{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z6WF2NUWH7ZV7QGMHOZHC2GXYG","short_pith_number":"pith:Z6WF2NUW","schema_version":"1.0","canonical_sha256":"cfac5d36963ff35fc0cc3bb27168d7c1ac658e3cd04683d23c95d4c65d9236cc","source":{"kind":"arxiv","id":"2409.07691","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Q&A Text Retrieval with Ranking Models: Benchmarking, fine-tuning and deploying Rerankers for RAG","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Benedikt Schifferer, Even Oldridge, Gabriel de Souza P. Moreira, Mengyao Xu, Radek Osmulski, Ronay Ak","submitted_at":"2024-09-12T01:51:06Z","abstract_excerpt":"Ranking models play a crucial role in enhancing overall accuracy of text retrieval systems. These multi-stage systems typically utilize either dense embedding models or sparse lexical indices to retrieve relevant passages based on a given query, followed by ranking models that refine the ordering of the candidate passages by its relevance to the query.\n  This paper benchmarks various publicly available ranking models and examines their impact on ranking accuracy. We focus on text retrieval for question-answering tasks, a common use case for Retrieval-Augmented Generation systems. Our evaluatio"},"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":"2409.07691","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2024-09-12T01:51:06Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"027a87ece75ff1eccc473c4b41c7aae37019db6e7171ab06f2f31d63f760354d","abstract_canon_sha256":"1f56add4104d720404c8a9a47e69041d26d8d23f6a4e73485be43a35687e244b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:13.533545Z","signature_b64":"rUD218LRYUMCbgcWdoype7N7KnblB8CD0Cfzw7vDw6LDlSSDX1GBKteccBkURVibLFDngUrKMS39iKugauFwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfac5d36963ff35fc0cc3bb27168d7c1ac658e3cd04683d23c95d4c65d9236cc","last_reissued_at":"2026-07-05T09:06:13.533048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:13.533048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Q&A Text Retrieval with Ranking Models: Benchmarking, fine-tuning and deploying Rerankers for RAG","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Benedikt Schifferer, Even Oldridge, Gabriel de Souza P. Moreira, Mengyao Xu, Radek Osmulski, Ronay Ak","submitted_at":"2024-09-12T01:51:06Z","abstract_excerpt":"Ranking models play a crucial role in enhancing overall accuracy of text retrieval systems. These multi-stage systems typically utilize either dense embedding models or sparse lexical indices to retrieve relevant passages based on a given query, followed by ranking models that refine the ordering of the candidate passages by its relevance to the query.\n  This paper benchmarks various publicly available ranking models and examines their impact on ranking accuracy. We focus on text retrieval for question-answering tasks, a common use case for Retrieval-Augmented Generation systems. Our evaluatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07691","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/2409.07691/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":"2409.07691","created_at":"2026-07-05T09:06:13.533106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07691v1","created_at":"2026-07-05T09:06:13.533106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07691","created_at":"2026-07-05T09:06:13.533106+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6WF2NUWH7ZV","created_at":"2026-07-05T09:06:13.533106+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6WF2NUWH7ZV7QGM","created_at":"2026-07-05T09:06:13.533106+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6WF2NUW","created_at":"2026-07-05T09:06:13.533106+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.29002","citing_title":"Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19899","citing_title":"A Reproducibility Study of Metacognitive Retrieval-Augmented Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18234","citing_title":"Evaluating Multi-Hop Reasoning in RAG Systems: A Comparison of LLM-Based Retriever Evaluation Strategies","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z6WF2NUWH7ZV7QGMHOZHC2GXYG","json":"https://pith.science/pith/Z6WF2NUWH7ZV7QGMHOZHC2GXYG.json","graph_json":"https://pith.science/api/pith-number/Z6WF2NUWH7ZV7QGMHOZHC2GXYG/graph.json","events_json":"https://pith.science/api/pith-number/Z6WF2NUWH7ZV7QGMHOZHC2GXYG/events.json","paper":"https://pith.science/paper/Z6WF2NUW"},"agent_actions":{"view_html":"https://pith.science/pith/Z6WF2NUWH7ZV7QGMHOZHC2GXYG","download_json":"https://pith.science/pith/Z6WF2NUWH7ZV7QGMHOZHC2GXYG.json","view_paper":"https://pith.science/paper/Z6WF2NUW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07691&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6WF2NUWH7ZV7QGMHOZHC2GXYG/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6WF2NUWH7ZV7QGMHOZHC2GXYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6WF2NUWH7ZV7QGMHOZHC2GXYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6WF2NUWH7ZV7QGMHOZHC2GXYG/action/storage_attestation","attest_author":"https://pith.science/pith/Z6WF2NUWH7ZV7QGMHOZHC2GXYG/action/author_attestation","sign_citation":"https://pith.science/pith/Z6WF2NUWH7ZV7QGMHOZHC2GXYG/action/citation_signature","submit_replication":"https://pith.science/pith/Z6WF2NUWH7ZV7QGMHOZHC2GXYG/action/replication_record"}},"created_at":"2026-07-05T09:06:13.533106+00:00","updated_at":"2026-07-05T09:06:13.533106+00:00"}