{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:O5XEB4P7S6NBSPPOLRW6NGGJGR","short_pith_number":"pith:O5XEB4P7","canonical_record":{"source":{"id":"2011.01075","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-02T16:04:42Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ab1e2b23aca469b0f6dbfec1c1263900d7fdecfa998ff54a0c88ce05a073fe4b","abstract_canon_sha256":"fb4f78cbbf3251ed1c6337f235b394197239f8d1232a9924a5d036897e5ae044"},"schema_version":"1.0"},"canonical_sha256":"776e40f1ff979a193dee5c6de698c9347a5c800f81dae44ec9bc9484a195e3bd","source":{"kind":"arxiv","id":"2011.01075","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.01075","created_at":"2026-07-05T01:49:06Z"},{"alias_kind":"arxiv_version","alias_value":"2011.01075v2","created_at":"2026-07-05T01:49:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01075","created_at":"2026-07-05T01:49:06Z"},{"alias_kind":"pith_short_12","alias_value":"O5XEB4P7S6NB","created_at":"2026-07-05T01:49:06Z"},{"alias_kind":"pith_short_16","alias_value":"O5XEB4P7S6NBSPPO","created_at":"2026-07-05T01:49:06Z"},{"alias_kind":"pith_short_8","alias_value":"O5XEB4P7","created_at":"2026-07-05T01:49:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:O5XEB4P7S6NBSPPOLRW6NGGJGR","target":"record","payload":{"canonical_record":{"source":{"id":"2011.01075","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-02T16:04:42Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ab1e2b23aca469b0f6dbfec1c1263900d7fdecfa998ff54a0c88ce05a073fe4b","abstract_canon_sha256":"fb4f78cbbf3251ed1c6337f235b394197239f8d1232a9924a5d036897e5ae044"},"schema_version":"1.0"},"canonical_sha256":"776e40f1ff979a193dee5c6de698c9347a5c800f81dae44ec9bc9484a195e3bd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:06.203689Z","signature_b64":"ZhlLlNoGoxdqIG+HhwvSqQkeJQJBDruOuvltSg0x5yjwlsoOmKbNDSJnmhst1epqkYZs7drlyRhEUzDfwIzGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"776e40f1ff979a193dee5c6de698c9347a5c800f81dae44ec9bc9484a195e3bd","last_reissued_at":"2026-07-05T01:49:06.203270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:06.203270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.01075","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":"2026-07-05T01:49:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HCgxMLf2ghEKvUBQZCdBiLxfxOBBCsONZMCDwA1w9Ci9/yjwo9FWr5YFcwGAZKu88PPW5U9JG5IOWGroMQeSBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T06:31:14.716980Z"},"content_sha256":"240d463519bc682f33b766e747ca765fc086cddcef4e9d7d6c09193744c694af","schema_version":"1.0","event_id":"sha256:240d463519bc682f33b766e747ca765fc086cddcef4e9d7d6c09193744c694af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:O5XEB4P7S6NBSPPOLRW6NGGJGR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Variant of the Wang-Foster-Kakade Lower Bound for the Discounted Setting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Nan Jiang, Philip Amortila, Tengyang Xie","submitted_at":"2020-11-02T16:04:42Z","abstract_excerpt":"Recently, Wang et al. (2020) showed a highly intriguing hardness result for batch reinforcement learning (RL) with linearly realizable value function and good feature coverage in the finite-horizon case. In this note we show that once adapted to the discounted setting, the construction can be simplified to a 2-state MDP with 1-dimensional features, such that learning is impossible even with an infinite amount of data."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01075","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/2011.01075/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":"2026-07-05T01:49:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SE4RX6CJn2zeHrr1kzjSujhJMHiI0xFkAEMZuKBRkz77b0hlTqhZsgYHLUq8l5Er35sUetEhi25lgLBTRlC9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T06:31:14.717377Z"},"content_sha256":"9a8da4dcacdd5dbc32e1f36da669973d8045d6c6621873bfba248fb5139a1128","schema_version":"1.0","event_id":"sha256:9a8da4dcacdd5dbc32e1f36da669973d8045d6c6621873bfba248fb5139a1128"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O5XEB4P7S6NBSPPOLRW6NGGJGR/bundle.json","state_url":"https://