{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:2IDVOITIOUAAZUUQVXAMYF4EIQ","short_pith_number":"pith:2IDVOITI","schema_version":"1.0","canonical_sha256":"d20757226875000cd290adc0cc17844408c3cc6f45b86d65c697319297bc7fb8","source":{"kind":"arxiv","id":"1503.01212","version":2},"attestation_state":"computed","paper":{"title":"Hierarchies of Relaxations for Online Prediction Problems with Evolving Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Karthik Sridharan","submitted_at":"2015-03-04T04:05:35Z","abstract_excerpt":"We study online prediction where regret of the algorithm is measured against a benchmark defined via evolving constraints. This framework captures online prediction on graphs, as well as other prediction problems with combinatorial structure. A key aspect here is that finding the optimal benchmark predictor (even in hindsight, given all the data) might be computationally hard due to the combinatorial nature of the constraints. Despite this, we provide polynomial-time \\emph{prediction} algorithms that achieve low regret against combinatorial benchmark sets. We do so by building improper learnin"},"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":"1503.01212","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-04T04:05:35Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"7dc9e9e46da78f326f5a7437ac65d2a27854f0c6ef8bd622b2cd7ac992c0e650","abstract_canon_sha256":"c388851df9d1877cd8c819075aee1d34912906b602faf0f6de475f981e01f91d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:51:49.218120Z","signature_b64":"OyhAmmGl5A5p1qKNwQINoL4dQoku/7JQxi988bV76M45bVZ2+sO233RC2BeAIywoTsecHGk3Y6cxJYg3kgvzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d20757226875000cd290adc0cc17844408c3cc6f45b86d65c697319297bc7fb8","last_reissued_at":"2026-05-18T01:51:49.217263Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:51:49.217263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchies of Relaxations for Online Prediction Problems with Evolving Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Karthik Sridharan","submitted_at":"2015-03-04T04:05:35Z","abstract_excerpt":"We study online prediction where regret of the algorithm is measured against a benchmark defined via evolving constraints. This framework captures online prediction on graphs, as well as other prediction problems with combinatorial structure. A key aspect here is that finding the optimal benchmark predictor (even in hindsight, given all the data) might be computationally hard due to the combinatorial nature of the constraints. Despite this, we provide polynomial-time \\emph{prediction} algorithms that achieve low regret against combinatorial benchmark sets. We do so by building improper learnin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.01212","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":"1503.01212","created_at":"2026-05-18T01:51:49.217407+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.01212v2","created_at":"2026-05-18T01:51:49.217407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.01212","created_at":"2026-05-18T01:51:49.217407+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IDVOITIOUAA","created_at":"2026-05-18T12:28:59.999130+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IDVOITIOUAAZUUQ","created_at":"2026-05-18T12:28:59.999130+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IDVOITI","created_at":"2026-05-18T12:28:59.999130+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/2IDVOITIOUAAZUUQVXAMYF4EIQ","json":"https://pith.science/pith/2IDVOITIOUAAZUUQVXAMYF4EIQ.json","graph_json":"https://pith.science/api/pith-number/2IDVOITIOUAAZUUQVXAMYF4EIQ/graph.json","events_json":"https://pith.science/api/pith-number/2IDVOITIOUAAZUUQVXAMYF4EIQ/events.json","paper":"https://pith.science/paper/2IDVOITI"},"agent_actions":{"view_html":"https://pith.science/pith/2IDVOITIOUAAZUUQVXAMYF4EIQ","download_json":"https://pith.science/pith/2IDVOITIOUAAZUUQVXAMYF4EIQ.json","view_paper":"https://pith.science/paper/2IDVOITI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.01212&json=true","fetch_graph":"https://pith.science/api/pith-number/2IDVOITIOUAAZUUQVXAMYF4EIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/2IDVOITIOUAAZUUQVXAMYF4EIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IDVOITIOUAAZUUQVXAMYF4EIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IDVOITIOUAAZUUQVXAMYF4EIQ/action/storage_attestation","attest_author":"https://pith.science/pith/2IDVOITIOUAAZUUQVXAMYF4EIQ/action/author_attestation","sign_citation":"https://pith.science/pith/2IDVOITIOUAAZUUQVXAMYF4EIQ/action/citation_signature","submit_replication":"https://pith.science/pith/2IDVOITIOUAAZUUQVXAMYF4EIQ/action/replication_record"}},"created_at":"2026-05-18T01:51:49.217407+00:00","updated_at":"2026-05-18T01:51:49.217407+00:00"}