{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q3526YJVFH5VYLSNZND6SPZIGL","short_pith_number":"pith:Q3526YJV","schema_version":"1.0","canonical_sha256":"86fbaf613529fb5c2e4dcb47e93f2832ebb9fc7d078a653d9399999d4f71cf01","source":{"kind":"arxiv","id":"2506.13681","version":2},"attestation_state":"computed","paper":{"title":"Min-p, Max Exaggeration: A Critical Analysis of Min-p Sampling in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Joshua Kazdan, Rylan Schaeffer, Yegor Denisov-Blanch","submitted_at":"2025-06-16T16:38:04Z","abstract_excerpt":"Sampling from language models impacts the quality and diversity of outputs, affecting both research and real-world applications. Recently, Nguyen et al. 2024's \"Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs\" introduced a new sampler called min-p, claiming it achieves superior quality and diversity over established samplers such as basic, top-k, and top-p sampling. The significance of these claims was underscored by the paper's recognition as the 18th highest-scoring submission to ICLR 2025 and selection for an Oral presentation. This paper conducts a comprehensive r"},"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":"2506.13681","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T16:38:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"966e9b6c20c1f42e452f33804ceedae4dfbf78a752f0b22b6fd225925faad16d","abstract_canon_sha256":"ce77ad6908a01c45900daf17673f514bd0b171f7dc6ac8c2a6652259ad12d3ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:23.918746Z","signature_b64":"VlWdUXQ3XlMJC3Gg1tiFGuYX0nS2NkmcZ5VQBQFSfzzhQokNSNYx7jYKpChnamK6h7hjnrDPC7egGDuC7bBZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86fbaf613529fb5c2e4dcb47e93f2832ebb9fc7d078a653d9399999d4f71cf01","last_reissued_at":"2026-07-05T11:24:23.918218Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:23.918218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Min-p, Max Exaggeration: A Critical Analysis of Min-p Sampling in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Joshua Kazdan, Rylan Schaeffer, Yegor Denisov-Blanch","submitted_at":"2025-06-16T16:38:04Z","abstract_excerpt":"Sampling from language models impacts the quality and diversity of outputs, affecting both research and real-world applications. Recently, Nguyen et al. 2024's \"Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs\" introduced a new sampler called min-p, claiming it achieves superior quality and diversity over established samplers such as basic, top-k, and top-p sampling. The significance of these claims was underscored by the paper's recognition as the 18th highest-scoring submission to ICLR 2025 and selection for an Oral presentation. This paper conducts a comprehensive r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13681","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/2506.13681/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":"2506.13681","created_at":"2026-07-05T11:24:23.918281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13681v2","created_at":"2026-07-05T11:24:23.918281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13681","created_at":"2026-07-05T11:24:23.918281+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3526YJVFH5V","created_at":"2026-07-05T11:24:23.918281+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3526YJVFH5VYLSN","created_at":"2026-07-05T11:24:23.918281+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3526YJV","created_at":"2026-07-05T11:24:23.918281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.19882","citing_title":"Position: Machine Learning Conferences Should Establish a \"Refutations and Critiques\" Track","ref_index":83,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3526YJVFH5VYLSNZND6SPZIGL","json":"https://pith.science/pith/Q3526YJVFH5VYLSNZND6SPZIGL.json","graph_json":"https://pith.science/api/pith-number/Q3526YJVFH5VYLSNZND6SPZIGL/graph.json","events_json":"https://pith.science/api/pith-number/Q3526YJVFH5VYLSNZND6SPZIGL/events.json","paper":"https://pith.science/paper/Q3526YJV"},"agent_actions":{"view_html":"https://pith.science/pith/Q3526YJVFH5VYLSNZND6SPZIGL","download_json":"https://pith.science/pith/Q3526YJVFH5VYLSNZND6SPZIGL.json","view_paper":"https://pith.science/paper/Q3526YJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13681&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3526YJVFH5VYLSNZND6SPZIGL/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3526YJVFH5VYLSNZND6SPZIGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3526YJVFH5VYLSNZND6SPZIGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3526YJVFH5VYLSNZND6SPZIGL/action/storage_attestation","attest_author":"https://pith.science/pith/Q3526YJVFH5VYLSNZND6SPZIGL/action/author_attestation","sign_citation":"https://pith.science/pith/Q3526YJVFH5VYLSNZND6SPZIGL/action/citation_signature","submit_replication":"https://pith.science/pith/Q3526YJVFH5VYLSNZND6SPZIGL/action/replication_record"}},"created_at":"2026-07-05T11:24:23.918281+00:00","updated_at":"2026-07-05T11:24:23.918281+00:00"}