{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:J3JKTJ77UE6XQV35IZUIKO6NXN","short_pith_number":"pith:J3JKTJ77","canonical_record":{"source":{"id":"1912.04136","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-09T15:47:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b08d736f9fd33dc354d06e6b2a66e83895a34e587bafdd74b870f18990ef645d","abstract_canon_sha256":"22b54d0b953c0a348a5bdd74f4854038e56ab72877a8e80c37ae41f9d4d69688"},"schema_version":"1.0"},"canonical_sha256":"4ed2a9a7ffa13d78577d4668853bcdbb7cc80eaa9528f91a047d716332a7e235","source":{"kind":"arxiv","id":"1912.04136","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.04136","created_at":"2026-07-05T00:24:52Z"},{"alias_kind":"arxiv_version","alias_value":"1912.04136v1","created_at":"2026-07-05T00:24:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.04136","created_at":"2026-07-05T00:24:52Z"},{"alias_kind":"pith_short_12","alias_value":"J3JKTJ77UE6X","created_at":"2026-07-05T00:24:52Z"},{"alias_kind":"pith_short_16","alias_value":"J3JKTJ77UE6XQV35","created_at":"2026-07-05T00:24:52Z"},{"alias_kind":"pith_short_8","alias_value":"J3JKTJ77","created_at":"2026-07-05T00:24:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:J3JKTJ77UE6XQV35IZUIKO6NXN","target":"record","payload":{"canonical_record":{"source":{"id":"1912.04136","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-09T15:47:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b08d736f9fd33dc354d06e6b2a66e83895a34e587bafdd74b870f18990ef645d","abstract_canon_sha256":"22b54d0b953c0a348a5bdd74f4854038e56ab72877a8e80c37ae41f9d4d69688"},"schema_version":"1.0"},"canonical_sha256":"4ed2a9a7ffa13d78577d4668853bcdbb7cc80eaa9528f91a047d716332a7e235","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:52.131593Z","signature_b64":"dnNIsun8IDtR2j4GwEZJHNmvbeEqIGutI6IHRZzB0fwdRCRMEs8LcQrr64dpmtMcjQpkOzwJ1/V8Sjty7KZKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ed2a9a7ffa13d78577d4668853bcdbb7cc80eaa9528f91a047d716332a7e235","last_reissued_at":"2026-07-05T00:24:52.131084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:52.131084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.04136","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:24:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XsVABnHNy942WPBZw0eQJZ0/iHNCe43fSKB0sU+qWc3aNK9Haf5Oc4PMpMcwSNMruGNWmsGxTnq9Qt7nWEuBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:54:41.804355Z"},"content_sha256":"1a7a9e9bf234e9cfdb7fc1f466f75997d3eaa2887ddd175931022ce597a92a99","schema_version":"1.0","event_id":"sha256:1a7a9e9bf234e9cfdb7fc1f466f75997d3eaa2887ddd175931022ce597a92a99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:J3JKTJ77UE6XQV35IZUIKO6NXN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimism in Reinforcement Learning with Generalized Linear Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Akshay Krishnamurthy, Ruosong Wang, Simon S. Du, Yining Wang","submitted_at":"2019-12-09T15:47:27Z","abstract_excerpt":"We design a new provably efficient algorithm for episodic reinforcement learning with generalized linear function approximation. We analyze the algorithm under a new expressivity assumption that we call \"optimistic closure,\" which is strictly weaker than assumptions from prior analyses for the linear setting. With optimistic closure, we prove that our algorithm enjoys a regret bound of $\\tilde{O}(\\sqrt{d^3 T})$ where $d$ is the dimensionality of the state-action features and $T$ is the number of episodes. This is the first statistically and computationally efficient algorithm for reinforcement"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.04136","kind":"arxiv","version":1},"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/1912.04136/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":"2026-07-05T00:24:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LfMA8kD/AsgWu01n53kxBuQTQ2+0i29RLa+OP8LbAtJe+k3sug4QMhtYnFROnpKAAoelm0/cDLsm/afZMBZ1BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:54:41.804876Z"},"content_sha256":"03969c84564fb6642732f8d1500104bf2c3f9aa73a57c22aa68bac12edc6b5e6","schema_version":"1.0","event_id":"sha256:03969c84564fb6642732f8d1500104bf2c3f9aa73a57c22aa68bac12edc6b5e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J3JKTJ77UE6XQV35IZUIKO6NXN/bundle.json","state_url":"https://pith.science/pith/J3JKTJ77UE6XQV35IZUIKO6NXN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J3JKTJ77UE6XQV35IZUIKO6NXN/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":"2026-08-10T09:54:41Z","links":{"resolver":"https://pith.science/pith/J3JKTJ77UE6XQV35IZUIKO6NXN","bundle":"https://pith.science/pith/J3JKTJ77UE6XQV35IZUIKO6NXN/bundle.json","state":"https://pith.science/pith/J3JKTJ77UE6XQV35IZUIKO6NXN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J3JKTJ77UE6XQV35IZUIKO6NXN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:J3JKTJ77UE6XQV35IZUIKO6NXN","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":"22b54d0b953c0a348a5bdd74f4854038e56ab72877a8e80c37ae41f9d4d69688","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-09T15:47:27Z","title_canon_sha256":"b08d736f9fd33dc354d06e6b2a66e83895a34e587bafdd74b870f18990ef645d"},"schema_version":"1.0","source":{"id":"1912.04136","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.04136","created_at":"2026-07-05T00:24:52Z"},{"alias_kind":"arxiv_version","alias_value":"1912.04136v1","created_at":"2026-07-05T00:24:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.04136","created_at":"2026-07-05T00:24:52Z"},{"alias_kind":"pith_short_12","alias_value":"J3JKTJ77UE6X","created_at":"2026-07-05T00:24:52Z"},{"alias_kind":"pith_short_16","alias_value":"J3JKTJ77UE6XQV35","created_at":"2026-07-05T00:24:52Z"},{"alias_kind":"pith_short_8","alias_value":"J3JKTJ77","created_at":"2026-07-05T00:24:52Z"}],"graph_snapshots":[{"event_id":"sha256:03969c84564fb6642732f8d1500104bf2c3f9aa73a57c22aa68bac12edc6b5e6","target":"graph","created_at":"2026-07-05T00:24:52Z","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/1912.04136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We design a new provably efficient algorithm for episodic reinforcement learning with generalized linear function approximation. We analyze the algorithm under a new expressivity assumption that we call \"optimistic closure,\" which is strictly weaker than assumptions from prior analyses for the linear setting. With optimistic closure, we prove that our algorithm enjoys a regret bound of $\\tilde{O}(\\sqrt{d^3 T})$ where $d$ is the dimensionality of the state-action features and $T$ is the number of episodes. This is the first statistically and computationally efficient algorithm for reinforcement","authors_text":"Akshay Krishnamurthy, Ruosong Wang, Simon S. Du, Yining Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-09T15:47:27Z","title":"Optimism in Reinforcement Learning with Generalized Linear Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.04136","kind":"arxiv","version":1},"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":"sha256:1a7a9e9bf234e9cfdb7fc1f466f75997d3eaa2887ddd175931022ce597a92a99","target":"record","created_at":"2026-07-05T00:24:52Z","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":"22b54d0b953c0a348a5bdd74f4854038e56ab72877a8e80c37ae41f9d4d69688","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-09T15:47:27Z","title_canon_sha256":"b08d736f9fd33dc354d06e6b2a66e83895a34e587bafdd74b870f18990ef645d"},"schema_version":"1.0","source":{"id":"1912.04136","kind":"arxiv","version":1}},"canonical_sha256":"4ed2a9a7ffa13d78577d4668853bcdbb7cc80eaa9528f91a047d716332a7e235","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ed2a9a7ffa13d78577d4668853bcdbb7cc80eaa9528f91a047d716332a7e235","first_computed_at":"2026-07-05T00:24:52.131084Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:24:52.131084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dnNIsun8IDtR2j4GwEZJHNmvbeEqIGutI6IHRZzB0fwdRCRMEs8LcQrr64dpmtMcjQpkOzwJ1/V8Sjty7KZKDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:24:52.131593Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.04136","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a7a9e9bf234e9cfdb7fc1f466f75997d3eaa2887ddd175931022ce597a92a99","sha256:03969c84564fb6642732f8d1500104bf2c3f9aa73a57c22aa68bac12edc6b5e6"],"state_sha256":"0563ea970afceb2c0337cdb25c538244f2642eb22ca2b2b05bda8e230941e6d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5qAfWKOZFa7uYKKnuxOqEnfKTquo+TWq0zAVGZuoVAe14lf3waU1PHMzkCZoJobl24Q/WmcOPwGWoqHjte3GDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:54:41.808981Z","bundle_sha256":"05552bc03ae4492fe73fd7b9a1aec33cdda30638d105ac04bfc18efc16f15169"}}