{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QUVVQCUIBCPON7F4N2CIIKNTHI","short_pith_number":"pith:QUVVQCUI","schema_version":"1.0","canonical_sha256":"852b580a88089ee6fcbc6e848429b33a26af9959ce740d3d540ed32670edaa7c","source":{"kind":"arxiv","id":"2007.05145","version":3},"attestation_state":"computed","paper":{"title":"Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Tauman Kalai, Omar Montasser, Shafi Goldwasser, Yael Tauman Kalai","submitted_at":"2020-07-10T03:00:12Z","abstract_excerpt":"We present a transductive learning algorithm that takes as input training examples from a distribution $P$ and arbitrary (unlabeled) test examples, possibly chosen by an adversary. This is unlike prior work that assumes that test examples are small perturbations of $P$. Our algorithm outputs a selective classifier, which abstains from predicting on some examples. By considering selective transductive learning, we give the first nontrivial guarantees for learning classes of bounded VC dimension with arbitrary train and test distributions---no prior guarantees were known even for simple classes "},"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":"2007.05145","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-10T03:00:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e15a13fdc826d4753575aea72b1ac57ff25f45a87fee1443d85f67de0d74e590","abstract_canon_sha256":"df23286fb88657a93b392658ead1497702d7a46b9ce863befb9925ef0cc0b27e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:14.671840Z","signature_b64":"ZjP+4Nk8Bn6k+bL+DBvQrpnlj31yQn/grXfM/LbKUo5yOroIJiCEgAV5gVXosxsaOknnhUVLI6oIV8OhzsokAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"852b580a88089ee6fcbc6e848429b33a26af9959ce740d3d540ed32670edaa7c","last_reissued_at":"2026-07-05T01:39:14.671382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:14.671382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Tauman Kalai, Omar Montasser, Shafi Goldwasser, Yael Tauman Kalai","submitted_at":"2020-07-10T03:00:12Z","abstract_excerpt":"We present a transductive learning algorithm that takes as input training examples from a distribution $P$ and arbitrary (unlabeled) test examples, possibly chosen by an adversary. This is unlike prior work that assumes that test examples are small perturbations of $P$. Our algorithm outputs a selective classifier, which abstains from predicting on some examples. By considering selective transductive learning, we give the first nontrivial guarantees for learning classes of bounded VC dimension with arbitrary train and test distributions---no prior guarantees were known even for simple classes "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.05145","kind":"arxiv","version":3},"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/2007.05145/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":"2007.05145","created_at":"2026-07-05T01:39:14.671441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.05145v3","created_at":"2026-07-05T01:39:14.671441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.05145","created_at":"2026-07-05T01:39:14.671441+00:00"},{"alias_kind":"pith_short_12","alias_value":"QUVVQCUIBCPO","created_at":"2026-07-05T01:39:14.671441+00:00"},{"alias_kind":"pith_short_16","alias_value":"QUVVQCUIBCPON7F4","created_at":"2026-07-05T01:39:14.671441+00:00"},{"alias_kind":"pith_short_8","alias_value":"QUVVQCUI","created_at":"2026-07-05T01:39:14.671441+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/QUVVQCUIBCPON7F4N2CIIKNTHI","json":"https://pith.science/pith/QUVVQCUIBCPON7F4N2CIIKNTHI.json","graph_json":"https://pith.science/api/pith-number/QUVVQCUIBCPON7F4N2CIIKNTHI/graph.json","events_json":"https://pith.science/api/pith-number/QUVVQCUIBCPON7F4N2CIIKNTHI/events.json","paper":"https://pith.science/paper/QUVVQCUI"},"agent_actions":{"view_html":"https://pith.science/pith/QUVVQCUIBCPON7F4N2CIIKNTHI","download_json":"https://pith.science/pith/QUVVQCUIBCPON7F4N2CIIKNTHI.json","view_paper":"https://pith.science/paper/QUVVQCUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.05145&json=true","fetch_graph":"https://pith.science/api/pith-number/QUVVQCUIBCPON7F4N2CIIKNTHI/graph.json","fetch_events":"https://pith.science/api/pith-number/QUVVQCUIBCPON7F4N2CIIKNTHI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QUVVQCUIBCPON7F4N2CIIKNTHI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QUVVQCUIBCPON7F4N2CIIKNTHI/action/storage_attestation","attest_author":"https://pith.science/pith/QUVVQCUIBCPON7F4N2CIIKNTHI/action/author_attestation","sign_citation":"https://pith.science/pith/QUVVQCUIBCPON7F4N2CIIKNTHI/action/citation_signature","submit_replication":"https://pith.science/pith/QUVVQCUIBCPON7F4N2CIIKNTHI/action/replication_record"}},"created_at":"2026-07-05T01:39:14.671441+00:00","updated_at":"2026-07-05T01:39:14.671441+00:00"}