{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:XMVOTQ2I27QNKJA76YUJOMRLGQ","short_pith_number":"pith:XMVOTQ2I","schema_version":"1.0","canonical_sha256":"bb2ae9c348d7e0d5241ff62897322b340bad5f1feabd091020a9cdca31eb6650","source":{"kind":"arxiv","id":"1602.07726","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Learning with Robust Generalization Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Aaron Roth, Katrina Ligett, Kobbi Nissim, Rachel Cummings, Zhiwei Steven Wu","submitted_at":"2016-02-24T21:59:30Z","abstract_excerpt":"The traditional notion of generalization---i.e., learning a hypothesis whose empirical error is close to its true error---is surprisingly brittle. As has recently been noted in [DFH+15b], even if several algorithms have this guarantee in isolation, the guarantee need not hold if the algorithms are composed adaptively. In this paper, we study three notions of generalization---increasing in strength---that are robust to postprocessing and amenable to adaptive composition, and examine the relationships between them. We call the weakest such notion Robust Generalization. A second, intermediate, no"},"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":"1602.07726","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2016-02-24T21:59:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2ab57b47419f5ccef4b3efa9cfbe9a828395c2088564bd96dcfd7a7b2bcfe736","abstract_canon_sha256":"d8b0a6d1ad7d4c2497c4747a99864085081f2e70506862396afe89b28bb22140"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:04.648006Z","signature_b64":"G4JfZPuXd7btmpZLMtbafFs5sIR/wgH7f2wKUwU2pmABQNNVO4QiPDOFjQy86gGBBSTK1as4SE1d1cMvi0QFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb2ae9c348d7e0d5241ff62897322b340bad5f1feabd091020a9cdca31eb6650","last_reissued_at":"2026-05-18T01:13:04.647649Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:04.647649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Learning with Robust Generalization Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Aaron Roth, Katrina Ligett, Kobbi Nissim, Rachel Cummings, Zhiwei Steven Wu","submitted_at":"2016-02-24T21:59:30Z","abstract_excerpt":"The traditional notion of generalization---i.e., learning a hypothesis whose empirical error is close to its true error---is surprisingly brittle. As has recently been noted in [DFH+15b], even if several algorithms have this guarantee in isolation, the guarantee need not hold if the algorithms are composed adaptively. In this paper, we study three notions of generalization---increasing in strength---that are robust to postprocessing and amenable to adaptive composition, and examine the relationships between them. We call the weakest such notion Robust Generalization. A second, intermediate, no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.07726","kind":"arxiv","version":2},"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":"1602.07726","created_at":"2026-05-18T01:13:04.647706+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.07726v2","created_at":"2026-05-18T01:13:04.647706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.07726","created_at":"2026-05-18T01:13:04.647706+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMVOTQ2I27QN","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMVOTQ2I27QNKJA7","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMVOTQ2I","created_at":"2026-05-18T12:30:51.357362+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/XMVOTQ2I27QNKJA76YUJOMRLGQ","json":"https://pith.science/pith/XMVOTQ2I27QNKJA76YUJOMRLGQ.json","graph_json":"https://pith.science/api/pith-number/XMVOTQ2I27QNKJA76YUJOMRLGQ/graph.json","events_json":"https://pith.science/api/pith-number/XMVOTQ2I27QNKJA76YUJOMRLGQ/events.json","paper":"https://pith.science/paper/XMVOTQ2I"},"agent_actions":{"view_html":"https://pith.science/pith/XMVOTQ2I27QNKJA76YUJOMRLGQ","download_json":"https://pith.science/pith/XMVOTQ2I27QNKJA76YUJOMRLGQ.json","view_paper":"https://pith.science/paper/XMVOTQ2I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.07726&json=true","fetch_graph":"https://pith.science/api/pith-number/XMVOTQ2I27QNKJA76YUJOMRLGQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XMVOTQ2I27QNKJA76YUJOMRLGQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMVOTQ2I27QNKJA76YUJOMRLGQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMVOTQ2I27QNKJA76YUJOMRLGQ/action/storage_attestation","attest_author":"https://pith.science/pith/XMVOTQ2I27QNKJA76YUJOMRLGQ/action/author_attestation","sign_citation":"https://pith.science/pith/XMVOTQ2I27QNKJA76YUJOMRLGQ/action/citation_signature","submit_replication":"https://pith.science/pith/XMVOTQ2I27QNKJA76YUJOMRLGQ/action/replication_record"}},"created_at":"2026-05-18T01:13:04.647706+00:00","updated_at":"2026-05-18T01:13:04.647706+00:00"}