{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:WEYFNAYLXIVHNEECXCFN35Q4MU","short_pith_number":"pith:WEYFNAYL","canonical_record":{"source":{"id":"2012.02876","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T22:33:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fed5f5635a160429e138db5c98df9e66791fa9a3ba2311d6b1ad01e7a8ea0f50","abstract_canon_sha256":"dcb2fd9fe5799a5998caffb8e09b07dced0e2445b2ac3212fdab239615cb6cde"},"schema_version":"1.0"},"canonical_sha256":"b13056830bba2a769082b88addf61c652fdd25b888f646391a8edbb2feb64f7a","source":{"kind":"arxiv","id":"2012.02876","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02876","created_at":"2026-07-05T01:57:23Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02876v1","created_at":"2026-07-05T01:57:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02876","created_at":"2026-07-05T01:57:23Z"},{"alias_kind":"pith_short_12","alias_value":"WEYFNAYLXIVH","created_at":"2026-07-05T01:57:23Z"},{"alias_kind":"pith_short_16","alias_value":"WEYFNAYLXIVHNEEC","created_at":"2026-07-05T01:57:23Z"},{"alias_kind":"pith_short_8","alias_value":"WEYFNAYL","created_at":"2026-07-05T01:57:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:WEYFNAYLXIVHNEECXCFN35Q4MU","target":"record","payload":{"canonical_record":{"source":{"id":"2012.02876","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T22:33:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fed5f5635a160429e138db5c98df9e66791fa9a3ba2311d6b1ad01e7a8ea0f50","abstract_canon_sha256":"dcb2fd9fe5799a5998caffb8e09b07dced0e2445b2ac3212fdab239615cb6cde"},"schema_version":"1.0"},"canonical_sha256":"b13056830bba2a769082b88addf61c652fdd25b888f646391a8edbb2feb64f7a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:23.267688Z","signature_b64":"DwO8KZoARl3FzWb3EGqnYyFdlCh8aqWDxHQYLpswb9s+fDU1g0Jfjnz0wr8MnKEzAjERlDc5mvc7suS2dP45DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b13056830bba2a769082b88addf61c652fdd25b888f646391a8edbb2feb64f7a","last_reissued_at":"2026-07-05T01:57:23.267184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:23.267184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.02876","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":"2026-07-05T01:57:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/3hnP3xWpVElbC25kITFrCODEzWu20NahmxN4ANiefyhOFijWkd3wibIuCT35VK32ixnVye7nHO4vGK8Gl3bAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:57:07.523556Z"},"content_sha256":"5db257e3054a5c439c6a3c02770515e06ce0c68f5eee5d64971a5aaa135271ee","schema_version":"1.0","event_id":"sha256:5db257e3054a5c439c6a3c02770515e06ce0c68f5eee5d64971a5aaa135271ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:WEYFNAYLXIVHNEECXCFN35Q4MU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"One-bit feedback is sufficient for upper confidence bound policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Vial, R. Srikant, Sanjay Shakkottai","submitted_at":"2020-12-04T22:33:53Z","abstract_excerpt":"We consider a variant of the traditional multi-armed bandit problem in which each arm is only able to provide one-bit feedback during each pull based on its past history of rewards. Our main result is the following: given an upper confidence bound policy which uses full-reward feedback, there exists a coding scheme for generating one-bit feedback, and a corresponding decoding scheme and arm selection policy, such that the ratio of the regret achieved by our policy and the regret of the full-reward feedback policy asymptotically approaches one."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02876","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/2012.02876/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:57:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IeOZTkFWWAaFxZc80HY4BHt3oNAzGUPKiqckYjYVQpXv8P9+8OKpdsif91vmrmHOFka0c1cr4ynGw+vZXkpFCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:57:07.524458Z"},"content_sha256":"0d4370bad54d9bbf0f16e9f407d4e4483823f3f8061613da0228587b69e91cec","schema_version":"1.0","event_id":"sha256:0d4370bad54d9bbf0f16e9f407d4e4483823f3f8061613da0228587b69e91cec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WEYFNAYLXIVHNEECXCFN35Q4MU/bundle.json","state_url":"https://pith.science/pith