{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YGHWTKTOSQMVMSBBUR4PGYOWSW","short_pith_number":"pith:YGHWTKTO","schema_version":"1.0","canonical_sha256":"c18f69aa6e9419564821a478f361d6958a372ecd50cb16b382e4f58ffb2c93a0","source":{"kind":"arxiv","id":"2410.02932","version":1},"attestation_state":"computed","paper":{"title":"Intrinsic Evaluation of RAG Systems for Deep-Logic Questions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jie Wang, Junyi Hu, You Zhou","submitted_at":"2024-10-03T19:25:05Z","abstract_excerpt":"We introduce the Overall Performance Index (OPI), an intrinsic metric to evaluate retrieval-augmented generation (RAG) mechanisms for applications involving deep-logic queries. OPI is computed as the harmonic mean of two key metrics: the Logical-Relation Correctness Ratio and the average of BERT embedding similarity scores between ground-truth and generated answers. We apply OPI to assess the performance of LangChain, a popular RAG tool, using a logical relations classifier fine-tuned from GPT-4o on the RAG-Dataset-12000 from Hugging Face. Our findings show a strong correlation between BERT em"},"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":"2410.02932","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-03T19:25:05Z","cross_cats_sorted":[],"title_canon_sha256":"c7f4ef0b957958594e330f521c7de3d5346cd5107114512dbc450ebdaccc898e","abstract_canon_sha256":"9c1829bd30b74d01da1f3fa94bd78f3436c957805965a1c2d155782ade6f90d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:41.698699Z","signature_b64":"+2tm3SUFoBJGcgO2vOrSdDJKH7SSw2EIECov0VaxoDSTtkFjIQ2RVmn2P45wzKyOSb3El0NWQzzmO31SzI/eBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c18f69aa6e9419564821a478f361d6958a372ecd50cb16b382e4f58ffb2c93a0","last_reissued_at":"2026-07-05T09:15:41.698153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:41.698153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intrinsic Evaluation of RAG Systems for Deep-Logic Questions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jie Wang, Junyi Hu, You Zhou","submitted_at":"2024-10-03T19:25:05Z","abstract_excerpt":"We introduce the Overall Performance Index (OPI), an intrinsic metric to evaluate retrieval-augmented generation (RAG) mechanisms for applications involving deep-logic queries. OPI is computed as the harmonic mean of two key metrics: the Logical-Relation Correctness Ratio and the average of BERT embedding similarity scores between ground-truth and generated answers. We apply OPI to assess the performance of LangChain, a popular RAG tool, using a logical relations classifier fine-tuned from GPT-4o on the RAG-Dataset-12000 from Hugging Face. Our findings show a strong correlation between BERT em"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02932","kind":"arxiv","version":1},"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/2410.02932/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":"2410.02932","created_at":"2026-07-05T09:15:41.698206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02932v1","created_at":"2026-07-05T09:15:41.698206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02932","created_at":"2026-07-05T09:15:41.698206+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGHWTKTOSQMV","created_at":"2026-07-05T09:15:41.698206+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGHWTKTOSQMVMSBB","created_at":"2026-07-05T09:15:41.698206+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGHWTKTO","created_at":"2026-07-05T09:15:41.698206+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.20119","citing_title":"Can LLMs Be Trusted for Evaluating RAG Systems? A Survey of Methods and Datasets","ref_index":71,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YGHWTKTOSQMVMSBBUR4PGYOWSW","json":"https://pith.science/pith/YGHWTKTOSQMVMSBBUR4PGYOWSW.json","graph_json":"https://pith.science/api/pith-number/YGHWTKTOSQMVMSBBUR4PGYOWSW/graph.json","events_json":"https://pith.science/api/pith-number/YGHWTKTOSQMVMSBBUR4PGYOWSW/events.json","paper":"https://pith.science/paper/YGHWTKTO"},"agent_actions":{"view_html":"https://pith.science/pith/YGHWTKTOSQMVMSBBUR4PGYOWSW","download_json":"https://pith.science/pith/YGHWTKTOSQMVMSBBUR4PGYOWSW.json","view_paper":"https://pith.science/paper/YGHWTKTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02932&json=true","fetch_graph":"https://pith.science/api/pith-number/YGHWTKTOSQMVMSBBUR4PGYOWSW/graph.json","fetch_events":"https://pith.science/api/pith-number/YGHWTKTOSQMVMSBBUR4PGYOWSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGHWTKTOSQMVMSBBUR4PGYOWSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGHWTKTOSQMVMSBBUR4PGYOWSW/action/storage_attestation","attest_author":"https://pith.science/pith/YGHWTKTOSQMVMSBBUR4PGYOWSW/action/author_attestation","sign_citation":"https://pith.science/pith/YGHWTKTOSQMVMSBBUR4PGYOWSW/action/citation_signature","submit_replication":"https://pith.science/pith/YGHWTKTOSQMVMSBBUR4PGYOWSW/action/replication_record"}},"created_at":"2026-07-05T09:15:41.698206+00:00","updated_at":"2026-07-05T09:15:41.698206+00:00"}