{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C27FO3AEXAT5PLYAZ7UE7RLY5D","short_pith_number":"pith:C27FO3AE","schema_version":"1.0","canonical_sha256":"16be576c04b827d7af00cfe84fc578e8ea4513030aa165b76c1d9f177cf33efe","source":{"kind":"arxiv","id":"2608.08528","version":1},"attestation_state":"computed","paper":{"title":"Task-to-Model Optimization for Enterprise LLM Coding Assistants: A Data-Driven Framework for Cost-Optimal Routing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ashwin Hegde, Fangbo Tu, Haifeng Wu, Jian Wan, Junhua Zhao, Kalyan Chakravarthi Podamekala, Maliah Rajan M, Mithun Sasidharan, Srinivasan Manoharan","submitted_at":"2026-08-09T06:57:53Z","abstract_excerpt":"Enterprise AI coding assistants incur substantial inference spend, and naive token-cost minimization often fails to reduce end-to-end cost once retries, escalations, and developer wait time are included. We present Task-to-Model Optimization (T2MO), a data-driven methodology for optimizing model selection in production coding workflows. We treat each developer session as a task that can be discovered, classified, graded for difficulty, benchmarked in a production-like harness, and routed to the cheapest model able to complete it within quality and latency constraints. The framework is a nine-s"},"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":"2608.08528","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-09T06:57:53Z","cross_cats_sorted":[],"title_canon_sha256":"0fcac5db2296107f67c364d3a694e33f30ae2a70fd602acb983bb71186a853bc","abstract_canon_sha256":"c032cfa5d69b278aad27746c63e8bcc1676d8f635f7b54de4d6964b46dc16301"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:22:52.992947Z","signature_b64":"LO90mWBu2jguVP2ZhPm3HkLh2al5GaLYNB7wT8ia+ExT/PLSwkhW6Q0mzmd+frnCTrN+RHV43KtTy7fWhexACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16be576c04b827d7af00cfe84fc578e8ea4513030aa165b76c1d9f177cf33efe","last_reissued_at":"2026-08-11T01:22:52.990607Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:22:52.990607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task-to-Model Optimization for Enterprise LLM Coding Assistants: A Data-Driven Framework for Cost-Optimal Routing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ashwin Hegde, Fangbo Tu, Haifeng Wu, Jian Wan, Junhua Zhao, Kalyan Chakravarthi Podamekala, Maliah Rajan M, Mithun Sasidharan, Srinivasan Manoharan","submitted_at":"2026-08-09T06:57:53Z","abstract_excerpt":"Enterprise AI coding assistants incur substantial inference spend, and naive token-cost minimization often fails to reduce end-to-end cost once retries, escalations, and developer wait time are included. We present Task-to-Model Optimization (T2MO), a data-driven methodology for optimizing model selection in production coding workflows. We treat each developer session as a task that can be discovered, classified, graded for difficulty, benchmarked in a production-like harness, and routed to the cheapest model able to complete it within quality and latency constraints. The framework is a nine-s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08528","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/2608.08528/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":"2608.08528","created_at":"2026-08-11T01:22:52.991316+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08528v1","created_at":"2026-08-11T01:22:52.991316+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08528","created_at":"2026-08-11T01:22:52.991316+00:00"},{"alias_kind":"pith_short_12","alias_value":"C27FO3AEXAT5","created_at":"2026-08-11T01:22:52.991316+00:00"},{"alias_kind":"pith_short_16","alias_value":"C27FO3AEXAT5PLYA","created_at":"2026-08-11T01:22:52.991316+00:00"},{"alias_kind":"pith_short_8","alias_value":"C27FO3AE","created_at":"2026-08-11T01:22:52.991316+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/C27FO3AEXAT5PLYAZ7UE7RLY5D","json":"https://pith.science/pith/C27FO3AEXAT5PLYAZ7UE7RLY5D.json","graph_json":"https://pith.science/api/pith-number/C27FO3AEXAT5PLYAZ7UE7RLY5D/graph.json","events_json":"https://pith.science/api/pith-number/C27FO3AEXAT5PLYAZ7UE7RLY5D/events.json","paper":"https://pith.science/paper/C27FO3AE"},"agent_actions":{"view_html":"https://pith.science/pith/C27FO3AEXAT5PLYAZ7UE7RLY5D","download_json":"https://pith.science/pith/C27FO3AEXAT5PLYAZ7UE7RLY5D.json","view_paper":"https://pith.science/paper/C27FO3AE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08528&json=true","fetch_graph":"https://pith.science/api/pith-number/C27FO3AEXAT5PLYAZ7UE7RLY5D/graph.json","fetch_events":"https://pith.science/api/pith-number/C27FO3AEXAT5PLYAZ7UE7RLY5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C27FO3AEXAT5PLYAZ7UE7RLY5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C27FO3AEXAT5PLYAZ7UE7RLY5D/action/storage_attestation","attest_author":"https://pith.science/pith/C27FO3AEXAT5PLYAZ7UE7RLY5D/action/author_attestation","sign_citation":"https://pith.science/pith/C27FO3AEXAT5PLYAZ7UE7RLY5D/action/citation_signature","submit_replication":"https://pith.science/pith/C27FO3AEXAT5PLYAZ7UE7RLY5D/action/replication_record"}},"created_at":"2026-08-11T01:22:52.991316+00:00","updated_at":"2026-08-11T01:22:52.991316+00:00"}