{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SRB67HNSWTYYVAX7G4MZFK7XNE","short_pith_number":"pith:SRB67HNS","canonical_record":{"source":{"id":"1904.08473","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-17T19:46:02Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8cdab9f2ea459af47c515be043d10a5344ecdc0ec17415293ec09ca6fab02607","abstract_canon_sha256":"25a93cc3e7f16faa47d7b3539f7d2dbb1f367a4974253ab795de678c46c0ca91"},"schema_version":"1.0"},"canonical_sha256":"9443ef9db2b4f18a82ff371992abf76907bb53059088b40dbebe880e2b19f497","source":{"kind":"arxiv","id":"1904.08473","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.08473","created_at":"2026-05-17T23:41:21Z"},{"alias_kind":"arxiv_version","alias_value":"1904.08473v2","created_at":"2026-05-17T23:41:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.08473","created_at":"2026-05-17T23:41:21Z"},{"alias_kind":"pith_short_12","alias_value":"SRB67HNSWTYY","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SRB67HNSWTYYVAX7","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SRB67HNS","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SRB67HNSWTYYVAX7G4MZFK7XNE","target":"record","payload":{"canonical_record":{"source":{"id":"1904.08473","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-17T19:46:02Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8cdab9f2ea459af47c515be043d10a5344ecdc0ec17415293ec09ca6fab02607","abstract_canon_sha256":"25a93cc3e7f16faa47d7b3539f7d2dbb1f367a4974253ab795de678c46c0ca91"},"schema_version":"1.0"},"canonical_sha256":"9443ef9db2b4f18a82ff371992abf76907bb53059088b40dbebe880e2b19f497","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:21.676265Z","signature_b64":"KjU47dewjPUZ3cxe4BnQ4MhFj1TjX4u34nUBUvGk9Jm9/wwvlhJpQEqVTL8Ig2lTLjhytObrUbAuLUKRe2FtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9443ef9db2b4f18a82ff371992abf76907bb53059088b40dbebe880e2b19f497","last_reissued_at":"2026-05-17T23:41:21.675585Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:21.675585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.08473","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":"2026-05-17T23:41:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J9Ncbr9EpDwfMzyN+fjU3p+/5F1porK5bB4Nc+6RZoHTmKEAGEstug/dzFD8Aaq8oVP7NKHF6J+44WEBDq0cCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:48:04.850430Z"},"content_sha256":"f23c32e7c2e30e0df5f9f223154cde03fc0718894da61dac7974cfb00066f4ee","schema_version":"1.0","event_id":"sha256:f23c32e7c2e30e0df5f9f223154cde03fc0718894da61dac7974cfb00066f4ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SRB67HNSWTYYVAX7G4MZFK7XNE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Off-Policy Policy Gradient with State Distribution Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adith Swaminathan, Alekh Agarwal, Emma Brunskill, Yao Liu","submitted_at":"2019-04-17T19:46:02Z","abstract_excerpt":"We study the problem of off-policy policy optimization in Markov decision processes, and develop a novel off-policy policy gradient method. Prior off-policy policy gradient approaches have generally ignored the mismatch between the distribution of states visited under the behavior policy used to collect data, and what would be the distribution of states under the learned policy. Here we build on recent progress for estimating the ratio of the state distributions under behavior and evaluation policies for policy evaluation, and present an off-policy policy gradient optimization technique that c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.08473","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":""},"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":"2026-05-17T23:41:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kd5eVBzKfBAjtvU8vSdRo1izX4U1J6BQzESX/6I1wKunA50z+voIW/AKpim0+XkKdrBQZt7QT8nfGxhZTO4nBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:48:04.851092Z"},"content_sha256":"d2a24883352f17f473f4e7ba04960fea541f8ae731174a5a6fa582caa96e8d06","schema_version":"1.0","event_id":"sha256:d2a24883352f17f473f4e7ba04960fea541f8ae731174a5a6fa582caa96e8d06"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SRB67HNSWTYYVAX7G4MZFK7XNE/bundle.json","state_url":"https