{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BCH2K7KMHJNAOIWTD6CUQX3XDC","short_pith_number":"pith:BCH2K7KM","schema_version":"1.0","canonical_sha256":"088fa57d4c3a5a0722d31f85485f77188f737d506d91a1d299441eef348bade5","source":{"kind":"arxiv","id":"2605.14450","version":1},"attestation_state":"computed","paper":{"title":"Stop Overthinking: Unlocking Efficient Listwise Reranking with Minimal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A length-regularized self-distillation method lets student rerankers match teacher effectiveness while cutting reasoning tokens by 34-37%.","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Danyang Liu, Kan Li","submitted_at":"2026-05-14T06:44:44Z","abstract_excerpt":"Listwise reranking utilizing Large Language Models (LLMs) has achieved state-of-the-art retrieval effectiveness. Recently, reasoning-enhanced models have further pushed these boundaries by employing Chain-of-Thought (CoT) to perform deep comparative analysis of candidate documents. However, this performance gain comes at a prohibitive computational cost, as models often generate thousands of reasoning tokens before producing a final ranking. In this work, we investigate the relationship between reasoning length and ranking quality, revealing an overthinking phenomenon where extended reasoning "},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.14450","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-14T06:44:44Z","cross_cats_sorted":[],"title_canon_sha256":"b53e38cb866b72e67cfe38c48de8f5ef5a38a1dcca3eb48ef192e272bca964cc","abstract_canon_sha256":"3afc3a2b06b55bde658dbbb1ad674fb8dab59005cf3fb93b0bc4e3012a779675"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:06.904686Z","signature_b64":"7VoZGGN2s1zBPzfB9LrFpxLbFZgoJFYK/x4em2coiYpym9GgtweWkH5v3m0ZDH19XJd+198fhpARzJ0J0opNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"088fa57d4c3a5a0722d31f85485f77188f737d506d91a1d299441eef348bade5","last_reissued_at":"2026-05-17T23:39:06.903989Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:06.903989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stop Overthinking: Unlocking Efficient Listwise Reranking with Minimal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A length-regularized self-distillation method lets student rerankers match teacher effectiveness while cutting reasoning tokens by 34-37%.","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Danyang Liu, Kan Li","submitted_at":"2026-05-14T06:44:44Z","abstract_excerpt":"Listwise reranking utilizing Large Language Models (LLMs) has achieved state-of-the-art retrieval effectiveness. Recently, reasoning-enhanced models have further pushed these boundaries by employing Chain-of-Thought (CoT) to perform deep comparative analysis of candidate documents. However, this performance gain comes at a prohibitive computational cost, as models often generate thousands of reasoning tokens before producing a final ranking. In this work, we investigate the relationship between reasoning length and ranking quality, revealing an overthinking phenomenon where extended reasoning "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on TREC Deep Learning and NeuCLIR benchmarks demonstrate that our method maintains the teacher's effectiveness while reducing inference token consumption by 34%-37% across different retrieval settings.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The Pareto-inspired filter reliably selects reasoning traces that preserve ranking quality when transferred to the student model; this transfer is assumed to work without additional validation on held-out data or different model scales.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Length-regularized self-distillation trains rerankers to use concise reasoning traces that match teacher performance at 34-37 percent lower token cost.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A length-regularized self-distillation method lets student rerankers match teacher effectiveness while cutting reasoning tokens by 34-37%.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"16c3e37d41985ab85009f9bd3b8ddd657f61dacff6c179a940328c509d76cacb"},"source":{"id":"2605.14450","kind":"arxiv","version":1},"verdict":{"id":"702478b1-86a5-4569-908c-94ecf807b62a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:07:57.820930Z","strongest_claim":"Experiments on TREC Deep Learning and NeuCLIR benchmarks demonstrate that our method maintains the teacher's effectiveness while reducing inference token consumption by 34%-37% across different retrieval settings.","one_line_summary":"Length-regularized self-distillation trains rerankers to use concise reasoning traces that match teacher performance at 34-37 percent lower token cost.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The Pareto-inspired filter reliably selects reasoning traces that preserve ranking quality when transferred to the student model; this transfer is assumed to work without additional validation on held-out data or different model scales.","pith_extraction_headline":"A length-regularized self-distillation method lets student rerankers match teacher effectiveness while cutting reasoning tokens by 34-37%."},"references":{"count":2,"sample":[{"doi":"","year":2019,"title":"R. Nogueira and K. Cho, ‘Passage Re-ranking with BERT’, ArXiv Prepr. ArXiv190104085, 2019. [19] S. Hongjin et al., ‘BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval’, in","work_id":"2ae19ad0-6558-413f-9850-4c9ee7dfcee8","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Chen et al., ‘TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy’, ArXiv Prepr","work_id":"dc4751f9-ee5d-40d6-8bee-e77c503fa779","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":2,"snapshot_sha256":"dad3146a84a35bfb7c8ce7a2f36dccfb4afb515df42c6a50b4642025944dec83","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":"2605.14450","created_at":"2026-05-17T23:39:06.904111+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14450v1","created_at":"2026-05-17T23:39:06.904111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14450","created_at":"2026-05-17T23:39:06.904111+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCH2K7KMHJNA","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCH2K7KMHJNAOIWT","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCH2K7KM","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BCH2K7KMHJNAOIWTD6CUQX3XDC","json":"https://pith.science/pith/BCH2K7KMHJNAOIWTD6CUQX3XDC.json","graph_json":"https://pith.science/api/pith-number/BCH2K7KMHJNAOIWTD6CUQX3XDC/graph.json","events_json":"https://pith.science/api/pith-number/BCH2K7KMHJNAOIWTD6CUQX3XDC/events.json","paper":"https://pith.science/paper/BCH2K7KM"},"agent_actions":{"view_html":"https://pith.science/pith/BCH2K7KMHJNAOIWTD6CUQX3XDC","download_json":"https://pith.science/pith/BCH2K7KMHJNAOIWTD6CUQX3XDC.json","view_paper":"https://pith.science/paper/BCH2K7KM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14450&json=true","fetch_graph":"https://pith.science/api/pith-number/BCH2K7KMHJNAOIWTD6CUQX3XDC/graph.json","fetch_events":"https://pith.science/api/pith-number/BCH2K7KMHJNAOIWTD6CUQX3XDC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCH2K7KMHJNAOIWTD6CUQX3XDC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCH2K7KMHJNAOIWTD6CUQX3XDC/action/storage_attestation","attest_author":"https://pith.science/pith/BCH2K7KMHJNAOIWTD6CUQX3XDC/action/author_attestation","sign_citation":"https://pith.science/pith/BCH2K7KMHJNAOIWTD6CUQX3XDC/action/citation_signature","submit_replication":"https://pith.science/pith/BCH2K7KMHJNAOIWTD6CUQX3XDC/action/replication_record"}},"created_at":"2026-05-17T23:39:06.904111+00:00","updated_at":"2026-05-17T23:39:06.904111+00:00"}