{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:IIZETBRBLNQ2URJISP2RNCZLWV","short_pith_number":"pith:IIZETBRB","canonical_record":{"source":{"id":"1905.07237","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-17T14:36:48Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e583dc6fba3db360b71419ab1ffac8a5982c17f0f62a708c434e2efae9b69957","abstract_canon_sha256":"9cec2b4c8231d2d2c4274aec1ffb4e9857ea63f2932537416d991821e828ebb4"},"schema_version":"1.0"},"canonical_sha256":"42324986215b61aa452893f5168b2bb5676a5902a391af78810adab971f13828","source":{"kind":"arxiv","id":"1905.07237","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07237","created_at":"2026-05-17T23:45:56Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07237v1","created_at":"2026-05-17T23:45:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07237","created_at":"2026-05-17T23:45:56Z"},{"alias_kind":"pith_short_12","alias_value":"IIZETBRBLNQ2","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IIZETBRBLNQ2URJI","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IIZETBRB","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:IIZETBRBLNQ2URJISP2RNCZLWV","target":"record","payload":{"canonical_record":{"source":{"id":"1905.07237","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-17T14:36:48Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e583dc6fba3db360b71419ab1ffac8a5982c17f0f62a708c434e2efae9b69957","abstract_canon_sha256":"9cec2b4c8231d2d2c4274aec1ffb4e9857ea63f2932537416d991821e828ebb4"},"schema_version":"1.0"},"canonical_sha256":"42324986215b61aa452893f5168b2bb5676a5902a391af78810adab971f13828","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:56.085947Z","signature_b64":"DcLTu00d4YSePKj8194yKV3elspGyWdmMsimq22AVF6IPoLTw9tFRC81gHRc/PBEjA34YoDb/jM1MPRbz5QDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42324986215b61aa452893f5168b2bb5676a5902a391af78810adab971f13828","last_reissued_at":"2026-05-17T23:45:56.085399Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:56.085399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.07237","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":"2026-05-17T23:45:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"THYcVmkQyBDNgr2BQt2CGtpkazFLf19pB97HbjBCeMN1Wr/2KMYPZp2SQv4nQY31L9UCcVbYB6ZFvadqjv2fAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:29:26.244834Z"},"content_sha256":"52f407f3f6f3e09a09a19ce062cf501b5556ab9adc9bbb7ff458cb398d1c020b","schema_version":"1.0","event_id":"sha256:52f407f3f6f3e09a09a19ce062cf501b5556ab9adc9bbb7ff458cb398d1c020b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:IIZETBRBLNQ2URJISP2RNCZLWV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TBQ($\\sigma$): Improving Efficiency of Trace Utilization for Off-Policy Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gang Pan, Longbing Cao, Longxiang Shi, Long Yang, Shijian Li","submitted_at":"2019-05-17T14:36:48Z","abstract_excerpt":"Off-policy reinforcement learning with eligibility traces is challenging because of the discrepancy between target policy and behavior policy. One common approach is to measure the difference between two policies in a probabilistic way, such as importance sampling and tree-backup. However, existing off-policy learning methods based on probabilistic policy measurement are inefficient when utilizing traces under a greedy target policy, which is ineffective for control problems. The traces are cut immediately when a non-greedy action is taken, which may lose the advantage of eligibility traces an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07237","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":""},"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":"2026-05-17T23:45:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KovrCeUM7X0GSL3PctFquVcncknEfDvNEepOhEtNPLZ/0U0tbOvQK/ZNsna99/9zlaDjKG7KLMQuxHzCgNMQCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:29:26.245731Z"},"content_sha256":"e6e5bd14dc0b6da2e549dbebb741aeb707f9203face932cf5ff9acbca65275e1","schema_version":"1.0","event_id":"sha256:e6e5bd14dc0b6da2e549dbebb741aeb707f9203face932cf5ff9acbca65275e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IIZETBRBLNQ2URJISP2RNCZLWV/bundle.json","state_url":"