{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7CLRH4BW2KCZA3VP6OP2RFDZGC","short_pith_number":"pith:7CLRH4BW","schema_version":"1.0","canonical_sha256":"f89713f036d285906eaff39fa8947930b6ccf6dabbf7d773f7668420b877e030","source":{"kind":"arxiv","id":"2101.05950","version":1},"attestation_state":"computed","paper":{"title":"Robusta: Robust AutoML for Feature Selection via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bhavya Kailkhura, Bo Li, Klara Nahrstedt, Xiaoyang Wang, Yibo Zhang","submitted_at":"2021-01-15T03:12:29Z","abstract_excerpt":"Several AutoML approaches have been proposed to automate the machine learning (ML) process, such as searching for the ML model architectures and hyper-parameters. However, these AutoML pipelines only focus on improving the learning accuracy of benign samples while ignoring the ML model robustness under adversarial attacks. As ML systems are increasingly being used in a variety of mission-critical applications, improving the robustness of ML systems has become of utmost importance. In this paper, we propose the first robust AutoML framework, Robusta--based on reinforcement learning (RL)--to per"},"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":"2101.05950","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-15T03:12:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"30133ae42e83780351fafb86de1a2f41f9688d65a664e85ba20a453b7ff5533b","abstract_canon_sha256":"008ef34e860ca0f47492068fb941774dacd2657184deb96d343617a9dbca2296"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:07:08.163268Z","signature_b64":"znv4gajC38sWcfscoJ7r9ZKHtMtHl0K3pTNrK5Uvnhl6uf4AWxqZzJfhi2itemDkYaqhPDR+OgxSv+2HWYBnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f89713f036d285906eaff39fa8947930b6ccf6dabbf7d773f7668420b877e030","last_reissued_at":"2026-07-05T02:07:08.162812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:07:08.162812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robusta: Robust AutoML for Feature Selection via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bhavya Kailkhura, Bo Li, Klara Nahrstedt, Xiaoyang Wang, Yibo Zhang","submitted_at":"2021-01-15T03:12:29Z","abstract_excerpt":"Several AutoML approaches have been proposed to automate the machine learning (ML) process, such as searching for the ML model architectures and hyper-parameters. However, these AutoML pipelines only focus on improving the learning accuracy of benign samples while ignoring the ML model robustness under adversarial attacks. As ML systems are increasingly being used in a variety of mission-critical applications, improving the robustness of ML systems has become of utmost importance. In this paper, we propose the first robust AutoML framework, Robusta--based on reinforcement learning (RL)--to per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.05950","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/2101.05950/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":"2101.05950","created_at":"2026-07-05T02:07:08.162868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.05950v1","created_at":"2026-07-05T02:07:08.162868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.05950","created_at":"2026-07-05T02:07:08.162868+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CLRH4BW2KCZ","created_at":"2026-07-05T02:07:08.162868+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CLRH4BW2KCZA3VP","created_at":"2026-07-05T02:07:08.162868+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CLRH4BW","created_at":"2026-07-05T02:07:08.162868+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/7CLRH4BW2KCZA3VP6OP2RFDZGC","json":"https://pith.science/pith/7CLRH4BW2KCZA3VP6OP2RFDZGC.json","graph_json":"https://pith.science/api/pith-number/7CLRH4BW2KCZA3VP6OP2RFDZGC/graph.json","events_json":"https://pith.science/api/pith-number/7CLRH4BW2KCZA3VP6OP2RFDZGC/events.json","paper":"https://pith.science/paper/7CLRH4BW"},"agent_actions":{"view_html":"https://pith.science/pith/7CLRH4BW2KCZA3VP6OP2RFDZGC","download_json":"https://pith.science/pith/7CLRH4BW2KCZA3VP6OP2RFDZGC.json","view_paper":"https://pith.science/paper/7CLRH4BW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.05950&json=true","fetch_graph":"https://pith.science/api/pith-number/7CLRH4BW2KCZA3VP6OP2RFDZGC/graph.json","fetch_events":"https://pith.science/api/pith-number/7CLRH4BW2KCZA3VP6OP2RFDZGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CLRH4BW2KCZA3VP6OP2RFDZGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CLRH4BW2KCZA3VP6OP2RFDZGC/action/storage_attestation","attest_author":"https://pith.science/pith/7CLRH4BW2KCZA3VP6OP2RFDZGC/action/author_attestation","sign_citation":"https://pith.science/pith/7CLRH4BW2KCZA3VP6OP2RFDZGC/action/citation_signature","submit_replication":"https://pith.science/pith/7CLRH4BW2KCZA3VP6OP2RFDZGC/action/replication_record"}},"created_at":"2026-07-05T02:07:08.162868+00:00","updated_at":"2026-07-05T02:07:08.162868+00:00"}