{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:465NOZE3SMBV6O3U77MJQF3SXR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e52f3244d5816c005958d5e8ea6095468285acf1fcc0002014153963d18f8006","cross_cats_sorted":["cond-mat.dis-nn","cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T10:37:32Z","title_canon_sha256":"7d1e2890476fa610a1edb192b7afab66a548ca73360dd0f44999b11ab81c2bd7"},"schema_version":"1.0","source":{"id":"2601.21522","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21522","created_at":"2026-06-09T01:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21522v2","created_at":"2026-06-09T01:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21522","created_at":"2026-06-09T01:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"465NOZE3SMBV","created_at":"2026-06-09T01:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"465NOZE3SMBV6O3U","created_at":"2026-06-09T01:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"465NOZE3","created_at":"2026-06-09T01:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:fb6035fa631243ff4bdfda6e9ad40ee214cf93f7c80c65681e03b8cfce7e84eb","target":"graph","created_at":"2026-06-09T01:05:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.21522/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The performance of large language models (LLMs) on verifiable tasks is usually measured by pass@k, the probability of answering a question correctly at least once in k trials. At a fixed budget, a more suitable metric is coverage@cost, the average number of unique questions answered as a function of the total number of attempts. We connect the two metrics and show that the empirically-observed power-law behavior in pass@k leads to a sublinear growth of the coverage@cost (diminishing returns). To solve this problem, we propose Reset-and-Discard (ReD), a query method of LLMs that increases cover","authors_text":"Barak Hirshberg, Noam Levi, Sagi Meir, Shlomi Reuveni, Tommer D. Keidar","cross_cats":["cond-mat.dis-nn","cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T10:37:32Z","title":"More Bang for the Buck: Improving the Inference of Large Language Models at a Fixed Budget using Reset and Discard (ReD)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21522","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4459087a8934f10c85de0f558b985524bbceefd9b2816f38e9d0219210624578","target":"record","created_at":"2026-06-09T01:05:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e52f3244d5816c005958d5e8ea6095468285acf1fcc0002014153963d18f8006","cross_cats_sorted":["cond-mat.dis-nn","cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T10:37:32Z","title_canon_sha256":"7d1e2890476fa610a1edb192b7afab66a548ca73360dd0f44999b11ab81c2bd7"},"schema_version":"1.0","source":{"id":"2601.21522","kind":"arxiv","version":2}},"canonical_sha256":"e7bad7649b93035f3b74ffd8981772bc6aa595ec707ae0e24901740eb76da41d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7bad7649b93035f3b74ffd8981772bc6aa595ec707ae0e24901740eb76da41d","first_computed_at":"2026-06-09T01:05:13.346790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:13.346790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p3SZfVf+2F7PzQuPT7ZKyxxOc7WowtETr3k8OXhOV84gdARt5T4c1SEp/lzDMyuGrIF85BCpnzDrGD2b810+Ag==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:13.347222Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.21522","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4459087a8934f10c85de0f558b985524bbceefd9b2816f38e9d0219210624578","sha256:fb6035fa631243ff4bdfda6e9ad40ee214cf93f7c80c65681e03b8cfce7e84eb"],"state_sha256":"5e1af805050e692ac5d05c03d18eae6facd4c38a8f422ec90afc200f35f50a75"}