{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L2KZ6GFWAF2IBCT3ZJGMTHYDRF","short_pith_number":"pith:L2KZ6GFW","schema_version":"1.0","canonical_sha256":"5e959f18b60174808a7bca4cc99f038947fd79f6f4dd028bd38b851e3f8fb831","source":{"kind":"arxiv","id":"2605.13695","version":1},"attestation_state":"computed","paper":{"title":"RTLC -- Research, Teach-to-Learn, Critique: A three-stage prompting paradigm inspired by the Feynman Learning Technique that lifts LLM-as-judge accuracy on JudgeBench with no fine-tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A three-stage prompting method lifts LLM judge accuracy from 65% to 79% on hard pairwise comparisons.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrea Morandi","submitted_at":"2026-05-13T15:48:16Z","abstract_excerpt":"LLM-as-a-judge is now the default measurement instrument for open-ended generation, but on the public JudgeBench benchmark even strong instruction-tuned judges barely scrape past random on objective-correctness pairwise items. We introduce RTLC, a three-stage prompting recipe -- Research, Teach-to-Learn, Critique -- that promotes a single black-box LLM into an ensemble-of-thought judge with no fine-tuning, retrieval, or external tools. Stage 1 wraps the input in a fixed pedagogical scaffold porting the Feynman Learning Technique (study $\\to$ teach $\\to$ find gaps $\\to$ simplify) into LLM promp"},"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":"2605.13695","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T15:48:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4779848ed5081b59722c936a564a648a6a165e56430d251b11740f808565f23","abstract_canon_sha256":"a356867732d5cd804f47160ad9c6aef81f170696de37075918f5dfdbe0367e1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:16.911085Z","signature_b64":"JPY+CBof+cylYrJR8p8cexUxvCAf7uXugPhXOnmw2SBr7mHNtjHlWp+BrTZ0MKAtozSxns3LJKZOVQJSanZcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e959f18b60174808a7bca4cc99f038947fd79f6f4dd028bd38b851e3f8fb831","last_reissued_at":"2026-05-18T02:44:16.910577Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:16.910577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RTLC -- Research, Teach-to-Learn, Critique: A three-stage prompting paradigm inspired by the Feynman Learning Technique that lifts LLM-as-judge accuracy on JudgeBench with no fine-tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A three-stage prompting method lifts LLM judge accuracy from 65% to 79% on hard pairwise comparisons.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrea Morandi","submitted_at":"2026-05-13T15:48:16Z","abstract_excerpt":"LLM-as-a-judge is now the default measurement instrument for open-ended generation, but on the public JudgeBench benchmark even strong instruction-tuned judges barely scrape past random on objective-correctness pairwise items. We introduce RTLC, a three-stage prompting recipe -- Research, Teach-to-Learn, Critique -- that promotes a single black-box LLM into an ensemble-of-thought judge with no fine-tuning, retrieval, or external tools. Stage 1 wraps the input in a fixed pedagogical scaffold porting the Feynman Learning Technique (study $\\to$ teach $\\to$ find gaps $\\to$ simplify) into LLM promp"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On JudgeBench-GPT (350 hard pairwise items), Claude 3.7 Sonnet's pairwise accuracy climbs from 64.6% (single-shot vanilla prompt) to 78.6% (RTLC critique-of-10) -- an absolute 14.0-percentage-point gain.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the reported accuracy gains are driven by the specific RTLC stages rather than increased token budget, model-specific behavior, or benchmark idiosyncrasies, and that the high-level stage descriptions translate to reproducible prompts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RTLC prompting lifts Claude 3.7 Sonnet pairwise accuracy on 350 hard JudgeBench items from 64.6% to 78.6% via a Research-Teach-Critique scaffold that beats self-consistency.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A three-stage prompting method lifts LLM judge accuracy from 65% to 79% on hard pairwise comparisons.