{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:P6BIDAS3XZTXJSP656QH75GHE4","short_pith_number":"pith:P6BIDAS3","canonical_record":{"source":{"id":"2103.14077","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-03-25T18:52:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2560e7755b1794276a8f586fa3bd9e868d04e683b6b836705b683fb6ff35888d","abstract_canon_sha256":"c56b0bb340cc383de3741e28020c2125f93cfe2aae58103746c687d4dd860043"},"schema_version":"1.0"},"canonical_sha256":"7f8281825bbe6774c9feefa07ff4c72717326805de8d72d6639c18aba1545308","source":{"kind":"arxiv","id":"2103.14077","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.14077","created_at":"2026-07-05T03:55:47Z"},{"alias_kind":"arxiv_version","alias_value":"2103.14077v3","created_at":"2026-07-05T03:55:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14077","created_at":"2026-07-05T03:55:47Z"},{"alias_kind":"pith_short_12","alias_value":"P6BIDAS3XZTX","created_at":"2026-07-05T03:55:47Z"},{"alias_kind":"pith_short_16","alias_value":"P6BIDAS3XZTXJSP6","created_at":"2026-07-05T03:55:47Z"},{"alias_kind":"pith_short_8","alias_value":"P6BIDAS3","created_at":"2026-07-05T03:55:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:P6BIDAS3XZTXJSP656QH75GHE4","target":"record","payload":{"canonical_record":{"source":{"id":"2103.14077","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-03-25T18:52:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2560e7755b1794276a8f586fa3bd9e868d04e683b6b836705b683fb6ff35888d","abstract_canon_sha256":"c56b0bb340cc383de3741e28020c2125f93cfe2aae58103746c687d4dd860043"},"schema_version":"1.0"},"canonical_sha256":"7f8281825bbe6774c9feefa07ff4c72717326805de8d72d6639c18aba1545308","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:55:47.290453Z","signature_b64":"BPbHnaNILrz2FcpekXBWFrd4NOemQiwEqcQERCsWzrXjTJ3Dv9CtfDRkOMSziEsLbeHNYe9eRmdt4Sd5cjsfAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f8281825bbe6774c9feefa07ff4c72717326805de8d72d6639c18aba1545308","last_reissued_at":"2026-07-05T03:55:47.289859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:55:47.289859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.14077","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:55:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2IwI5QO0DJjl0nLVGwZ1tKkzchqrXShawKIR8RDiKwEj9ulpFGSem5oD9jZw4kEvi9xIBgBzvyNkPE/d70gMAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T20:56:55.891931Z"},"content_sha256":"b09804f81348dc9a6e25bff7c67eb01558c142c13c5147bf3d322b201a557685","schema_version":"1.0","event_id":"sha256:b09804f81348dc9a6e25bff7c67eb01558c142c13c5147bf3d322b201a557685"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:P6BIDAS3XZTXJSP656QH75GHE4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nearly Horizon-Free Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bo Dai, Jialian Li, Simon S. Du, Sujay Sanghavi, Tongzheng Ren","submitted_at":"2021-03-25T18:52:17Z","abstract_excerpt":"We revisit offline reinforcement learning on episodic time-homogeneous Markov Decision Processes (MDP). For tabular MDP with $S$ states and $A$ actions, or linear MDP with anchor points and feature dimension $d$, given the collected $K$ episodes data with minimum visiting probability of (anchor) state-action pairs $d_m$, we obtain nearly horizon $H$-free sample complexity bounds for offline reinforcement learning when the total reward is upper bounded by $1$. Specifically: 1. For offline policy evaluation, we obtain an $\\tilde{O}\\left(\\sqrt{\\frac{1}{Kd_m}} \\right)$ error bound for the plug-in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14077","kind":"arxiv","version":3},"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/2103.14077/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":"2026-07-05T03:55:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gVHGdt1EoP6f+cdaftmf197VieWIcifc+2U7vNhwAy+5vlQRLnnjw8y+77/26+5QM44YArOk52l+nr32B2lSDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T20:56:55.892332Z"},"content_sha256":"aa9177d2a5201b16c098cfcc373313f71c0491631ef8103a61b4f2d660bafef8","schema_version":"1.0","event_id":"sha256:aa9177d2a5201b16c098cfcc373313f71c0491631ef8103a61b4f2d660bafef8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P6BIDAS3XZTXJSP656QH75GHE4/bundle.json","state_url":"https://pith.science