{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5BHPE63YQFSXYID4TZBBTNM7A6","short_pith_number":"pith:5BHPE63Y","schema_version":"1.0","canonical_sha256":"e84ef27b7881657c207c9e4219b59f07ad1269ce8173351c664ddc0987dd636e","source":{"kind":"arxiv","id":"2406.18740","version":1},"attestation_state":"computed","paper":{"title":"Re-Ranking Step by Step: Investigating Pre-Filtering for Re-Ranking with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Baharan Nouriinanloo, Maxime Lamothe","submitted_at":"2024-06-26T20:12:24Z","abstract_excerpt":"Large Language Models (LLMs) have been revolutionizing a myriad of natural language processing tasks with their diverse zero-shot capabilities. Indeed, existing work has shown that LLMs can be used to great effect for many tasks, such as information retrieval (IR), and passage ranking. However, current state-of-the-art results heavily lean on the capabilities of the LLM being used. Currently, proprietary, and very large LLMs such as GPT-4 are the highest performing passage re-rankers. Hence, users without the resources to leverage top of the line LLMs, or ones that are closed source, are at a "},"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":"2406.18740","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T20:12:24Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"1ae447cf0308e35215a81c2f2b60dfa16d46dc66d1cd2964b856384eeeb1f852","abstract_canon_sha256":"b8449005ef507b231219ac8cd79d73c8a0ee4347e1d048220a17c65f8d2be5ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:25.134242Z","signature_b64":"5s+Rgvz5mTFTaPELQTLjg/ay3wKIM91wX5BObPfahAJIjM4W0H4kzs8/OUlwT3vJgTCKKOUTz3TKx1VLnyhaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e84ef27b7881657c207c9e4219b59f07ad1269ce8173351c664ddc0987dd636e","last_reissued_at":"2026-07-05T08:37:25.133788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:25.133788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Re-Ranking Step by Step: Investigating Pre-Filtering for Re-Ranking with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Baharan Nouriinanloo, Maxime Lamothe","submitted_at":"2024-06-26T20:12:24Z","abstract_excerpt":"Large Language Models (LLMs) have been revolutionizing a myriad of natural language processing tasks with their diverse zero-shot capabilities. Indeed, existing work has shown that LLMs can be used to great effect for many tasks, such as information retrieval (IR), and passage ranking. However, current state-of-the-art results heavily lean on the capabilities of the LLM being used. Currently, proprietary, and very large LLMs such as GPT-4 are the highest performing passage re-rankers. Hence, users without the resources to leverage top of the line LLMs, or ones that are closed source, are at a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18740","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/2406.18740/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":"2406.18740","created_at":"2026-07-05T08:37:25.133845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18740v1","created_at":"2026-07-05T08:37:25.133845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18740","created_at":"2026-07-05T08:37:25.133845+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BHPE63YQFSX","created_at":"2026-07-05T08:37:25.133845+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BHPE63YQFSXYID4","created_at":"2026-07-05T08:37:25.133845+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BHPE63Y","created_at":"2026-07-05T08:37:25.133845+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.14634","citing_title":"Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty Evaluation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2603.15970","citing_title":"100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5BHPE63YQFSXYID4TZBBTNM7A6","json":"https://pith.science/pith/5BHPE63YQFSXYID4TZBBTNM7A6.json","graph_json":"https://pith.science/api/pith-number/5BHPE63YQFSXYID4TZBBTNM7A6/graph.json","events_json":"https://pith.science/api/pith-number/5BHPE63YQFSXYID4TZBBTNM7A6/events.json","paper":"https://pith.science/paper/5BHPE63Y"},"agent_actions":{"view_html":"https://pith.science/pith/5BHPE63YQFSXYID4TZBBTNM7A6","download_json":"https://pith.science/pith/5BHPE63YQFSXYID4TZBBTNM7A6.json","view_paper":"https://pith.science/paper/5BHPE63Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18740&json=true","fetch_graph":"https://pith.science/api/pith-number/5BHPE63YQFSXYID4TZBBTNM7A6/graph.json","fetch_events":"https://pith.science/api/pith-number/5BHPE63YQFSXYID4TZBBTNM7A6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BHPE63YQFSXYID4TZBBTNM7A6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BHPE63YQFSXYID4TZBBTNM7A6/action/storage_attestation","attest_author":"https://pith.science/pith/5BHPE63YQFSXYID4TZBBTNM7A6/action/author_attestation","sign_citation":"https://pith.science/pith/5BHPE63YQFSXYID4TZBBTNM7A6/action/citation_signature","submit_replication":"https://pith.science/pith/5BHPE63YQFSXYID4TZBBTNM7A6/action/replication_record"}},"created_at":"2026-07-05T08:37:25.133845+00:00","updated_at":"2026-07-05T08:37:25.133845+00:00"}