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1f8360bf3e1fdcfe4c0292cb93aba3641979ef47104dde83b5e6e6c9d4137993"},"source":{"id":"2605.13695","kind":"arxiv","version":1},"verdict":{"id":"e822b72b-d1c5-4474-8f83-a3888ecdfb48","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:33:16.648397Z","strongest_claim":"On JudgeBench-GPT (350 hard pairwise items), Claude 3.7 Sonnet's pairwise accuracy climbs from 64.6% (single-shot vanilla prompt) to 78.6% (RTLC critique-of-10) -- an absolute 14.0-percentage-point gain.","one_line_summary":"RTLC prompting lifts Claude 3.7 Sonnet pairwise accuracy on 350 hard JudgeBench items from 64.6% to 78.6% via a Research-Teach-Critique scaffold that beats self-consistency.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the reported accuracy gains are driven by the specific RTLC stages rather than increased token budget, model-specific behavior, or benchmark idiosyncrasies, and that the high-level stage descriptions translate to reproducible prompts.","pith_extraction_headline":"A three-stage prompting method lifts LLM judge accuracy from 65% to 79% on hard pairwise comparisons."},"references":{"count":10,"sample":[{"doi":"","year":2025,"title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","work_id":"7255b223-8380-468c-9951-e1617432eb73","ref_index":1,"cited_arxiv_id":"2410.12784","is_internal_anchor":true},{"doi":"","year":2026,"title":"Two ways to de-bias an LLM-as-a-Judge: A continuous- score comparison of hierarchical Bayesian calibration and Neural-ODE score transport,","work_id":"ff0ca1ec-586f-4a0a-93f4-85f3b089f968","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","work_id":"cccce1f9-7736-4f3d-8edd-e8144f4dd4b0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"UltraFeedback: Boosting language models with scaled AI feedback,","work_id":"f52ce90f-710f-46f7-b2e5-bf897147b498","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","work_id":"8c6d5a6b-b5cc-4105-9c84-9c34bb9375bb","ref_index":5,"cited_arxiv_id":"2203.11171","is_internal_anchor":true}],"resolved_work":10,"snapshot_sha256":"8ceda67c5036921e5336dc75d7d24f02f81f7056a3a9087c77cdb44db396f195","internal_anchors":5},"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":"2605.13695","created_at":"2026-05-18T02:44:16.910659+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13695v1","created_at":"2026-05-18T02:44:16.910659+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13695","created_at":"2026-05-18T02:44:16.910659+00:00"},{"alias_kind":"pith_short_12","alias_value":"L2KZ6GFWAF2I","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"L2KZ6GFWAF2IBCT3","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"L2KZ6GFW","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.19193","citing_title":"Sequential Consensus for Multi-Agent LLM Debates: A Wald-SPRT compute governor with calibration-based failure detection","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L2KZ6GFWAF2IBCT3ZJGMTHYDRF","json":"https://pith.science/pith/L2KZ6GFWAF2IBCT3ZJGMTHYDRF.json","graph_json":"https://pith.science/api/pith-number/L2KZ6GFWAF2IBCT3ZJGMTHYDRF/graph.json","events_json":"https://pith.science/api/pith-number/L2KZ6GFWAF2IBCT3ZJGMTHYDRF/events.json","paper":"https://pith.science/paper/L2KZ6GFW"},"agent_actions":{"view_html":"https://pith.science/pith/L2KZ6GFWAF2IBCT3ZJGMTHYDRF","download_json":"https://pith.science/pith/L2KZ6GFWAF2IBCT3ZJGMTHYDRF.json","view_paper":"https://pith.science/paper/L2KZ6GFW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13695&json=true","fetch_graph":"https://pith.science/api/pith-number/L2KZ6GFWAF2IBCT3ZJGMTHYDRF/graph.json","fetch_events":"https://pith.science/api/pith-number/L2KZ6GFWAF2IBCT3ZJGMTHYDRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L2KZ6GFWAF2IBCT3ZJGMTHYDRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L2KZ6GFWAF2IBCT3ZJGMTHYDRF/action/storage_attestation","attest_author":"https://pith.science/pith/L2KZ6GFWAF2IBCT3ZJGMTHYDRF/action/author_attestation","sign_citation":"https://pith.science/pith/L2KZ6GFWAF2IBCT3ZJGMTHYDRF/action/citation_signature","submit_replication":"https://pith.science/pith/L2KZ6GFWAF2IBCT3ZJGMTHYDRF/action/replication_record"}},"created_at":"2026-05-18T02:44:16.910659+00:00","updated_at":"2026-05-18T02:44:16.910659+00:00"}