{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UJQC6IOHWLAU7UIAHXTIKLCKW7","short_pith_number":"pith:UJQC6IOH","schema_version":"1.0","canonical_sha256":"a2602f21c7b2c14fd1003de6852c4ab7e7792eac9e58573ac9e889d39a67c37d","source":{"kind":"arxiv","id":"2407.11619","version":1},"attestation_state":"computed","paper":{"title":"Strategic Littlestone Dimension: Improved Bounds on Online Strategic Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Hanrui Zhang, Kunhe Yang, Saba Ahmadi","submitted_at":"2024-07-16T11:31:20Z","abstract_excerpt":"We study the problem of online binary classification in settings where strategic agents can modify their observable features to receive a positive classification. We model the set of feasible manipulations by a directed graph over the feature space, and assume the learner only observes the manipulated features instead of the original ones. We introduce the Strategic Littlestone Dimension, a new combinatorial measure that captures the joint complexity of the hypothesis class and the manipulation graph. We demonstrate that it characterizes the instance-optimal mistake bounds for deterministic le"},"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":"2407.11619","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-16T11:31:20Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"1a32bb99681d73ec13a13bf764ba71d035cce0f42ca406178632d28eda10c968","abstract_canon_sha256":"6d19fcb541892504d7a74db5ec1fb4c3b34198baa3a4d433a96c212e6e97cdf4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:27.021915Z","signature_b64":"8wnv9WE4ZIPjTHXK/v+R4F/D1qqoQFKknHqqc39h7n9+LooO//16hVhP1yVDCZ73vFM9RlwEG/QKb2BJMisKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2602f21c7b2c14fd1003de6852c4ab7e7792eac9e58573ac9e889d39a67c37d","last_reissued_at":"2026-07-05T08:44:27.021391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:27.021391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Strategic Littlestone Dimension: Improved Bounds on Online Strategic Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Hanrui Zhang, Kunhe Yang, Saba Ahmadi","submitted_at":"2024-07-16T11:31:20Z","abstract_excerpt":"We study the problem of online binary classification in settings where strategic agents can modify their observable features to receive a positive classification. We model the set of feasible manipulations by a directed graph over the feature space, and assume the learner only observes the manipulated features instead of the original ones. We introduce the Strategic Littlestone Dimension, a new combinatorial measure that captures the joint complexity of the hypothesis class and the manipulation graph. We demonstrate that it characterizes the instance-optimal mistake bounds for deterministic le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11619","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/2407.11619/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":"2407.11619","created_at":"2026-07-05T08:44:27.021464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11619v1","created_at":"2026-07-05T08:44:27.021464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11619","created_at":"2026-07-05T08:44:27.021464+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJQC6IOHWLAU","created_at":"2026-07-05T08:44:27.021464+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJQC6IOHWLAU7UIA","created_at":"2026-07-05T08:44:27.021464+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJQC6IOH","created_at":"2026-07-05T08:44:27.021464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05211","citing_title":"Incentive-Aware Machine Learning; Robustness, Fairness, Improvement & Causality","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UJQC6IOHWLAU7UIAHXTIKLCKW7","json":"https://pith.science/pith/UJQC6IOHWLAU7UIAHXTIKLCKW7.json","graph_json":"https://pith.science/api/pith-number/UJQC6IOHWLAU7UIAHXTIKLCKW7/graph.json","events_json":"https://pith.science/api/pith-number/UJQC6IOHWLAU7UIAHXTIKLCKW7/events.json","paper":"https://pith.science/paper/UJQC6IOH"},"agent_actions":{"view_html":"https://pith.science/pith/UJQC6IOHWLAU7UIAHXTIKLCKW7","download_json":"https://pith.science/pith/UJQC6IOHWLAU7UIAHXTIKLCKW7.json","view_paper":"https://pith.science/paper/UJQC6IOH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11619&json=true","fetch_graph":"https://pith.science/api/pith-number/UJQC6IOHWLAU7UIAHXTIKLCKW7/graph.json","fetch_events":"https://pith.science/api/pith-number/UJQC6IOHWLAU7UIAHXTIKLCKW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJQC6IOHWLAU7UIAHXTIKLCKW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJQC6IOHWLAU7UIAHXTIKLCKW7/action/storage_attestation","attest_author":"https://pith.science/pith/UJQC6IOHWLAU7UIAHXTIKLCKW7/action/author_attestation","sign_citation":"https://pith.science/pith/UJQC6IOHWLAU7UIAHXTIKLCKW7/action/citation_signature","submit_replication":"https://pith.science/pith/UJQC6IOHWLAU7UIAHXTIKLCKW7/action/replication_record"}},"created_at":"2026-07-05T08:44:27.021464+00:00","updated_at":"2026-07-05T08:44:27.021464+00:00"}