{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SDVJB5LAQSE3TNSM6XBLDSL7NJ","short_pith_number":"pith:SDVJB5LA","schema_version":"1.0","canonical_sha256":"90ea90f5608489b9b64cf5c2b1c97f6a40e1132ba96e8b7be9f6386bf2218502","source":{"kind":"arxiv","id":"2601.10504","version":2},"attestation_state":"computed","paper":{"title":"DR-Arena: an Automated Evaluation Framework for Deep Research Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ruochen Zhao, Wenxuan Zhang, Yang Deng, Yiwen Gao","submitted_at":"2026-01-15T15:28:21Z","abstract_excerpt":"As Large Language Models (LLMs) increasingly operate as Deep Research (DR) Agents capable of autonomous investigation and information synthesis, reliable evaluation of their task performance has become a critical bottleneck. Current benchmarks predominantly rely on static datasets, which suffer from several limitations: limited task generality, temporal misalignment, and data contamination. To address these, we introduce DR-Arena, a fully automated evaluation framework that pushes DR agents to their capability limits through dynamic investigation. DR-Arena constructs real-time Information Tree"},"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":"2601.10504","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-15T15:28:21Z","cross_cats_sorted":[],"title_canon_sha256":"3d979b6e5d362d05fa775d396840897d9e64cf49fa731b3320d7885a14b8bddf","abstract_canon_sha256":"cbaac8bf5b2c4d912f46099696b00364e33fc32a0facad5f87b181f978df4179"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:18:57.439648Z","signature_b64":"IUj7i5la+iPv9duwRK1VYpOCyBGpzz6KY9UY8WWg63xYilpHE/BCIgWzTFi3LFO5N1nekNKErn7hczoS9l67Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90ea90f5608489b9b64cf5c2b1c97f6a40e1132ba96e8b7be9f6386bf2218502","last_reissued_at":"2026-07-10T01:18:57.439137Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:18:57.439137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DR-Arena: an Automated Evaluation Framework for Deep Research Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ruochen Zhao, Wenxuan Zhang, Yang Deng, Yiwen Gao","submitted_at":"2026-01-15T15:28:21Z","abstract_excerpt":"As Large Language Models (LLMs) increasingly operate as Deep Research (DR) Agents capable of autonomous investigation and information synthesis, reliable evaluation of their task performance has become a critical bottleneck. Current benchmarks predominantly rely on static datasets, which suffer from several limitations: limited task generality, temporal misalignment, and data contamination. To address these, we introduce DR-Arena, a fully automated evaluation framework that pushes DR agents to their capability limits through dynamic investigation. DR-Arena constructs real-time Information Tree"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.10504","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/2601.10504/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":"2601.10504","created_at":"2026-07-10T01:18:57.439196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.10504v2","created_at":"2026-07-10T01:18:57.439196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.10504","created_at":"2026-07-10T01:18:57.439196+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDVJB5LAQSE3","created_at":"2026-07-10T01:18:57.439196+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDVJB5LAQSE3TNSM","created_at":"2026-07-10T01:18:57.439196+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDVJB5LA","created_at":"2026-07-10T01:18:57.439196+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/SDVJB5LAQSE3TNSM6XBLDSL7NJ","json":"https://pith.science/pith/SDVJB5LAQSE3TNSM6XBLDSL7NJ.json","graph_json":"https://pith.science/api/pith-number/SDVJB5LAQSE3TNSM6XBLDSL7NJ/graph.json","events_json":"https://pith.science/api/pith-number/SDVJB5LAQSE3TNSM6XBLDSL7NJ/events.json","paper":"https://pith.science/paper/SDVJB5LA"},"agent_actions":{"view_html":"https://pith.science/pith/SDVJB5LAQSE3TNSM6XBLDSL7NJ","download_json":"https://pith.science/pith/SDVJB5LAQSE3TNSM6XBLDSL7NJ.json","view_paper":"https://pith.science/paper/SDVJB5LA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.10504&json=true","fetch_graph":"https://pith.science/api/pith-number/SDVJB5LAQSE3TNSM6XBLDSL7NJ/graph.json","fetch_events":"https://pith.science/api/pith-number/SDVJB5LAQSE3TNSM6XBLDSL7NJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDVJB5LAQSE3TNSM6XBLDSL7NJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDVJB5LAQSE3TNSM6XBLDSL7NJ/action/storage_attestation","attest_author":"https://pith.science/pith/SDVJB5LAQSE3TNSM6XBLDSL7NJ/action/author_attestation","sign_citation":"https://pith.science/pith/SDVJB5LAQSE3TNSM6XBLDSL7NJ/action/citation_signature","submit_replication":"https://pith.science/pith/SDVJB5LAQSE3TNSM6XBLDSL7NJ/action/replication_record"}},"created_at":"2026-07-10T01:18:57.439196+00:00","updated_at":"2026-07-10T01:18:57.439196+00:00"}