/pith/P6BIDAS3XZTXJSP656QH75GHE4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P6BIDAS3XZTXJSP656QH75GHE4/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":"2026-07-10T20:56:55Z","links":{"resolver":"https://pith.science/pith/P6BIDAS3XZTXJSP656QH75GHE4","bundle":"https://pith.science/pith/P6BIDAS3XZTXJSP656QH75GHE4/bundle.json","state":"https://pith.science/pith/P6BIDAS3XZTXJSP656QH75GHE4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P6BIDAS3XZTXJSP656QH75GHE4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:P6BIDAS3XZTXJSP656QH75GHE4","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":"c56b0bb340cc383de3741e28020c2125f93cfe2aae58103746c687d4dd860043","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-03-25T18:52:17Z","title_canon_sha256":"2560e7755b1794276a8f586fa3bd9e868d04e683b6b836705b683fb6ff35888d"},"schema_version":"1.0","source":{"id":"2103.14077","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.14077","created_at":"2026-07-05T03:55:47Z"},{"alias_kind":"arxiv_version","alias_value":"2103.14077v3","created_at":"2026-07-05T03:55:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14077","created_at":"2026-07-05T03:55:47Z"},{"alias_kind":"pith_short_12","alias_value":"P6BIDAS3XZTX","created_at":"2026-07-05T03:55:47Z"},{"alias_kind":"pith_short_16","alias_value":"P6BIDAS3XZTXJSP6","created_at":"2026-07-05T03:55:47Z"},{"alias_kind":"pith_short_8","alias_value":"P6BIDAS3","created_at":"2026-07-05T03:55:47Z"}],"graph_snapshots":[{"event_id":"sha256:aa9177d2a5201b16c098cfcc373313f71c0491631ef8103a61b4f2d660bafef8","target":"graph","created_at":"2026-07-05T03:55:47Z","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/2103.14077/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We revisit offline reinforcement learning on episodic time-homogeneous Markov Decision Processes (MDP). For tabular MDP with $S$ states and $A$ actions, or linear MDP with anchor points and feature dimension $d$, given the collected $K$ episodes data with minimum visiting probability of (anchor) state-action pairs $d_m$, we obtain nearly horizon $H$-free sample complexity bounds for offline reinforcement learning when the total reward is upper bounded by $1$. Specifically: 1. For offline policy evaluation, we obtain an $\\tilde{O}\\left(\\sqrt{\\frac{1}{Kd_m}} \\right)$ error bound for the plug-in ","authors_text":"Bo Dai, Jialian Li, Simon S. Du, Sujay Sanghavi, Tongzheng Ren","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-03-25T18:52:17Z","title":"Nearly Horizon-Free Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14077","kind":"arxiv","version":3},"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:b09804f81348dc9a6e25bff7c67eb01558c142c13c5147bf3d322b201a557685","target":"record","created_at":"2026-07-05T03:55:47Z","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":"c56b0bb340cc383de3741e28020c2125f93cfe2aae58103746c687d4dd860043","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-03-25T18:52:17Z","title_canon_sha256":"2560e7755b1794276a8f586fa3bd9e868d04e683b6b836705b683fb6ff35888d"},"schema_version":"1.0","source":{"id":"2103.14077","kind":"arxiv","version":3}},"canonical_sha256":"7f8281825bbe6774c9feefa07ff4c72717326805de8d72d6639c18aba1545308","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f8281825bbe6774c9feefa07ff4c72717326805de8d72d6639c18aba1545308","first_computed_at":"2026-07-05T03:55:47.289859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:55:47.289859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BPbHnaNILrz2FcpekXBWFrd4NOemQiwEqcQERCsWzrXjTJ3Dv9CtfDRkOMSziEsLbeHNYe9eRmdt4Sd5cjsfAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:55:47.290453Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.14077","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b09804f81348dc9a6e25bff7c67eb01558c142c13c5147bf3d322b201a557685","sha256:aa9177d2a5201b16c098cfcc373313f71c0491631ef8103a61b4f2d660bafef8"],"state_sha256":"3851d711ba087186ee20b475638b051b341c41530db17e3abb3dab87a3bed5e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IyIuhAUFpMMpW7ZBAO+zMKlMD8qz94TAVcQHkQ6akVZc2XWqhABIzXodkTLIdDtfCvl19/SeWY3KgQJPGTnyBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T20:56:55.894306Z","bundle_sha256":"f06bf67e7af39d479b7fc455128d05515f371dfcc08cc4de5c51e813f5c79157"}}