{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F5GCF6TEH2QBILT7KEFQHPE6EW","short_pith_number":"pith:F5GCF6TE","schema_version":"1.0","canonical_sha256":"2f4c22fa643ea0142e7f510b03bc9e2583c55a3cb038c10f4840f3cf9ecdafc7","source":{"kind":"arxiv","id":"2403.10379","version":1},"attestation_state":"computed","paper":{"title":"Regret Minimization via Saddle Point Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Csaba Szepesv\\'ari, Johannes Kirschner, Kushagra Chandak, Seyed Alireza Bakhtiari, Volodymyr Tkachuk","submitted_at":"2024-03-15T15:09:13Z","abstract_excerpt":"A long line of works characterizes the sample complexity of regret minimization in sequential decision-making by min-max programs. In the corresponding saddle-point game, the min-player optimizes the sampling distribution against an adversarial max-player that chooses confusing models leading to large regret. The most recent instantiation of this idea is the decision-estimation coefficient (DEC), which was shown to provide nearly tight lower and upper bounds on the worst-case expected regret in structured bandits and reinforcement learning. By re-parametrizing the offset DEC with the confidenc"},"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":"2403.10379","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T15:09:13Z","cross_cats_sorted":[],"title_canon_sha256":"ae5bd4d035d6af9eea877f1eb0cb16090a7156f9ce04c91d58eb9996476a2814","abstract_canon_sha256":"76850c88d0b602b7c2168cd1affe965579381b397ea26e5918654da290086379"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:34.559068Z","signature_b64":"6uvEPIl3WE/2Q8h4bw8BnoFXdC9bhSlOBZipH133Ga1fBG/LgR3fpEe8GYp659nS2hS/riIZbRJBRM2NTp7gDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f4c22fa643ea0142e7f510b03bc9e2583c55a3cb038c10f4840f3cf9ecdafc7","last_reissued_at":"2026-07-05T07:56:34.558661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:34.558661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regret Minimization via Saddle Point Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Csaba Szepesv\\'ari, Johannes Kirschner, Kushagra Chandak, Seyed Alireza Bakhtiari, Volodymyr Tkachuk","submitted_at":"2024-03-15T15:09:13Z","abstract_excerpt":"A long line of works characterizes the sample complexity of regret minimization in sequential decision-making by min-max programs. In the corresponding saddle-point game, the min-player optimizes the sampling distribution against an adversarial max-player that chooses confusing models leading to large regret. The most recent instantiation of this idea is the decision-estimation coefficient (DEC), which was shown to provide nearly tight lower and upper bounds on the worst-case expected regret in structured bandits and reinforcement learning. By re-parametrizing the offset DEC with the confidenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10379","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/2403.10379/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":"2403.10379","created_at":"2026-07-05T07:56:34.558721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10379v1","created_at":"2026-07-05T07:56:34.558721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10379","created_at":"2026-07-05T07:56:34.558721+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5GCF6TEH2QB","created_at":"2026-07-05T07:56:34.558721+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5GCF6TEH2QBILT7","created_at":"2026-07-05T07:56:34.558721+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5GCF6TE","created_at":"2026-07-05T07:56:34.558721+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/F5GCF6TEH2QBILT7KEFQHPE6EW","json":"https://pith.science/pith/F5GCF6TEH2QBILT7KEFQHPE6EW.json","graph_json":"https://pith.science/api/pith-number/F5GCF6TEH2QBILT7KEFQHPE6EW/graph.json","events_json":"https://pith.science/api/pith-number/F5GCF6TEH2QBILT7KEFQHPE6EW/events.json","paper":"https://pith.science/paper/F5GCF6TE"},"agent_actions":{"view_html":"https://pith.science/pith/F5GCF6TEH2QBILT7KEFQHPE6EW","download_json":"https://pith.science/pith/F5GCF6TEH2QBILT7KEFQHPE6EW.json","view_paper":"https://pith.science/paper/F5GCF6TE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10379&json=true","fetch_graph":"https://pith.science/api/pith-number/F5GCF6TEH2QBILT7KEFQHPE6EW/graph.json","fetch_events":"https://pith.science/api/pith-number/F5GCF6TEH2QBILT7KEFQHPE6EW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5GCF6TEH2QBILT7KEFQHPE6EW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5GCF6TEH2QBILT7KEFQHPE6EW/action/storage_attestation","attest_author":"https://pith.science/pith/F5GCF6TEH2QBILT7KEFQHPE6EW/action/author_attestation","sign_citation":"https://pith.science/pith/F5GCF6TEH2QBILT7KEFQHPE6EW/action/citation_signature","submit_replication":"https://pith.science/pith/F5GCF6TEH2QBILT7KEFQHPE6EW/action/replication_record"}},"created_at":"2026-07-05T07:56:34.558721+00:00","updated_at":"2026-07-05T07:56:34.558721+00:00"}