{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:RPGEINVATZ3CM44NWGMGIZUSTD","short_pith_number":"pith:RPGEINVA","schema_version":"1.0","canonical_sha256":"8bcc4436a09e7626738db19864669298f43347f0470453435caf44c79645c7e2","source":{"kind":"arxiv","id":"1605.06651","version":3},"attestation_state":"computed","paper":{"title":"Gambler's Ruin Bandit Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cem Tekin, Nima Akbarzadeh","submitted_at":"2016-05-21T14:43:44Z","abstract_excerpt":"In this paper, we propose a new multi-armed bandit problem called the Gambler's Ruin Bandit Problem (GRBP). In the GRBP, the learner proceeds in a sequence of rounds, where each round is a Markov Decision Process (MDP) with two actions (arms): a continuation action that moves the learner randomly over the state space around the current state; and a terminal action that moves the learner directly into one of the two terminal states (goal and dead-end state). The current round ends when a terminal state is reached, and the learner incurs a positive reward only when the goal state is reached. The"},"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":"1605.06651","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-21T14:43:44Z","cross_cats_sorted":[],"title_canon_sha256":"c48ef50517e3ff966350d05ed66b035ecf7b6f0b4dc9779e6231020ecb1fe557","abstract_canon_sha256":"79f62c03c21c753d9d0f297bed7b4c4d13b35d1476c7927a38f1d215a57f3025"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:40.637552Z","signature_b64":"Awryd4kAfG2N2MjUG30o0zlIqP1jy89pMkay4SgtBOW4RF4K7yg5T8D5/1zlpO2Vdya77L5rzhfGXaU2e/bjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bcc4436a09e7626738db19864669298f43347f0470453435caf44c79645c7e2","last_reissued_at":"2026-05-18T01:03:40.636957Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:40.636957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gambler's Ruin Bandit Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cem Tekin, Nima Akbarzadeh","submitted_at":"2016-05-21T14:43:44Z","abstract_excerpt":"In this paper, we propose a new multi-armed bandit problem called the Gambler's Ruin Bandit Problem (GRBP). In the GRBP, the learner proceeds in a sequence of rounds, where each round is a Markov Decision Process (MDP) with two actions (arms): a continuation action that moves the learner randomly over the state space around the current state; and a terminal action that moves the learner directly into one of the two terminal states (goal and dead-end state). The current round ends when a terminal state is reached, and the learner incurs a positive reward only when the goal state is reached. The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.06651","kind":"arxiv","version":3},"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":"1605.06651","created_at":"2026-05-18T01:03:40.637049+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.06651v3","created_at":"2026-05-18T01:03:40.637049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.06651","created_at":"2026-05-18T01:03:40.637049+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPGEINVATZ3C","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPGEINVATZ3CM44N","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPGEINVA","created_at":"2026-05-18T12:30:41.710351+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/RPGEINVATZ3CM44NWGMGIZUSTD","json":"https://pith.science/pith/RPGEINVATZ3CM44NWGMGIZUSTD.json","graph_json":"https://pith.science/api/pith-number/RPGEINVATZ3CM44NWGMGIZUSTD/graph.json","events_json":"https://pith.science/api/pith-number/RPGEINVATZ3CM44NWGMGIZUSTD/events.json","paper":"https://pith.science/paper/RPGEINVA"},"agent_actions":{"view_html":"https://pith.science/pith/RPGEINVATZ3CM44NWGMGIZUSTD","download_json":"https://pith.science/pith/RPGEINVATZ3CM44NWGMGIZUSTD.json","view_paper":"https://pith.science/paper/RPGEINVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.06651&json=true","fetch_graph":"https://pith.science/api/pith-number/RPGEINVATZ3CM44NWGMGIZUSTD/graph.json","fetch_events":"https://pith.science/api/pith-number/RPGEINVATZ3CM44NWGMGIZUSTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPGEINVATZ3CM44NWGMGIZUSTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPGEINVATZ3CM44NWGMGIZUSTD/action/storage_attestation","attest_author":"https://pith.science/pith/RPGEINVATZ3CM44NWGMGIZUSTD/action/author_attestation","sign_citation":"https://pith.science/pith/RPGEINVATZ3CM44NWGMGIZUSTD/action/citation_signature","submit_replication":"https://pith.science/pith/RPGEINVATZ3CM44NWGMGIZUSTD/action/replication_record"}},"created_at":"2026-05-18T01:03:40.637049+00:00","updated_at":"2026-05-18T01:03:40.637049+00:00"}