{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N2VSIKP7O35HPNUIR7ZYACV2RZ","short_pith_number":"pith:N2VSIKP7","schema_version":"1.0","canonical_sha256":"6eab2429ff76fa77b6888ff3800aba8e680193a2375e7fb888d72f3ad62fa668","source":{"kind":"arxiv","id":"2606.03092","version":1},"attestation_state":"computed","paper":{"title":"The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guang Chen, Jianwei Cai, Mingyang Sun, Speed Zhu, Wiggin Zhou, XiMing Huang, Xu Wan","submitted_at":"2026-06-02T03:26:55Z","abstract_excerpt":"Inference-time scaling has emerged as a critical avenue for enhancing Large Language Models' performance, yet real-world deployment is constrained by strict computational budgets. In this work, we formulate inference budget allocation as a global constrained optimization problem governed by economic principles. By modeling per-query reasoning utility with a shifted-surge function, we derive an optimal allocation policy based on a global shadow price that equilibrates marginal utility under resource scarcity. Based on this theory, we propose Constrained Latent-utility Equilibrium Allocation for"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.03092","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T03:26:55Z","cross_cats_sorted":[],"title_canon_sha256":"9311fd1d8faa7a8bbb029da38c23060a6f66546b2d43ce95be25d621c7f4966d","abstract_canon_sha256":"232c14c32f10fb4ff359cf2c2ae93b50e87fef11b55d3e999aedd8af1d3dfe76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:31.444610Z","signature_b64":"dI3I4x3/Q4WJ9W449/epUnttI+z9ouc/AUshrpv8chn9rq3j6RULPc088nCqbdXbHBUuv7wgVfBWkqS8LHUHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6eab2429ff76fa77b6888ff3800aba8e680193a2375e7fb888d72f3ad62fa668","last_reissued_at":"2026-06-03T01:05:31.444170Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:31.444170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guang Chen, Jianwei Cai, Mingyang Sun, Speed Zhu, Wiggin Zhou, XiMing Huang, Xu Wan","submitted_at":"2026-06-02T03:26:55Z","abstract_excerpt":"Inference-time scaling has emerged as a critical avenue for enhancing Large Language Models' performance, yet real-world deployment is constrained by strict computational budgets. In this work, we formulate inference budget allocation as a global constrained optimization problem governed by economic principles. By modeling per-query reasoning utility with a shifted-surge function, we derive an optimal allocation policy based on a global shadow price that equilibrates marginal utility under resource scarcity. Based on this theory, we propose Constrained Latent-utility Equilibrium Allocation for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03092","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/2606.03092/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.03092","created_at":"2026-06-03T01:05:31.444227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03092v1","created_at":"2026-06-03T01:05:31.444227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03092","created_at":"2026-06-03T01:05:31.444227+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2VSIKP7O35H","created_at":"2026-06-03T01:05:31.444227+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2VSIKP7O35HPNUI","created_at":"2026-06-03T01:05:31.444227+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2VSIKP7","created_at":"2026-06-03T01:05:31.444227+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2VSIKP7O35HPNUIR7ZYACV2RZ","json":"https://pith.science/pith/N2VSIKP7O35HPNUIR7ZYACV2RZ.json","graph_json":"https://pith.science/api/pith-number/N2VSIKP7O35HPNUIR7ZYACV2RZ/graph.json","events_json":"https://pith.science/api/pith-number/N2VSIKP7O35HPNUIR7ZYACV2RZ/events.json","paper":"https://pith.science/paper/N2VSIKP7"},"agent_actions":{"view_html":"https://pith.science/pith/N2VSIKP7O35HPNUIR7ZYACV2RZ","download_json":"https://pith.science/pith/N2VSIKP7O35HPNUIR7ZYACV2RZ.json","view_paper":"https://pith.science/paper/N2VSIKP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03092&json=true","fetch_graph":"https://pith.science/api/pith-number/N2VSIKP7O35HPNUIR7ZYACV2RZ/graph.json","fetch_events":"https://pith.science/api/pith-number/N2VSIKP7O35HPNUIR7ZYACV2RZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2VSIKP7O35HPNUIR7ZYACV2RZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2VSIKP7O35HPNUIR7ZYACV2RZ/action/storage_attestation","attest_author":"https://pith.science/pith/N2VSIKP7O35HPNUIR7ZYACV2RZ/action/author_attestation","sign_citation":"https://pith.science/pith/N2VSIKP7O35HPNUIR7ZYACV2RZ/action/citation_signature","submit_replication":"https://pith.science/pith/N2VSIKP7O35HPNUIR7ZYACV2RZ/action/replication_record"}},"created_at":"2026-06-03T01:05:31.444227+00:00","updated_at":"2026-06-03T01:05:31.444227+00:00"}