{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VSOARE5SK7EU5ACXM6CRVCIKO7","short_pith_number":"pith:VSOARE5S","canonical_record":{"source":{"id":"2502.04004","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T12:03:24Z","cross_cats_sorted":[],"title_canon_sha256":"7f93610db00e3bc0ecf344d9860494238ca19feaf858a754223486891650e650","abstract_canon_sha256":"bb73de204d7283f89b3920599992f26712a1cabc8cd65f970513b01da4782916"},"schema_version":"1.0"},"canonical_sha256":"ac9c0893b257c94e805767851a890a77da3d69110079e823dbd2c235d0e57839","source":{"kind":"arxiv","id":"2502.04004","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04004","created_at":"2026-07-05T10:10:32Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04004v1","created_at":"2026-07-05T10:10:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04004","created_at":"2026-07-05T10:10:32Z"},{"alias_kind":"pith_short_12","alias_value":"VSOARE5SK7EU","created_at":"2026-07-05T10:10:32Z"},{"alias_kind":"pith_short_16","alias_value":"VSOARE5SK7EU5ACX","created_at":"2026-07-05T10:10:32Z"},{"alias_kind":"pith_short_8","alias_value":"VSOARE5S","created_at":"2026-07-05T10:10:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VSOARE5SK7EU5ACXM6CRVCIKO7","target":"record","payload":{"canonical_record":{"source":{"id":"2502.04004","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T12:03:24Z","cross_cats_sorted":[],"title_canon_sha256":"7f93610db00e3bc0ecf344d9860494238ca19feaf858a754223486891650e650","abstract_canon_sha256":"bb73de204d7283f89b3920599992f26712a1cabc8cd65f970513b01da4782916"},"schema_version":"1.0"},"canonical_sha256":"ac9c0893b257c94e805767851a890a77da3d69110079e823dbd2c235d0e57839","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:32.715720Z","signature_b64":"oDT5evgEPmFzToQV0ZXOwpIJNEgf+8MAwAmsiV9f6MU0rL8f1+lGoB2cwC1jUr4NRygpGWNpBlx6mzZYtPxLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac9c0893b257c94e805767851a890a77da3d69110079e823dbd2c235d0e57839","last_reissued_at":"2026-07-05T10:10:32.715238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:32.715238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.04004","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":"2026-07-05T10:10:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"snrRd09ZADCTRJNXqGZ8Du23QHKmgpvoKIiD1gm5Fe4i9l8PUTHmyAA7q3WGHLahGIXy04cY3FQXaERLt1ubCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T00:52:24.111897Z"},"content_sha256":"36b22e3553b0aecc68e2875302bac336ef84ce0cc3092d1f2492ebdae5999702","schema_version":"1.0","event_id":"sha256:36b22e3553b0aecc68e2875302bac336ef84ce0cc3092d1f2492ebdae5999702"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VSOARE5SK7EU5ACXM6CRVCIKO7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Tal Lancewicki, Yishay Mansour","submitted_at":"2025-02-06T12:03:24Z","abstract_excerpt":"We study online finite-horizon Markov Decision Processes with adversarially changing loss and aggregate bandit feedback (a.k.a full-bandit). Under this type of feedback, the agent observes only the total loss incurred over the entire trajectory, rather than the individual losses at each intermediate step within the trajectory. We introduce the first Policy Optimization algorithms for this setting. In the known-dynamics case, we achieve the first \\textit{optimal} regret bound of $\\tilde \\Theta(H^2\\sqrt{SAK})$, where $K$ is the number of episodes, $H$ is the episode horizon, $S$ is the number of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04004","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/2502.04004/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":"2026-07-05T10:10:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XfNSYDOLG7AkHIEEJ/hwHOSURFNWgrBGm4u90DttdBEgmZVmpZ3aMwdq0eWHR6MZRocrKr5kaNnODHefckqdBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T00:52:24.112526Z"},"content_sha256":"32cf20891deaf03899b7edfb95f3c5921c4e1af66106ece7854c9aa461989e01","schema_version":"1.0","event_id":"sha256:32cf20891deaf03899b7edfb95f3c5921c4e1af66106ece7854c9aa461989e01"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VSOARE5SK7EU5ACXM6CRVCIKO7/bundle.json","state_url":"https://pith.science/pith/VSOARE5SK7EU5