{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MO7TX7BR5Y57SURKFIN7VFYR7P","short_pith_number":"pith:MO7TX7BR","canonical_record":{"source":{"id":"2103.12690","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-23T17:05:54Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6469ea0bb39e56cf4ea8c09eb5a185c22411ebed548d7441e8270e7cf34c6f50","abstract_canon_sha256":"d477d560b448ba844397d783c2ec0b2c8bc3687a3fb0261dfe8da428a9c25c57"},"schema_version":"1.0"},"canonical_sha256":"63bf3bfc31ee3bf9522a2a1bfa9711fbecd2c3934e764b81a7f1917109fc7f88","source":{"kind":"arxiv","id":"2103.12690","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12690","created_at":"2026-07-05T03:24:09Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12690v2","created_at":"2026-07-05T03:24:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12690","created_at":"2026-07-05T03:24:09Z"},{"alias_kind":"pith_short_12","alias_value":"MO7TX7BR5Y57","created_at":"2026-07-05T03:24:09Z"},{"alias_kind":"pith_short_16","alias_value":"MO7TX7BR5Y57SURK","created_at":"2026-07-05T03:24:09Z"},{"alias_kind":"pith_short_8","alias_value":"MO7TX7BR","created_at":"2026-07-05T03:24:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MO7TX7BR5Y57SURKFIN7VFYR7P","target":"record","payload":{"canonical_record":{"source":{"id":"2103.12690","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-23T17:05:54Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6469ea0bb39e56cf4ea8c09eb5a185c22411ebed548d7441e8270e7cf34c6f50","abstract_canon_sha256":"d477d560b448ba844397d783c2ec0b2c8bc3687a3fb0261dfe8da428a9c25c57"},"schema_version":"1.0"},"canonical_sha256":"63bf3bfc31ee3bf9522a2a1bfa9711fbecd2c3934e764b81a7f1917109fc7f88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:09.408369Z","signature_b64":"CQxgzsx+k8ViBpD3phDK06n+LSisWl+vre29gWxHnuys8VuOG3znitDM1wOrOUhwCCjgkllQWjN9WQ52l89GCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63bf3bfc31ee3bf9522a2a1bfa9711fbecd2c3934e764b81a7f1917109fc7f88","last_reissued_at":"2026-07-05T03:24:09.407912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:09.407912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.12690","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":"2026-07-05T03:24:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0HmPD8FNtEGwj9qxM0qmBhQOhOyFK4U7I8UrSHsu7wkxeLrLdaNOsQ1kyzWdqw2LaeIwGreJs0jrde5fwSsMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:15:48.460459Z"},"content_sha256":"34722007eaf436fd542e20311dd47140cf3bc031f401ab8713407504027f5917","schema_version":"1.0","event_id":"sha256:34722007eaf436fd542e20311dd47140cf3bc031f401ab8713407504027f5917"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MO7TX7BR5Y57SURKFIN7VFYR7P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ruosong Wang, Sham M. Kakade, Yuanhao Wang","submitted_at":"2021-03-23T17:05:54Z","abstract_excerpt":"A fundamental question in the theory of reinforcement learning is: suppose the optimal $Q$-function lies in the linear span of a given $d$ dimensional feature mapping, is sample-efficient reinforcement learning (RL) possible? The recent and remarkable result of Weisz et al. (2020) resolved this question in the negative, providing an exponential (in $d$) sample size lower bound, which holds even if the agent has access to a generative model of the environment. One may hope that this information theoretic barrier for RL can be circumvented by further supposing an even more favorable assumption: "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12690","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/2103.12690/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":"2026-07-05T03:24:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L4s4fwfZD5Cc4KQMdsiAPAVpELPynFcAHWcCZq5deUaZmICE86j12o73mMuJqxMue0Xt68FBLwjD1gBB/+afAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:15:48.461091Z"},"content_sha256":"6525f235262d827db117a34036ceeec30e276604982464411ddd5f330d7943e8","schema_version":"1.0","event_id":"sha256:6525f235262d827db117a34036ceeec30e276604982464411ddd5f330d7943e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MO7TX7BR5Y57SURKFIN7VFYR7P/bundle.json","state_url":"https://pith.science/pith/MO7TX7BR5Y57SURKFIN7VFYR7P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MO7TX7BR5Y57SURKFIN7VFYR7P/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":"2026-08-11T02:15:48Z","links":{"resolver":"https://pith.science/pith/MO7TX7BR5Y57SURKFIN7VFYR7P","bundle":"https://pith.science/pith/MO7TX7BR5Y57SURKFIN7VFYR7P/bundle.json","state":"https://pith.science/pith/MO7TX7BR5Y57SURKFIN7VFYR7P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MO7TX7BR5Y57SURKFIN7VFYR7P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MO7TX7BR5Y57SURKFIN7VFYR7P","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":"d477d560b448ba844397d783c2ec0b2c8bc3687a3fb0261dfe8da428a9c25c57","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-23T17:05:54Z","title_canon_sha256":"6469ea0bb39e56cf4ea8c09eb5a185c22411ebed548d7441e8270e7cf34c6f50"},"schema_version":"1.0","source":{"id":"2103.12690","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12690","created_at":"2026-07-05T03:24:09Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12690v2","created_at":"2026-07-05T03:24:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12690","created_at":"2026-07-05T03:24:09Z"},{"alias_kind":"pith_short_12","alias_value":"MO7TX7BR5Y57","created_at":"2026-07-05T03:24:09Z"},{"alias_kind":"pith_short_16","alias_value":"MO7TX7BR5Y57SURK","created_at":"2026-07-05T03:24:09Z"},{"alias_kind":"pith_short_8","alias_value":"MO7TX7BR","created_at":"2026-07-05T03:24:09Z"}],"graph_snapshots":[{"event_id":"sha256:6525f235262d827db117a34036ceeec30e276604982464411ddd5f330d7943e8","target":"graph","created_at":"2026-07-05T03:24:09Z","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/2103.12690/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A fundamental question in the theory of reinforcement learning is: suppose the optimal $Q$-function lies in the linear span of a given $d$ dimensional feature mapping, is sample-efficient reinforcement learning (RL) possible? The recent and remarkable result of Weisz et al. (2020) resolved this question in the negative, providing an exponential (in $d$) sample size lower bound, which holds even if the agent has access to a generative model of the environment. One may hope that this information theoretic barrier for RL can be circumvented by further supposing an even more favorable assumption: ","authors_text":"Ruosong Wang, Sham M. Kakade, Yuanhao Wang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-23T17:05:54Z","title":"An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12690","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":"sha256:34722007eaf436fd542e20311dd47140cf3bc031f401ab8713407504027f5917","target":"record","created_at":"2026-07-05T03:24:09Z","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":"d477d560b448ba844397d783c2ec0b2c8bc3687a3fb0261dfe8da428a9c25c57","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-23T17:05:54Z","title_canon_sha256":"6469ea0bb39e56cf4ea8c09eb5a185c22411ebed548d7441e8270e7cf34c6f50"},"schema_version":"1.0","source":{"id":"2103.12690","kind":"arxiv","version":2}},"canonical_sha256":"63bf3bfc31ee3bf9522a2a1bfa9711fbecd2c3934e764b81a7f1917109fc7f88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63bf3bfc31ee3bf9522a2a1bfa9711fbecd2c3934e764b81a7f1917109fc7f88","first_computed_at":"2026-07-05T03:24:09.407912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:24:09.407912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CQxgzsx+k8ViBpD3phDK06n+LSisWl+vre29gWxHnuys8VuOG3znitDM1wOrOUhwCCjgkllQWjN9WQ52l89GCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:24:09.408369Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.12690","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34722007eaf436fd542e20311dd47140cf3bc031f401ab8713407504027f5917","sha256:6525f235262d827db117a34036ceeec30e276604982464411ddd5f330d7943e8"],"state_sha256":"648f8e87389806ce939660ceba92023abeb19a9a4160ca32fceff63dd70caa53"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PKXSEr0g0meX1FdN0H4AY2n6+yg2AGSINj3XTe8+zz2Ups571sCwXGUm7TTqLcqbch71m5hkGVI8M5iWJIJ+Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T02:15:48.469589Z","bundle_sha256":"7181bad7bb4b9a9dd492b3a74164b8f1f412612e5677123032bb2ec56ef52054"}}