{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YCJAW5T2A6JMQTO6U77DKIEPLU","short_pith_number":"pith:YCJAW5T2","canonical_record":{"source":{"id":"1907.05388","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-11T17:06:11Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"4fe9cd94fb6c5ffc4ed4196f1b5e9569309a272ab97b16966557e34aabcf22b9","abstract_canon_sha256":"14f2bf426fd3abdd2d3a2f88476a1361682a98eeac10bdf71b184c2632b6c73c"},"schema_version":"1.0"},"canonical_sha256":"c0920b767a0792c84ddea7fe35208f5d0e3043e90b678c798dbe34ae3be57169","source":{"kind":"arxiv","id":"1907.05388","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.05388","created_at":"2026-07-04T23:52:21Z"},{"alias_kind":"arxiv_version","alias_value":"1907.05388v2","created_at":"2026-07-04T23:52:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05388","created_at":"2026-07-04T23:52:21Z"},{"alias_kind":"pith_short_12","alias_value":"YCJAW5T2A6JM","created_at":"2026-07-04T23:52:21Z"},{"alias_kind":"pith_short_16","alias_value":"YCJAW5T2A6JMQTO6","created_at":"2026-07-04T23:52:21Z"},{"alias_kind":"pith_short_8","alias_value":"YCJAW5T2","created_at":"2026-07-04T23:52:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YCJAW5T2A6JMQTO6U77DKIEPLU","target":"record","payload":{"canonical_record":{"source":{"id":"1907.05388","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-11T17:06:11Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"4fe9cd94fb6c5ffc4ed4196f1b5e9569309a272ab97b16966557e34aabcf22b9","abstract_canon_sha256":"14f2bf426fd3abdd2d3a2f88476a1361682a98eeac10bdf71b184c2632b6c73c"},"schema_version":"1.0"},"canonical_sha256":"c0920b767a0792c84ddea7fe35208f5d0e3043e90b678c798dbe34ae3be57169","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:52:21.973098Z","signature_b64":"Tfy7AIh1qf+Cox5ba+bqQ/g1yYC8FiBRV2zmedzAM0Wq11ARCoIfIXuPYEJprP/sUg3WhUHpTP2IR9p8X4oCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0920b767a0792c84ddea7fe35208f5d0e3043e90b678c798dbe34ae3be57169","last_reissued_at":"2026-07-04T23:52:21.972674Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:52:21.972674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.05388","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":"2026-07-04T23:52:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SY3YcWuRtc2FhJ6bNUZpdhlWrDfIr0cLjIIsYFJEDVneKwWV1Fj86m3GuMR8DaQDe+ecNadrXu3mhlPji6GVCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:55:14.328519Z"},"content_sha256":"4d28a85d5f680b88740bae22208a196bc02825071dd533f549bf79fd7871bfa6","schema_version":"1.0","event_id":"sha256:4d28a85d5f680b88740bae22208a196bc02825071dd533f549bf79fd7871bfa6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YCJAW5T2A6JMQTO6U77DKIEPLU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi Jin, Michael I. Jordan, Zhaoran Wang, Zhuoran Yang","submitted_at":"2019-07-11T17:06:11Z","abstract_excerpt":"Modern Reinforcement Learning (RL) is commonly applied to practical problems with an enormous number of states, where function approximation must be deployed to approximate either the value function or the policy. The introduction of function approximation raises a fundamental set of challenges involving computational and statistical efficiency, especially given the need to manage the exploration/exploitation tradeoff. As a result, a core RL question remains open: how can we design provably efficient RL algorithms that incorporate function approximation? This question persists even in a basic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05388","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/1907.05388/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":"2026-07-04T23:52:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YOF63QpAxELrHKqcQGnq6gdWpFGlL+1aZMa1i30PWmPFOiaXsISuQT7YgjVPRQ8nfH+tQq4VFxF/i/6kA/rhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:55:14.329109Z"},"content_sha256":"6c03a3bb0a1f772528fa420aa71ff7563f756cc918c552edb6d34628ecf3ee23","schema_version":"1.0","event_id":"sha256:6c03a3bb0a1f772528fa420aa71ff7563f756cc918c552edb6d34628ecf3ee23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YCJAW5T2A6JMQTO6U77DKIEPLU/bundle.json","state_url":"https://pith.science/pith/YCJAW5T2A6JMQTO