{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G6LGO2OO7I2323JSEBOW4KJFXE","short_pith_number":"pith:G6LGO2OO","schema_version":"1.0","canonical_sha256":"37966769cefa35bd6d32205d6e2925b9361e97e1928242f9caef895d70885a4b","source":{"kind":"arxiv","id":"2505.12938","version":2},"attestation_state":"computed","paper":{"title":"Leveraging LLM Inconsistency to Boost Pass@k Performance","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Dan Lahav, Meirav Segal, Omer Nevo, Uri Dalal, Zvika Ben-Haim","submitted_at":"2025-05-19T10:22:04Z","abstract_excerpt":"Large language models (LLMs) achieve impressive abilities in numerous domains, but exhibit inconsistent performance in response to minor input changes. Rather than view this as a drawback, in this paper we introduce a novel method for leveraging models' inconsistency to boost Pass@k performance. Specifically, we present a \"Variator\" agent that generates k variants of a given task and submits one candidate solution for each one. Our variant generation approach is applicable to a wide range of domains as it is task agnostic and compatible with free-form inputs. We demonstrate the efficacy of our"},"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":"2505.12938","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T10:22:04Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"35ad84149574ccde2f998fa880f0c80d96d7b446b7283a6e3e25ef28f6c60690","abstract_canon_sha256":"315dc87469f935ebb07921c82e5062e795e20eb403a2b11290ad3b208f075d00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:45.677473Z","signature_b64":"60BrECGTic/fefSVjh8v9u7an2itlLskK+aVe+DdEWqYhJ8Kp1chiIwNzRrMZrFSdF9FJmD1apCsbelsLVEkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37966769cefa35bd6d32205d6e2925b9361e97e1928242f9caef895d70885a4b","last_reissued_at":"2026-07-05T11:05:45.677026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:45.677026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging LLM Inconsistency to Boost Pass@k Performance","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Dan Lahav, Meirav Segal, Omer Nevo, Uri Dalal, Zvika Ben-Haim","submitted_at":"2025-05-19T10:22:04Z","abstract_excerpt":"Large language models (LLMs) achieve impressive abilities in numerous domains, but exhibit inconsistent performance in response to minor input changes. Rather than view this as a drawback, in this paper we introduce a novel method for leveraging models' inconsistency to boost Pass@k performance. Specifically, we present a \"Variator\" agent that generates k variants of a given task and submits one candidate solution for each one. Our variant generation approach is applicable to a wide range of domains as it is task agnostic and compatible with free-form inputs. We demonstrate the efficacy of our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12938","kind":"arxiv","version":2},"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/2505.12938/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":"2505.12938","created_at":"2026-07-05T11:05:45.677075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12938v2","created_at":"2026-07-05T11:05:45.677075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12938","created_at":"2026-07-05T11:05:45.677075+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6LGO2OO7I23","created_at":"2026-07-05T11:05:45.677075+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6LGO2OO7I2323JS","created_at":"2026-07-05T11:05:45.677075+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6LGO2OO","created_at":"2026-07-05T11:05:45.677075+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.04265","citing_title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6LGO2OO7I2323JSEBOW4KJFXE","json":"https://pith.science/pith/G6LGO2OO7I2323JSEBOW4KJFXE.json","graph_json":"https://pith.science/api/pith-number/G6LGO2OO7I2323JSEBOW4KJFXE/graph.json","events_json":"https://pith.science/api/pith-number/G6LGO2OO7I2323JSEBOW4KJFXE/events.json","paper":"https://pith.science/paper/G6LGO2OO"},"agent_actions":{"view_html":"https://pith.science/pith/G6LGO2OO7I2323JSEBOW4KJFXE","download_json":"https://pith.science/pith/G6LGO2OO7I2323JSEBOW4KJFXE.json","view_paper":"https://pith.science/paper/G6LGO2OO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12938&json=true","fetch_graph":"https://pith.science/api/pith-number/G6LGO2OO7I2323JSEBOW4KJFXE/graph.json","fetch_events":"https://pith.science/api/pith-number/G6LGO2OO7I2323JSEBOW4KJFXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6LGO2OO7I2323JSEBOW4KJFXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6LGO2OO7I2323JSEBOW4KJFXE/action/storage_attestation","attest_author":"https://pith.science/pith/G6LGO2OO7I2323JSEBOW4KJFXE/action/author_attestation","sign_citation":"https://pith.science/pith/G6LGO2OO7I2323JSEBOW4KJFXE/action/citation_signature","submit_replication":"https://pith.science/pith/G6LGO2OO7I2323JSEBOW4KJFXE/action/replication_record"}},"created_at":"2026-07-05T11:05:45.677075+00:00","updated_at":"2026-07-05T11:05:45.677075+00:00"}