{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3BQWZ52JXPWGXO5WYSI2RITLWK","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":"8c2c04c78f505aaf54ce72cf57e7e730508447bedb749e4f4fb6076ef5b7bfee","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-29T22:10:11Z","title_canon_sha256":"0557ddbe1f980289245498e81c630ada919021fff4e9154be74d6bf535897f53"},"schema_version":"1.0","source":{"id":"2001.11113","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.11113","created_at":"2026-07-05T01:54:42Z"},{"alias_kind":"arxiv_version","alias_value":"2001.11113v7","created_at":"2026-07-05T01:54:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.11113","created_at":"2026-07-05T01:54:42Z"},{"alias_kind":"pith_short_12","alias_value":"3BQWZ52JXPWG","created_at":"2026-07-05T01:54:42Z"},{"alias_kind":"pith_short_16","alias_value":"3BQWZ52JXPWGXO5W","created_at":"2026-07-05T01:54:42Z"},{"alias_kind":"pith_short_8","alias_value":"3BQWZ52J","created_at":"2026-07-05T01:54:42Z"}],"graph_snapshots":[{"event_id":"sha256:0b3741d0461fd08ba24046103cbae67a1394a2bac74187185b4bde3f9488f82d","target":"graph","created_at":"2026-07-05T01:54:42Z","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/2001.11113/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present GradientDICE for estimating the density ratio between the state distribution of the target policy and the sampling distribution in off-policy reinforcement learning. GradientDICE fixes several problems of GenDICE (Zhang et al., 2020), the state-of-the-art for estimating such density ratios. Namely, the optimization problem in GenDICE is not a convex-concave saddle-point problem once nonlinearity in optimization variable parameterization is introduced to ensure positivity, so any primal-dual algorithm is not guaranteed to converge or find the desired solution. However, such nonlinear","authors_text":"Bo Liu, Shangtong Zhang, Shimon Whiteson","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-29T22:10:11Z","title":"GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.11113","kind":"arxiv","version":7},"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:cb75948aa6e4e408c497c1939f7f5039e5ef9160e443a751d6625c14a988844b","target":"record","created_at":"2026-07-05T01:54:42Z","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":"8c2c04c78f505aaf54ce72cf57e7e730508447bedb749e4f4fb6076ef5b7bfee","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-29T22:10:11Z","title_canon_sha256":"0557ddbe1f980289245498e81c630ada919021fff4e9154be74d6bf535897f53"},"schema_version":"1.0","source":{"id":"2001.11113","kind":"arxiv","version":7}},"canonical_sha256":"d8616cf749bbec6bbbb6c491a8a26bb283be6aded42bb9e79875c02fde160b77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8616cf749bbec6bbbb6c491a8a26bb283be6aded42bb9e79875c02fde160b77","first_computed_at":"2026-07-05T01:54:42.595457Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:54:42.595457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6e4IbFCTvY3y/qsWu5Dtg1TFixpG22jk4tO2vAE8YrUEFfm8y6f+1vhvX/SGQEq7WXQHb3YwnxQCn4oThG1dDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:54:42.595884Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.11113","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb75948aa6e4e408c497c1939f7f5039e5ef9160e443a751d6625c14a988844b","sha256:0b3741d0461fd08ba24046103cbae67a1394a2bac74187185b4bde3f9488f82d"],"state_sha256":"f18c14d58e8a6738826a6d09b2028a4278d7a6b755984eaae33bd2dd2537f040"}