{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OUZCBK43LT2NCIC2EFSELFKYDF","short_pith_number":"pith:OUZCBK43","schema_version":"1.0","canonical_sha256":"753220ab9b5cf4d1205a216445955819798301c60da91523ba390ce4cc701516","source":{"kind":"arxiv","id":"2412.13018","version":2},"attestation_state":"computed","paper":{"title":"OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiejun Tan, Ji-Rong Wen, Shuting Wang, Zhicheng Dou","submitted_at":"2024-12-17T15:38:42Z","abstract_excerpt":"As a typical and practical application of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) techniques have gained extensive attention, particularly in vertical domains where LLMs may lack domain-specific knowledge. In this paper, we introduce an omnidirectional and automatic RAG benchmark, OmniEval, in the financial domain. Our benchmark is characterized by its multi-dimensional evaluation framework, including (1) a matrix-based RAG scenario evaluation system that categorizes queries into five task classes and 16 financial topics, leading to a structured assessment of diverse"},"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":"2412.13018","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T15:38:42Z","cross_cats_sorted":[],"title_canon_sha256":"8806c5a67d67e8c02f5b3e46de6ce0bc1ae32cc00868999ae35c31fc898d9e23","abstract_canon_sha256":"d368d27cce6eb3fb614461415bcbba82eefb935b68a016231b3c39a7e42e15f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:23.892966Z","signature_b64":"r1RQZitzDf7k0iDeybTAwmKq84jnkZe5KipPKv6MRvYmXXqJiRNOUzJ+o0m/4E+dryxeedu4v+SQlLxSgbT2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"753220ab9b5cf4d1205a216445955819798301c60da91523ba390ce4cc701516","last_reissued_at":"2026-07-05T10:15:23.892462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:23.892462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiejun Tan, Ji-Rong Wen, Shuting Wang, Zhicheng Dou","submitted_at":"2024-12-17T15:38:42Z","abstract_excerpt":"As a typical and practical application of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) techniques have gained extensive attention, particularly in vertical domains where LLMs may lack domain-specific knowledge. In this paper, we introduce an omnidirectional and automatic RAG benchmark, OmniEval, in the financial domain. Our benchmark is characterized by its multi-dimensional evaluation framework, including (1) a matrix-based RAG scenario evaluation system that categorizes queries into five task classes and 16 financial topics, leading to a structured assessment of diverse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13018","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/2412.13018/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":"2412.13018","created_at":"2026-07-05T10:15:23.892517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13018v2","created_at":"2026-07-05T10:15:23.892517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13018","created_at":"2026-07-05T10:15:23.892517+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUZCBK43LT2N","created_at":"2026-07-05T10:15:23.892517+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUZCBK43LT2NCIC2","created_at":"2026-07-05T10:15:23.892517+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUZCBK43","created_at":"2026-07-05T10:15:23.892517+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":244,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31608","citing_title":"CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning","ref_index":142,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18758","citing_title":"OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14488","citing_title":"Deepchecks: Evaluating Retrieval-Augmented Generation (RAG)","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24544","citing_title":"STELLAR-E: a Synthetic, Tailored, End-to-end LLM Application Rigorous Evaluator","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OUZCBK43LT2NCIC2EFSELFKYDF","json":"https://pith.science/pith/OUZCBK43LT2NCIC2EFSELFKYDF.json","graph_json":"https://pith.science/api/pith-number/OUZCBK43LT2NCIC2EFSELFKYDF/graph.json","events_json":"https://pith.science/api/pith-number/OUZCBK43LT2NCIC2EFSELFKYDF/events.json","paper":"https://pith.science/paper/OUZCBK43"},"agent_actions":{"view_html":"https://pith.science/pith/OUZCBK43LT2NCIC2EFSELFKYDF","download_json":"https://pith.science/pith/OUZCBK43LT2NCIC2EFSELFKYDF.json","view_paper":"https://pith.science/paper/OUZCBK43","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13018&json=true","fetch_graph":"https://pith.science/api/pith-number/OUZCBK43LT2NCIC2EFSELFKYDF/graph.json","fetch_events":"https://pith.science/api/pith-number/OUZCBK43LT2NCIC2EFSELFKYDF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUZCBK43LT2NCIC2EFSELFKYDF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUZCBK43LT2NCIC2EFSELFKYDF/action/storage_attestation","attest_author":"https://pith.science/pith/OUZCBK43LT2NCIC2EFSELFKYDF/action/author_attestation","sign_citation":"https://pith.science/pith/OUZCBK43LT2NCIC2EFSELFKYDF/action/citation_signature","submit_replication":"https://pith.science/pith/OUZCBK43LT2NCIC2EFSELFKYDF/action/replication_record"}},"created_at":"2026-07-05T10:15:23.892517+00:00","updated_at":"2026-07-05T10:15:23.892517+00:00"}