{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ACAXJY2DQ6G6DREBBK75W3PORT","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":"5e5cdbc9e235f49407bf80656433554c18f0de2372f4175d12602e10a153d835","cross_cats_sorted":["cs.AI","stat.ME"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-19T15:11:13Z","title_canon_sha256":"3b634097dd028024fba6300755890e8da827e2319ec86a4ce1bb32cb195d55df"},"schema_version":"1.0","source":{"id":"2603.19005","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.19005","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"2603.19005v2","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.19005","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"ACAXJY2DQ6G6","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"pith_short_16","alias_value":"ACAXJY2DQ6G6DREB","created_at":"2026-06-02T01:03:45Z"},{"alias_kind":"pith_short_8","alias_value":"ACAXJY2D","created_at":"2026-06-02T01:03:45Z"}],"graph_snapshots":[{"event_id":"sha256:16d68e0d8c7b6980154cd69a6fbcd79e1733689473183db7dc5d116a80dcc247","target":"graph","created_at":"2026-06-02T01:03:45Z","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/2603.19005/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data science plays a critical role in transforming complex data into actionable insights across numerous domains. Recent developments in large language models (LLMs) and artificial intelligence (AI) agents have significantly automated data science workflow. However, it remains unclear to what extent AI agents can match the performance of human experts on domain-specific data science tasks, and in which aspects human expertise continues to provide advantages. We introduce AgentDS, a benchmark and competition designed to evaluate both AI agents and human-AI collaboration performance in domain-sp","authors_text":"An Luo, Ashish Kundu, Charles Fleming, Fangqiao Tian, Galin Jones, Ganghua Wang, Jayanth Srinivasa, Jie Ding, Jin Du, Mingyi Hong, Robert Specht, Rui Zhang, Tianxi Li, Xuan Bi, Xun Xian","cross_cats":["cs.AI","stat.ME"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-19T15:11:13Z","title":"AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.19005","kind":"arxiv","version":2},"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":"sha256:10a3eda67357fa6e3cfec13e1165cab2755416850784786708c6dbd94cce8c9b","target":"record","created_at":"2026-06-02T01:03:45Z","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":"5e5cdbc9e235f49407bf80656433554c18f0de2372f4175d12602e10a153d835","cross_cats_sorted":["cs.AI","stat.ME"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-19T15:11:13Z","title_canon_sha256":"3b634097dd028024fba6300755890e8da827e2319ec86a4ce1bb32cb195d55df"},"schema_version":"1.0","source":{"id":"2603.19005","kind":"arxiv","version":2}},"canonical_sha256":"008174e343878de1c4810abfdb6dee8cdd45b83a2947c5bf0e5f3c3a5ef6c35a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"008174e343878de1c4810abfdb6dee8cdd45b83a2947c5bf0e5f3c3a5ef6c35a","first_computed_at":"2026-06-02T01:03:45.787464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:45.787464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y/JE9WExnjMpqXExit0KJ4Da4P/9YhD+hK3ccY4bVjcthATcS2KYCXmr/NUNdIb0xTHPYvulp3YCWzHmiAWQAg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:45.788053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.19005","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10a3eda67357fa6e3cfec13e1165cab2755416850784786708c6dbd94cce8c9b","sha256:16d68e0d8c7b6980154cd69a6fbcd79e1733689473183db7dc5d116a80dcc247"],"state_sha256":"6555995568e9e3cc56052defd27717701278715fc949632f9c93ebc160ff59db"}