{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5","short_pith_number":"pith:N7JJ5YQ5","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"},"canonical_sha256":"6fd29ee21d91ed3e86ac7221a3d26f8741a66201eac899ee3523c4a34eb429c6","source":{"kind":"arxiv","id":"2606.05238","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5","target":"record","payload":{"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"},"canonical_sha256":"6fd29ee21d91ed3e86ac7221a3d26f8741a66201eac899ee3523c4a34eb429c6","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"},"source_kind":"arxiv","source_id":"2606.05238","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T00:13:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YjE7euqsHX/vn0jqyyFDBp+NMPTe39q7nct6Ky1BjdGB736xqfcZyLQW+PTxe1yaA6AMT3Yw005lrMGXSXJzAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T06:26:33.580370Z"},"content_sha256":"5695e0c707b88ab08c4e568f3254e5c0ba82c9a0b812d84590119891659942a2","schema_version":"1.0","event_id":"sha256:5695e0c707b88ab08c4e568f3254e5c0ba82c9a0b812d84590119891659942a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T00:13:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YsrP/of0rQZkyGxG8erIm0yUhFwo1ca9ayix58qXxoSHAeNdnEXjS9a26A4+5J7UzhyWNbKaZMxdccNVfeQeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T06:26:33.581189Z"},"content_sha256":"1d3a8103bb77b87dd1bdc7d0cd5972cf9c7f58ca6f47d8fb663c36e6c17cba86","schema_version":"1.0","event_id":"sha256:1d3a8103bb77b87dd1bdc7d0cd5972cf9c7f58ca6f47d8fb663c36e6c17cba86"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5/bundle.json","state_url":"https://pith.science/pith/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-10T06:26:33Z","links":{"resolver":"https://pith.science/pith/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5","bundle":"https://pith.science/pith/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5/bundle.json","state":"https://pith.science/pith/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N7JJ5YQ5SHWT5BVMOIQ2HUTPQ5/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zNbT8n5QpeGbhZiNF7iDA1Y+TKmvKD+zvBPSFesDVwWdJuARIEt4f7CBuXUXwyLta36ZF5L9pPFkB55paySCAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T06:26:33.585920Z","bundle_sha256":"daa0386c6108fd8ed9987853992a03c14524cc7fc47ac95067e68ad915c12601"}}