{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PVQFLF7HT33P5AJKR3LBFHQUDB","short_pith_number":"pith:PVQFLF7H","schema_version":"1.0","canonical_sha256":"7d605597e79ef6fe812a8ed6129e14187712eb74570379841fcf8cba54c44058","source":{"kind":"arxiv","id":"2507.03834","version":1},"attestation_state":"computed","paper":{"title":"Economic Evaluation of LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Matt Thomson, Michael J. Zellinger","submitted_at":"2025-07-04T23:16:02Z","abstract_excerpt":"Practitioners often navigate LLM performance trade-offs by plotting Pareto frontiers of optimal accuracy-cost trade-offs. However, this approach offers no way to compare between LLMs with distinct strengths and weaknesses: for example, a cheap, error-prone model vs a pricey but accurate one. To address this gap, we propose economic evaluation of LLMs. Our framework quantifies the performance trade-off of an LLM as a single number based on the economic constraints of a concrete use case, all expressed in dollars: the cost of making a mistake, the cost of incremental latency, and the cost of abs"},"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":"2507.03834","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-04T23:16:02Z","cross_cats_sorted":[],"title_canon_sha256":"9da67b77d08cff91861fdf1720e1aed007c1aa1bb7509069901c07dada10ac47","abstract_canon_sha256":"37b82c9438988a5f6132adb1c7137092018bf697b2e4c6050bf9aa7effa950ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:35.171277Z","signature_b64":"qNJ/HIEsEapIVehbXx9aeIDZMm5YYeEEZtzIUnPYrEej+/Gomj38EBr4aqckfafDOYoLIxz2z8FOWO5iuODCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d605597e79ef6fe812a8ed6129e14187712eb74570379841fcf8cba54c44058","last_reissued_at":"2026-07-05T11:32:35.170830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:35.170830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Economic Evaluation of LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Matt Thomson, Michael J. Zellinger","submitted_at":"2025-07-04T23:16:02Z","abstract_excerpt":"Practitioners often navigate LLM performance trade-offs by plotting Pareto frontiers of optimal accuracy-cost trade-offs. However, this approach offers no way to compare between LLMs with distinct strengths and weaknesses: for example, a cheap, error-prone model vs a pricey but accurate one. To address this gap, we propose economic evaluation of LLMs. Our framework quantifies the performance trade-off of an LLM as a single number based on the economic constraints of a concrete use case, all expressed in dollars: the cost of making a mistake, the cost of incremental latency, and the cost of abs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03834","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/2507.03834/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":"2507.03834","created_at":"2026-07-05T11:32:35.170897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.03834v1","created_at":"2026-07-05T11:32:35.170897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03834","created_at":"2026-07-05T11:32:35.170897+00:00"},{"alias_kind":"pith_short_12","alias_value":"PVQFLF7HT33P","created_at":"2026-07-05T11:32:35.170897+00:00"},{"alias_kind":"pith_short_16","alias_value":"PVQFLF7HT33P5AJK","created_at":"2026-07-05T11:32:35.170897+00:00"},{"alias_kind":"pith_short_8","alias_value":"PVQFLF7H","created_at":"2026-07-05T11:32:35.170897+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/PVQFLF7HT33P5AJKR3LBFHQUDB","json":"https://pith.science/pith/PVQFLF7HT33P5AJKR3LBFHQUDB.json","graph_json":"https://pith.science/api/pith-number/PVQFLF7HT33P5AJKR3LBFHQUDB/graph.json","events_json":"https://pith.science/api/pith-number/PVQFLF7HT33P5AJKR3LBFHQUDB/events.json","paper":"https://pith.science/paper/PVQFLF7H"},"agent_actions":{"view_html":"https://pith.science/pith/PVQFLF7HT33P5AJKR3LBFHQUDB","download_json":"https://pith.science/pith/PVQFLF7HT33P5AJKR3LBFHQUDB.json","view_paper":"https://pith.science/paper/PVQFLF7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.03834&json=true","fetch_graph":"https://pith.science/api/pith-number/PVQFLF7HT33P5AJKR3LBFHQUDB/graph.json","fetch_events":"https://pith.science/api/pith-number/PVQFLF7HT33P5AJKR3LBFHQUDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PVQFLF7HT33P5AJKR3LBFHQUDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PVQFLF7HT33P5AJKR3LBFHQUDB/action/storage_attestation","attest_author":"https://pith.science/pith/PVQFLF7HT33P5AJKR3LBFHQUDB/action/author_attestation","sign_citation":"https://pith.science/pith/PVQFLF7HT33P5AJKR3LBFHQUDB/action/citation_signature","submit_replication":"https://pith.science/pith/PVQFLF7HT33P5AJKR3LBFHQUDB/action/replication_record"}},"created_at":"2026-07-05T11:32:35.170897+00:00","updated_at":"2026-07-05T11:32:35.170897+00:00"}