{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PBL7RSRELPQO6ROXBYHOVARPXC","short_pith_number":"pith:PBL7RSRE","canonical_record":{"source":{"id":"1812.00365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-02T10:38:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8bef4a5d4828c0ab1f6c897dd1bc09aad99143063bebea351dd2b0be13f164d3","abstract_canon_sha256":"15cf2f6ce803fb450da53df731147b5152283f2089bf2f256116fd6c6ebda04f"},"schema_version":"1.0"},"canonical_sha256":"7857f8ca245be0ef45d70e0eea822fb891da592439b319028b59a1d30af4250c","source":{"kind":"arxiv","id":"1812.00365","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.00365","created_at":"2026-05-17T23:59:21Z"},{"alias_kind":"arxiv_version","alias_value":"1812.00365v1","created_at":"2026-05-17T23:59:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00365","created_at":"2026-05-17T23:59:21Z"},{"alias_kind":"pith_short_12","alias_value":"PBL7RSRELPQO","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PBL7RSRELPQO6ROX","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PBL7RSRE","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PBL7RSRELPQO6ROXBYHOVARPXC","target":"record","payload":{"canonical_record":{"source":{"id":"1812.00365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-02T10:38:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8bef4a5d4828c0ab1f6c897dd1bc09aad99143063bebea351dd2b0be13f164d3","abstract_canon_sha256":"15cf2f6ce803fb450da53df731147b5152283f2089bf2f256116fd6c6ebda04f"},"schema_version":"1.0"},"canonical_sha256":"7857f8ca245be0ef45d70e0eea822fb891da592439b319028b59a1d30af4250c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:21.531751Z","signature_b64":"92q8wc6ORm+slF3BhIbRVYbHaPbaf68o3VvUhArvIcSY97F0rgen4ufjUc1WnemWmOuPOw+51CcwZE2pN5KTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7857f8ca245be0ef45d70e0eea822fb891da592439b319028b59a1d30af4250c","last_reissued_at":"2026-05-17T23:59:21.531388Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:21.531388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.00365","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IoHnHJTiEHhkJKnIh0DXkCMpdHdb9Zv2U1m4YSEmNC63iq/RuKNFAJEB2TXMV/rSicuWoCtUAc5rwqIWX9OgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T02:37:14.695582Z"},"content_sha256":"caaaf488d705866d8515ee251517ef3f726c668832535b463df52ef62e7eb475","schema_version":"1.0","event_id":"sha256:caaaf488d705866d8515ee251517ef3f726c668832535b463df52ef62e7eb475"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PBL7RSRELPQO6ROXBYHOVARPXC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quick Best Action Identification in Linear Bandit Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jun Geng, Lifeng Lai","submitted_at":"2018-12-02T10:38:45Z","abstract_excerpt":"In this paper, we consider a best action identification problem in the stochastic linear bandit setup with a fixed confident constraint. In the considered best action identification problem, instead of minimizing the accumulative regret as done in existing works, the learner aims to obtain an accurate estimate of the underlying parameter based on his action and reward sequences. To improve the estimation efficiency, the learner is allowed to select his action based his historical information; hence the whole procedure is designed in a sequential adaptive manner. We first show that the existing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00365","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"igtx2uZaUDswU0voqqBsgg2RAiA4rgMByycBDowvXwq9+lnA0n2K0tUxu6t+mPq78rbRaxQb2H0W5i4X4FveBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T02:37:14.696220Z"},"content_sha256":"5eeacf46c0b04555945c9a98a713214ba095cd81386b315eab3cdf44e752f3db","schema_version":"1.0","event_id":"sha256:5eeacf46c0b04555945c9a98a713214ba095cd81386b315eab3cdf44e752f3db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PBL7RSRELPQO6ROXBYHOVARPXC/bundle.json","state_url":"https://pith.science/pith/PBL7RSRELPQO6ROXBYHOVARPXC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PBL7RSRELPQO6ROXBYHOVARPXC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T02:37:14Z","links":{"resolver":"https://pith.science/pith/PBL7RSRELPQO6ROXBYHOVARPXC","bundle":"https://pith.science/pith/PBL7RSRELPQO6ROXBYHOVARPXC/bundle.json","state":"https://pith.science/pith/PBL7RSRELPQO6ROXBYHOVARPXC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PBL7RSRELPQO6ROXBYHOVARPXC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PBL7RSRELPQO6ROXBYHOVARPXC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"15cf2f6ce803fb450da53df731147b5152283f2089bf2f256116fd6c6ebda04f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-02T10:38:45Z","title_canon_sha256":"8bef4a5d4828c0ab1f6c897dd1bc09aad99143063bebea351dd2b0be13f164d3"},"schema_version":"1.0","source":{"id":"1812.00365","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.00365","created_at":"2026-05-17T23:59:21Z"},{"alias_kind":"arxiv_version","alias_value":"1812.00365v1","created_at":"2026-05-17T23:59:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00365","created_at":"2026-05-17T23:59:21Z"},{"alias_kind":"pith_short_12","alias_value":"PBL7RSRELPQO","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PBL7RSRELPQO6ROX","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PBL7RSRE","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:5eeacf46c0b04555945c9a98a713214ba095cd81386b315eab3cdf44e752f3db","target":"graph","created_at":"2026-05-17T23:59:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In this paper, we consider a best action identification problem in the stochastic linear bandit setup with a fixed confident constraint. In the considered best action identification problem, instead of minimizing the accumulative regret as done in existing works, the learner aims to obtain an accurate estimate of the underlying parameter based on his action and reward sequences. To improve the estimation efficiency, the learner is allowed to select his action based his historical information; hence the whole procedure is designed in a sequential adaptive manner. We first show that the existing","authors_text":"Jun Geng, Lifeng Lai","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-02T10:38:45Z","title":"Quick Best Action Identification in Linear Bandit Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00365","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:caaaf488d705866d8515ee251517ef3f726c668832535b463df52ef62e7eb475","target":"record","created_at":"2026-05-17T23:59:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"15cf2f6ce803fb450da53df731147b5152283f2089bf2f256116fd6c6ebda04f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-02T10:38:45Z","title_canon_sha256":"8bef4a5d4828c0ab1f6c897dd1bc09aad99143063bebea351dd2b0be13f164d3"},"schema_version":"1.0","source":{"id":"1812.00365","kind":"arxiv","version":1}},"canonical_sha256":"7857f8ca245be0ef45d70e0eea822fb891da592439b319028b59a1d30af4250c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7857f8ca245be0ef45d70e0eea822fb891da592439b319028b59a1d30af4250c","first_computed_at":"2026-05-17T23:59:21.531388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:21.531388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"92q8wc6ORm+slF3BhIbRVYbHaPbaf68o3VvUhArvIcSY97F0rgen4ufjUc1WnemWmOuPOw+51CcwZE2pN5KTCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:21.531751Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.00365","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:caaaf488d705866d8515ee251517ef3f726c668832535b463df52ef62e7eb475","sha256:5eeacf46c0b04555945c9a98a713214ba095cd81386b315eab3cdf44e752f3db"],"state_sha256":"41fe9d54d9c244370b22bd6bf4b0b22a62e992312169d3ba63d65278dfbd2f0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cgXWVUJrJDBWJzL53vbE9UaAQdXBccHm8vzTNFiCfsAnMM/tj5BSkQwj5w/tUxTLWXEpH1xbZub5eVLa6hT6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T02:37:14.699379Z","bundle_sha256":"88dd75f4653a54236d40e51de90bfc87f6319bf3b95d8587d243d9a75610dcb8"}}