{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LRPWFSUKBBXTJNDBOFUGHWTVPE","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":"837f20a76b72a6dfd2a79d72c7ed5c950f61049d173d4635771ce47401a2d5ca","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-13T03:26:30Z","title_canon_sha256":"68f2df85c2bf59df21b558a2d9cab22f8096e12ff0148d76d9659d506dc63ea2"},"schema_version":"1.0","source":{"id":"2406.10291","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10291","created_at":"2026-07-05T12:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10291v3","created_at":"2026-07-05T12:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10291","created_at":"2026-07-05T12:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"LRPWFSUKBBXT","created_at":"2026-07-05T12:06:00Z"},{"alias_kind":"pith_short_16","alias_value":"LRPWFSUKBBXTJNDB","created_at":"2026-07-05T12:06:00Z"},{"alias_kind":"pith_short_8","alias_value":"LRPWFSUK","created_at":"2026-07-05T12:06:00Z"}],"graph_snapshots":[{"event_id":"sha256:5867e6a134bee21638cb15bdf04a7b3783dd8c2ef6957949d4ea1cacccb18c89","target":"graph","created_at":"2026-07-05T12:06:00Z","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/2406.10291/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) excel across many natural language processing tasks but face challenges in domain-specific, analytical tasks such as conducting research surveys. This study introduces ResearchArena, a benchmark designed to evaluate LLMs' capabilities in conducting academic surveys -- a foundational step in academic research. ResearchArena models the process in three stages: (1) information discovery, identifying relevant literature; (2) information selection, evaluating papers' relevance and impact; and (3) information organization, structuring knowledge into hierarchical framewor","authors_text":"Chenyan Xiong, Hao Kang","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-13T03:26:30Z","title":"ResearchArena: Benchmarking Large Language Models' Ability to Collect and Organize Information as Research Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10291","kind":"arxiv","version":3},"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":"sha256:1128ccbb8515b8c7e21038299b164436b9d6d0756cbd76f289834b3cc9aef3b6","target":"record","created_at":"2026-07-05T12:06:00Z","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":"837f20a76b72a6dfd2a79d72c7ed5c950f61049d173d4635771ce47401a2d5ca","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-13T03:26:30Z","title_canon_sha256":"68f2df85c2bf59df21b558a2d9cab22f8096e12ff0148d76d9659d506dc63ea2"},"schema_version":"1.0","source":{"id":"2406.10291","kind":"arxiv","version":3}},"canonical_sha256":"5c5f62ca8a086f34b461716863da757932584a376701a9e57056cee9f81bfad4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c5f62ca8a086f34b461716863da757932584a376701a9e57056cee9f81bfad4","first_computed_at":"2026-07-05T12:06:00.325577Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:00.325577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5BgZXLKocQM6gtyUh+9LLcs9ctU9zMSGpXc2ch3PLG9Cc0luUVhyWbovFsXW/xhCndaob8Bp87RUqnQjLUBGAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:00.326090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10291","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1128ccbb8515b8c7e21038299b164436b9d6d0756cbd76f289834b3cc9aef3b6","sha256:5867e6a134bee21638cb15bdf04a7b3783dd8c2ef6957949d4ea1cacccb18c89"],"state_sha256":"75219779c9317f4f3790363d3b0caca204203b7b571e875b05a6a6b8ae71eb48"}