/WEYFNAYLXIVHNEECXCFN35Q4MU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WEYFNAYLXIVHNEECXCFN35Q4MU/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":"2026-08-10T05:57:07Z","links":{"resolver":"https://pith.science/pith/WEYFNAYLXIVHNEECXCFN35Q4MU","bundle":"https://pith.science/pith/WEYFNAYLXIVHNEECXCFN35Q4MU/bundle.json","state":"https://pith.science/pith/WEYFNAYLXIVHNEECXCFN35Q4MU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WEYFNAYLXIVHNEECXCFN35Q4MU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:WEYFNAYLXIVHNEECXCFN35Q4MU","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":"dcb2fd9fe5799a5998caffb8e09b07dced0e2445b2ac3212fdab239615cb6cde","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T22:33:53Z","title_canon_sha256":"fed5f5635a160429e138db5c98df9e66791fa9a3ba2311d6b1ad01e7a8ea0f50"},"schema_version":"1.0","source":{"id":"2012.02876","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02876","created_at":"2026-07-05T01:57:23Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02876v1","created_at":"2026-07-05T01:57:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02876","created_at":"2026-07-05T01:57:23Z"},{"alias_kind":"pith_short_12","alias_value":"WEYFNAYLXIVH","created_at":"2026-07-05T01:57:23Z"},{"alias_kind":"pith_short_16","alias_value":"WEYFNAYLXIVHNEEC","created_at":"2026-07-05T01:57:23Z"},{"alias_kind":"pith_short_8","alias_value":"WEYFNAYL","created_at":"2026-07-05T01:57:23Z"}],"graph_snapshots":[{"event_id":"sha256:0d4370bad54d9bbf0f16e9f407d4e4483823f3f8061613da0228587b69e91cec","target":"graph","created_at":"2026-07-05T01:57:23Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2012.02876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider a variant of the traditional multi-armed bandit problem in which each arm is only able to provide one-bit feedback during each pull based on its past history of rewards. Our main result is the following: given an upper confidence bound policy which uses full-reward feedback, there exists a coding scheme for generating one-bit feedback, and a corresponding decoding scheme and arm selection policy, such that the ratio of the regret achieved by our policy and the regret of the full-reward feedback policy asymptotically approaches one.","authors_text":"Daniel Vial, R. Srikant, Sanjay Shakkottai","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T22:33:53Z","title":"One-bit feedback is sufficient for upper confidence bound policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02876","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":"sha256:5db257e3054a5c439c6a3c02770515e06ce0c68f5eee5d64971a5aaa135271ee","target":"record","created_at":"2026-07-05T01:57:23Z","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":"dcb2fd9fe5799a5998caffb8e09b07dced0e2445b2ac3212fdab239615cb6cde","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T22:33:53Z","title_canon_sha256":"fed5f5635a160429e138db5c98df9e66791fa9a3ba2311d6b1ad01e7a8ea0f50"},"schema_version":"1.0","source":{"id":"2012.02876","kind":"arxiv","version":1}},"canonical_sha256":"b13056830bba2a769082b88addf61c652fdd25b888f646391a8edbb2feb64f7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b13056830bba2a769082b88addf61c652fdd25b888f646391a8edbb2feb64f7a","first_computed_at":"2026-07-05T01:57:23.267184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:57:23.267184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DwO8KZoARl3FzWb3EGqnYyFdlCh8aqWDxHQYLpswb9s+fDU1g0Jfjnz0wr8MnKEzAjERlDc5mvc7suS2dP45DA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:57:23.267688Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.02876","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5db257e3054a5c439c6a3c02770515e06ce0c68f5eee5d64971a5aaa135271ee","sha256:0d4370bad54d9bbf0f16e9f407d4e4483823f3f8061613da0228587b69e91cec"],"state_sha256":"98321ad14b04990341f1d4e30ee4e8a3c8cc454df922c533152141c72bf38236"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WfvE0Xwt9zEksYAgJHi5/LQygpeb75wPJzJjaAFs27pMQVm7iQ5YqPwiJO92LXEgnZA0JCSsQf7prvHNPrk/BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T05:57:07.531678Z","bundle_sha256":"b7a010858c051bc480a8c345e3041776f1d5c6fb6ba269ed4047577ab357e562"}}