{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:X7MKUW2R4ZMPH5K7OVIDNBVYKS","short_pith_number":"pith:X7MKUW2R","canonical_record":{"source":{"id":"2410.19705","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T17:27:58Z","cross_cats_sorted":[],"title_canon_sha256":"fde928fd98283f4c69964d77daca7f4cc634b6b265638eba8ba494f26c2863c6","abstract_canon_sha256":"3f547c82e58a087d24216fb2f40dd60f25b25018239a04032b6e957ecd4064fe"},"schema_version":"1.0"},"canonical_sha256":"bfd8aa5b51e658f3f55f75503686b8549bc59cd358428eb119febd77834973eb","source":{"kind":"arxiv","id":"2410.19705","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19705","created_at":"2026-07-05T09:26:00Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19705v1","created_at":"2026-07-05T09:26:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19705","created_at":"2026-07-05T09:26:00Z"},{"alias_kind":"pith_short_12","alias_value":"X7MKUW2R4ZMP","created_at":"2026-07-05T09:26:00Z"},{"alias_kind":"pith_short_16","alias_value":"X7MKUW2R4ZMPH5K7","created_at":"2026-07-05T09:26:00Z"},{"alias_kind":"pith_short_8","alias_value":"X7MKUW2R","created_at":"2026-07-05T09:26:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:X7MKUW2R4ZMPH5K7OVIDNBVYKS","target":"record","payload":{"canonical_record":{"source":{"id":"2410.19705","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T17:27:58Z","cross_cats_sorted":[],"title_canon_sha256":"fde928fd98283f4c69964d77daca7f4cc634b6b265638eba8ba494f26c2863c6","abstract_canon_sha256":"3f547c82e58a087d24216fb2f40dd60f25b25018239a04032b6e957ecd4064fe"},"schema_version":"1.0"},"canonical_sha256":"bfd8aa5b51e658f3f55f75503686b8549bc59cd358428eb119febd77834973eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:00.474012Z","signature_b64":"8GdlLMnqoioMaS0KdxOYwqsm+fLBKfvJpO9oAla91of7fXzmtd3ieCN947pHR3Goouw8D8BNrL9JrErVoOzHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfd8aa5b51e658f3f55f75503686b8549bc59cd358428eb119febd77834973eb","last_reissued_at":"2026-07-05T09:26:00.473547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:00.473547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.19705","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":"2026-07-05T09:26:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tpVK7mL0rM9mX2GGbvRozI66uu96V3wk+4KM7To0UAQs4re1hJJ4KpzEiTJJwyVt+xnHK9CRhHkFMeFhfWvcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:00:46.353176Z"},"content_sha256":"8be93ff5f5c4ffde36bc320a55c5a7f5e987103ddd87db7e49a2f8e773a04649","schema_version":"1.0","event_id":"sha256:8be93ff5f5c4ffde36bc320a55c5a7f5e987103ddd87db7e49a2f8e773a04649"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:X7MKUW2R4ZMPH5K7OVIDNBVYKS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Thompson Sampling Algorithms Against Reward Poisoning Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gagandeep Singh, Yinglun Xu, Zhiwei Wang","submitted_at":"2024-10-25T17:27:58Z","abstract_excerpt":"Thompson sampling is one of the most popular learning algorithms for online sequential decision-making problems and has rich real-world applications. However, current Thompson sampling algorithms are limited by the assumption that the rewards received are uncorrupted, which may not be true in real-world applications where adversarial reward poisoning exists. To make Thompson sampling more reliable, we want to make it robust against adversarial reward poisoning. The main challenge is that one can no longer compute the actual posteriors for the true reward, as the agent can only observe the rewa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19705","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/2410.19705/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":"2026-07-05T09:26:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aQRh52QLVi8bTZm4HK9hGpwCA9r+ZxNG5O0BecnoudYfAHPtLsFanXadt/9gMK/wuZQSo3wAKpD/MPHFHcp5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:00:46.353775Z"},"content_sha256":"ea0d565ce70d233879beb4b14965800cad81931ef47bcd3e73e53295b8b0119d","schema_version":"1.0","event_id":"sha256:ea0d565ce70d233879beb4b14965800cad81931ef47bcd3e73e53295b8b0119d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X7MKUW2R4ZMPH5K7OVIDNBVYKS/bundle.json","state_url":"https://pith.science