{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CBOYE6LPJLM3VLFZRKT6XRXOVJ","short_pith_number":"pith:CBOYE6LP","schema_version":"1.0","canonical_sha256":"105d82796f4ad9baacb98aa7ebc6eeaa40e0d57ccda179d3d4dc13150348c217","source":{"kind":"arxiv","id":"2105.13420","version":1},"attestation_state":"computed","paper":{"title":"Model Selection for Production System via Automated Online Experiments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ben Carterette, Ghazal Fazelnia, Mounia Lalmas-Roelleke, Praveen Chandar, Zhenwen Dai","submitted_at":"2021-05-27T19:48:23Z","abstract_excerpt":"A challenge that machine learning practitioners in the industry face is the task of selecting the best model to deploy in production. As a model is often an intermediate component of a production system, online controlled experiments such as A/B tests yield the most reliable estimation of the effectiveness of the whole system, but can only compare two or a few models due to budget constraints. We propose an automated online experimentation mechanism that can efficiently perform model selection from a large pool of models with a small number of online experiments. We derive the probability dist"},"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":"2105.13420","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-05-27T19:48:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"29d145989356d8d864c2a70c864d0dc9a59d92195692a85cb341504aa07a08cd","abstract_canon_sha256":"c9cf1ece0d9d2ec6495d26d452e661cab2c2a82fd2dda2b7851e4e0ad45a4d14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:07.799872Z","signature_b64":"viwB14IfFC47gaz3lFQPiUGSK6M9hpt+q0ba20lDxfyhj33icoPdBqffzP5cG8rqFoal18yhcVXVANWXxdOLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"105d82796f4ad9baacb98aa7ebc6eeaa40e0d57ccda179d3d4dc13150348c217","last_reissued_at":"2026-07-05T02:44:07.799389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:07.799389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model Selection for Production System via Automated Online Experiments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ben Carterette, Ghazal Fazelnia, Mounia Lalmas-Roelleke, Praveen Chandar, Zhenwen Dai","submitted_at":"2021-05-27T19:48:23Z","abstract_excerpt":"A challenge that machine learning practitioners in the industry face is the task of selecting the best model to deploy in production. As a model is often an intermediate component of a production system, online controlled experiments such as A/B tests yield the most reliable estimation of the effectiveness of the whole system, but can only compare two or a few models due to budget constraints. We propose an automated online experimentation mechanism that can efficiently perform model selection from a large pool of models with a small number of online experiments. We derive the probability dist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13420","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/2105.13420/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":"2105.13420","created_at":"2026-07-05T02:44:07.799445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.13420v1","created_at":"2026-07-05T02:44:07.799445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13420","created_at":"2026-07-05T02:44:07.799445+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBOYE6LPJLM3","created_at":"2026-07-05T02:44:07.799445+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBOYE6LPJLM3VLFZ","created_at":"2026-07-05T02:44:07.799445+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBOYE6LP","created_at":"2026-07-05T02:44:07.799445+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/CBOYE6LPJLM3VLFZRKT6XRXOVJ","json":"https://pith.science/pith/CBOYE6LPJLM3VLFZRKT6XRXOVJ.json","graph_json":"https://pith.science/api/pith-number/CBOYE6LPJLM3VLFZRKT6XRXOVJ/graph.json","events_json":"https://pith.science/api/pith-number/CBOYE6LPJLM3VLFZRKT6XRXOVJ/events.json","paper":"https://pith.science/paper/CBOYE6LP"},"agent_actions":{"view_html":"https://pith.science/pith/CBOYE6LPJLM3VLFZRKT6XRXOVJ","download_json":"https://pith.science/pith/CBOYE6LPJLM3VLFZRKT6XRXOVJ.json","view_paper":"https://pith.science/paper/CBOYE6LP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.13420&json=true","fetch_graph":"https://pith.science/api/pith-number/CBOYE6LPJLM3VLFZRKT6XRXOVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/CBOYE6LPJLM3VLFZRKT6XRXOVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBOYE6LPJLM3VLFZRKT6XRXOVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBOYE6LPJLM3VLFZRKT6XRXOVJ/action/storage_attestation","attest_author":"https://pith.science/pith/CBOYE6LPJLM3VLFZRKT6XRXOVJ/action/author_attestation","sign_citation":"https://pith.science/pith/CBOYE6LPJLM3VLFZRKT6XRXOVJ/action/citation_signature","submit_replication":"https://pith.science/pith/CBOYE6LPJLM3VLFZRKT6XRXOVJ/action/replication_record"}},"created_at":"2026-07-05T02:44:07.799445+00:00","updated_at":"2026-07-05T02:44:07.799445+00:00"}