{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GI2GAZWDPRJP5RLVBW4TBQYCA4","short_pith_number":"pith:GI2GAZWD","canonical_record":{"source":{"id":"2010.00827","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-02T07:44:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e2bd6219a857211a3ba4cd5bf952b39ead2542b1e7aa652d105587183d3ae10a","abstract_canon_sha256":"1faaac05cbdd85a8db77a6bf7063879476ede39c38aa2cb66cde271aa6aeb7e9"},"schema_version":"1.0"},"canonical_sha256":"32346066c37c52fec5750db930c30207349616c978a428a9ef03a48113b67bb8","source":{"kind":"arxiv","id":"2010.00827","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.00827","created_at":"2026-07-05T03:44:27Z"},{"alias_kind":"arxiv_version","alias_value":"2010.00827v2","created_at":"2026-07-05T03:44:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.00827","created_at":"2026-07-05T03:44:27Z"},{"alias_kind":"pith_short_12","alias_value":"GI2GAZWDPRJP","created_at":"2026-07-05T03:44:27Z"},{"alias_kind":"pith_short_16","alias_value":"GI2GAZWDPRJP5RLV","created_at":"2026-07-05T03:44:27Z"},{"alias_kind":"pith_short_8","alias_value":"GI2GAZWD","created_at":"2026-07-05T03:44:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GI2GAZWDPRJP5RLVBW4TBQYCA4","target":"record","payload":{"canonical_record":{"source":{"id":"2010.00827","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-02T07:44:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e2bd6219a857211a3ba4cd5bf952b39ead2542b1e7aa652d105587183d3ae10a","abstract_canon_sha256":"1faaac05cbdd85a8db77a6bf7063879476ede39c38aa2cb66cde271aa6aeb7e9"},"schema_version":"1.0"},"canonical_sha256":"32346066c37c52fec5750db930c30207349616c978a428a9ef03a48113b67bb8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:27.964492Z","signature_b64":"Lh6skcOZQhkdj7gUdzGa/5CKmwJT72brwPTjAVfOUa/tdEP9o8BAcsYYnsZ+GiX4o+6W53PDdREKUvuCzU0xDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32346066c37c52fec5750db930c30207349616c978a428a9ef03a48113b67bb8","last_reissued_at":"2026-07-05T03:44:27.963978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:27.963978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.00827","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:44:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SsQyISO8kCLbyq/vcN5XBlFPejHVr5YvS25KS2oYixwgQB5onMxSRKZyJHrpCdy7KVvnpQyIG3oLgynPWDYxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:09:41.080333Z"},"content_sha256":"47ec2e1ff8420d062a9b62420384975a259350e2ef961b8fc03b225daa0dbcc8","schema_version":"1.0","event_id":"sha256:47ec2e1ff8420d062a9b62420384975a259350e2ef961b8fc03b225daa0dbcc8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GI2GAZWDPRJP5RLVBW4TBQYCA4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Thompson Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Lihong Li, Quanquan Gu, Weitong Zhang","submitted_at":"2020-10-02T07:44:09Z","abstract_excerpt":"Thompson Sampling (TS) is one of the most effective algorithms for solving contextual multi-armed bandit problems. In this paper, we propose a new algorithm, called Neural Thompson Sampling, which adapts deep neural networks for both exploration and exploitation. At the core of our algorithm is a novel posterior distribution of the reward, where its mean is the neural network approximator, and its variance is built upon the neural tangent features of the corresponding neural network. We prove that, provided the underlying reward function is bounded, the proposed algorithm is guaranteed to achi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.00827","kind":"arxiv","version":2},"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/2010.00827/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":"2026-07-05T03:44:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LQiMLMJF1zBzEhG6+n2hd82oQKzA8bgslLU+llQp293qb71lLkgx0Ru4hXDGuZvFWHJGJ8c3P7dk9Ni0wIM2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:09:41.081037Z"},"content_sha256":"9aa9129af97ce3d4e9c914c4ba5491c465013ddba9ddb7d0748c3546ee91ff84","schema_version":"1.0","event_id":"sha256:9aa9129af97ce3d4e9c914c4ba5491c465013ddba9ddb7d0748c3546ee91ff84"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GI2GAZWDPRJP5RLVBW4TBQYCA4/bundle.json","state_url":"https://pith.science/pith/GI2