{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YNVAIZKQTMUNCFBI3RPRPDUSXI","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":"7241f3c1badf9530171f9f674afab4fb9fa4a58af2247e3b27d3c762679325cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-15T18:39:22Z","title_canon_sha256":"12032393abede4d2c8dcb085182c15ca8765c9d4cfd01c74c1d9794982b94477"},"schema_version":"1.0","source":{"id":"2409.09819","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09819","created_at":"2026-07-05T09:20:02Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09819v2","created_at":"2026-07-05T09:20:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09819","created_at":"2026-07-05T09:20:02Z"},{"alias_kind":"pith_short_12","alias_value":"YNVAIZKQTMUN","created_at":"2026-07-05T09:20:02Z"},{"alias_kind":"pith_short_16","alias_value":"YNVAIZKQTMUNCFBI","created_at":"2026-07-05T09:20:02Z"},{"alias_kind":"pith_short_8","alias_value":"YNVAIZKQ","created_at":"2026-07-05T09:20:02Z"}],"graph_snapshots":[{"event_id":"sha256:d59876524e5edfe4a7a3f74f378aec896add12f81d20f2eed1f4cf5697f24395","target":"graph","created_at":"2026-07-05T09:20:02Z","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/2409.09819/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Variance regularized counterfactual risk minimization (VRCRM) has been proposed as an alternative off-policy learning (OPL) method. VRCRM method uses a lower-bound on the $f$-divergence between the logging policy and the target policy as regularization during learning and was shown to improve performance over existing OPL alternatives on multi-label classification tasks. In this work, we revisit the original experimental setting of VRCRM and propose to minimize the $f$-divergence directly, instead of optimizing for the lower bound using a $f$-GAN approach. Surprisingly, we were unable to repro","authors_text":"Harrie Oosterhuis, Hua Chang Bakker, Shashank Gupta","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-15T18:39:22Z","title":"A Simpler Alternative to Variational Regularized Counterfactual Risk Minimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09819","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":"sha256:112da352fb36c7528271a066a06284b12f193a6b7d854dd05d31878f311230a2","target":"record","created_at":"2026-07-05T09:20:02Z","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":"7241f3c1badf9530171f9f674afab4fb9fa4a58af2247e3b27d3c762679325cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-15T18:39:22Z","title_canon_sha256":"12032393abede4d2c8dcb085182c15ca8765c9d4cfd01c74c1d9794982b94477"},"schema_version":"1.0","source":{"id":"2409.09819","kind":"arxiv","version":2}},"canonical_sha256":"c36a0465509b28d11428dc5f178e92ba19122670978a3edb53478bd424153f5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c36a0465509b28d11428dc5f178e92ba19122670978a3edb53478bd424153f5b","first_computed_at":"2026-07-05T09:20:02.765774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:02.765774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LL5mForlvyzaFXbgtWuJ3+RAYulXV92jwUMR0593vvFLpKs79uJlhgP8mtwBp/q+R5MXXtQHVwwaVRn1FrFNDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:02.766247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.09819","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:112da352fb36c7528271a066a06284b12f193a6b7d854dd05d31878f311230a2","sha256:d59876524e5edfe4a7a3f74f378aec896add12f81d20f2eed1f4cf5697f24395"],"state_sha256":"4992efb439d9ba0be9a22a99fd7a8991847169c56bcc8a349bd65c2f3859aa48"}