{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:IVNCGYH4A2HWN6UP5N34R7ODS3","short_pith_number":"pith:IVNCGYH4","canonical_record":{"source":{"id":"2011.04622","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-09T18:32:22Z","cross_cats_sorted":["cs.AI","math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"20da91304d141aa9d787afeaac21fc2794057ce04fe72952e88d97a329aa15a1","abstract_canon_sha256":"b8a0e319a58fd4ebeabd0c38c9225fa7f052d5f5daa59e14fdd1be2164d2c5af"},"schema_version":"1.0"},"canonical_sha256":"455a2360fc068f66fa8feb77c8fdc396c3ec55204ddb17d5158787e8d7df621e","source":{"kind":"arxiv","id":"2011.04622","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.04622","created_at":"2026-07-05T02:02:56Z"},{"alias_kind":"arxiv_version","alias_value":"2011.04622v2","created_at":"2026-07-05T02:02:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04622","created_at":"2026-07-05T02:02:56Z"},{"alias_kind":"pith_short_12","alias_value":"IVNCGYH4A2HW","created_at":"2026-07-05T02:02:56Z"},{"alias_kind":"pith_short_16","alias_value":"IVNCGYH4A2HWN6UP","created_at":"2026-07-05T02:02:56Z"},{"alias_kind":"pith_short_8","alias_value":"IVNCGYH4","created_at":"2026-07-05T02:02:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:IVNCGYH4A2HWN6UP5N34R7ODS3","target":"record","payload":{"canonical_record":{"source":{"id":"2011.04622","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-09T18:32:22Z","cross_cats_sorted":["cs.AI","math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"20da91304d141aa9d787afeaac21fc2794057ce04fe72952e88d97a329aa15a1","abstract_canon_sha256":"b8a0e319a58fd4ebeabd0c38c9225fa7f052d5f5daa59e14fdd1be2164d2c5af"},"schema_version":"1.0"},"canonical_sha256":"455a2360fc068f66fa8feb77c8fdc396c3ec55204ddb17d5158787e8d7df621e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:02:56.886816Z","signature_b64":"m/uNMMw8wckejAk3d2uvmj66AVDGVfldtBIg8WGns6ZQ8k8BVTNf5h2BSbgytw/iw0Z7lr1N7jO5Z8DiOOv8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"455a2360fc068f66fa8feb77c8fdc396c3ec55204ddb17d5158787e8d7df621e","last_reissued_at":"2026-07-05T02:02:56.886427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:02:56.886427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.04622","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":"2026-07-05T02:02:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JWBZ8dDNn4rMPfJ74LzVKACQotPQSs4EnQXLd1RrNUZYVTfB2l8px1kZMt9Zss5o1MBFd7W9Vs3OyvJzKM55AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:29:44.268980Z"},"content_sha256":"e389790a96e10520eb6598331aca8d77c0839bd1bc98108d935c0b6ebc09b3f0","schema_version":"1.0","event_id":"sha256:e389790a96e10520eb6598331aca8d77c0839bd1bc98108d935c0b6ebc09b3f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:IVNCGYH4A2HWN6UP5N34R7ODS3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Chi Jin, Mengdi Wang, Michael I. Jordan, Zhaoran Wang, Zhuoran Yang","submitted_at":"2020-11-09T18:32:22Z","abstract_excerpt":"The classical theory of reinforcement learning (RL) has focused on tabular and linear representations of value functions. Further progress hinges on combining RL with modern function approximators such as kernel functions and deep neural networks, and indeed there have been many empirical successes that have exploited such combinations in large-scale applications. There are profound challenges, however, in developing a theory to support this enterprise, most notably the need to take into consideration the exploration-exploitation tradeoff at the core of RL in conjunction with the computational"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04622","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/2011.04622/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":"2026-07-05T02:02:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dl49JCCXMDim9v2oHaeQ61XLPQ3BmV2qFnGt4iA9xhfFIWQ4C+DoZN/yvzd2Zl1FyiKlZ6RXK3j/GZz2JBDdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:29:44.269990Z"},"content_sha256":"c77f6f6cda30c41459909f7007bc8304f1fcb94407709c3755ec4f026bcfa990","schema_version":"1.0","event_id":"sha256:c77f6f6cda30c41459909f7007bc8304f1fcb94407709c3755ec4f026bcfa990"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IVNCGYH4A2HWN6UP5N34R7ODS3/bundle.json","state_url":"https://pith.science/pith/IVNCGYH4A2HWN6UP5N34R