{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QJIWELKM5ZWEVAECOVRKETVLOC","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":"0ae8a01668ac6da75d58be818805384855d0af4b067e0e756cbc76d3fe39e17b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T06:12:17Z","title_canon_sha256":"e8241db3ddd52ad5ee88d9a3afc4ef892a788372e14b1ffeb8188882ea9e6a49"},"schema_version":"1.0","source":{"id":"2407.10457","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10457","created_at":"2026-07-05T08:43:59Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10457v1","created_at":"2026-07-05T08:43:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10457","created_at":"2026-07-05T08:43:59Z"},{"alias_kind":"pith_short_12","alias_value":"QJIWELKM5ZWE","created_at":"2026-07-05T08:43:59Z"},{"alias_kind":"pith_short_16","alias_value":"QJIWELKM5ZWEVAEC","created_at":"2026-07-05T08:43:59Z"},{"alias_kind":"pith_short_8","alias_value":"QJIWELKM","created_at":"2026-07-05T08:43:59Z"}],"graph_snapshots":[{"event_id":"sha256:4bdacb2a48967f039c5db4e51888eca7f269792cb93f29f43b06636c1aa0ba70","target":"graph","created_at":"2026-07-05T08:43:59Z","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/2407.10457/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current evaluations of large language models (LLMs) often overlook non-determinism, typically focusing on a single output per example. This limits our understanding of LLM performance variability in real-world applications. Our study addresses this issue by exploring key questions about the performance differences between greedy decoding and sampling, identifying benchmarks' consistency regarding non-determinism, and examining unique model behaviors. Through extensive experiments, we observe that greedy decoding generally outperforms sampling methods for most evaluated tasks. We also observe c","authors_text":"Bill Yuchen Lin, Guoyin Wang, Sujian Li, Yifan Song","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T06:12:17Z","title":"The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10457","kind":"arxiv","version":1},"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":"sha256:441a0dce1135996f78dae8e01af5461c715aa2b437316b03cddfa029919d2573","target":"record","created_at":"2026-07-05T08:43:59Z","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":"0ae8a01668ac6da75d58be818805384855d0af4b067e0e756cbc76d3fe39e17b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T06:12:17Z","title_canon_sha256":"e8241db3ddd52ad5ee88d9a3afc4ef892a788372e14b1ffeb8188882ea9e6a49"},"schema_version":"1.0","source":{"id":"2407.10457","kind":"arxiv","version":1}},"canonical_sha256":"8251622d4cee6c4a80827562a24eab70aa139a0ec46137e7954678817851c034","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8251622d4cee6c4a80827562a24eab70aa139a0ec46137e7954678817851c034","first_computed_at":"2026-07-05T08:43:59.811741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:59.811741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Db7VEfmFn7zZGxdPOUL8tu2q+cYxiXVYUjDZc7p/xAtSAEGFLK2NHaAbbD3RbL8LFon1FHQkVNz0rjmsCBsCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:59.812238Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.10457","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:441a0dce1135996f78dae8e01af5461c715aa2b437316b03cddfa029919d2573","sha256:4bdacb2a48967f039c5db4e51888eca7f269792cb93f29f43b06636c1aa0ba70"],"state_sha256":"5d076e81b6949b9c52d3c32c4f67852aac4b3d8c2525794ce2e96bbbcee36240"}