{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OWNZSBWA5XEYNKD67N4R6BYNQV","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f6e43660f447b3ed3048c870de6dbb86550ea0e967e545c9756f8d999bd59cae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T11:17:27Z","title_canon_sha256":"66f12a06b2fac4b991221da8db25dd737e95c2df614f6e6f4041e078f28dc01d"},"schema_version":"1.0","source":{"id":"2607.28033","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28033","created_at":"2026-07-31T01:35:26Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28033v1","created_at":"2026-07-31T01:35:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28033","created_at":"2026-07-31T01:35:26Z"},{"alias_kind":"pith_short_12","alias_value":"OWNZSBWA5XEY","created_at":"2026-07-31T01:35:26Z"},{"alias_kind":"pith_short_16","alias_value":"OWNZSBWA5XEYNKD6","created_at":"2026-07-31T01:35:26Z"},{"alias_kind":"pith_short_8","alias_value":"OWNZSBWA","created_at":"2026-07-31T01:35:26Z"}],"graph_snapshots":[{"event_id":"sha256:eff68565ef2a9acf4061168648092f738a6398de2adb3b5f65730f97685eeb44","target":"graph","created_at":"2026-07-31T01:35:26Z","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/2607.28033/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) and LLM-based agents are increasingly being deployed to automate complex workflows, promising to revolutionize data management and processing. However, existing benchmarks predominantly focus on simplified Text-to-SQL translation or data analysis, leaving the critical and complex domain of end-to-end data engineering largely unexplored. To bridge this gap, we introduce DataClawEval, the first comprehensive benchmark designed specifically to evaluate the end-to-end task completion capabilities of autonomous agents in real-world data engineering scenarios. Built upon","authors_text":"Debin Meng, Haining Xie, Jiaming Yang, Peng Chen, Tengyue Xu, Yang Li, Zefang Zong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T11:17:27Z","title":"DataClawEval: A Benchmark for Data Engineering Agents in Real Industrial Harness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28033","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":"sha256:2c1524e2c2a3e64d22be222e767f3b2cfed8898393175aa1aa51fa29749453aa","target":"record","created_at":"2026-07-31T01:35:26Z","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":"f6e43660f447b3ed3048c870de6dbb86550ea0e967e545c9756f8d999bd59cae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T11:17:27Z","title_canon_sha256":"66f12a06b2fac4b991221da8db25dd737e95c2df614f6e6f4041e078f28dc01d"},"schema_version":"1.0","source":{"id":"2607.28033","kind":"arxiv","version":1}},"canonical_sha256":"759b9906c0edc986a87efb791f070d8548332a1ea39ef5b94d9a618094406d77","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"759b9906c0edc986a87efb791f070d8548332a1ea39ef5b94d9a618094406d77","first_computed_at":"2026-07-31T01:35:26.933708Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:35:26.933708Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28033","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c1524e2c2a3e64d22be222e767f3b2cfed8898393175aa1aa51fa29749453aa","sha256:eff68565ef2a9acf4061168648092f738a6398de2adb3b5f65730f97685eeb44","sha256:eb71a4554d4f2d9684df5851b29d03c108395fff681ad53ce64f346c716304b8"],"state_sha256":"3c1257928a833cfa526006ab735d92e7a3d1b4e61b1b2fcc06efb5887d4a5516"}