{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YGGXKUIEVTLSUF2R36O447M2MR","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":"b8820db3a9c5e4437505978bbb623330209e7f97e144dc221d184bd43043de22","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-12T15:11:35Z","title_canon_sha256":"08a13543f79fda7c7d25dd7ba19fe430de47acaadff6f19c7a623f92242f8cf6"},"schema_version":"1.0","source":{"id":"2608.12150","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12150","created_at":"2026-08-13T01:30:14Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12150v1","created_at":"2026-08-13T01:30:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12150","created_at":"2026-08-13T01:30:14Z"},{"alias_kind":"pith_short_12","alias_value":"YGGXKUIEVTLS","created_at":"2026-08-13T01:30:14Z"},{"alias_kind":"pith_short_16","alias_value":"YGGXKUIEVTLSUF2R","created_at":"2026-08-13T01:30:14Z"},{"alias_kind":"pith_short_8","alias_value":"YGGXKUIE","created_at":"2026-08-13T01:30:14Z"}],"graph_snapshots":[{"event_id":"sha256:10d5fbdcaac36c189913925e1c11df94b51d70cb994ea2f8ba918e0cca48630a","target":"graph","created_at":"2026-08-13T01:30:14Z","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/2608.12150/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard evaluation of large language models assumes stable model rankings across inference conditions. We challenge this assumption by varying the token generation budget, i.e., the maximum tokens a model may produce, across seven levels (64--4,096), evaluating four models on three reasoning benchmarks (56,476 inferences). We report four findings: (i) 3--19% of items exhibit non-monotone behavior (accuracy decreasing with more budget), even after controlling for truncation, and this phenomenon is model-specific (cross-model overlap: 6--14%). (ii) Model rankings reverse across budgets on all b","authors_text":"Alison R. Panisson, Rodrigo Guedes de Souza","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-12T15:11:35Z","title":"Who Thinks Best Depends on How Long You Let Them: Budget-Dependent Rankings in LLM Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12150","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":"sha256:2e6c78625d743e687547ac7a370d74385a0c58bd37ffd14cb0232b72c994d791","target":"record","created_at":"2026-08-13T01:30:14Z","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":"b8820db3a9c5e4437505978bbb623330209e7f97e144dc221d184bd43043de22","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-12T15:11:35Z","title_canon_sha256":"08a13543f79fda7c7d25dd7ba19fe430de47acaadff6f19c7a623f92242f8cf6"},"schema_version":"1.0","source":{"id":"2608.12150","kind":"arxiv","version":1}},"canonical_sha256":"c18d755104acd72a1751df9dce7d9a644468ebdeb1dde7e5d907cc0a0df4b46d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c18d755104acd72a1751df9dce7d9a644468ebdeb1dde7e5d907cc0a0df4b46d","first_computed_at":"2026-08-13T01:30:14.345013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T01:30:14.345013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S9oibrbuRYxauTfn/n1wO6giMitwY4xynLHt/joKRwMrYjq7/Dyh4fXeJkXPrYS3DyBPXLNKRj65h9u3tSo7DA==","signature_status":"signed_v1","signed_at":"2026-08-13T01:30:14.347711Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.12150","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e6c78625d743e687547ac7a370d74385a0c58bd37ffd14cb0232b72c994d791","sha256:10d5fbdcaac36c189913925e1c11df94b51d70cb994ea2f8ba918e0cca48630a"],"state_sha256":"c1bdba3833a85a84a8051133c429022c05dd73bcc62d38db79a4b209b61ce456"}