ACXM6CRVCIKO7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VSOARE5SK7EU5ACXM6CRVCIKO7/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":"2026-07-07T00:52:24Z","links":{"resolver":"https://pith.science/pith/VSOARE5SK7EU5ACXM6CRVCIKO7","bundle":"https://pith.science/pith/VSOARE5SK7EU5ACXM6CRVCIKO7/bundle.json","state":"https://pith.science/pith/VSOARE5SK7EU5ACXM6CRVCIKO7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VSOARE5SK7EU5ACXM6CRVCIKO7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VSOARE5SK7EU5ACXM6CRVCIKO7","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":"bb73de204d7283f89b3920599992f26712a1cabc8cd65f970513b01da4782916","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T12:03:24Z","title_canon_sha256":"7f93610db00e3bc0ecf344d9860494238ca19feaf858a754223486891650e650"},"schema_version":"1.0","source":{"id":"2502.04004","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04004","created_at":"2026-07-05T10:10:32Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04004v1","created_at":"2026-07-05T10:10:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04004","created_at":"2026-07-05T10:10:32Z"},{"alias_kind":"pith_short_12","alias_value":"VSOARE5SK7EU","created_at":"2026-07-05T10:10:32Z"},{"alias_kind":"pith_short_16","alias_value":"VSOARE5SK7EU5ACX","created_at":"2026-07-05T10:10:32Z"},{"alias_kind":"pith_short_8","alias_value":"VSOARE5S","created_at":"2026-07-05T10:10:32Z"}],"graph_snapshots":[{"event_id":"sha256:32cf20891deaf03899b7edfb95f3c5921c4e1af66106ece7854c9aa461989e01","target":"graph","created_at":"2026-07-05T10:10:32Z","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/2502.04004/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study online finite-horizon Markov Decision Processes with adversarially changing loss and aggregate bandit feedback (a.k.a full-bandit). Under this type of feedback, the agent observes only the total loss incurred over the entire trajectory, rather than the individual losses at each intermediate step within the trajectory. We introduce the first Policy Optimization algorithms for this setting. In the known-dynamics case, we achieve the first \\textit{optimal} regret bound of $\\tilde \\Theta(H^2\\sqrt{SAK})$, where $K$ is the number of episodes, $H$ is the episode horizon, $S$ is the number of","authors_text":"Tal Lancewicki, Yishay Mansour","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T12:03:24Z","title":"Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04004","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":"sha256:36b22e3553b0aecc68e2875302bac336ef84ce0cc3092d1f2492ebdae5999702","target":"record","created_at":"2026-07-05T10:10:32Z","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":"bb73de204d7283f89b3920599992f26712a1cabc8cd65f970513b01da4782916","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T12:03:24Z","title_canon_sha256":"7f93610db00e3bc0ecf344d9860494238ca19feaf858a754223486891650e650"},"schema_version":"1.0","source":{"id":"2502.04004","kind":"arxiv","version":1}},"canonical_sha256":"ac9c0893b257c94e805767851a890a77da3d69110079e823dbd2c235d0e57839","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac9c0893b257c94e805767851a890a77da3d69110079e823dbd2c235d0e57839","first_computed_at":"2026-07-05T10:10:32.715238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:32.715238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oDT5evgEPmFzToQV0ZXOwpIJNEgf+8MAwAmsiV9f6MU0rL8f1+lGoB2cwC1jUr4NRygpGWNpBlx6mzZYtPxLAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:32.715720Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04004","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36b22e3553b0aecc68e2875302bac336ef84ce0cc3092d1f2492ebdae5999702","sha256:32cf20891deaf03899b7edfb95f3c5921c4e1af66106ece7854c9aa461989e01"],"state_sha256":"465a12b3125322460aaab7db4e1de100a42dce362a15becf80b5501deb282c18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DTkuoC3n2l1Ib9alwwgIFH6Q2PaCXYzZi8pUlqn4WVrK//d8wydXdlPzylDLaF4F+j4sKPQD4nWhNEPUs8rZAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T00:52:24.115845Z","bundle_sha256":"5834148fe0ae7a82a9dc6906784eac0a422e86c004262a368b735fc8c950b847"}}