{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7IKQDUZ7CUX3JVRTJYDEP7DVRO","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":"707cc79d38e01a14fd5a0a758b43424ff07163deb3858ac4f2896ccc61840a57","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-31T03:01:55Z","title_canon_sha256":"e8661c24375d88f99a0ea61eed8d32594a01e59d8f7315c77badfe3e1d9350a7"},"schema_version":"1.0","source":{"id":"1912.13151","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.13151","created_at":"2026-07-05T01:10:57Z"},{"alias_kind":"arxiv_version","alias_value":"1912.13151v2","created_at":"2026-07-05T01:10:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.13151","created_at":"2026-07-05T01:10:57Z"},{"alias_kind":"pith_short_12","alias_value":"7IKQDUZ7CUX3","created_at":"2026-07-05T01:10:57Z"},{"alias_kind":"pith_short_16","alias_value":"7IKQDUZ7CUX3JVRT","created_at":"2026-07-05T01:10:57Z"},{"alias_kind":"pith_short_8","alias_value":"7IKQDUZ7","created_at":"2026-07-05T01:10:57Z"}],"graph_snapshots":[{"event_id":"sha256:6225748ddd1e2740cdb5de338e0d93eb1bc51a5ef1697da399995179724de822","target":"graph","created_at":"2026-07-05T01:10:57Z","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/1912.13151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sequence generation models are commonly refined with reinforcement learning over user-defined metrics. However, high gradient variance hinders the practical use of this method. To stabilize this method, we adapt to contextual generation of categorical sequences a policy gradient estimator, which evaluates a set of correlated Monte Carlo (MC) rollouts for variance control. Due to the correlation, the number of unique rollouts is random and adaptive to model uncertainty; those rollouts naturally become baselines for each other, and hence are combined to effectively reduce gradient variance. We a","authors_text":"Mingyuan Zhou, Xinjie Fan, Yizhe Zhang, Zhendong Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-31T03:01:55Z","title":"Adaptive Correlated Monte Carlo for Contextual Categorical Sequence Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.13151","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":"sha256:5e39344f3cde1ffa39bf23281eaac92dba187ad787e93e4b7a69cc839672c274","target":"record","created_at":"2026-07-05T01:10:57Z","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":"707cc79d38e01a14fd5a0a758b43424ff07163deb3858ac4f2896ccc61840a57","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-31T03:01:55Z","title_canon_sha256":"e8661c24375d88f99a0ea61eed8d32594a01e59d8f7315c77badfe3e1d9350a7"},"schema_version":"1.0","source":{"id":"1912.13151","kind":"arxiv","version":2}},"canonical_sha256":"fa1501d33f152fb4d6334e0647fc758baca42aef3399eff2bf0154de6eb975a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa1501d33f152fb4d6334e0647fc758baca42aef3399eff2bf0154de6eb975a6","first_computed_at":"2026-07-05T01:10:57.209498Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:10:57.209498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LWq4pT3bhWFgbO7K5a3KQ0r5TJ9rCYsPR01NDYIAqIBy99zZpMVpRXiMimHaOojd7vrElfDUCBU3peI+bF1vBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:10:57.209959Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.13151","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e39344f3cde1ffa39bf23281eaac92dba187ad787e93e4b7a69cc839672c274","sha256:6225748ddd1e2740cdb5de338e0d93eb1bc51a5ef1697da399995179724de822"],"state_sha256":"7432f78e69cf1c614b207242b3aa5ac337558deb0399fc5109ad3a20dbb749a4"}