{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QZLGQW7BXOQGYHHGUVKRVPZLVD","short_pith_number":"pith:QZLGQW7B","canonical_record":{"source":{"id":"2402.12711","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T04:21:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3c2728d899036c043e05aaeaf2d5db6afc1b21b2793695c2160c55ebdc00fa56","abstract_canon_sha256":"3e70484c1ce26a96a0099953c7f88e80e914a0cd1651448808940543b60a0e45"},"schema_version":"1.0"},"canonical_sha256":"8656685be1bba06c1ce6a5551abf2ba8f579441d7d930549446a62cc2a854189","source":{"kind":"arxiv","id":"2402.12711","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12711","created_at":"2026-07-05T09:28:48Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12711v2","created_at":"2026-07-05T09:28:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12711","created_at":"2026-07-05T09:28:48Z"},{"alias_kind":"pith_short_12","alias_value":"QZLGQW7BXOQG","created_at":"2026-07-05T09:28:48Z"},{"alias_kind":"pith_short_16","alias_value":"QZLGQW7BXOQGYHHG","created_at":"2026-07-05T09:28:48Z"},{"alias_kind":"pith_short_8","alias_value":"QZLGQW7B","created_at":"2026-07-05T09:28:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QZLGQW7BXOQGYHHGUVKRVPZLVD","target":"record","payload":{"canonical_record":{"source":{"id":"2402.12711","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T04:21:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3c2728d899036c043e05aaeaf2d5db6afc1b21b2793695c2160c55ebdc00fa56","abstract_canon_sha256":"3e70484c1ce26a96a0099953c7f88e80e914a0cd1651448808940543b60a0e45"},"schema_version":"1.0"},"canonical_sha256":"8656685be1bba06c1ce6a5551abf2ba8f579441d7d930549446a62cc2a854189","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:48.094261Z","signature_b64":"+TBEcoSJycMq23Bb47xgKIzig+XqWklaoyXRs9A/dWk9YXNVVx/9nwpTDilYPhChOpDxk93rOwT7h7oMltqhAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8656685be1bba06c1ce6a5551abf2ba8f579441d7d930549446a62cc2a854189","last_reissued_at":"2026-07-05T09:28:48.093809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:48.093809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.12711","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":"2026-07-05T09:28:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DQtodAlp7/F+xxc07wjfr9AeDPpgWkXx1gOXBOvLMfUFXJ4/4qo8Fa7VsBYAdQq8DCMTJoMiRiAx939oaJ09Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T12:47:51.598059Z"},"content_sha256":"de8e1a71a272d8fae8ca3b4501cb5f24f614cdd4ac8fc93b945eaafb41259f38","schema_version":"1.0","event_id":"sha256:de8e1a71a272d8fae8ca3b4501cb5f24f614cdd4ac8fc93b945eaafb41259f38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QZLGQW7BXOQGYHHGUVKRVPZLVD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uniform Last-Iterate Guarantee for Bandits and Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Junyan Liu, Lin F. Yang, Ruosong Wang, Yunfan Li","submitted_at":"2024-02-20T04:21:13Z","abstract_excerpt":"Existing metrics for reinforcement learning (RL) such as regret, PAC bounds, or uniform-PAC (Dann et al., 2017), typically evaluate the cumulative performance, while allowing the agent to play an arbitrarily bad policy at any finite time t. Such a behavior can be highly detrimental in high-stakes applications. This paper introduces a stronger metric, uniform last-iterate (ULI) guarantee, capturing both cumulative and instantaneous performance of RL algorithms. Specifically, ULI characterizes the instantaneous performance by ensuring that the per-round suboptimality of the played policy is boun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12711","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/2402.12711/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":"2026-07-05T09:28:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KZTKNp1UpBOTZAMJjDVf4B4q1Fmvw85MPyIk67xF1Zcxx9KQ2SMub2owQ1XAnVouGZOB4yiT68Y/CufLStugDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T12:47:51.598616Z"},"content_sha256":"5c98f4698c2248a9d0bd83d96a8cac553b362977538f99347483ea31e7f5545d","schema_version":"1.0","event_id":"sha256:5c98f4698c2248a9d0bd83d96a8cac553b362977538f99347483ea31e7f5545d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QZLGQW7BXOQGYHHGUVKRVPZLVD/bundle.json","state_url":"https