{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5","short_pith_number":"pith:N7JJ5YQ5","schema_version":"1.0","canonical_sha256":"6fd29ee21d91ed3e86ac7221a3d26f8741a66201eac899ee3523c4a34eb429c6","source":{"kind":"arxiv","id":"2606.05238","version":1},"attestation_state":"computed","paper":{"title":"DeployBench: Benchmarking LLM Agents for Research Artifact Deployment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Hanhan Zhou, Huanzhi Mao, Jindan Huang, Liqiang Jing, Qiuyang Mang, Tianfu Fu, Wendong Fan, Wenhao Chai, Yaoyao Qian, Yuanli Wang, Yue Zhang","submitted_at":"2026-06-03T04:59:34Z","abstract_excerpt":"LLM agents have made rapid progress on software engineering and ML research tasks, but these advances often assume access to a working runnable environment. For research artifacts released alongside published papers, setting up such an environment from a fresh machine remains a major bottleneck. Existing environment setup benchmarks do not cover the full scope of research artifact deployment, which involves multi-language toolchains, system-level dependencies beyond containers (e.g. GPU/CUDA and kernel configurations), and legacy artifact compatibility. We introduce DeployBench, a multi-domain"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.05238","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-03T04:59:34Z","cross_cats_sorted":[],"title_canon_sha256":"ed6647121be93ef6a705e50688b5c3b7e2d2a7a5bf9591220aebbd1b0c65d11e","abstract_canon_sha256":"292b57feb8330ef6661c0ef68cac93a33f8fca4cc1a37821568ea1ff8a02ccac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:50.040923Z","signature_b64":"A7qzlLUX1oHx8a4trC3YbXhVkrmDs5dIswMPdESMVT6IdoOY2rAywPx8kpoxli2hb+OPj4cH+4FeAhjP1JnPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fd29ee21d91ed3e86ac7221a3d26f8741a66201eac899ee3523c4a34eb429c6","last_reissued_at":"2026-06-05T00:13:50.040414Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:50.040414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeployBench: Benchmarking LLM Agents for Research Artifact Deployment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Hanhan Zhou, Huanzhi Mao, Jindan Huang, Liqiang Jing, Qiuyang Mang, Tianfu Fu, Wendong Fan, Wenhao Chai, Yaoyao Qian, Yuanli Wang, Yue Zhang","submitted_at":"2026-06-03T04:59:34Z","abstract_excerpt":"LLM agents have made rapid progress on software engineering and ML research tasks, but these advances often assume access to a working runnable environment. For research artifacts released alongside published papers, setting up such an environment from a fresh machine remains a major bottleneck. Existing environment setup benchmarks do not cover the full scope of research artifact deployment, which involves multi-language toolchains, system-level dependencies beyond containers (e.g. GPU/CUDA and kernel configurations), and legacy artifact compatibility. We introduce DeployBench, a multi-domain"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05238","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.05238/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.05238","created_at":"2026-06-05T00:13:50.040514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05238v1","created_at":"2026-06-05T00:13:50.040514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05238","created_at":"2026-06-05T00:13:50.040514+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7JJ5YQ5SHWT","created_at":"2026-06-05T00:13:50.040514+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7JJ5YQ5SHWT5BVM","created_at":"2026-06-05T00:13:50.040514+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7JJ5YQ5","created_at":"2026-06-05T00:13:50.040514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5","json":"https://pith.science/pith/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5.json","graph_json":"https://pith.science/api/pith-number/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5/graph.json","events_json":"https://pith.science/api/pith-number/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5/events.json","paper":"https://pith.science/paper/N7JJ5YQ5"},"agent_actions":{"view_html":"https://pith.science/pith/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5","download_json":"https://pith.science/pith/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5.json","view_paper":"https://pith.science/paper/N7JJ5YQ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05238&json=true","fetch_graph":"https://pith.science/api/pith-number/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5/action/storage_attestation","attest_author":"https://pith.science/pith/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5/action/author_attestation","sign_citation":"https://pith.science/pith/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5/action/citation_signature","submit_replication":"https://pith.science/pith/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5/action/replication_record"}},"created_at":"2026-06-05T00:13:50.040514+00:00","updated_at":"2026-06-05T00:13:50.040514+00:00"}