{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6AYVX2RCKMJCQFUDRIHOWDGC2H","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":"ce250a371ff37b2aa0d13ce9c37916a64ef92bb31c346971b97ef4ec4103a41c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-08T07:04:28Z","title_canon_sha256":"b85cff3b6787e9e985093ea1214159b115cc954e2466fc4784e1aa1910129930"},"schema_version":"1.0","source":{"id":"2608.07968","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07968","created_at":"2026-08-11T01:21:15Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07968v1","created_at":"2026-08-11T01:21:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07968","created_at":"2026-08-11T01:21:15Z"},{"alias_kind":"pith_short_12","alias_value":"6AYVX2RCKMJC","created_at":"2026-08-11T01:21:15Z"},{"alias_kind":"pith_short_16","alias_value":"6AYVX2RCKMJCQFUD","created_at":"2026-08-11T01:21:15Z"},{"alias_kind":"pith_short_8","alias_value":"6AYVX2RC","created_at":"2026-08-11T01:21:15Z"}],"graph_snapshots":[{"event_id":"sha256:21927d6d6e1a465fa521006fa41aad440889a186eea4a1a89e656c9f539b8c9b","target":"graph","created_at":"2026-08-11T01:21:15Z","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/2608.07968/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning language models increasingly use test-time compute to improve performance, but existing evaluations typically study this compute one question at a time. Yet when multiple problems share an end-to-end cost or latency constraint, models must decide how to divide limited inference compute among them. We introduce an exam-style evaluation framework for studying this setting, in which a model must distribute one shared token budget across questions with different difficulty and point values to maximize its total score. Across several open and frontier reasoning models, we find that models","authors_text":"Chenrui Fan, Ming Li, Soheil Feizi, Tianyi Zhou, Yize Cheng, Yongyuan Liang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-08T07:04:28Z","title":"Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07968","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":"sha256:7ddad3869f23b608d5d59ce5122bc06138a31af4676c5d72ec4295a43fd5ec9c","target":"record","created_at":"2026-08-11T01:21:15Z","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":"ce250a371ff37b2aa0d13ce9c37916a64ef92bb31c346971b97ef4ec4103a41c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-08T07:04:28Z","title_canon_sha256":"b85cff3b6787e9e985093ea1214159b115cc954e2466fc4784e1aa1910129930"},"schema_version":"1.0","source":{"id":"2608.07968","kind":"arxiv","version":1}},"canonical_sha256":"f0315bea2253122816838a0eeb0cc2d1f6dc58ece27cca7dbfd259aaca576269","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0315bea2253122816838a0eeb0cc2d1f6dc58ece27cca7dbfd259aaca576269","first_computed_at":"2026-08-11T01:21:15.759118Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:21:15.759118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ex7VjG/u9gwCsaFaR9ruwdFGg7suu6YngxsKg3elVXW+ScWvxLfzKYUseqcXFzqXIsdaECD2F7Ul2LbLBQv+Dg==","signature_status":"signed_v1","signed_at":"2026-08-11T01:21:15.762239Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.07968","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ddad3869f23b608d5d59ce5122bc06138a31af4676c5d72ec4295a43fd5ec9c","sha256:21927d6d6e1a465fa521006fa41aad440889a186eea4a1a89e656c9f539b8c9b"],"state_sha256":"1272f0bc893b9723295ccef9eb15c28bfac14323b95db47c2760883396396bfe"}