{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:CTWZR74FKOM3AWZOGHDCE4CTUR","short_pith_number":"pith:CTWZR74F","schema_version":"1.0","canonical_sha256":"14ed98ff855399b05b2e31c6227053a467fe0f2cd5f7c8e3d3fef08533079144","source":{"kind":"arxiv","id":"1407.7635","version":1},"attestation_state":"computed","paper":{"title":"Chasing Ghosts: Competing with Stateful Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Moshe Tennenholtz, Tomer Koren, Uriel Feige","submitted_at":"2014-07-29T06:17:49Z","abstract_excerpt":"We consider sequential decision making in a setting where regret is measured with respect to a set of stateful reference policies, and feedback is limited to observing the rewards of the actions performed (the so called \"bandit\" setting). If either the reference policies are stateless rather than stateful, or the feedback includes the rewards of all actions (the so called \"expert\" setting), previous work shows that the optimal regret grows like $\\Theta(\\sqrt{T})$ in terms of the number of decision rounds $T$.\n  The difficulty in our setting is that the decision maker unavoidably loses track of"},"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":"1407.7635","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-07-29T06:17:49Z","cross_cats_sorted":[],"title_canon_sha256":"29f17a995485876cf8e9d15f0a5dfac43547045ccc9828bee4eaddae47f772ad","abstract_canon_sha256":"8ec96692f118f7d862df6debc0fa31fcbe9314f106a3d3358bb72f6060cdee96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:46:22.131040Z","signature_b64":"Ouz286LT50XYVRXcZuvEIOhLA2+WE/ke05NKdHZGKzxtqEI3exntmrJzVoz8/3kbKObHrTLoE4xdp3CMrUvvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14ed98ff855399b05b2e31c6227053a467fe0f2cd5f7c8e3d3fef08533079144","last_reissued_at":"2026-05-18T02:46:22.130588Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:46:22.130588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chasing Ghosts: Competing with Stateful Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Moshe Tennenholtz, Tomer Koren, Uriel Feige","submitted_at":"2014-07-29T06:17:49Z","abstract_excerpt":"We consider sequential decision making in a setting where regret is measured with respect to a set of stateful reference policies, and feedback is limited to observing the rewards of the actions performed (the so called \"bandit\" setting). If either the reference policies are stateless rather than stateful, or the feedback includes the rewards of all actions (the so called \"expert\" setting), previous work shows that the optimal regret grows like $\\Theta(\\sqrt{T})$ in terms of the number of decision rounds $T$.\n  The difficulty in our setting is that the decision maker unavoidably loses track of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.7635","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":""},"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":"1407.7635","created_at":"2026-05-18T02:46:22.130654+00:00"},{"alias_kind":"arxiv_version","alias_value":"1407.7635v1","created_at":"2026-05-18T02:46:22.130654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.7635","created_at":"2026-05-18T02:46:22.130654+00:00"},{"alias_kind":"pith_short_12","alias_value":"CTWZR74FKOM3","created_at":"2026-05-18T12:28:25.294606+00:00"},{"alias_kind":"pith_short_16","alias_value":"CTWZR74FKOM3AWZO","created_at":"2026-05-18T12:28:25.294606+00:00"},{"alias_kind":"pith_short_8","alias_value":"CTWZR74F","created_at":"2026-05-18T12:28:25.294606+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/CTWZR74FKOM3AWZOGHDCE4CTUR","json":"https://pith.science/pith/CTWZR74FKOM3AWZOGHDCE4CTUR.json","graph_json":"https://pith.science/api/pith-number/CTWZR74FKOM3AWZOGHDCE4CTUR/graph.json","events_json":"https://pith.science/api/pith-number/CTWZR74FKOM3AWZOGHDCE4CTUR/events.json","paper":"https://pith.science/paper/CTWZR74F"},"agent_actions":{"view_html":"https://pith.science/pith/CTWZR74FKOM3AWZOGHDCE4CTUR","download_json":"https://pith.science/pith/CTWZR74FKOM3AWZOGHDCE4CTUR.json","view_paper":"https://pith.science/paper/CTWZR74F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1407.7635&json=true","fetch_graph":"https://pith.science/api/pith-number/CTWZR74FKOM3AWZOGHDCE4CTUR/graph.json","fetch_events":"https://pith.science/api/pith-number/CTWZR74FKOM3AWZOGHDCE4CTUR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CTWZR74FKOM3AWZOGHDCE4CTUR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CTWZR74FKOM3AWZOGHDCE4CTUR/action/storage_attestation","attest_author":"https://pith.science/pith/CTWZR74FKOM3AWZOGHDCE4CTUR/action/author_attestation","sign_citation":"https://pith.science/pith/CTWZR74FKOM3AWZOGHDCE4CTUR/action/citation_signature","submit_replication":"https://pith.science/pith/CTWZR74FKOM3AWZOGHDCE4CTUR/action/replication_record"}},"created_at":"2026-05-18T02:46:22.130654+00:00","updated_at":"2026-05-18T02:46:22.130654+00:00"}