{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UFJPSCJYBIAQICCLFCRWEMBGCP","short_pith_number":"pith:UFJPSCJY","canonical_record":{"source":{"id":"2403.10738","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T23:50:58Z","cross_cats_sorted":[],"title_canon_sha256":"361fd675c7806050965b22752bc5bf202d50dcfd49042c3e5d82b111826e3d23","abstract_canon_sha256":"ef654a87eba5f4c32e093be5c45163c4f5057d5ac25d4bc71dd94f2daaa2e105"},"schema_version":"1.0"},"canonical_sha256":"a152f909380a0104084b28a362302613df3d3ae80eb0fffb07388c34c2e7067a","source":{"kind":"arxiv","id":"2403.10738","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.10738","created_at":"2026-07-05T07:57:05Z"},{"alias_kind":"arxiv_version","alias_value":"2403.10738v1","created_at":"2026-07-05T07:57:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10738","created_at":"2026-07-05T07:57:05Z"},{"alias_kind":"pith_short_12","alias_value":"UFJPSCJYBIAQ","created_at":"2026-07-05T07:57:05Z"},{"alias_kind":"pith_short_16","alias_value":"UFJPSCJYBIAQICCL","created_at":"2026-07-05T07:57:05Z"},{"alias_kind":"pith_short_8","alias_value":"UFJPSCJY","created_at":"2026-07-05T07:57:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UFJPSCJYBIAQICCLFCRWEMBGCP","target":"record","payload":{"canonical_record":{"source":{"id":"2403.10738","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T23:50:58Z","cross_cats_sorted":[],"title_canon_sha256":"361fd675c7806050965b22752bc5bf202d50dcfd49042c3e5d82b111826e3d23","abstract_canon_sha256":"ef654a87eba5f4c32e093be5c45163c4f5057d5ac25d4bc71dd94f2daaa2e105"},"schema_version":"1.0"},"canonical_sha256":"a152f909380a0104084b28a362302613df3d3ae80eb0fffb07388c34c2e7067a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:05.847189Z","signature_b64":"iuZJBCZKGQJWO+uf6iFiyhFzxW6nfv3cKAH2GBy3MbtdYT0N7Vb/18AINkawtSqsbJ/OKhc7EXqtA70ZFIdCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a152f909380a0104084b28a362302613df3d3ae80eb0fffb07388c34c2e7067a","last_reissued_at":"2026-07-05T07:57:05.846506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:05.846506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.10738","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":"2026-07-05T07:57:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z2P1JMFk3weWh0BCX3+c2wK1mw6oTM2GIPq/XkhCdK1e/SFkvrdnBU1Jn4aV0axW9rulgL12j5SceUcS2FDBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:34:13.362702Z"},"content_sha256":"1235ed1fa71637607440601718c9416449e1450c9df10a162ae9ee5f3d044fc0","schema_version":"1.0","event_id":"sha256:1235ed1fa71637607440601718c9416449e1450c9df10a162ae9ee5f3d044fc0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UFJPSCJYBIAQICCLFCRWEMBGCP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Horizon-Free Regret for Linear Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jason D. Lee, Simon S. Du, Yuxin Chen, Zihan Zhang","submitted_at":"2024-03-15T23:50:58Z","abstract_excerpt":"A recent line of works showed regret bounds in reinforcement learning (RL) can be (nearly) independent of planning horizon, a.k.a.~the horizon-free bounds. However, these regret bounds only apply to settings where a polynomial dependency on the size of transition model is allowed, such as tabular Markov Decision Process (MDP) and linear mixture MDP. We give the first horizon-free bound for the popular linear MDP setting where the size of the transition model can be exponentially large or even uncountable. In contrast to prior works which explicitly estimate the transition model and compute the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10738","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/2403.10738/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":"2026-07-05T07:57:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/oZ5lIZ+Vl8IR/St/VC7Yjfo7R6Xq76kPJJzKbM+Ak9JwNNp6EndvXXb8YAncSSmriUH+H3y4XRErfIpJpHuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:34:13.363624Z"},"content_sha256":"b7abf5a3f1f8fb88b27e664b9df5beb2dad6b5b01f0f76cb68eb6e6f9146d6ad","schema_version":"1.0","event_id":"sha256:b7abf5a3f1f8fb88b27e664b9df5beb2dad6b5b01f0f76cb68eb6e6f9146d6ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UFJPSCJYBIAQICCLFCRWEMBGCP/bundle.json","state_url":"https://pith.science