6U77DKIEPLU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YCJAW5T2A6JMQTO6U77DKIEPLU/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":"2026-08-18T03:55:14Z","links":{"resolver":"https://pith.science/pith/YCJAW5T2A6JMQTO6U77DKIEPLU","bundle":"https://pith.science/pith/YCJAW5T2A6JMQTO6U77DKIEPLU/bundle.json","state":"https://pith.science/pith/YCJAW5T2A6JMQTO6U77DKIEPLU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YCJAW5T2A6JMQTO6U77DKIEPLU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YCJAW5T2A6JMQTO6U77DKIEPLU","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":"14f2bf426fd3abdd2d3a2f88476a1361682a98eeac10bdf71b184c2632b6c73c","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-11T17:06:11Z","title_canon_sha256":"4fe9cd94fb6c5ffc4ed4196f1b5e9569309a272ab97b16966557e34aabcf22b9"},"schema_version":"1.0","source":{"id":"1907.05388","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.05388","created_at":"2026-07-04T23:52:21Z"},{"alias_kind":"arxiv_version","alias_value":"1907.05388v2","created_at":"2026-07-04T23:52:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05388","created_at":"2026-07-04T23:52:21Z"},{"alias_kind":"pith_short_12","alias_value":"YCJAW5T2A6JM","created_at":"2026-07-04T23:52:21Z"},{"alias_kind":"pith_short_16","alias_value":"YCJAW5T2A6JMQTO6","created_at":"2026-07-04T23:52:21Z"},{"alias_kind":"pith_short_8","alias_value":"YCJAW5T2","created_at":"2026-07-04T23:52:21Z"}],"graph_snapshots":[{"event_id":"sha256:6c03a3bb0a1f772528fa420aa71ff7563f756cc918c552edb6d34628ecf3ee23","target":"graph","created_at":"2026-07-04T23:52:21Z","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/1907.05388/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern Reinforcement Learning (RL) is commonly applied to practical problems with an enormous number of states, where function approximation must be deployed to approximate either the value function or the policy. The introduction of function approximation raises a fundamental set of challenges involving computational and statistical efficiency, especially given the need to manage the exploration/exploitation tradeoff. As a result, a core RL question remains open: how can we design provably efficient RL algorithms that incorporate function approximation? This question persists even in a basic ","authors_text":"Chi Jin, Michael I. Jordan, Zhaoran Wang, Zhuoran Yang","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-11T17:06:11Z","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05388","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":"sha256:4d28a85d5f680b88740bae22208a196bc02825071dd533f549bf79fd7871bfa6","target":"record","created_at":"2026-07-04T23:52:21Z","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":"14f2bf426fd3abdd2d3a2f88476a1361682a98eeac10bdf71b184c2632b6c73c","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-11T17:06:11Z","title_canon_sha256":"4fe9cd94fb6c5ffc4ed4196f1b5e9569309a272ab97b16966557e34aabcf22b9"},"schema_version":"1.0","source":{"id":"1907.05388","kind":"arxiv","version":2}},"canonical_sha256":"c0920b767a0792c84ddea7fe35208f5d0e3043e90b678c798dbe34ae3be57169","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0920b767a0792c84ddea7fe35208f5d0e3043e90b678c798dbe34ae3be57169","first_computed_at":"2026-07-04T23:52:21.972674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:52:21.972674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tfy7AIh1qf+Cox5ba+bqQ/g1yYC8FiBRV2zmedzAM0Wq11ARCoIfIXuPYEJprP/sUg3WhUHpTP2IR9p8X4oCBA==","signature_status":"signed_v1","signed_at":"2026-07-04T23:52:21.973098Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.05388","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d28a85d5f680b88740bae22208a196bc02825071dd533f549bf79fd7871bfa6","sha256:6c03a3bb0a1f772528fa420aa71ff7563f756cc918c552edb6d34628ecf3ee23"],"state_sha256":"ebce75ff060ca4e43633dd9eabaf21fd8fb10d6fbf17501a71c1ae2d0fb8aaf7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8cOfJKIj1ebcit6u/p+SED0KZASpZ78a3IRs1DOud5jRZIa+fnr3MUi6jdvts0u74CqiBAORInDlMYyYpKyDDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T03:55:14.334909Z","bundle_sha256":"f37eebd53cdd97161eec677ddda55b5e77ec3f3800e1d6e2f6ce750e7b2b6db9"}}