/pith/X7MKUW2R4ZMPH5K7OVIDNBVYKS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X7MKUW2R4ZMPH5K7OVIDNBVYKS/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":"2026-08-09T14:00:46Z","links":{"resolver":"https://pith.science/pith/X7MKUW2R4ZMPH5K7OVIDNBVYKS","bundle":"https://pith.science/pith/X7MKUW2R4ZMPH5K7OVIDNBVYKS/bundle.json","state":"https://pith.science/pith/X7MKUW2R4ZMPH5K7OVIDNBVYKS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X7MKUW2R4ZMPH5K7OVIDNBVYKS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X7MKUW2R4ZMPH5K7OVIDNBVYKS","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":"3f547c82e58a087d24216fb2f40dd60f25b25018239a04032b6e957ecd4064fe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T17:27:58Z","title_canon_sha256":"fde928fd98283f4c69964d77daca7f4cc634b6b265638eba8ba494f26c2863c6"},"schema_version":"1.0","source":{"id":"2410.19705","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19705","created_at":"2026-07-05T09:26:00Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19705v1","created_at":"2026-07-05T09:26:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19705","created_at":"2026-07-05T09:26:00Z"},{"alias_kind":"pith_short_12","alias_value":"X7MKUW2R4ZMP","created_at":"2026-07-05T09:26:00Z"},{"alias_kind":"pith_short_16","alias_value":"X7MKUW2R4ZMPH5K7","created_at":"2026-07-05T09:26:00Z"},{"alias_kind":"pith_short_8","alias_value":"X7MKUW2R","created_at":"2026-07-05T09:26:00Z"}],"graph_snapshots":[{"event_id":"sha256:ea0d565ce70d233879beb4b14965800cad81931ef47bcd3e73e53295b8b0119d","target":"graph","created_at":"2026-07-05T09:26:00Z","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/2410.19705/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Thompson sampling is one of the most popular learning algorithms for online sequential decision-making problems and has rich real-world applications. However, current Thompson sampling algorithms are limited by the assumption that the rewards received are uncorrupted, which may not be true in real-world applications where adversarial reward poisoning exists. To make Thompson sampling more reliable, we want to make it robust against adversarial reward poisoning. The main challenge is that one can no longer compute the actual posteriors for the true reward, as the agent can only observe the rewa","authors_text":"Gagandeep Singh, Yinglun Xu, Zhiwei Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T17:27:58Z","title":"Robust Thompson Sampling Algorithms Against Reward Poisoning Attacks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19705","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":"sha256:8be93ff5f5c4ffde36bc320a55c5a7f5e987103ddd87db7e49a2f8e773a04649","target":"record","created_at":"2026-07-05T09:26:00Z","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":"3f547c82e58a087d24216fb2f40dd60f25b25018239a04032b6e957ecd4064fe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T17:27:58Z","title_canon_sha256":"fde928fd98283f4c69964d77daca7f4cc634b6b265638eba8ba494f26c2863c6"},"schema_version":"1.0","source":{"id":"2410.19705","kind":"arxiv","version":1}},"canonical_sha256":"bfd8aa5b51e658f3f55f75503686b8549bc59cd358428eb119febd77834973eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfd8aa5b51e658f3f55f75503686b8549bc59cd358428eb119febd77834973eb","first_computed_at":"2026-07-05T09:26:00.473547Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:26:00.473547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8GdlLMnqoioMaS0KdxOYwqsm+fLBKfvJpO9oAla91of7fXzmtd3ieCN947pHR3Goouw8D8BNrL9JrErVoOzHDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:26:00.474012Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.19705","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8be93ff5f5c4ffde36bc320a55c5a7f5e987103ddd87db7e49a2f8e773a04649","sha256:ea0d565ce70d233879beb4b14965800cad81931ef47bcd3e73e53295b8b0119d"],"state_sha256":"3d0ecba054850b9de7eb913b840f11ada319cee215a71ba1e4f7ff16b79e8639"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dcihq04HH+qon1VCv6mtwL98pTDOaQrz3gRTKVdj8IrnjhFDJTlsyMPyGzDOrHVdxyoVFTSz3w6q8UWyDjCcDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:00:46.357099Z","bundle_sha256":"9b254152444632b7ccc2d15f1ff06b844b98abea927d66088154c0ffc5b4ff51"}}