7ODS3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IVNCGYH4A2HWN6UP5N34R7ODS3/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":"2026-08-10T20:29:44Z","links":{"resolver":"https://pith.science/pith/IVNCGYH4A2HWN6UP5N34R7ODS3","bundle":"https://pith.science/pith/IVNCGYH4A2HWN6UP5N34R7ODS3/bundle.json","state":"https://pith.science/pith/IVNCGYH4A2HWN6UP5N34R7ODS3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IVNCGYH4A2HWN6UP5N34R7ODS3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IVNCGYH4A2HWN6UP5N34R7ODS3","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":"b8a0e319a58fd4ebeabd0c38c9225fa7f052d5f5daa59e14fdd1be2164d2c5af","cross_cats_sorted":["cs.AI","math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-09T18:32:22Z","title_canon_sha256":"20da91304d141aa9d787afeaac21fc2794057ce04fe72952e88d97a329aa15a1"},"schema_version":"1.0","source":{"id":"2011.04622","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.04622","created_at":"2026-07-05T02:02:56Z"},{"alias_kind":"arxiv_version","alias_value":"2011.04622v2","created_at":"2026-07-05T02:02:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04622","created_at":"2026-07-05T02:02:56Z"},{"alias_kind":"pith_short_12","alias_value":"IVNCGYH4A2HW","created_at":"2026-07-05T02:02:56Z"},{"alias_kind":"pith_short_16","alias_value":"IVNCGYH4A2HWN6UP","created_at":"2026-07-05T02:02:56Z"},{"alias_kind":"pith_short_8","alias_value":"IVNCGYH4","created_at":"2026-07-05T02:02:56Z"}],"graph_snapshots":[{"event_id":"sha256:c77f6f6cda30c41459909f7007bc8304f1fcb94407709c3755ec4f026bcfa990","target":"graph","created_at":"2026-07-05T02:02:56Z","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/2011.04622/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The classical theory of reinforcement learning (RL) has focused on tabular and linear representations of value functions. Further progress hinges on combining RL with modern function approximators such as kernel functions and deep neural networks, and indeed there have been many empirical successes that have exploited such combinations in large-scale applications. There are profound challenges, however, in developing a theory to support this enterprise, most notably the need to take into consideration the exploration-exploitation tradeoff at the core of RL in conjunction with the computational","authors_text":"Chi Jin, Mengdi Wang, Michael I. Jordan, Zhaoran Wang, Zhuoran Yang","cross_cats":["cs.AI","math.OC","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-09T18:32:22Z","title":"On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04622","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:e389790a96e10520eb6598331aca8d77c0839bd1bc98108d935c0b6ebc09b3f0","target":"record","created_at":"2026-07-05T02:02:56Z","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":"b8a0e319a58fd4ebeabd0c38c9225fa7f052d5f5daa59e14fdd1be2164d2c5af","cross_cats_sorted":["cs.AI","math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-09T18:32:22Z","title_canon_sha256":"20da91304d141aa9d787afeaac21fc2794057ce04fe72952e88d97a329aa15a1"},"schema_version":"1.0","source":{"id":"2011.04622","kind":"arxiv","version":2}},"canonical_sha256":"455a2360fc068f66fa8feb77c8fdc396c3ec55204ddb17d5158787e8d7df621e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"455a2360fc068f66fa8feb77c8fdc396c3ec55204ddb17d5158787e8d7df621e","first_computed_at":"2026-07-05T02:02:56.886427Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:02:56.886427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m/uNMMw8wckejAk3d2uvmj66AVDGVfldtBIg8WGns6ZQ8k8BVTNf5h2BSbgytw/iw0Z7lr1N7jO5Z8DiOOv8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:02:56.886816Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.04622","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e389790a96e10520eb6598331aca8d77c0839bd1bc98108d935c0b6ebc09b3f0","sha256:c77f6f6cda30c41459909f7007bc8304f1fcb94407709c3755ec4f026bcfa990"],"state_sha256":"3a170ff153277602ab5392757252f5426a5f1fc545d055e9d8d6e5811afc0be0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8YrEzZLGGS9wwGy1M97tpDIw5y2sfzYqaqH23eGOT2ZP9Y2Yq1594KwX8AwFl5wOntSTtt+J8p9+uW1uUyINDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T20:29:44.278949Z","bundle_sha256":"31c7abc17458592e40fbf0a9a3056e639ee2221169692c1eb3685a72c3646696"}}