{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BD3J6CJSPYL2XLHWFM7HOHLUIN","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":"8aa74818ce1e9483f44c886ee7050d63993f8812271d9ae8a5518c2b0c411011","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-05T17:31:14Z","title_canon_sha256":"ecb77102ca30b700ca5cd3892fd774d990b8fa46a9a062ba717a22676a5fa18b"},"schema_version":"1.0","source":{"id":"2509.09705","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09705","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09705v1","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09705","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"BD3J6CJSPYL2","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"BD3J6CJSPYL2XLHW","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"BD3J6CJS","created_at":"2026-07-05T12:09:47Z"}],"graph_snapshots":[{"event_id":"sha256:99c52bff9c14352d270288862303b46d4a356679fb82a74b625b2012880f1171","target":"graph","created_at":"2026-07-05T12:09:47Z","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/2509.09705/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work explores the consistency of small LLMs (2B-8B parameters) in answering multiple times the same question. We present a study on known, open-source LLMs responding to 10 repetitions of questions from the multiple-choice benchmarks MMLU-Redux and MedQA, considering different inference temperatures, small vs. medium models (50B-80B), finetuned vs. base models, and other parameters. We also look into the effects of requiring multi-trial answer consistency on accuracy and the trade-offs involved in deciding which model best provides both of them. To support those studies, we propose some n","authors_text":"Cassia Sanctos, Claudio Pinhanez, Marcelo Grave, Paulo Cavalin, Yago Primerano","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-05T17:31:14Z","title":"The Non-Determinism of Small LLMs: Evidence of Low Answer Consistency in Repetition Trials of Standard Multiple-Choice Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09705","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:efdd9d9f5e855a7e812d4c788c175eedc4b23bfaa886e242c5680171a49ca19d","target":"record","created_at":"2026-07-05T12:09:47Z","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":"8aa74818ce1e9483f44c886ee7050d63993f8812271d9ae8a5518c2b0c411011","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-05T17:31:14Z","title_canon_sha256":"ecb77102ca30b700ca5cd3892fd774d990b8fa46a9a062ba717a22676a5fa18b"},"schema_version":"1.0","source":{"id":"2509.09705","kind":"arxiv","version":1}},"canonical_sha256":"08f69f09327e17abacf62b3e771d7443524ebe0e959646c7dac41c77166395f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08f69f09327e17abacf62b3e771d7443524ebe0e959646c7dac41c77166395f7","first_computed_at":"2026-07-05T12:09:47.520465Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:47.520465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4HnNzWbEEkbdOiaIHdmAvaU2lXLjmTBlezDaIZRYGac1yk2ZbhrZpJEuNwxGaEBTuVKhG45qjXfGCDygcPOfDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:47.520956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.09705","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efdd9d9f5e855a7e812d4c788c175eedc4b23bfaa886e242c5680171a49ca19d","sha256:99c52bff9c14352d270288862303b46d4a356679fb82a74b625b2012880f1171"],"state_sha256":"237a6a7540d9e0227e1dfb0f75b5b262ef502af55c87c7a3429fbef8650870dc"}