{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LRPWFSUKBBXTJNDBOFUGHWTVPE","short_pith_number":"pith:LRPWFSUK","schema_version":"1.0","canonical_sha256":"5c5f62ca8a086f34b461716863da757932584a376701a9e57056cee9f81bfad4","source":{"kind":"arxiv","id":"2406.10291","version":3},"attestation_state":"computed","paper":{"title":"ResearchArena: Benchmarking Large Language Models' Ability to Collect and Organize Information as Research Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Chenyan Xiong, Hao Kang","submitted_at":"2024-06-13T03:26:30Z","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"},"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":"2406.10291","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-13T03:26:30Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"68f2df85c2bf59df21b558a2d9cab22f8096e12ff0148d76d9659d506dc63ea2","abstract_canon_sha256":"837f20a76b72a6dfd2a79d72c7ed5c950f61049d173d4635771ce47401a2d5ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:00.326090Z","signature_b64":"5BgZXLKocQM6gtyUh+9LLcs9ctU9zMSGpXc2ch3PLG9Cc0luUVhyWbovFsXW/xhCndaob8Bp87RUqnQjLUBGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c5f62ca8a086f34b461716863da757932584a376701a9e57056cee9f81bfad4","last_reissued_at":"2026-07-05T12:06:00.325577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:00.325577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ResearchArena: Benchmarking Large Language Models' Ability to Collect and Organize Information as Research Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Chenyan Xiong, Hao Kang","submitted_at":"2024-06-13T03:26:30Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10291","kind":"arxiv","version":3},"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/2406.10291/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":"2406.10291","created_at":"2026-07-05T12:06:00.325639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10291v3","created_at":"2026-07-05T12:06:00.325639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10291","created_at":"2026-07-05T12:06:00.325639+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRPWFSUKBBXT","created_at":"2026-07-05T12:06:00.325639+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRPWFSUKBBXTJNDB","created_at":"2026-07-05T12:06:00.325639+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRPWFSUK","created_at":"2026-07-05T12:06:00.325639+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.11336","citing_title":"XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2507.11810","citing_title":"Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LRPWFSUKBBXTJNDBOFUGHWTVPE","json":"https://pith.science/pith/LRPWFSUKBBXTJNDBOFUGHWTVPE.json","graph_json":"https://pith.science/api/pith-number/LRPWFSUKBBXTJNDBOFUGHWTVPE/graph.json","events_json":"https://pith.science/api/pith-number/LRPWFSUKBBXTJNDBOFUGHWTVPE/events.json","paper":"https://pith.science/paper/LRPWFSUK"},"agent_actions":{"view_html":"https://pith.science/pith/LRPWFSUKBBXTJNDBOFUGHWTVPE","download_json":"https://pith.science/pith/LRPWFSUKBBXTJNDBOFUGHWTVPE.json","view_paper":"https://pith.science/paper/LRPWFSUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10291&json=true","fetch_graph":"https://pith.science/api/pith-number/LRPWFSUKBBXTJNDBOFUGHWTVPE/graph.json","fetch_events":"https://pith.science/api/pith-number/LRPWFSUKBBXTJNDBOFUGHWTVPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRPWFSUKBBXTJNDBOFUGHWTVPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRPWFSUKBBXTJNDBOFUGHWTVPE/action/storage_attestation","attest_author":"https://pith.science/pith/LRPWFSUKBBXTJNDBOFUGHWTVPE/action/author_attestation","sign_citation":"https://pith.science/pith/LRPWFSUKBBXTJNDBOFUGHWTVPE/action/citation_signature","submit_replication":"https://pith.science/pith/LRPWFSUKBBXTJNDBOFUGHWTVPE/action/replication_record"}},"created_at":"2026-07-05T12:06:00.325639+00:00","updated_at":"2026-07-05T12:06:00.325639+00:00"}