{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BCR6YZTAORDN4IDBFM25JX3VFU","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":"b8cf4cc3b49e174b55c1e23c07db764ad7bdc4b37539e413b3ee4d5b08f8a287","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-30T10:49:21Z","title_canon_sha256":"1b423777e86a71908dc7e60e402261597efca1d0dd84990eb55761fac22626b2"},"schema_version":"1.0","source":{"id":"2506.23719","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23719","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23719v1","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23719","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"pith_short_12","alias_value":"BCR6YZTAORDN","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"BCR6YZTAORDN4IDB","created_at":"2026-07-05T11:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"BCR6YZTA","created_at":"2026-07-05T11:29:27Z"}],"graph_snapshots":[{"event_id":"sha256:e469117fe1ba17d1926f0bad42aee24e789bdab3dd5e7c11f8537c16108f10d9","target":"graph","created_at":"2026-07-05T11:29:27Z","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/2506.23719/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce DABstep, a novel benchmark for evaluating AI agents on realistic multi-step data analysis tasks. DABstep comprises over 450 real-world challenges derived from a financial analytics platform, requiring models to combine code-based data processing with contextual reasoning over heterogeneous documentation. Each task demands an iterative, multi-step problem-solving approach, testing capabilities in data manipulation, cross-referencing multiple sources, and precise result reporting. The benchmark provides a factoid-style answer format with automatic correctness checks for objective sc","authors_text":"Alex Egg, Andreu Mora, Friso Kingma, Leandro Von Werra, Martin Iglesias Goyanes, Thomas Wolf","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-30T10:49:21Z","title":"DABstep: Data Agent Benchmark for Multi-step Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23719","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":"sha256:52a8fab9616511e0fb67528449bfab6e11c749d9238c528d592689834f9d56b8","target":"record","created_at":"2026-07-05T11:29:27Z","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":"b8cf4cc3b49e174b55c1e23c07db764ad7bdc4b37539e413b3ee4d5b08f8a287","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-30T10:49:21Z","title_canon_sha256":"1b423777e86a71908dc7e60e402261597efca1d0dd84990eb55761fac22626b2"},"schema_version":"1.0","source":{"id":"2506.23719","kind":"arxiv","version":1}},"canonical_sha256":"08a3ec66607446de20612b35d4df752d220d0af371aae34b130a6384943f6d63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08a3ec66607446de20612b35d4df752d220d0af371aae34b130a6384943f6d63","first_computed_at":"2026-07-05T11:29:27.017831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:27.017831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NIVH49JGtWaaBPXgrH0r+ZbfiBzGPor5RMUo4jqoYf/zSB9VE8+5jCx5ObHrFs7x2YwPsH+M8srMzmM0L/EcDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:27.018393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23719","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52a8fab9616511e0fb67528449bfab6e11c749d9238c528d592689834f9d56b8","sha256:e469117fe1ba17d1926f0bad42aee24e789bdab3dd5e7c11f8537c16108f10d9"],"state_sha256":"896240dcdbb5e489aee81696f192b889e6e55b3568825c15e972ed4c8b5643a1"}