GAZWDPRJP5RLVBW4TBQYCA4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GI2GAZWDPRJP5RLVBW4TBQYCA4/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":"2026-08-09T11:09:41Z","links":{"resolver":"https://pith.science/pith/GI2GAZWDPRJP5RLVBW4TBQYCA4","bundle":"https://pith.science/pith/GI2GAZWDPRJP5RLVBW4TBQYCA4/bundle.json","state":"https://pith.science/pith/GI2GAZWDPRJP5RLVBW4TBQYCA4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GI2GAZWDPRJP5RLVBW4TBQYCA4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GI2GAZWDPRJP5RLVBW4TBQYCA4","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":"1faaac05cbdd85a8db77a6bf7063879476ede39c38aa2cb66cde271aa6aeb7e9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-02T07:44:09Z","title_canon_sha256":"e2bd6219a857211a3ba4cd5bf952b39ead2542b1e7aa652d105587183d3ae10a"},"schema_version":"1.0","source":{"id":"2010.00827","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.00827","created_at":"2026-07-05T03:44:27Z"},{"alias_kind":"arxiv_version","alias_value":"2010.00827v2","created_at":"2026-07-05T03:44:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.00827","created_at":"2026-07-05T03:44:27Z"},{"alias_kind":"pith_short_12","alias_value":"GI2GAZWDPRJP","created_at":"2026-07-05T03:44:27Z"},{"alias_kind":"pith_short_16","alias_value":"GI2GAZWDPRJP5RLV","created_at":"2026-07-05T03:44:27Z"},{"alias_kind":"pith_short_8","alias_value":"GI2GAZWD","created_at":"2026-07-05T03:44:27Z"}],"graph_snapshots":[{"event_id":"sha256:9aa9129af97ce3d4e9c914c4ba5491c465013ddba9ddb7d0748c3546ee91ff84","target":"graph","created_at":"2026-07-05T03:44:27Z","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/2010.00827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Thompson Sampling (TS) is one of the most effective algorithms for solving contextual multi-armed bandit problems. In this paper, we propose a new algorithm, called Neural Thompson Sampling, which adapts deep neural networks for both exploration and exploitation. At the core of our algorithm is a novel posterior distribution of the reward, where its mean is the neural network approximator, and its variance is built upon the neural tangent features of the corresponding neural network. We prove that, provided the underlying reward function is bounded, the proposed algorithm is guaranteed to achi","authors_text":"Dongruo Zhou, Lihong Li, Quanquan Gu, Weitong Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-02T07:44:09Z","title":"Neural Thompson Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.00827","kind":"arxiv","version":2},"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":"sha256:47ec2e1ff8420d062a9b62420384975a259350e2ef961b8fc03b225daa0dbcc8","target":"record","created_at":"2026-07-05T03:44:27Z","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":"1faaac05cbdd85a8db77a6bf7063879476ede39c38aa2cb66cde271aa6aeb7e9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-02T07:44:09Z","title_canon_sha256":"e2bd6219a857211a3ba4cd5bf952b39ead2542b1e7aa652d105587183d3ae10a"},"schema_version":"1.0","source":{"id":"2010.00827","kind":"arxiv","version":2}},"canonical_sha256":"32346066c37c52fec5750db930c30207349616c978a428a9ef03a48113b67bb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32346066c37c52fec5750db930c30207349616c978a428a9ef03a48113b67bb8","first_computed_at":"2026-07-05T03:44:27.963978Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:44:27.963978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lh6skcOZQhkdj7gUdzGa/5CKmwJT72brwPTjAVfOUa/tdEP9o8BAcsYYnsZ+GiX4o+6W53PDdREKUvuCzU0xDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:44:27.964492Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.00827","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47ec2e1ff8420d062a9b62420384975a259350e2ef961b8fc03b225daa0dbcc8","sha256:9aa9129af97ce3d4e9c914c4ba5491c465013ddba9ddb7d0748c3546ee91ff84"],"state_sha256":"395202f89c3707953f3405a1fbb4c62a9a92fdd48aeb73712f8252fbf452b369"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HeZ+zw/Qwp4xclFowdRd3ekjB3ShIfP1Ur9nIhXnlKMG+gKJNssrf6WF5jgajucpgYDoo5RoI8ek4HUwwMNSAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:09:41.087879Z","bundle_sha256":"83c86a1d5b49cf11437a871aed39a1b8ac84f19b02e6957e5dd704504960ba21"}}