{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ECTZRGFWZL6LN34BAIJQQS6JVB","short_pith_number":"pith:ECTZRGFW","schema_version":"1.0","canonical_sha256":"20a79898b6cafcb6ef810213084bc9a874028d592d5c36d7d782e2e316f524c8","source":{"kind":"arxiv","id":"2602.02039","version":2},"attestation_state":"computed","paper":{"title":"Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.DB","cs.LG"],"primary_cat":"cs.AI","authors_text":"Michele Orini, Peijie Yu, Wei Liu, Yali Du, Yulan He","submitted_at":"2026-02-02T12:36:57Z","abstract_excerpt":"The agency expected of Agentic Large Language Models goes beyond answering correctly, requiring autonomy to set goals and decide what to explore. We term this investigatory intelligence, distinguishing it from executional intelligence, which merely completes assigned tasks. Data Science provides a natural testbed, as real-world analysis starts from raw data rather than explicit queries, yet few benchmarks focus on it. To address this, we introduce Deep Data Research (DDR), an open-ended task where LLMs autonomously extract key insights from databases, and DDR-Bench, a large-scale, checklist-ba"},"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":"2602.02039","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-02T12:36:57Z","cross_cats_sorted":["cs.CL","cs.DB","cs.LG"],"title_canon_sha256":"37159c3b3c7d88977e30dfcebebd31177fafead02966964af2097a0b4621e891","abstract_canon_sha256":"944e6c8205ba28f66edd24b0111827840014566aa1b4d12e93fde1887eb849ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:09.298084Z","signature_b64":"cRSzREHMVZR+HfTniz0Veiq39mJB2+pwy7LFX4ucQPksywp8HF2iSUppgVBItAZDcJK0ZKSYM4yBDVpUIfx7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20a79898b6cafcb6ef810213084bc9a874028d592d5c36d7d782e2e316f524c8","last_reissued_at":"2026-05-20T00:02:09.296399Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:09.296399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.DB","cs.LG"],"primary_cat":"cs.AI","authors_text":"Michele Orini, Peijie Yu, Wei Liu, Yali Du, Yulan He","submitted_at":"2026-02-02T12:36:57Z","abstract_excerpt":"The agency expected of Agentic Large Language Models goes beyond answering correctly, requiring autonomy to set goals and decide what to explore. We term this investigatory intelligence, distinguishing it from executional intelligence, which merely completes assigned tasks. Data Science provides a natural testbed, as real-world analysis starts from raw data rather than explicit queries, yet few benchmarks focus on it. To address this, we introduce Deep Data Research (DDR), an open-ended task where LLMs autonomously extract key insights from databases, and DDR-Bench, a large-scale, checklist-ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02039","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.02039/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2602.02039","created_at":"2026-05-20T00:02:09.296906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.02039v2","created_at":"2026-05-20T00:02:09.296906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02039","created_at":"2026-05-20T00:02:09.296906+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECTZRGFWZL6L","created_at":"2026-05-20T00:02:09.296906+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECTZRGFWZL6LN34B","created_at":"2026-05-20T00:02:09.296906+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECTZRGFW","created_at":"2026-05-20T00:02:09.296906+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.24198","citing_title":"Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ECTZRGFWZL6LN34BAIJQQS6JVB","json":"https://pith.science/pith/ECTZRGFWZL6LN34BAIJQQS6JVB.json","graph_json":"https://pith.science/api/pith-number/ECTZRGFWZL6LN34BAIJQQS6JVB/graph.json","events_json":"https://pith.science/api/pith-number/ECTZRGFWZL6LN34BAIJQQS6JVB/events.json","paper":"https://pith.science/paper/ECTZRGFW"},"agent_actions":{"view_html":"https://pith.science/pith/ECTZRGFWZL6LN34BAIJQQS6JVB","download_json":"https://pith.science/pith/ECTZRGFWZL6LN34BAIJQQS6JVB.json","view_paper":"https://pith.science/paper/ECTZRGFW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.02039&json=true","fetch_graph":"https://pith.science/api/pith-number/ECTZRGFWZL6LN34BAIJQQS6JVB/graph.json","fetch_events":"https://pith.science/api/pith-number/ECTZRGFWZL6LN34BAIJQQS6JVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECTZRGFWZL6LN34BAIJQQS6JVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECTZRGFWZL6LN34BAIJQQS6JVB/action/storage_attestation","attest_author":"https://pith.science/pith/ECTZRGFWZL6LN34BAIJQQS6JVB/action/author_attestation","sign_citation":"https://pith.science/pith/ECTZRGFWZL6LN34BAIJQQS6JVB/action/citation_signature","submit_replication":"https://pith.science/pith/ECTZRGFWZL6LN34BAIJQQS6JVB/action/replication_record"}},"created_at":"2026-05-20T00:02:09.296906+00:00","updated_at":"2026-05-20T00:02:09.296906+00:00"}