{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HKZBBPV6C5LHMNLK7I4FW3IFJ5","short_pith_number":"pith:HKZBBPV6","canonical_record":{"source":{"id":"2502.02486","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-04T17:03:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8d529f9cf1573a94bc805ceeaeac51df6a353a6d865e86b107b45a1722475597","abstract_canon_sha256":"08ce262d52f4108f6113bb415bb7abe51d1b8771b0dabcfee301d38a5f37f98c"},"schema_version":"1.0"},"canonical_sha256":"3ab210bebe175676356afa385b6d054f4b9a0f9c2c8e0936585a01794314d659","source":{"kind":"arxiv","id":"2502.02486","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02486","created_at":"2026-07-05T10:09:29Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02486v1","created_at":"2026-07-05T10:09:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02486","created_at":"2026-07-05T10:09:29Z"},{"alias_kind":"pith_short_12","alias_value":"HKZBBPV6C5LH","created_at":"2026-07-05T10:09:29Z"},{"alias_kind":"pith_short_16","alias_value":"HKZBBPV6C5LHMNLK","created_at":"2026-07-05T10:09:29Z"},{"alias_kind":"pith_short_8","alias_value":"HKZBBPV6","created_at":"2026-07-05T10:09:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HKZBBPV6C5LHMNLK7I4FW3IFJ5","target":"record","payload":{"canonical_record":{"source":{"id":"2502.02486","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-04T17:03:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8d529f9cf1573a94bc805ceeaeac51df6a353a6d865e86b107b45a1722475597","abstract_canon_sha256":"08ce262d52f4108f6113bb415bb7abe51d1b8771b0dabcfee301d38a5f37f98c"},"schema_version":"1.0"},"canonical_sha256":"3ab210bebe175676356afa385b6d054f4b9a0f9c2c8e0936585a01794314d659","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:29.305437Z","signature_b64":"jNJivlFP0PUmDfyC4i0TIXcORnFbSIlLFbPd0hgc2DM30XkjFsavsmpaTcfLek+W9QfkWMaeIazwVTXnyJstDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ab210bebe175676356afa385b6d054f4b9a0f9c2c8e0936585a01794314d659","last_reissued_at":"2026-07-05T10:09:29.304985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:29.304985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.02486","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":"2026-07-05T10:09:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0u+gewXc7EVFofnfh+m++Xzjdib52LzQaKiIdju6150+1J6SNbAR60Nzwx+njchrGjRVjxAIDrqEMTzBFD3pAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:37:29.850243Z"},"content_sha256":"53d35b2025c1a3504541336306ddf564c3ad43f5b04f9806b28eb7073bebaeb2","schema_version":"1.0","event_id":"sha256:53d35b2025c1a3504541336306ddf564c3ad43f5b04f9806b28eb7073bebaeb2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HKZBBPV6C5LHMNLK7I4FW3IFJ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Catoni Contextual Bandits are Robust to Heavy-tailed Rewards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alekh Agarwal, Chenlu Ye, Tong Zhang, Yujia Jin","submitted_at":"2025-02-04T17:03:32Z","abstract_excerpt":"Typical contextual bandit algorithms assume that the rewards at each round lie in some fixed range $[0, R]$, and their regret scales polynomially with this reward range $R$. However, many practical scenarios naturally involve heavy-tailed rewards or rewards where the worst-case range can be substantially larger than the variance. In this paper, we develop an algorithmic approach building on Catoni's estimator from robust statistics, and apply it to contextual bandits with general function approximation. When the variance of the reward at each round is known, we use a variance-weighted regressi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02486","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/2502.02486/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":"2026-07-05T10:09:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JnIqv5cDafMDFmb6mpP2tLGwMkPdD8+NMqPV/DfzNtXJESfKq3RhAGAMW32rDOwpWUkKwdVFoNn3DZnp8oAqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:37:29.850756Z"},"content_sha256":"27b510a74a396a311c4bd1f6bcff3ef1719b36ccaaa4b5c5cdb1439b1e525199","schema_version":"1.0","event_id":"sha256:27b510a74a396a311c4bd1f6bcff3ef1719b36ccaaa4b5c5cdb1439b1e525199"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HKZBBPV6C5LHMNLK7I4FW3IFJ5/bundle.json","state_url":"https://