{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"292b57feb8330ef6661c0ef68cac93a33f8fca4cc1a37821568ea1ff8a02ccac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-03T04:59:34Z","title_canon_sha256":"ed6647121be93ef6a705e50688b5c3b7e2d2a7a5bf9591220aebbd1b0c65d11e"},"schema_version":"1.0","source":{"id":"2606.05238","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05238","created_at":"2026-06-05T00:13:50Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05238v1","created_at":"2026-06-05T00:13:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05238","created_at":"2026-06-05T00:13:50Z"},{"alias_kind":"pith_short_12","alias_value":"N7JJ5YQ5SHWT","created_at":"2026-06-05T00:13:50Z"},{"alias_kind":"pith_short_16","alias_value":"N7JJ5YQ5SHWT5BVM","created_at":"2026-06-05T00:13:50Z"},{"alias_kind":"pith_short_8","alias_value":"N7JJ5YQ5","created_at":"2026-06-05T00:13:50Z"}],"graph_snapshots":[{"event_id":"sha256:1d3a8103bb77b87dd1bdc7d0cd5972cf9c7f58ca6f47d8fb663c36e6c17cba86","target":"graph","created_at":"2026-06-05T00:13:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.05238/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hanhan Zhou, Huanzhi Mao, Jindan Huang, Liqiang Jing, Qiuyang Mang, Tianfu Fu, Wendong Fan, Wenhao Chai, Yaoyao Qian, Yuanli Wang, Yue Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-03T04:59:34Z","title":"DeployBench: Benchmarking LLM Agents for Research Artifact Deployment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05238","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5695e0c707b88ab08c4e568f3254e5c0ba82c9a0b812d84590119891659942a2","target":"record","created_at":"2026-06-05T00:13:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"292b57feb8330ef6661c0ef68cac93a33f8fca4cc1a37821568ea1ff8a02ccac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-03T04:59:34Z","title_canon_sha256":"ed6647121be93ef6a705e50688b5c3b7e2d2a7a5bf9591220aebbd1b0c65d11e"},"schema_version":"1.0","source":{"id":"2606.05238","kind":"arxiv","version":1}},"canonical_sha256":"6fd29ee21d91ed3e86ac7221a3d26f8741a66201eac899ee3523c4a34eb429c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fd29ee21d91ed3e86ac7221a3d26f8741a66201eac899ee3523c4a34eb429c6","first_computed_at":"2026-06-05T00:13:50.040414Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T00:13:50.040414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A7qzlLUX1oHx8a4trC3YbXhVkrmDs5dIswMPdESMVT6IdoOY2rAywPx8kpoxli2hb+OPj4cH+4FeAhjP1JnPAQ==","signature_status":"signed_v1","signed_at":"2026-06-05T00:13:50.040923Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05238","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5695e0c707b88ab08c4e568f3254e5c0ba82c9a0b812d84590119891659942a2","sha256:1d3a8103bb77b87dd1bdc7d0cd5972cf9c7f58ca6f47d8fb663c36e6c17cba86"],"state_sha256":"f65f0463e21475117c8f5e0d72f28e5140681d1f1f8a009c7fbbca00b7fcf2d2"}