{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7EP7XGF65GGPIDRTLBO3X6ACR4","short_pith_number":"pith:7EP7XGF6","schema_version":"1.0","canonical_sha256":"f91ffb98bee98cf40e33585dbbf8028f1580961df1cd6522c93cc4fda0599ddc","source":{"kind":"arxiv","id":"2308.08061","version":1},"attestation_state":"computed","paper":{"title":"The Costly Dilemma: Generalization, Evaluation and Cost-Optimal Deployment of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Aakash Kumar Nain, Abi Aryan, Andrew McMahon, Harpreet Singh Sahota, Lucas Augusto Meyer","submitted_at":"2023-08-15T22:26:58Z","abstract_excerpt":"When deploying machine learning models in production for any product/application, there are three properties that are commonly desired. First, the models should be generalizable, in that we can extend it to further use cases as our knowledge of the domain area develops. Second they should be evaluable, so that there are clear metrics for performance and the calculation of those metrics in production settings are feasible. Finally, the deployment should be cost-optimal as far as possible. In this paper we propose that these three objectives (i.e. generalization, evaluation and cost-optimality) "},"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":"2308.08061","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-15T22:26:58Z","cross_cats_sorted":["cs.LG","cs.SE"],"title_canon_sha256":"79e04ba2894ccfe9c8df8c3f153c5230e5e4c7a5199e9d775a6ff1f0dea54fb0","abstract_canon_sha256":"6ba96db5b0b27324ae83cc6e71945736e7433db739d3607777e5708283e426d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:53.795283Z","signature_b64":"L+bPurt3Q9UK8ziOZ1wg/NvFI4ScwgoqBbiztnpTZiLoyIWwgRlKByaEbc6+KSL+1beWNUoRjrAk2nviFtbHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f91ffb98bee98cf40e33585dbbf8028f1580961df1cd6522c93cc4fda0599ddc","last_reissued_at":"2026-07-05T06:41:53.794780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:53.794780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Costly Dilemma: Generalization, Evaluation and Cost-Optimal Deployment of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Aakash Kumar Nain, Abi Aryan, Andrew McMahon, Harpreet Singh Sahota, Lucas Augusto Meyer","submitted_at":"2023-08-15T22:26:58Z","abstract_excerpt":"When deploying machine learning models in production for any product/application, there are three properties that are commonly desired. First, the models should be generalizable, in that we can extend it to further use cases as our knowledge of the domain area develops. Second they should be evaluable, so that there are clear metrics for performance and the calculation of those metrics in production settings are feasible. Finally, the deployment should be cost-optimal as far as possible. In this paper we propose that these three objectives (i.e. generalization, evaluation and cost-optimality) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.08061","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/2308.08061/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":"2308.08061","created_at":"2026-07-05T06:41:53.794840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.08061v1","created_at":"2026-07-05T06:41:53.794840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.08061","created_at":"2026-07-05T06:41:53.794840+00:00"},{"alias_kind":"pith_short_12","alias_value":"7EP7XGF65GGP","created_at":"2026-07-05T06:41:53.794840+00:00"},{"alias_kind":"pith_short_16","alias_value":"7EP7XGF65GGPIDRT","created_at":"2026-07-05T06:41:53.794840+00:00"},{"alias_kind":"pith_short_8","alias_value":"7EP7XGF6","created_at":"2026-07-05T06:41:53.794840+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17548","citing_title":"Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review","ref_index":243,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17548","citing_title":"Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review","ref_index":243,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7EP7XGF65GGPIDRTLBO3X6ACR4","json":"https://pith.science/pith/7EP7XGF65GGPIDRTLBO3X6ACR4.json","graph_json":"https://pith.science/api/pith-number/7EP7XGF65GGPIDRTLBO3X6ACR4/graph.json","events_json":"https://pith.science/api/pith-number/7EP7XGF65GGPIDRTLBO3X6ACR4/events.json","paper":"https://pith.science/paper/7EP7XGF6"},"agent_actions":{"view_html":"https://pith.science/pith/7EP7XGF65GGPIDRTLBO3X6ACR4","download_json":"https://pith.science/pith/7EP7XGF65GGPIDRTLBO3X6ACR4.json","view_paper":"https://pith.science/paper/7EP7XGF6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.08061&json=true","fetch_graph":"https://pith.science/api/pith-number/7EP7XGF65GGPIDRTLBO3X6ACR4/graph.json","fetch_events":"https://pith.science/api/pith-number/7EP7XGF65GGPIDRTLBO3X6ACR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7EP7XGF65GGPIDRTLBO3X6ACR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7EP7XGF65GGPIDRTLBO3X6ACR4/action/storage_attestation","attest_author":"https://pith.science/pith/7EP7XGF65GGPIDRTLBO3X6ACR4/action/author_attestation","sign_citation":"https://pith.science/pith/7EP7XGF65GGPIDRTLBO3X6ACR4/action/citation_signature","submit_replication":"https://pith.science/pith/7EP7XGF65GGPIDRTLBO3X6ACR4/action/replication_record"}},"created_at":"2026-07-05T06:41:53.794840+00:00","updated_at":"2026-07-05T06:41:53.794840+00:00"}