{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:46LFMSDKR6GYDUJOC5XBZ4ILXE","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":"350da54569194c076cd223c51272ce13d529f4125e283debf7e1dbef40438068","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T09:31:48Z","title_canon_sha256":"e369c6a796f01143a307d14292b2596507eb2aa69918e0995fa9f236ee375aff"},"schema_version":"1.0","source":{"id":"2608.09351","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09351","created_at":"2026-08-11T02:22:24Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09351v1","created_at":"2026-08-11T02:22:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09351","created_at":"2026-08-11T02:22:24Z"},{"alias_kind":"pith_short_12","alias_value":"46LFMSDKR6GY","created_at":"2026-08-11T02:22:24Z"},{"alias_kind":"pith_short_16","alias_value":"46LFMSDKR6GYDUJO","created_at":"2026-08-11T02:22:24Z"},{"alias_kind":"pith_short_8","alias_value":"46LFMSDK","created_at":"2026-08-11T02:22:24Z"}],"graph_snapshots":[{"event_id":"sha256:bb56c1f1a3913afe8d9633665dc7dec8c6982133ab9aa76a321d31451b68120b","target":"graph","created_at":"2026-08-11T02:22:24Z","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/2608.09351/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Test-time scaling improves LLM accuracy but multiplies inference cost, making the accuracy gained per unit of compute the metric that matters in deployment. Self-consistency is one of the established approaches, which spends this budget entirely on the output side by sampling repeated reasoning paths. We study Test-Time Augmentation (TTA), which extends self-consistency by also perturbing the input, aggregating predictions across transformed versions of the input, and ask whether input-side diversity converts compute into accuracy more efficiently than output-side diversity. We perform a syste","authors_text":"Jack Butler, Nikita Kozodoi, Zainab Afolabi","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T09:31:48Z","title":"Test-Time Augmentation for LLMs: When Input Diversity Beats Output Diversity at Matched Compute"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09351","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:d492210f7202e010e36125578607e8ade80c068f0e84a3ef583e33435d9c96aa","target":"record","created_at":"2026-08-11T02:22:24Z","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":"350da54569194c076cd223c51272ce13d529f4125e283debf7e1dbef40438068","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T09:31:48Z","title_canon_sha256":"e369c6a796f01143a307d14292b2596507eb2aa69918e0995fa9f236ee375aff"},"schema_version":"1.0","source":{"id":"2608.09351","kind":"arxiv","version":1}},"canonical_sha256":"e79656486a8f8d81d12e176e1cf10bb93f1c8944b0974f6dc02c7ae91de6d39f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e79656486a8f8d81d12e176e1cf10bb93f1c8944b0974f6dc02c7ae91de6d39f","first_computed_at":"2026-08-11T02:22:24.518430Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:22:24.518430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/fMeopo6xWR53wdtMeHSh6T7RyK5hWrohJ73eH+/gsnM5zPggfyO4qJ+8Qw3gTW0tgbHo3zu7UH2ymfec11jBA==","signature_status":"signed_v1","signed_at":"2026-08-11T02:22:24.519924Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09351","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d492210f7202e010e36125578607e8ade80c068f0e84a3ef583e33435d9c96aa","sha256:bb56c1f1a3913afe8d9633665dc7dec8c6982133ab9aa76a321d31451b68120b"],"state_sha256":"ebe6fc54bb8744bd233e30d1eca353fd1a56a44e3aaabbc840a45946aeae1f63"}