{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IJKP4FFB3EMTB6LWXPBXIYVRF5","short_pith_number":"pith:IJKP4FFB","canonical_record":{"source":{"id":"2605.20592","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T00:58:07Z","cross_cats_sorted":[],"title_canon_sha256":"fe94470218da3ea2163c0ec7b2b202e2993ed60c8fe8a9244d93655d95bc0afa","abstract_canon_sha256":"ea10a70a8432052644522787a8a9b79e234b2c3da316771f6e60d0f8bcca46fe"},"schema_version":"1.0"},"canonical_sha256":"4254fe14a1d91930f976bbc37462b12f47b3c96b43c4644fefb3d882ef3366d3","source":{"kind":"arxiv","id":"2605.20592","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20592","created_at":"2026-05-21T01:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20592v1","created_at":"2026-05-21T01:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20592","created_at":"2026-05-21T01:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"IJKP4FFB3EMT","created_at":"2026-05-21T01:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"IJKP4FFB3EMTB6LW","created_at":"2026-05-21T01:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"IJKP4FFB","created_at":"2026-05-21T01:04:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IJKP4FFB3EMTB6LWXPBXIYVRF5","target":"record","payload":{"canonical_record":{"source":{"id":"2605.20592","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T00:58:07Z","cross_cats_sorted":[],"title_canon_sha256":"fe94470218da3ea2163c0ec7b2b202e2993ed60c8fe8a9244d93655d95bc0afa","abstract_canon_sha256":"ea10a70a8432052644522787a8a9b79e234b2c3da316771f6e60d0f8bcca46fe"},"schema_version":"1.0"},"canonical_sha256":"4254fe14a1d91930f976bbc37462b12f47b3c96b43c4644fefb3d882ef3366d3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:43.812780Z","signature_b64":"LRocbRRfqTiTbFcF6Nd35Y5o8XuuCP8kxzHgvJjZE/FQg/nG5MVY+75c+6r3lZwhtms+OZrQcMm9y0Vu2bhRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4254fe14a1d91930f976bbc37462b12f47b3c96b43c4644fefb3d882ef3366d3","last_reissued_at":"2026-05-21T01:04:43.812245Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:43.812245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.20592","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":"2026-05-21T01:04:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+3FM3GK8HNAFW4ozA8sUPBnHkdSXzQF/hJ+nWl1bziAi6ItOFO1AWpaXLfmVqGzhXp/rRsPRcN7z//Lq8JTnDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:45:52.089332Z"},"content_sha256":"eeac728b63a3b6fa125e9f88521ee5ec416fc9dc5c14c897860d551a42dac0cb","schema_version":"1.0","event_id":"sha256:eeac728b63a3b6fa125e9f88521ee5ec416fc9dc5c14c897860d551a42dac0cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IJKP4FFB3EMTB6LWXPBXIYVRF5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ReversedQ: Opportunities for Faster Q-Learning in Episodic Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aviva Prins, Sofia R. Miskala-Dinc","submitted_at":"2026-05-20T00:58:07Z","abstract_excerpt":"We study model-free Q-learning in finite-horizon episodic Markov Decision Processes (MDPs) with stationary dynamics across episodes. We identify a central issue in nascent model-free posterior-sampling works: the reliance on delayed learning in order to prove theoretical guarantees. In particular, we identify three opportunities for faster learning - (i) value-function update order, (ii) update frequencies, and (iii) value-function initialization. Using Wang et al.'s RandomizedQ as a basis, we illustrate these changes and their individual (as well as cumulative) impact in multiple empirical st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20592","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/2605.20592/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":"2026-05-21T01:04:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HwTnRvt9R/ov0F/t+SSPMJ0r0SxXA+OdUq/7/JoSGtXO65qhBByVhTXhbU8ZMmrUAbmupdKwiD8PhoJWPvatDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:45:52.090031Z"},"content_sha256":"6491690e4584e1f12557cf6fbe01ca6518a53779fd0f48e497678f07be90a311","schema_version":"1.0","event_id":"sha256:6491690e4584e1f12557cf6fbe01ca6518a53779fd0f48e497678f07be90a311"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IJKP4FFB3EMTB6LWXPBXIYVRF5/bundle.json","state_url":"https://pith.science/pith/IJKP4FFB3EMTB6LWXPBXIYVRF5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IJKP4FFB3EMTB6LWXPBXIYVRF5/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":"2026-05-26T10:45:52Z","links":{"resolver":"https://pith.science/pith/IJKP4FFB3EMTB6LWXPBXIYVRF5","bundle":"https://pith.science/pith/IJKP4FFB3EMTB6LWXPBXIYVRF5/bundle.json","state":"https://pith.science/pith/IJKP4FFB3EMTB6LWXPBXIYVRF5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IJKP4FFB3EMTB6LWXPBXIYVRF5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IJKP4FFB3EMTB6LWXPBXIYVRF5","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":"ea10a70a8432052644522787a8a9b79e234b2c3da316771f6e60d0f8bcca46fe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T00:58:07Z","title_canon_sha256":"fe94470218da3ea2163c0ec7b2b202e2993ed60c8fe8a9244d93655d95bc0afa"},"schema_version":"1.0","source":{"id":"2605.20592","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20592","created_at":"2026-05-21T01:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20592v1","created_at":"2026-05-21T01:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20592","created_at":"2026-05-21T01:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"IJKP4FFB3EMT","created_at":"2026-05-21T01:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"IJKP4FFB3EMTB6LW","created_at":"2026-05-21T01:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"IJKP4FFB","created_at":"2026-05-21T01:04:43Z"}],"graph_snapshots":[{"event_id":"sha256:6491690e4584e1f12557cf6fbe01ca6518a53779fd0f48e497678f07be90a311","target":"graph","created_at":"2026-05-21T01:04:43Z","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/2605.20592/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study model-free Q-learning in finite-horizon episodic Markov Decision Processes (MDPs) with stationary dynamics across episodes. We identify a central issue in nascent model-free posterior-sampling works: the reliance on delayed learning in order to prove theoretical guarantees. In particular, we identify three opportunities for faster learning - (i) value-function update order, (ii) update frequencies, and (iii) value-function initialization. Using Wang et al.'s RandomizedQ as a basis, we illustrate these changes and their individual (as well as cumulative) impact in multiple empirical st","authors_text":"Aviva Prins, Sofia R. Miskala-Dinc","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T00:58:07Z","title":"ReversedQ: Opportunities for Faster Q-Learning in Episodic Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20592","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:eeac728b63a3b6fa125e9f88521ee5ec416fc9dc5c14c897860d551a42dac0cb","target":"record","created_at":"2026-05-21T01:04:43Z","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":"ea10a70a8432052644522787a8a9b79e234b2c3da316771f6e60d0f8bcca46fe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T00:58:07Z","title_canon_sha256":"fe94470218da3ea2163c0ec7b2b202e2993ed60c8fe8a9244d93655d95bc0afa"},"schema_version":"1.0","source":{"id":"2605.20592","kind":"arxiv","version":1}},"canonical_sha256":"4254fe14a1d91930f976bbc37462b12f47b3c96b43c4644fefb3d882ef3366d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4254fe14a1d91930f976bbc37462b12f47b3c96b43c4644fefb3d882ef3366d3","first_computed_at":"2026-05-21T01:04:43.812245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:43.812245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LRocbRRfqTiTbFcF6Nd35Y5o8XuuCP8kxzHgvJjZE/FQg/nG5MVY+75c+6r3lZwhtms+OZrQcMm9y0Vu2bhRBw==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:43.812780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20592","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeac728b63a3b6fa125e9f88521ee5ec416fc9dc5c14c897860d551a42dac0cb","sha256:6491690e4584e1f12557cf6fbe01ca6518a53779fd0f48e497678f07be90a311"],"state_sha256":"d4451fd6a0527a45321847e5b5f7f8278220bd21195bfab5c312284804dee2b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CMOm/81HM6eG5QewML58+v773iW791KtAjpwSOaJYYxalvMO5IfGIrutHRq5PQPcOAc9z7/y9K9NFWjzsAWuAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T10:45:52.093615Z","bundle_sha256":"3aa57726a45c72296b6a11045c5785aaef6cf482722ac35e93d16758f304d1ad"}}