{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IBP2AWOZN6FA7SXRWFBD527S5W","short_pith_number":"pith:IBP2AWOZ","schema_version":"1.0","canonical_sha256":"405fa059d96f8a0fcaf1b1423eebf2ed86fc9ac129efa8f3beedf19c828ac94b","source":{"kind":"arxiv","id":"2503.02119","version":1},"attestation_state":"computed","paper":{"title":"An Efficient Plugin Method for Metric Optimization of Black-Box Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anirudh Srinivasan, Branislav Kveton, Gaurush Hiranandani, Nurendra Choudhary, Sahika Genc, Siddartha Devic","submitted_at":"2025-03-03T23:01:36Z","abstract_excerpt":"Many machine learning algorithms and classifiers are available only via API queries as a ``black-box'' -- that is, the downstream user has no ability to change, re-train, or fine-tune the model on a particular target distribution. Indeed, the downstream user may not even have knowledge of the \\emph{original} training distribution or performance metric used to construct and optimize the black-box model. We propose a simple and efficient method, Plugin, which \\emph{post-processes} arbitrary multiclass predictions from any black-box classifier in order to simultaneously (1) adapt these prediction"},"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":"2503.02119","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-03T23:01:36Z","cross_cats_sorted":[],"title_canon_sha256":"b3c538d1301ce60621774807edfe430c3d37c89b7c5c994f901a12f72464933a","abstract_canon_sha256":"8f0bdecc297ec9a76e8f11c48750fe6b0bc91038420f237ce5c70edbcfecb278"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:36.943486Z","signature_b64":"OLd+L2bW4NZMGEVwC+b7PSYQkjrvcS3nRcH52PDraetCcYuWGU9xdXBQq7KjakJzcq7+ymsA5ah16rfKey3wCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"405fa059d96f8a0fcaf1b1423eebf2ed86fc9ac129efa8f3beedf19c828ac94b","last_reissued_at":"2026-07-05T10:23:36.942869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:36.942869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Efficient Plugin Method for Metric Optimization of Black-Box Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anirudh Srinivasan, Branislav Kveton, Gaurush Hiranandani, Nurendra Choudhary, Sahika Genc, Siddartha Devic","submitted_at":"2025-03-03T23:01:36Z","abstract_excerpt":"Many machine learning algorithms and classifiers are available only via API queries as a ``black-box'' -- that is, the downstream user has no ability to change, re-train, or fine-tune the model on a particular target distribution. Indeed, the downstream user may not even have knowledge of the \\emph{original} training distribution or performance metric used to construct and optimize the black-box model. We propose a simple and efficient method, Plugin, which \\emph{post-processes} arbitrary multiclass predictions from any black-box classifier in order to simultaneously (1) adapt these prediction"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02119","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/2503.02119/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":"2503.02119","created_at":"2026-07-05T10:23:36.942936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02119v1","created_at":"2026-07-05T10:23:36.942936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02119","created_at":"2026-07-05T10:23:36.942936+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBP2AWOZN6FA","created_at":"2026-07-05T10:23:36.942936+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBP2AWOZN6FA7SXR","created_at":"2026-07-05T10:23:36.942936+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBP2AWOZ","created_at":"2026-07-05T10:23:36.942936+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/IBP2AWOZN6FA7SXRWFBD527S5W","json":"https://pith.science/pith/IBP2AWOZN6FA7SXRWFBD527S5W.json","graph_json":"https://pith.science/api/pith-number/IBP2AWOZN6FA7SXRWFBD527S5W/graph.json","events_json":"https://pith.science/api/pith-number/IBP2AWOZN6FA7SXRWFBD527S5W/events.json","paper":"https://pith.science/paper/IBP2AWOZ"},"agent_actions":{"view_html":"https://pith.science/pith/IBP2AWOZN6FA7SXRWFBD527S5W","download_json":"https://pith.science/pith/IBP2AWOZN6FA7SXRWFBD527S5W.json","view_paper":"https://pith.science/paper/IBP2AWOZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02119&json=true","fetch_graph":"https://pith.science/api/pith-number/IBP2AWOZN6FA7SXRWFBD527S5W/graph.json","fetch_events":"https://pith.science/api/pith-number/IBP2AWOZN6FA7SXRWFBD527S5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBP2AWOZN6FA7SXRWFBD527S5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBP2AWOZN6FA7SXRWFBD527S5W/action/storage_attestation","attest_author":"https://pith.science/pith/IBP2AWOZN6FA7SXRWFBD527S5W/action/author_attestation","sign_citation":"https://pith.science/pith/IBP2AWOZN6FA7SXRWFBD527S5W/action/citation_signature","submit_replication":"https://pith.science/pith/IBP2AWOZN6FA7SXRWFBD527S5W/action/replication_record"}},"created_at":"2026-07-05T10:23:36.942936+00:00","updated_at":"2026-07-05T10:23:36.942936+00:00"}