pith.science/pith/HKZBBPV6C5LHMNLK7I4FW3IFJ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HKZBBPV6C5LHMNLK7I4FW3IFJ5/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":"2026-08-10T05:37:29Z","links":{"resolver":"https://pith.science/pith/HKZBBPV6C5LHMNLK7I4FW3IFJ5","bundle":"https://pith.science/pith/HKZBBPV6C5LHMNLK7I4FW3IFJ5/bundle.json","state":"https://pith.science/pith/HKZBBPV6C5LHMNLK7I4FW3IFJ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HKZBBPV6C5LHMNLK7I4FW3IFJ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HKZBBPV6C5LHMNLK7I4FW3IFJ5","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":"08ce262d52f4108f6113bb415bb7abe51d1b8771b0dabcfee301d38a5f37f98c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-04T17:03:32Z","title_canon_sha256":"8d529f9cf1573a94bc805ceeaeac51df6a353a6d865e86b107b45a1722475597"},"schema_version":"1.0","source":{"id":"2502.02486","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02486","created_at":"2026-07-05T10:09:29Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02486v1","created_at":"2026-07-05T10:09:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02486","created_at":"2026-07-05T10:09:29Z"},{"alias_kind":"pith_short_12","alias_value":"HKZBBPV6C5LH","created_at":"2026-07-05T10:09:29Z"},{"alias_kind":"pith_short_16","alias_value":"HKZBBPV6C5LHMNLK","created_at":"2026-07-05T10:09:29Z"},{"alias_kind":"pith_short_8","alias_value":"HKZBBPV6","created_at":"2026-07-05T10:09:29Z"}],"graph_snapshots":[{"event_id":"sha256:27b510a74a396a311c4bd1f6bcff3ef1719b36ccaaa4b5c5cdb1439b1e525199","target":"graph","created_at":"2026-07-05T10:09:29Z","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/2502.02486/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Typical contextual bandit algorithms assume that the rewards at each round lie in some fixed range $[0, R]$, and their regret scales polynomially with this reward range $R$. However, many practical scenarios naturally involve heavy-tailed rewards or rewards where the worst-case range can be substantially larger than the variance. In this paper, we develop an algorithmic approach building on Catoni's estimator from robust statistics, and apply it to contextual bandits with general function approximation. When the variance of the reward at each round is known, we use a variance-weighted regressi","authors_text":"Alekh Agarwal, Chenlu Ye, Tong Zhang, Yujia Jin","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-04T17:03:32Z","title":"Catoni Contextual Bandits are Robust to Heavy-tailed Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02486","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":"sha256:53d35b2025c1a3504541336306ddf564c3ad43f5b04f9806b28eb7073bebaeb2","target":"record","created_at":"2026-07-05T10:09:29Z","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":"08ce262d52f4108f6113bb415bb7abe51d1b8771b0dabcfee301d38a5f37f98c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-04T17:03:32Z","title_canon_sha256":"8d529f9cf1573a94bc805ceeaeac51df6a353a6d865e86b107b45a1722475597"},"schema_version":"1.0","source":{"id":"2502.02486","kind":"arxiv","version":1}},"canonical_sha256":"3ab210bebe175676356afa385b6d054f4b9a0f9c2c8e0936585a01794314d659","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ab210bebe175676356afa385b6d054f4b9a0f9c2c8e0936585a01794314d659","first_computed_at":"2026-07-05T10:09:29.304985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:29.304985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jNJivlFP0PUmDfyC4i0TIXcORnFbSIlLFbPd0hgc2DM30XkjFsavsmpaTcfLek+W9QfkWMaeIazwVTXnyJstDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:29.305437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02486","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53d35b2025c1a3504541336306ddf564c3ad43f5b04f9806b28eb7073bebaeb2","sha256:27b510a74a396a311c4bd1f6bcff3ef1719b36ccaaa4b5c5cdb1439b1e525199"],"state_sha256":"c120c7c67f3b2779697a25d2b1fbaacfd877eefe4715d08a8a7a7125925e2eed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eu6rA9rS8/XXC2Sw8z8I0bSb7RSU7lCNd5oetYCGi0+ucXyuKuu+fj7X2Ks7AFVyabXb6Pc1On0BBEoXm5etAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T05:37:29.854894Z","bundle_sha256":"72219c52a8afbe998c3dc99fb76e524f1e04fa60181ec7775c381e8a2995f9b6"}}