://pith.science/pith/QZLGQW7BXOQGYHHGUVKRVPZLVD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QZLGQW7BXOQGYHHGUVKRVPZLVD/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":"2026-08-23T12:47:51Z","links":{"resolver":"https://pith.science/pith/QZLGQW7BXOQGYHHGUVKRVPZLVD","bundle":"https://pith.science/pith/QZLGQW7BXOQGYHHGUVKRVPZLVD/bundle.json","state":"https://pith.science/pith/QZLGQW7BXOQGYHHGUVKRVPZLVD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QZLGQW7BXOQGYHHGUVKRVPZLVD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QZLGQW7BXOQGYHHGUVKRVPZLVD","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":"3e70484c1ce26a96a0099953c7f88e80e914a0cd1651448808940543b60a0e45","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T04:21:13Z","title_canon_sha256":"3c2728d899036c043e05aaeaf2d5db6afc1b21b2793695c2160c55ebdc00fa56"},"schema_version":"1.0","source":{"id":"2402.12711","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12711","created_at":"2026-07-05T09:28:48Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12711v2","created_at":"2026-07-05T09:28:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12711","created_at":"2026-07-05T09:28:48Z"},{"alias_kind":"pith_short_12","alias_value":"QZLGQW7BXOQG","created_at":"2026-07-05T09:28:48Z"},{"alias_kind":"pith_short_16","alias_value":"QZLGQW7BXOQGYHHG","created_at":"2026-07-05T09:28:48Z"},{"alias_kind":"pith_short_8","alias_value":"QZLGQW7B","created_at":"2026-07-05T09:28:48Z"}],"graph_snapshots":[{"event_id":"sha256:5c98f4698c2248a9d0bd83d96a8cac553b362977538f99347483ea31e7f5545d","target":"graph","created_at":"2026-07-05T09:28:48Z","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/2402.12711/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing metrics for reinforcement learning (RL) such as regret, PAC bounds, or uniform-PAC (Dann et al., 2017), typically evaluate the cumulative performance, while allowing the agent to play an arbitrarily bad policy at any finite time t. Such a behavior can be highly detrimental in high-stakes applications. This paper introduces a stronger metric, uniform last-iterate (ULI) guarantee, capturing both cumulative and instantaneous performance of RL algorithms. Specifically, ULI characterizes the instantaneous performance by ensuring that the per-round suboptimality of the played policy is boun","authors_text":"Junyan Liu, Lin F. Yang, Ruosong Wang, Yunfan Li","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T04:21:13Z","title":"Uniform Last-Iterate Guarantee for Bandits and Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12711","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:de8e1a71a272d8fae8ca3b4501cb5f24f614cdd4ac8fc93b945eaafb41259f38","target":"record","created_at":"2026-07-05T09:28:48Z","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":"3e70484c1ce26a96a0099953c7f88e80e914a0cd1651448808940543b60a0e45","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T04:21:13Z","title_canon_sha256":"3c2728d899036c043e05aaeaf2d5db6afc1b21b2793695c2160c55ebdc00fa56"},"schema_version":"1.0","source":{"id":"2402.12711","kind":"arxiv","version":2}},"canonical_sha256":"8656685be1bba06c1ce6a5551abf2ba8f579441d7d930549446a62cc2a854189","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8656685be1bba06c1ce6a5551abf2ba8f579441d7d930549446a62cc2a854189","first_computed_at":"2026-07-05T09:28:48.093809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:48.093809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+TBEcoSJycMq23Bb47xgKIzig+XqWklaoyXRs9A/dWk9YXNVVx/9nwpTDilYPhChOpDxk93rOwT7h7oMltqhAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:48.094261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12711","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de8e1a71a272d8fae8ca3b4501cb5f24f614cdd4ac8fc93b945eaafb41259f38","sha256:5c98f4698c2248a9d0bd83d96a8cac553b362977538f99347483ea31e7f5545d"],"state_sha256":"f7ca02af3fc9af0ed351371ad113e1758d2b1670cd5e6c4c7abb05c4b503d7b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pfnj1XkX32tdxSerLfkcqpqbryd+QYZ73OEbEpkMk9fZu/z9P0OOkKROnObLvR/q9Go6lyukDJA1kaizXOJXAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T12:47:51.603032Z","bundle_sha256":"696cc11e71fa588eabf0cacd42726f43255c313f68044610a5fe98ea1e886236"}}