{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RVM4OZWJMYWZAZTWTMIAIFCAEP","short_pith_number":"pith:RVM4OZWJ","schema_version":"1.0","canonical_sha256":"8d59c766c9662d9066769b1004144023c7ead728611f38ee17ab2acae2fbd6ed","source":{"kind":"arxiv","id":"1803.03155","version":4},"attestation_state":"computed","paper":{"title":"Learning Rules-First Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amir Globerson, Amit Daniely, Deborah Cohen, Gal Elidan","submitted_at":"2018-03-08T15:32:49Z","abstract_excerpt":"Complex classifiers may exhibit \"embarassing\" failures in cases where humans can easily provide a justified classification. Avoiding such failures is obviously of key importance. In this work, we focus on one such setting, where a label is perfectly predictable if the input contains certain features, or rules, and otherwise it is predictable by a linear classifier. We define a hypothesis class that captures this notion and determine its sample complexity. We also give evidence that efficient algorithms cannot achieve this sample complexity. We then derive a simple and efficient algorithm and 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":"1803.03155","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-08T15:32:49Z","cross_cats_sorted":[],"title_canon_sha256":"4c390e94ab0b88075997724c505b63a9cc780979075ea628e5d4cea904ee0f3b","abstract_canon_sha256":"8acd48bde5cdb777cbdec4bdf6b3f306b8771b0500d7f07e7e0782a1ed7fb87d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:28.505812Z","signature_b64":"TRfIC4/Yzj2oE1VJ3YAeAepWgc9YT+rNEAjezCh4/jiPmS45OZH8J6DG8m69VaQo71ZSiqewgN2A0FCiAL7uCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d59c766c9662d9066769b1004144023c7ead728611f38ee17ab2acae2fbd6ed","last_reissued_at":"2026-05-17T23:43:28.505249Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:28.505249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Rules-First Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amir Globerson, Amit Daniely, Deborah Cohen, Gal Elidan","submitted_at":"2018-03-08T15:32:49Z","abstract_excerpt":"Complex classifiers may exhibit \"embarassing\" failures in cases where humans can easily provide a justified classification. Avoiding such failures is obviously of key importance. In this work, we focus on one such setting, where a label is perfectly predictable if the input contains certain features, or rules, and otherwise it is predictable by a linear classifier. We define a hypothesis class that captures this notion and determine its sample complexity. We also give evidence that efficient algorithms cannot achieve this sample complexity. We then derive a simple and efficient algorithm and s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.03155","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1803.03155","created_at":"2026-05-17T23:43:28.505310+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.03155v4","created_at":"2026-05-17T23:43:28.505310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.03155","created_at":"2026-05-17T23:43:28.505310+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVM4OZWJMYWZ","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVM4OZWJMYWZAZTW","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVM4OZWJ","created_at":"2026-05-18T12:32:50.500415+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/RVM4OZWJMYWZAZTWTMIAIFCAEP","json":"https://pith.science/pith/RVM4OZWJMYWZAZTWTMIAIFCAEP.json","graph_json":"https://pith.science/api/pith-number/RVM4OZWJMYWZAZTWTMIAIFCAEP/graph.json","events_json":"https://pith.science/api/pith-number/RVM4OZWJMYWZAZTWTMIAIFCAEP/events.json","paper":"https://pith.science/paper/RVM4OZWJ"},"agent_actions":{"view_html":"https://pith.science/pith/RVM4OZWJMYWZAZTWTMIAIFCAEP","download_json":"https://pith.science/pith/RVM4OZWJMYWZAZTWTMIAIFCAEP.json","view_paper":"https://pith.science/paper/RVM4OZWJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.03155&json=true","fetch_graph":"https://pith.science/api/pith-number/RVM4OZWJMYWZAZTWTMIAIFCAEP/graph.json","fetch_events":"https://pith.science/api/pith-number/RVM4OZWJMYWZAZTWTMIAIFCAEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVM4OZWJMYWZAZTWTMIAIFCAEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVM4OZWJMYWZAZTWTMIAIFCAEP/action/storage_attestation","attest_author":"https://pith.science/pith/RVM4OZWJMYWZAZTWTMIAIFCAEP/action/author_attestation","sign_citation":"https://pith.science/pith/RVM4OZWJMYWZAZTWTMIAIFCAEP/action/citation_signature","submit_replication":"https://pith.science/pith/RVM4OZWJMYWZAZTWTMIAIFCAEP/action/replication_record"}},"created_at":"2026-05-17T23:43:28.505310+00:00","updated_at":"2026-05-17T23:43:28.505310+00:00"}