{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OUE7E4IRD4E4BDQPP4FWUXBJNI","short_pith_number":"pith:OUE7E4IR","schema_version":"1.0","canonical_sha256":"7509f271111f09c08e0f7f0b6a5c296a33ec362696478ece8c9b30b563de34b7","source":{"kind":"arxiv","id":"2510.10528","version":3},"attestation_state":"computed","paper":{"title":"Merlin's Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chak Tou Leong, Cunxiao Du, Heming Xia, Rui Li, Wenjie Li, Yongqi Li","submitted_at":"2025-10-12T09:56:47Z","abstract_excerpt":"Large reasoning models (LRMs) have demonstrated remarkable proficiency in tackling complex tasks through step-by-step thinking. However, this lengthy reasoning process incurs substantial computational and latency overheads, hindering the practical deployment of LRMs. This work presents a new approach to mitigating overthinking in LRMs via black-box persuasive prompting. By treating LRMs as black-box communicators, we investigate how to persuade them to generate concise responses without compromising accuracy. We introduce Whisper, an iterative refinement framework that generates high-quality p"},"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":"2510.10528","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-12T09:56:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"64019da87b43349b49bd977924dd3208a17d3353713491ad7bd193907122a05e","abstract_canon_sha256":"965ff702bf919299f7c52409b66c25202a72fd2a9317f60154bc40860e169178"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:14.576619Z","signature_b64":"3NhxyhZ0kUQQqGRH5xFF8XygsxwFHlFRyX3a5CcYhn0KKmDieMuzRr9qFpvZTuJwUh+C9V2Kh9v8oAr8npGVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7509f271111f09c08e0f7f0b6a5c296a33ec362696478ece8c9b30b563de34b7","last_reissued_at":"2026-05-20T00:04:14.575692Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:14.575692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Merlin's Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chak Tou Leong, Cunxiao Du, Heming Xia, Rui Li, Wenjie Li, Yongqi Li","submitted_at":"2025-10-12T09:56:47Z","abstract_excerpt":"Large reasoning models (LRMs) have demonstrated remarkable proficiency in tackling complex tasks through step-by-step thinking. However, this lengthy reasoning process incurs substantial computational and latency overheads, hindering the practical deployment of LRMs. This work presents a new approach to mitigating overthinking in LRMs via black-box persuasive prompting. By treating LRMs as black-box communicators, we investigate how to persuade them to generate concise responses without compromising accuracy. We introduce Whisper, an iterative refinement framework that generates high-quality p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.10528","kind":"arxiv","version":3},"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/2510.10528/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":"2510.10528","created_at":"2026-05-20T00:04:14.575854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.10528v3","created_at":"2026-05-20T00:04:14.575854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.10528","created_at":"2026-05-20T00:04:14.575854+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUE7E4IRD4E4","created_at":"2026-05-20T00:04:14.575854+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUE7E4IRD4E4BDQP","created_at":"2026-05-20T00:04:14.575854+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUE7E4IR","created_at":"2026-05-20T00:04:14.575854+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/OUE7E4IRD4E4BDQPP4FWUXBJNI","json":"https://pith.science/pith/OUE7E4IRD4E4BDQPP4FWUXBJNI.json","graph_json":"https://pith.science/api/pith-number/OUE7E4IRD4E4BDQPP4FWUXBJNI/graph.json","events_json":"https://pith.science/api/pith-number/OUE7E4IRD4E4BDQPP4FWUXBJNI/events.json","paper":"https://pith.science/paper/OUE7E4IR"},"agent_actions":{"view_html":"https://pith.science/pith/OUE7E4IRD4E4BDQPP4FWUXBJNI","download_json":"https://pith.science/pith/OUE7E4IRD4E4BDQPP4FWUXBJNI.json","view_paper":"https://pith.science/paper/OUE7E4IR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.10528&json=true","fetch_graph":"https://pith.science/api/pith-number/OUE7E4IRD4E4BDQPP4FWUXBJNI/graph.json","fetch_events":"https://pith.science/api/pith-number/OUE7E4IRD4E4BDQPP4FWUXBJNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUE7E4IRD4E4BDQPP4FWUXBJNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUE7E4IRD4E4BDQPP4FWUXBJNI/action/storage_attestation","attest_author":"https://pith.science/pith/OUE7E4IRD4E4BDQPP4FWUXBJNI/action/author_attestation","sign_citation":"https://pith.science/pith/OUE7E4IRD4E4BDQPP4FWUXBJNI/action/citation_signature","submit_replication":"https://pith.science/pith/OUE7E4IRD4E4BDQPP4FWUXBJNI/action/replication_record"}},"created_at":"2026-05-20T00:04:14.575854+00:00","updated_at":"2026-05-20T00:04:14.575854+00:00"}