{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:E5K7KBOUPDPERRJ4KDMYIHXC3D","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":"2965c07cad88467b2b33495863f0ca090747df7fe59dbf811f4f7f2ad3921727","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-04T11:57:09Z","title_canon_sha256":"720a4c194459e580dcb5d9ff539965707026035ed064780469b889af330045d3"},"schema_version":"1.0","source":{"id":"2605.02503","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.02503","created_at":"2026-05-20T00:04:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.02503v2","created_at":"2026-05-20T00:04:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.02503","created_at":"2026-05-20T00:04:33Z"},{"alias_kind":"pith_short_12","alias_value":"E5K7KBOUPDPE","created_at":"2026-05-20T00:04:33Z"},{"alias_kind":"pith_short_16","alias_value":"E5K7KBOUPDPERRJ4","created_at":"2026-05-20T00:04:33Z"},{"alias_kind":"pith_short_8","alias_value":"E5K7KBOU","created_at":"2026-05-20T00:04:33Z"}],"graph_snapshots":[{"event_id":"sha256:cac5f434199f0e7dd558b0fd3f72e6ccb5e23668e4053763f9fb1a59b85ae34d","target":"graph","created_at":"2026-05-20T00:04:33Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments with eight advanced LLMs show that current agents remain far from reliable in this setting, with seven models achieving below 50% overall accuracy."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the 492 cross-domain tasks and their intermediate milestone annotations faithfully represent the process and difficulty of real-world exploratory data analysis in underexplored environments."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DataClaw supplies a process-oriented benchmark of real-world noisy data and milestone-annotated tasks that shows seven of eight tested LLMs achieve below 50% accuracy on exploratory analysis."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"DataClaw is a new benchmark that evaluates data-analysis agents on noisy real-world records by tracking their step-by-step progress through 492 annotated tasks."}],"snapshot_sha256":"388d2dbc7f236389b11922f571f9d73666cf1f8dd807a44ef81a616431d92315"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T16:20:13.844192Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.02503/integrity.json","findings":[],"snapshot_sha256":"5b6c16b0532279806b0f9209ade9bf009423c020ea04c8c36a91583636e839b5","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autonomous data analysis agents are increasingly expected to conduct exploratory analysis over underexplored data environments. This burden is especially salient in complex financial analytics, where relevant evidence is rarely pre-specified. However, existing benchmarks typically evaluate such agents in prior-guided settings, providing selected data sources, explicit data schemas, or cleaned data, thereby understating the exploratory burden. We introduce DataClawBench, a benchmark for exploratory real-world financial data analysis under limited prior guidance. DataClawBench contains approxima","authors_text":"Bowen Deng, BoYuan Li, Chuan Chen, Jialong Chen, Jianhao Lin, Qiaohong Zhang, Weihao Ye, Wei-Shi Zheng, Yi Luo, Zibin Zheng","cross_cats":[],"headline":"DataClaw is a new benchmark that evaluates data-analysis agents on noisy real-world records by tracking their step-by-step progress through 492 annotated tasks.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-04T11:57:09Z","title":"DataClawBench: An Agent Benchmark for Exploratory Real-World Financial Data Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.02503","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T18:20:13.877925Z","id":"e48c4361-3e8b-4b1b-9bc5-74be690e0db3","model_set":{"reader":"grok-4.3"},"one_line_summary":"DataClaw supplies a process-oriented benchmark of real-world noisy data and milestone-annotated tasks that shows seven of eight tested LLMs achieve below 50% accuracy on exploratory analysis.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"DataClaw is a new benchmark that evaluates data-analysis agents on noisy real-world records by tracking their step-by-step progress through 492 annotated tasks.","strongest_claim":"Experiments with eight advanced LLMs show that current agents remain far from reliable in this setting, with seven models achieving below 50% overall accuracy.","weakest_assumption":"That the 492 cross-domain tasks and their intermediate milestone annotations faithfully represent the process and difficulty of real-world exploratory data analysis in underexplored environments."}},"verdict_id":"e48c4361-3e8b-4b1b-9bc5-74be690e0db3"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9f833924f9af135febd38727858c4bf1017ccee0d17ac603e9d656c2e3f280ff","target":"record","created_at":"2026-05-20T00:04:33Z","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":"2965c07cad88467b2b33495863f0ca090747df7fe59dbf811f4f7f2ad3921727","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-04T11:57:09Z","title_canon_sha256":"720a4c194459e580dcb5d9ff539965707026035ed064780469b889af330045d3"},"schema_version":"1.0","source":{"id":"2605.02503","kind":"arxiv","version":2}},"canonical_sha256":"2755f505d478de48c53c50d9841ee2d8e0fa5c428507e1617fce2f5dd823db08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2755f505d478de48c53c50d9841ee2d8e0fa5c428507e1617fce2f5dd823db08","first_computed_at":"2026-05-20T00:04:33.747376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:33.747376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NFegHJC35U1YywxP658V5fK535dXZt4iFXhlV8E+T63D0oMRGvjdX7Dgk25hF6fX8Qqwim8L09XaWdscXIBEAw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:33.748081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.02503","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f833924f9af135febd38727858c4bf1017ccee0d17ac603e9d656c2e3f280ff","sha256:cac5f434199f0e7dd558b0fd3f72e6ccb5e23668e4053763f9fb1a59b85ae34d"],"state_sha256":"9b8ba0793f51a7f45400f5b87eb85923966b94e92611e173d8b6182b41c3f90c"}