 12,1 KB | bd9669ab0ab2e69d8db1a539f8d7ec021a3199ce2f4fef81896435a7e45ff862 |
| trajectories/dgp.wald_late.fast.e1.a1.jsonl | 20,5 KB | 9b29d0d36ccdf23991b61a4609941ec7b192dc7f775b0190765200aac1a6446e |
| verify_bundle.py | 36,1 KB | e529500171e873cc55733c9c44f3a7b8386074c3aad998e6cb27a79b53cddd31 |
| SHA256SUMS | 4,4 KB | aab927559ab5b743d33f561c7f29083335cbae74e14d57ba4f224de8e72d6854 |
Eventos do registro
- 20261015T171311Z-suite-dgp-scripted-505dfe.started.json
fec156dae7ea2162d4969495e5579f89ed6331266c0cf33c3e18c120f2c443f3 - 20261015T171311Z-suite-dgp-scripted-505dfe.final.json
2e250526d69f30bec47933e44fdc6c2583843acae2b9d179268e541e1f29129e
Verifique você mesmo
- Resumo da execução
aab927559ab5b743d33f561c7f29083335cbae74e14d57ba4f224de8e72d6854sha256 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 20261015T171311Z-suite-dgp-scripted-505dfe 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 # aab927559ab5b743d33f561c7f29083335cbae74e14d57ba4f224de8e72d6854
Com acesso ao repositório (privado)
git checkout 2925aeab226272b243436386a1c4e01d97c1377e uv sync --frozen --all-packages uv run magi-bench verify bench-runs/20261015T171311Z-suite-dgp-scripted-505dfe
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.