{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E5K7KBOUPDPERRJ4KDMYIHXC3D","short_pith_number":"pith:E5K7KBOU","schema_version":"1.0","canonical_sha256":"2755f505d478de48c53c50d9841ee2d8e0fa5c428507e1617fce2f5dd823db08","source":{"kind":"arxiv","id":"2605.02503","version":2},"attestation_state":"computed","paper":{"title":"DataClawBench: An Agent Benchmark for Exploratory Real-World Financial Data Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","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.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bowen Deng, BoYuan Li, Chuan Chen, Jialong Chen, Jianhao Lin, Qiaohong Zhang, Weihao Ye, Wei-Shi Zheng, Yi Luo, Zibin Zheng","submitted_at":"2026-05-04T11:57:09Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.02503","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-04T11:57:09Z","cross_cats_sorted":[],"title_canon_sha256":"720a4c194459e580dcb5d9ff539965707026035ed064780469b889af330045d3","abstract_canon_sha256":"2965c07cad88467b2b33495863f0ca090747df7fe59dbf811f4f7f2ad3921727"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:33.748081Z","signature_b64":"NFegHJC35U1YywxP658V5fK535dXZt4iFXhlV8E+T63D0oMRGvjdX7Dgk25hF6fX8Qqwim8L09XaWdscXIBEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2755f505d478de48c53c50d9841ee2d8e0fa5c428507e1617fce2f5dd823db08","last_reissued_at":"2026-05-20T00:04:33.747376Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:33.747376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DataClawBench: An Agent Benchmark for Exploratory Real-World Financial Data Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","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.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bowen Deng, BoYuan Li, Chuan Chen, Jialong Chen, Jianhao Lin, Qiaohong Zhang, Weihao Ye, Wei-Shi Zheng, Yi Luo, Zibin Zheng","submitted_at":"2026-05-04T11:57:09Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","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.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"388d2dbc7f236389b11922f571f9d73666cf1f8dd807a44ef81a616431d92315"},"source":{"id":"2605.02503","kind":"arxiv","version":2},"verdict":{"id":"e48c4361-3e8b-4b1b-9bc5-74be690e0db3","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T18:20:13.877925Z","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.","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","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.","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."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.02503/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T16:20:13.844192Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"5b6c16b0532279806b0f9209ade9bf009423c020ea04c8c36a91583636e839b5"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.02503","created_at":"2026-05-20T00:04:33.747481+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.02503v2","created_at":"2026-05-20T00:04:33.747481+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.02503","created_at":"2026-05-20T00:04:33.747481+00:00"},{"alias_kind":"pith_short_12","alias_value":"E5K7KBOUPDPE","created_at":"2026-05-20T00:04:33.747481+00:00"},{"alias_kind":"pith_short_16","alias_value":"E5K7KBOUPDPERRJ4","created_at":"2026-05-20T00:04:33.747481+00:00"},{"alias_kind":"pith_short_8","alias_value":"E5K7KBOU","created_at":"2026-05-20T00:04:33.747481+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E5K7KBOUPDPERRJ4KDMYIHXC3D","json":"https://pith.science/pith/E5K7KBOUPDPERRJ4KDMYIHXC3D.json","graph_json":"https://pith.science/api/pith-number/E5K7KBOUPDPERRJ4KDMYIHXC3D/graph.json","events_json":"https://pith.science/api/pith-number/E5K7KBOUPDPERRJ4KDMYIHXC3D/events.json","paper":"https://pith.science/paper/E5K7KBOU"},"agent_actions":{"view_html":"https://pith.science/pith/E5K7KBOUPDPERRJ4KDMYIHXC3D","download_json":"https://pith.science/pith/E5K7KBOUPDPERRJ4KDMYIHXC3D.json","view_paper":"https://pith.science/paper/E5K7KBOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.02503&json=true","fetch_graph":"https://pith.science/api/pith-number/E5K7KBOUPDPERRJ4KDMYIHXC3D/graph.json","fetch_events":"https://pith.science/api/pith-number/E5K7KBOUPDPERRJ4KDMYIHXC3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E5K7KBOUPDPERRJ4KDMYIHXC3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E5K7KBOUPDPERRJ4KDMYIHXC3D/action/storage_attestation","attest_author":"https://pith.science/pith/E5K7KBOUPDPERRJ4KDMYIHXC3D/action/author_attestation","sign_citation":"https://pith.science/pith/E5K7KBOUPDPERRJ4KDMYIHXC3D/action/citation_signature","submit_replication":"https://pith.science/pith/E5K7KBOUPDPERRJ4KDMYIHXC3D/action/replication_record"}},"created_at":"2026-05-20T00:04:33.747481+00:00","updated_at":"2026-05-20T00:04:33.747481+00:00"}