{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YBPOGTJYAIHETN4MAIGAO3NW2T","short_pith_number":"pith:YBPOGTJY","schema_version":"1.0","canonical_sha256":"c05ee34d38020e49b78c020c076db6d4e6c429982c5316d04694b1bf3e7868f0","source":{"kind":"arxiv","id":"2605.28873","version":1},"attestation_state":"computed","paper":{"title":"Pre-Registering the Detectable Effect: A Paired-MDE Budget for 4-bit Quantization Benchmarks, with a Pilot Audit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yanhang Li, Zexin Zhuang, Zhichao Fan","submitted_at":"2026-05-25T07:13:35Z","abstract_excerpt":"This is a planning-method note with an unpaired pilot audit. We adapt the classical paired-binary sample-size calculation (Miettinen, 1968) to quantization benchmarks, giving a conservative minimum detectable effect (MDE) bound $\\delta^{*} \\le (z_{1-\\alpha/2}+z_{1-\\beta})\\sqrt{\\rho_d/m}$ in the paired item count $m$ and the FP16-NF4 disagreement rate $\\rho_d$. The bound turns \"how reliable is my quantization claim?\" into a one-line budget a benchmark designer can commit to before running. We illustrate the bound on four models and four benchmarks ($k=5$ splits of $n=100$), and add a parallel M"},"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":"2605.28873","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T07:13:35Z","cross_cats_sorted":[],"title_canon_sha256":"a21b40fdc4993a5b2883cf202367485185b0befea55b7eae33b2bcf585582bcf","abstract_canon_sha256":"40e732ea96e4d8cc3ad6f9affa6caa98ad3efe45f874fa59d768e67eae35d900"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T00:04:14.955429Z","signature_b64":"G4yufoB39uED4H3GBIjsHQlSSOPdHzAYAq+Og0q9K6QQX11ZwQ0g0p8N9vjrj8SAboT8XXyHU9m3Tq5SuEaOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c05ee34d38020e49b78c020c076db6d4e6c429982c5316d04694b1bf3e7868f0","last_reissued_at":"2026-05-29T00:04:14.954954Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T00:04:14.954954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-Registering the Detectable Effect: A Paired-MDE Budget for 4-bit Quantization Benchmarks, with a Pilot Audit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yanhang Li, Zexin Zhuang, Zhichao Fan","submitted_at":"2026-05-25T07:13:35Z","abstract_excerpt":"This is a planning-method note with an unpaired pilot audit. We adapt the classical paired-binary sample-size calculation (Miettinen, 1968) to quantization benchmarks, giving a conservative minimum detectable effect (MDE) bound $\\delta^{*} \\le (z_{1-\\alpha/2}+z_{1-\\beta})\\sqrt{\\rho_d/m}$ in the paired item count $m$ and the FP16-NF4 disagreement rate $\\rho_d$. The bound turns \"how reliable is my quantization claim?\" into a one-line budget a benchmark designer can commit to before running. We illustrate the bound on four models and four benchmarks ($k=5$ splits of $n=100$), and add a parallel M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28873","kind":"arxiv","version":1},"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/2605.28873/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":"2605.28873","created_at":"2026-05-29T00:04:14.955018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28873v1","created_at":"2026-05-29T00:04:14.955018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28873","created_at":"2026-05-29T00:04:14.955018+00:00"},{"alias_kind":"pith_short_12","alias_value":"YBPOGTJYAIHE","created_at":"2026-05-29T00:04:14.955018+00:00"},{"alias_kind":"pith_short_16","alias_value":"YBPOGTJYAIHETN4M","created_at":"2026-05-29T00:04:14.955018+00:00"},{"alias_kind":"pith_short_8","alias_value":"YBPOGTJY","created_at":"2026-05-29T00:04:14.955018+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/YBPOGTJYAIHETN4MAIGAO3NW2T","json":"https://pith.science/pith/YBPOGTJYAIHETN4MAIGAO3NW2T.json","graph_json":"https://pith.science/api/pith-number/YBPOGTJYAIHETN4MAIGAO3NW2T/graph.json","events_json":"https://pith.science/api/pith-number/YBPOGTJYAIHETN4MAIGAO3NW2T/events.json","paper":"https://pith.science/paper/YBPOGTJY"},"agent_actions":{"view_html":"https://pith.science/pith/YBPOGTJYAIHETN4MAIGAO3NW2T","download_json":"https://pith.science/pith/YBPOGTJYAIHETN4MAIGAO3NW2T.json","view_paper":"https://pith.science/paper/YBPOGTJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28873&json=true","fetch_graph":"https://pith.science/api/pith-number/YBPOGTJYAIHETN4MAIGAO3NW2T/graph.json","fetch_events":"https://pith.science/api/pith-number/YBPOGTJYAIHETN4MAIGAO3NW2T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YBPOGTJYAIHETN4MAIGAO3NW2T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YBPOGTJYAIHETN4MAIGAO3NW2T/action/storage_attestation","attest_author":"https://pith.science/pith/YBPOGTJYAIHETN4MAIGAO3NW2T/action/author_attestation","sign_citation":"https://pith.science/pith/YBPOGTJYAIHETN4MAIGAO3NW2T/action/citation_signature","submit_replication":"https://pith.science/pith/YBPOGTJYAIHETN4MAIGAO3NW2T/action/replication_record"}},"created_at":"2026-05-29T00:04:14.955018+00:00","updated_at":"2026-05-29T00:04:14.955018+00:00"}