{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BD3J6CJSPYL2XLHWFM7HOHLUIN","short_pith_number":"pith:BD3J6CJS","canonical_record":{"source":{"id":"2509.09705","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-05T17:31:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ecb77102ca30b700ca5cd3892fd774d990b8fa46a9a062ba717a22676a5fa18b","abstract_canon_sha256":"8aa74818ce1e9483f44c886ee7050d63993f8812271d9ae8a5518c2b0c411011"},"schema_version":"1.0"},"canonical_sha256":"08f69f09327e17abacf62b3e771d7443524ebe0e959646c7dac41c77166395f7","source":{"kind":"arxiv","id":"2509.09705","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BD3J6CJSPYL2XLHWFM7HOHLUIN","target":"record","payload":{"canonical_record":{"source":{"id":"2509.09705","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-05T17:31:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ecb77102ca30b700ca5cd3892fd774d990b8fa46a9a062ba717a22676a5fa18b","abstract_canon_sha256":"8aa74818ce1e9483f44c886ee7050d63993f8812271d9ae8a5518c2b0c411011"},"schema_version":"1.0"},"canonical_sha256":"08f69f09327e17abacf62b3e771d7443524ebe0e959646c7dac41c77166395f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:47.520956Z","signature_b64":"4HnNzWbEEkbdOiaIHdmAvaU2lXLjmTBlezDaIZRYGac1yk2ZbhrZpJEuNwxGaEBTuVKhG45qjXfGCDygcPOfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08f69f09327e17abacf62b3e771d7443524ebe0e959646c7dac41c77166395f7","last_reissued_at":"2026-07-05T12:09:47.520465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:47.520465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.09705","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"enQbeqnA5MXgK0b1oaPTcH/EnjslDS1L8FU+yA5srJTacXBjXmcV9MsUytIBqyHDWUfELBuSDPlAIXo4YUR0BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:18:31.146218Z"},"content_sha256":"efdd9d9f5e855a7e812d4c788c175eedc4b23bfaa886e242c5680171a49ca19d","schema_version":"1.0","event_id":"sha256:efdd9d9f5e855a7e812d4c788c175eedc4b23bfaa886e242c5680171a49ca19d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BD3J6CJSPYL2XLHWFM7HOHLUIN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Non-Determinism of Small LLMs: Evidence of Low Answer Consistency in Repetition Trials of Standard Multiple-Choice Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cassia Sanctos, Claudio Pinhanez, Marcelo Grave, Paulo Cavalin, Yago Primerano","submitted_at":"2025-09-05T17:31:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09705","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/2509.09705/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8GAXnGyaR3VE2VLAOWN1U7wLtj9T+V5rW5kToNyl5HIemscRgOka9kjH8tQvrCtdOxrQU5TDzD29VP9KoYoXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:18:31.146742Z"},"content_sha256":"99c52bff9c14352d270288862303b46d4a356679fb82a74b625b2012880f1171","schema_version":"1.0","event_id":"sha256:99c52bff9c14352d270288862303b46d4a356679fb82a74b625b2012880f1171"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BD3J6CJSPYL2XLHWFM7HOHLUIN/bundle.json","state_url":"https://pith.science/pith/BD3J6CJSPYL2XLHWFM7HOHLUIN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BD3J6CJSPYL2XLHWFM7HOHLUIN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T13:18:31Z","links":{"resolver":"https://pith.science/pith/BD3J6CJSPYL2XLHWFM7HOHLUIN","bundle":"https://pith.science/pith/BD3J6CJSPYL2XLHWFM7HOHLUIN/bundle.json","state":"https://pith.science/pith/BD3J6CJSPYL2XLHWFM7HOHLUIN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BD3J6CJSPYL2XLHWFM7HOHLUIN/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZUSd7nnP6+BHh3BYkIRrFOVt8BA7Dy8ZDaurVtpTIGR8yMAxGHpX0oL2YcN175Xop7EoNsNiYhR0KLFhgipYBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:18:31.151758Z","bundle_sha256":"6abdb549b8c08855271798e80b13e359ae0c5985422d1b4faf59cdedf999e65d"}}