https://pith.science/pith/IIZETBRBLNQ2URJISP2RNCZLWV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IIZETBRBLNQ2URJISP2RNCZLWV/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":"2026-08-14T10:29:26Z","links":{"resolver":"https://pith.science/pith/IIZETBRBLNQ2URJISP2RNCZLWV","bundle":"https://pith.science/pith/IIZETBRBLNQ2URJISP2RNCZLWV/bundle.json","state":"https://pith.science/pith/IIZETBRBLNQ2URJISP2RNCZLWV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IIZETBRBLNQ2URJISP2RNCZLWV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IIZETBRBLNQ2URJISP2RNCZLWV","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":"9cec2b4c8231d2d2c4274aec1ffb4e9857ea63f2932537416d991821e828ebb4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-17T14:36:48Z","title_canon_sha256":"e583dc6fba3db360b71419ab1ffac8a5982c17f0f62a708c434e2efae9b69957"},"schema_version":"1.0","source":{"id":"1905.07237","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07237","created_at":"2026-05-17T23:45:56Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07237v1","created_at":"2026-05-17T23:45:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07237","created_at":"2026-05-17T23:45:56Z"},{"alias_kind":"pith_short_12","alias_value":"IIZETBRBLNQ2","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IIZETBRBLNQ2URJI","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IIZETBRB","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:e6e5bd14dc0b6da2e549dbebb741aeb707f9203face932cf5ff9acbca65275e1","target":"graph","created_at":"2026-05-17T23:45:56Z","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"},"paper":{"abstract_excerpt":"Off-policy reinforcement learning with eligibility traces is challenging because of the discrepancy between target policy and behavior policy. One common approach is to measure the difference between two policies in a probabilistic way, such as importance sampling and tree-backup. However, existing off-policy learning methods based on probabilistic policy measurement are inefficient when utilizing traces under a greedy target policy, which is ineffective for control problems. The traces are cut immediately when a non-greedy action is taken, which may lose the advantage of eligibility traces an","authors_text":"Gang Pan, Longbing Cao, Longxiang Shi, Long Yang, Shijian Li","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-17T14:36:48Z","title":"TBQ($\\sigma$): Improving Efficiency of Trace Utilization for Off-Policy Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07237","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":"sha256:52f407f3f6f3e09a09a19ce062cf501b5556ab9adc9bbb7ff458cb398d1c020b","target":"record","created_at":"2026-05-17T23:45:56Z","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":"9cec2b4c8231d2d2c4274aec1ffb4e9857ea63f2932537416d991821e828ebb4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-17T14:36:48Z","title_canon_sha256":"e583dc6fba3db360b71419ab1ffac8a5982c17f0f62a708c434e2efae9b69957"},"schema_version":"1.0","source":{"id":"1905.07237","kind":"arxiv","version":1}},"canonical_sha256":"42324986215b61aa452893f5168b2bb5676a5902a391af78810adab971f13828","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42324986215b61aa452893f5168b2bb5676a5902a391af78810adab971f13828","first_computed_at":"2026-05-17T23:45:56.085399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:56.085399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DcLTu00d4YSePKj8194yKV3elspGyWdmMsimq22AVF6IPoLTw9tFRC81gHRc/PBEjA34YoDb/jM1MPRbz5QDCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:56.085947Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.07237","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52f407f3f6f3e09a09a19ce062cf501b5556ab9adc9bbb7ff458cb398d1c020b","sha256:e6e5bd14dc0b6da2e549dbebb741aeb707f9203face932cf5ff9acbca65275e1"],"state_sha256":"a29c64706e7f4295ed5b3f7db4e9cc237afa3d91ecfb7ac491f9e55f9f3c665e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q0KKC8I+COhvzpMYRTM1Gnj/dRnVRZBVVJ9n6y0vnlmGP/v2U/mS4mGNXpYy1Mck9ST7AW0e3782DowEW5hMDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T10:29:26.252055Z","bundle_sha256":"aae4e1cc697f71056ae9dcd2fb2f59c57b785d0b977cfebf6fabb4d811f71075"}}