pith.science/pith/O5XEB4P7S6NBSPPOLRW6NGGJGR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O5XEB4P7S6NBSPPOLRW6NGGJGR/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":"2026-07-12T06:31:14Z","links":{"resolver":"https://pith.science/pith/O5XEB4P7S6NBSPPOLRW6NGGJGR","bundle":"https://pith.science/pith/O5XEB4P7S6NBSPPOLRW6NGGJGR/bundle.json","state":"https://pith.science/pith/O5XEB4P7S6NBSPPOLRW6NGGJGR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O5XEB4P7S6NBSPPOLRW6NGGJGR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:O5XEB4P7S6NBSPPOLRW6NGGJGR","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":"fb4f78cbbf3251ed1c6337f235b394197239f8d1232a9924a5d036897e5ae044","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-02T16:04:42Z","title_canon_sha256":"ab1e2b23aca469b0f6dbfec1c1263900d7fdecfa998ff54a0c88ce05a073fe4b"},"schema_version":"1.0","source":{"id":"2011.01075","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.01075","created_at":"2026-07-05T01:49:06Z"},{"alias_kind":"arxiv_version","alias_value":"2011.01075v2","created_at":"2026-07-05T01:49:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01075","created_at":"2026-07-05T01:49:06Z"},{"alias_kind":"pith_short_12","alias_value":"O5XEB4P7S6NB","created_at":"2026-07-05T01:49:06Z"},{"alias_kind":"pith_short_16","alias_value":"O5XEB4P7S6NBSPPO","created_at":"2026-07-05T01:49:06Z"},{"alias_kind":"pith_short_8","alias_value":"O5XEB4P7","created_at":"2026-07-05T01:49:06Z"}],"graph_snapshots":[{"event_id":"sha256:9a8da4dcacdd5dbc32e1f36da669973d8045d6c6621873bfba248fb5139a1128","target":"graph","created_at":"2026-07-05T01:49:06Z","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/2011.01075/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, Wang et al. (2020) showed a highly intriguing hardness result for batch reinforcement learning (RL) with linearly realizable value function and good feature coverage in the finite-horizon case. In this note we show that once adapted to the discounted setting, the construction can be simplified to a 2-state MDP with 1-dimensional features, such that learning is impossible even with an infinite amount of data.","authors_text":"Nan Jiang, Philip Amortila, Tengyang Xie","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-02T16:04:42Z","title":"A Variant of the Wang-Foster-Kakade Lower Bound for the Discounted Setting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01075","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":"sha256:240d463519bc682f33b766e747ca765fc086cddcef4e9d7d6c09193744c694af","target":"record","created_at":"2026-07-05T01:49:06Z","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":"fb4f78cbbf3251ed1c6337f235b394197239f8d1232a9924a5d036897e5ae044","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-02T16:04:42Z","title_canon_sha256":"ab1e2b23aca469b0f6dbfec1c1263900d7fdecfa998ff54a0c88ce05a073fe4b"},"schema_version":"1.0","source":{"id":"2011.01075","kind":"arxiv","version":2}},"canonical_sha256":"776e40f1ff979a193dee5c6de698c9347a5c800f81dae44ec9bc9484a195e3bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"776e40f1ff979a193dee5c6de698c9347a5c800f81dae44ec9bc9484a195e3bd","first_computed_at":"2026-07-05T01:49:06.203270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:06.203270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZhlLlNoGoxdqIG+HhwvSqQkeJQJBDruOuvltSg0x5yjwlsoOmKbNDSJnmhst1epqkYZs7drlyRhEUzDfwIzGCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:06.203689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.01075","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:240d463519bc682f33b766e747ca765fc086cddcef4e9d7d6c09193744c694af","sha256:9a8da4dcacdd5dbc32e1f36da669973d8045d6c6621873bfba248fb5139a1128"],"state_sha256":"70dac61946394999e18d6b4cfcc5f626d5595c870e321d675792b8d981500aa4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"90QfRWRXJvRRNbK1sxFsysj7+mWKdcOpJy5Nkvys4Z/I9Ap5LTzEvd96lLt+NY56Mh/TAazEx/3PDm52iFWDDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T06:31:14.719662Z","bundle_sha256":"e193d5025b994f2a0738d38d601b4e39945de43c93aecd0063b58ec2b891e9da"}}