{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6FH6U7EN2UI47JNP6ZU6TFQ7S2","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":"ab7a76c80ee272e263250eb868d7d93a2c29ddd33b41b2c32e4776438d959f07","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-11T01:45:56Z","title_canon_sha256":"f49cbf2a67e5462f70b446025653e9b6d9a38fb10e2614e4402de52b43912fcc"},"schema_version":"1.0","source":{"id":"2608.10366","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10366","created_at":"2026-08-12T00:23:58Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10366v1","created_at":"2026-08-12T00:23:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10366","created_at":"2026-08-12T00:23:58Z"},{"alias_kind":"pith_short_12","alias_value":"6FH6U7EN2UI4","created_at":"2026-08-12T00:23:58Z"},{"alias_kind":"pith_short_16","alias_value":"6FH6U7EN2UI47JNP","created_at":"2026-08-12T00:23:58Z"},{"alias_kind":"pith_short_8","alias_value":"6FH6U7EN","created_at":"2026-08-12T00:23:58Z"}],"graph_snapshots":[{"event_id":"sha256:9f1914df3f23dadc2bf1a842b92dc32bd4582eb11398bfcf4bbfadd0029a81db","target":"graph","created_at":"2026-08-12T00:23:58Z","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/2608.10366/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-world data science involves long-horizon workflows that span data wrangling, exploration, modeling, visualization, and validation, and require coordinated use of tools such as notebooks, IDEs, terminals, browsers, and databases within real operating environments. Yet existing benchmarks lack real-computer interaction and do not evaluate whether agents can execute complete end-to-end data-science workflows in realistic computing environments, failing to capture the multi-stage, multi-tool nature of data-science practice. We introduce DSAgentBench, the first benchmark to evaluate whether ag","authors_text":"Enamul Hoque Prince, Md Tahmid Rahman Laskar, Mizanur Rahman, Mohammed Saidul Islam, Ridwan Mahbub, Shafiq Joty","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-11T01:45:56Z","title":"DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10366","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:ca8f464d90b7b64377dc42aba3c12782f5df75a4b679a7d9b50fa7eb6bd2b021","target":"record","created_at":"2026-08-12T00:23:58Z","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":"ab7a76c80ee272e263250eb868d7d93a2c29ddd33b41b2c32e4776438d959f07","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-11T01:45:56Z","title_canon_sha256":"f49cbf2a67e5462f70b446025653e9b6d9a38fb10e2614e4402de52b43912fcc"},"schema_version":"1.0","source":{"id":"2608.10366","kind":"arxiv","version":1}},"canonical_sha256":"f14fea7c8dd511cfa5aff669e9961f969465d7407d1afb8280fb36de02a45530","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f14fea7c8dd511cfa5aff669e9961f969465d7407d1afb8280fb36de02a45530","first_computed_at":"2026-08-12T00:23:58.047590Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T00:23:58.047590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Vbi+5Rva2CV8lC0wtd8wB6mX4A++QdlgrtiKEANYNLmIR3b8vwcTTI0/X50bua6uLsicGF4xij5lvrdhgSFBw==","signature_status":"signed_v1","signed_at":"2026-08-12T00:23:58.049100Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10366","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca8f464d90b7b64377dc42aba3c12782f5df75a4b679a7d9b50fa7eb6bd2b021","sha256:9f1914df3f23dadc2bf1a842b92dc32bd4582eb11398bfcf4bbfadd0029a81db"],"state_sha256":"2bc533553adce7f34cfbac895511821f4ab995d904e431927ddde4b0f01af534"}