{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FIMZCRZX3UEL7KUBRNC25LOY3M","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":"8daa7a53cf39de306a5a7d34e3c5349d636d4e949388503ad2bcc470945f0fe0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-12-19T16:46:20Z","title_canon_sha256":"c9a05d302f5b6d5aa3cd8e197d430b28f4feef90ddcc88c20f21be8ea8070891"},"schema_version":"1.0","source":{"id":"2512.17776","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.17776","created_at":"2026-07-14T01:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"2512.17776v5","created_at":"2026-07-14T01:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.17776","created_at":"2026-07-14T01:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"FIMZCRZX3UEL","created_at":"2026-07-14T01:22:02Z"},{"alias_kind":"pith_short_16","alias_value":"FIMZCRZX3UEL7KUB","created_at":"2026-07-14T01:22:02Z"},{"alias_kind":"pith_short_8","alias_value":"FIMZCRZX","created_at":"2026-07-14T01:22:02Z"}],"graph_snapshots":[{"event_id":"sha256:e337e3c6c9bd502ecfa4f2af34cda10f853bff0113ba1e95704f8493d1da3063","target":"graph","created_at":"2026-07-14T01:22:02Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2512.17776/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Changho Lee, Dahm Lee, Heegyu Kim, Honglak Lee, Hosung Song, Janghoon Han, Min Hyung Park, Moontae Lee, Stanley Jungkyu Choi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-12-19T16:46:20Z","title":"DEER: A Benchmark for Evaluating Deep Research Agents on Expert Report Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.17776","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1bbc454f09835fd1bb4ed5e76fe562924df12f31e4297aec331ffc7b1f8948b3","target":"record","created_at":"2026-07-14T01:22:02Z","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":"8daa7a53cf39de306a5a7d34e3c5349d636d4e949388503ad2bcc470945f0fe0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-12-19T16:46:20Z","title_canon_sha256":"c9a05d302f5b6d5aa3cd8e197d430b28f4feef90ddcc88c20f21be8ea8070891"},"schema_version":"1.0","source":{"id":"2512.17776","kind":"arxiv","version":5}},"canonical_sha256":"2a19914737dd08bfaa818b45aeadd8db0fda60d88ba1522b2d453e558c264ba0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a19914737dd08bfaa818b45aeadd8db0fda60d88ba1522b2d453e558c264ba0","first_computed_at":"2026-07-14T01:22:02.650000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:22:02.650000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KZQhKWjc+AFWmkQwAacHMEV3db8w3jiRt5LLFLKg8PoxyMehql7gyTvslMzbXJHgKxuTwTa6CNZMc0t1DogTBg==","signature_status":"signed_v1","signed_at":"2026-07-14T01:22:02.650929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.17776","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bbc454f09835fd1bb4ed5e76fe562924df12f31e4297aec331ffc7b1f8948b3","sha256:e337e3c6c9bd502ecfa4f2af34cda10f853bff0113ba1e95704f8493d1da3063"],"state_sha256":"0076800180132c411fa74b49d3210d733579c6b70147f67c925ea8c044b3de76"}