{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FIMZCRZX3UEL7KUBRNC25LOY3M","short_pith_number":"pith:FIMZCRZX","schema_version":"1.0","canonical_sha256":"2a19914737dd08bfaa818b45aeadd8db0fda60d88ba1522b2d453e558c264ba0","source":{"kind":"arxiv","id":"2512.17776","version":5},"attestation_state":"computed","paper":{"title":"DEER: A Benchmark for Evaluating Deep Research Agents on Expert Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changho Lee, Dahm Lee, Heegyu Kim, Honglak Lee, Hosung Song, Janghoon Han, Min Hyung Park, Moontae Lee, Stanley Jungkyu Choi","submitted_at":"2025-12-19T16:46:20Z","abstract_excerpt":"Recent advances in large language models have enabled deep research systems that generate expert-level reports through multi-step reasoning and evidence-based synthesis. However, evaluating such reports remains challenging: report quality is multifaceted, making it difficult to determine what to assess and which criteria to use; LLM-based judges may miss errors that require domain expertise to identify; and because deep research relies on retrieved evidence, report-wide claim verification is also necessary. To address these issues, we propose DEER, a benchmark for evaluating expert-level deep "},"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":"2512.17776","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-12-19T16:46:20Z","cross_cats_sorted":[],"title_canon_sha256":"c9a05d302f5b6d5aa3cd8e197d430b28f4feef90ddcc88c20f21be8ea8070891","abstract_canon_sha256":"8daa7a53cf39de306a5a7d34e3c5349d636d4e949388503ad2bcc470945f0fe0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:22:02.650929Z","signature_b64":"KZQhKWjc+AFWmkQwAacHMEV3db8w3jiRt5LLFLKg8PoxyMehql7gyTvslMzbXJHgKxuTwTa6CNZMc0t1DogTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a19914737dd08bfaa818b45aeadd8db0fda60d88ba1522b2d453e558c264ba0","last_reissued_at":"2026-07-14T01:22:02.650000Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:22:02.650000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DEER: A Benchmark for Evaluating Deep Research Agents on Expert Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changho Lee, Dahm Lee, Heegyu Kim, Honglak Lee, Hosung Song, Janghoon Han, Min Hyung Park, Moontae Lee, Stanley Jungkyu Choi","submitted_at":"2025-12-19T16:46:20Z","abstract_excerpt":"Recent advances in large language models have enabled deep research systems that generate expert-level reports through multi-step reasoning and evidence-based synthesis. However, evaluating such reports remains challenging: report quality is multifaceted, making it difficult to determine what to assess and which criteria to use; LLM-based judges may miss errors that require domain expertise to identify; and because deep research relies on retrieved evidence, report-wide claim verification is also necessary. To address these issues, we propose DEER, a benchmark for evaluating expert-level deep "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.17776","kind":"arxiv","version":5},"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/2512.17776/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":"2512.17776","created_at":"2026-07-14T01:22:02.650452+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.17776v5","created_at":"2026-07-14T01:22:02.650452+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.17776","created_at":"2026-07-14T01:22:02.650452+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIMZCRZX3UEL","created_at":"2026-07-14T01:22:02.650452+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIMZCRZX3UEL7KUB","created_at":"2026-07-14T01:22:02.650452+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIMZCRZX","created_at":"2026-07-14T01:22:02.650452+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.17458","citing_title":"ICBCBench: An Industry Consortium Benchmark for Financial Deep Research","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19196","citing_title":"Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02368","citing_title":"Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14518","citing_title":"Mind DeepResearch Technical Report","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FIMZCRZX3UEL7KUBRNC25LOY3M","json":"https://pith.science/pith/FIMZCRZX3UEL7KUBRNC25LOY3M.json","graph_json":"https://pith.science/api/pith-number/FIMZCRZX3UEL7KUBRNC25LOY3M/graph.json","events_json":"https://pith.science/api/pith-number/FIMZCRZX3UEL7KUBRNC25LOY3M/events.json","paper":"https://pith.science/paper/FIMZCRZX"},"agent_actions":{"view_html":"https://pith.science/pith/FIMZCRZX3UEL7KUBRNC25LOY3M","download_json":"https://pith.science/pith/FIMZCRZX3UEL7KUBRNC25LOY3M.json","view_paper":"https://pith.science/paper/FIMZCRZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.17776&json=true","fetch_graph":"https://pith.science/api/pith-number/FIMZCRZX3UEL7KUBRNC25LOY3M/graph.json","fetch_events":"https://pith.science/api/pith-number/FIMZCRZX3UEL7KUBRNC25LOY3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIMZCRZX3UEL7KUBRNC25LOY3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIMZCRZX3UEL7KUBRNC25LOY3M/action/storage_attestation","attest_author":"https://pith.science/pith/FIMZCRZX3UEL7KUBRNC25LOY3M/action/author_attestation","sign_citation":"https://pith.science/pith/FIMZCRZX3UEL7KUBRNC25LOY3M/action/citation_signature","submit_replication":"https://pith.science/pith/FIMZCRZX3UEL7KUBRNC25LOY3M/action/replication_record"}},"created_at":"2026-07-14T01:22:02.650452+00:00","updated_at":"2026-07-14T01:22:02.650452+00:00"}