://pith.science/pith/SRB67HNSWTYYVAX7G4MZFK7XNE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SRB67HNSWTYYVAX7G4MZFK7XNE/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":"2026-05-26T20:48:04Z","links":{"resolver":"https://pith.science/pith/SRB67HNSWTYYVAX7G4MZFK7XNE","bundle":"https://pith.science/pith/SRB67HNSWTYYVAX7G4MZFK7XNE/bundle.json","state":"https://pith.science/pith/SRB67HNSWTYYVAX7G4MZFK7XNE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SRB67HNSWTYYVAX7G4MZFK7XNE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SRB67HNSWTYYVAX7G4MZFK7XNE","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":"25a93cc3e7f16faa47d7b3539f7d2dbb1f367a4974253ab795de678c46c0ca91","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-17T19:46:02Z","title_canon_sha256":"8cdab9f2ea459af47c515be043d10a5344ecdc0ec17415293ec09ca6fab02607"},"schema_version":"1.0","source":{"id":"1904.08473","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.08473","created_at":"2026-05-17T23:41:21Z"},{"alias_kind":"arxiv_version","alias_value":"1904.08473v2","created_at":"2026-05-17T23:41:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.08473","created_at":"2026-05-17T23:41:21Z"},{"alias_kind":"pith_short_12","alias_value":"SRB67HNSWTYY","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SRB67HNSWTYYVAX7","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SRB67HNS","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:d2a24883352f17f473f4e7ba04960fea541f8ae731174a5a6fa582caa96e8d06","target":"graph","created_at":"2026-05-17T23:41:21Z","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"},"paper":{"abstract_excerpt":"We study the problem of off-policy policy optimization in Markov decision processes, and develop a novel off-policy policy gradient method. Prior off-policy policy gradient approaches have generally ignored the mismatch between the distribution of states visited under the behavior policy used to collect data, and what would be the distribution of states under the learned policy. Here we build on recent progress for estimating the ratio of the state distributions under behavior and evaluation policies for policy evaluation, and present an off-policy policy gradient optimization technique that c","authors_text":"Adith Swaminathan, Alekh Agarwal, Emma Brunskill, Yao Liu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-17T19:46:02Z","title":"Off-Policy Policy Gradient with State Distribution Correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.08473","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:f23c32e7c2e30e0df5f9f223154cde03fc0718894da61dac7974cfb00066f4ee","target":"record","created_at":"2026-05-17T23:41:21Z","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":"25a93cc3e7f16faa47d7b3539f7d2dbb1f367a4974253ab795de678c46c0ca91","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-17T19:46:02Z","title_canon_sha256":"8cdab9f2ea459af47c515be043d10a5344ecdc0ec17415293ec09ca6fab02607"},"schema_version":"1.0","source":{"id":"1904.08473","kind":"arxiv","version":2}},"canonical_sha256":"9443ef9db2b4f18a82ff371992abf76907bb53059088b40dbebe880e2b19f497","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9443ef9db2b4f18a82ff371992abf76907bb53059088b40dbebe880e2b19f497","first_computed_at":"2026-05-17T23:41:21.675585Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:21.675585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KjU47dewjPUZ3cxe4BnQ4MhFj1TjX4u34nUBUvGk9Jm9/wwvlhJpQEqVTL8Ig2lTLjhytObrUbAuLUKRe2FtCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:21.676265Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.08473","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f23c32e7c2e30e0df5f9f223154cde03fc0718894da61dac7974cfb00066f4ee","sha256:d2a24883352f17f473f4e7ba04960fea541f8ae731174a5a6fa582caa96e8d06"],"state_sha256":"9180ae7fb06ce08138c796e2a62ba881a5af8a6399bef5a81dd36768d6e07993"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l3Yx+V+INwPMnoXRflUomFkLB6JPTdvcug5Rxppwq+buaBAt8komFyNMW+D30NzjUUQAPB2lBUQxrN2lfhqOAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T20:48:04.854125Z","bundle_sha256":"422ac9bf471b8472ff2eedbce57b70b79bca41a29a53bff6daa2cdd61e481822"}}