/pith/UFJPSCJYBIAQICCLFCRWEMBGCP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UFJPSCJYBIAQICCLFCRWEMBGCP/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":"2026-08-10T19:34:13Z","links":{"resolver":"https://pith.science/pith/UFJPSCJYBIAQICCLFCRWEMBGCP","bundle":"https://pith.science/pith/UFJPSCJYBIAQICCLFCRWEMBGCP/bundle.json","state":"https://pith.science/pith/UFJPSCJYBIAQICCLFCRWEMBGCP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UFJPSCJYBIAQICCLFCRWEMBGCP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UFJPSCJYBIAQICCLFCRWEMBGCP","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":"ef654a87eba5f4c32e093be5c45163c4f5057d5ac25d4bc71dd94f2daaa2e105","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T23:50:58Z","title_canon_sha256":"361fd675c7806050965b22752bc5bf202d50dcfd49042c3e5d82b111826e3d23"},"schema_version":"1.0","source":{"id":"2403.10738","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.10738","created_at":"2026-07-05T07:57:05Z"},{"alias_kind":"arxiv_version","alias_value":"2403.10738v1","created_at":"2026-07-05T07:57:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10738","created_at":"2026-07-05T07:57:05Z"},{"alias_kind":"pith_short_12","alias_value":"UFJPSCJYBIAQ","created_at":"2026-07-05T07:57:05Z"},{"alias_kind":"pith_short_16","alias_value":"UFJPSCJYBIAQICCL","created_at":"2026-07-05T07:57:05Z"},{"alias_kind":"pith_short_8","alias_value":"UFJPSCJY","created_at":"2026-07-05T07:57:05Z"}],"graph_snapshots":[{"event_id":"sha256:b7abf5a3f1f8fb88b27e664b9df5beb2dad6b5b01f0f76cb68eb6e6f9146d6ad","target":"graph","created_at":"2026-07-05T07:57:05Z","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/2403.10738/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A recent line of works showed regret bounds in reinforcement learning (RL) can be (nearly) independent of planning horizon, a.k.a.~the horizon-free bounds. However, these regret bounds only apply to settings where a polynomial dependency on the size of transition model is allowed, such as tabular Markov Decision Process (MDP) and linear mixture MDP. We give the first horizon-free bound for the popular linear MDP setting where the size of the transition model can be exponentially large or even uncountable. In contrast to prior works which explicitly estimate the transition model and compute the","authors_text":"Jason D. Lee, Simon S. Du, Yuxin Chen, Zihan Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T23:50:58Z","title":"Horizon-Free Regret for Linear Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10738","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":"sha256:1235ed1fa71637607440601718c9416449e1450c9df10a162ae9ee5f3d044fc0","target":"record","created_at":"2026-07-05T07:57:05Z","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":"ef654a87eba5f4c32e093be5c45163c4f5057d5ac25d4bc71dd94f2daaa2e105","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T23:50:58Z","title_canon_sha256":"361fd675c7806050965b22752bc5bf202d50dcfd49042c3e5d82b111826e3d23"},"schema_version":"1.0","source":{"id":"2403.10738","kind":"arxiv","version":1}},"canonical_sha256":"a152f909380a0104084b28a362302613df3d3ae80eb0fffb07388c34c2e7067a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a152f909380a0104084b28a362302613df3d3ae80eb0fffb07388c34c2e7067a","first_computed_at":"2026-07-05T07:57:05.846506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:05.846506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iuZJBCZKGQJWO+uf6iFiyhFzxW6nfv3cKAH2GBy3MbtdYT0N7Vb/18AINkawtSqsbJ/OKhc7EXqtA70ZFIdCDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:05.847189Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.10738","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1235ed1fa71637607440601718c9416449e1450c9df10a162ae9ee5f3d044fc0","sha256:b7abf5a3f1f8fb88b27e664b9df5beb2dad6b5b01f0f76cb68eb6e6f9146d6ad"],"state_sha256":"8fd95fd05eabea9cfd607d35616a25ebfa31dd247159b6d5c9f71117343c2f5f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bQqQc5M/2FmzBiicy1dvFMAJno2bea4Yu4ckWvbVVLFteRr+KtclnziahtASAvNhAUmQnSE3SodpIZGsYZsMDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T19:34:13.371563Z","bundle_sha256":"8f29b8da75ac694e682d48f75911c17a46c42608e372f047984976b2945ec3d5"}}