{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:22LQHGSBFXBOJNAEQYXIHGZCYS","short_pith_number":"pith:22LQHGSB","canonical_record":{"source":{"id":"2007.03438","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T13:45:56Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"662352abf861c71462cfba9888bb115ff2e916953632c7d752eb1ea9f5633160","abstract_canon_sha256":"887d1cc064fc14f08244641edb6cfc378d1ce7a97ed836cb545678cbaafb3b63"},"schema_version":"1.0"},"canonical_sha256":"d697039a412dc2e4b404862e839b22c482ae75ab5f41380c31090cc8577ec2c5","source":{"kind":"arxiv","id":"2007.03438","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03438","created_at":"2026-07-05T01:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03438v2","created_at":"2026-07-05T01:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03438","created_at":"2026-07-05T01:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"22LQHGSBFXBO","created_at":"2026-07-05T01:22:02Z"},{"alias_kind":"pith_short_16","alias_value":"22LQHGSBFXBOJNAE","created_at":"2026-07-05T01:22:02Z"},{"alias_kind":"pith_short_8","alias_value":"22LQHGSB","created_at":"2026-07-05T01:22:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:22LQHGSBFXBOJNAEQYXIHGZCYS","target":"record","payload":{"canonical_record":{"source":{"id":"2007.03438","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T13:45:56Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"662352abf861c71462cfba9888bb115ff2e916953632c7d752eb1ea9f5633160","abstract_canon_sha256":"887d1cc064fc14f08244641edb6cfc378d1ce7a97ed836cb545678cbaafb3b63"},"schema_version":"1.0"},"canonical_sha256":"d697039a412dc2e4b404862e839b22c482ae75ab5f41380c31090cc8577ec2c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:22:02.490407Z","signature_b64":"ey/5qOxsVs6poL0wfVCVrUOpqPJP3s5T8bkxqaYJHFPQPpe4hdmYRMOohjUxOo6PWo/a5fcxX3tPFIaGoBo6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d697039a412dc2e4b404862e839b22c482ae75ab5f41380c31090cc8577ec2c5","last_reissued_at":"2026-07-05T01:22:02.489990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:22:02.489990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.03438","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":"2026-07-05T01:22:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vLHxtbzNICmtD8Q5MeK2aqj2B9tEtyqJHQhFGv4OiTz1gViQGsYiSIQShmWXiFqrG51QU1KrermWKcFfuAHYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T06:20:28.858288Z"},"content_sha256":"2c550a3e88340df8ca46522358a9aa50b11c0666a8d4cf086f3c88afb7aa9f76","schema_version":"1.0","event_id":"sha256:2c550a3e88340df8ca46522358a9aa50b11c0666a8d4cf086f3c88afb7aa9f76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:22LQHGSBFXBOJNAEQYXIHGZCYS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Off-Policy Evaluation via the Regularized Lagrangian","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Dai, Dale Schuurmans, Lihong Li, Mengjiao Yang, Ofir Nachum","submitted_at":"2020-07-07T13:45:56Z","abstract_excerpt":"The recently proposed distribution correction estimation (DICE) family of estimators has advanced the state of the art in off-policy evaluation from behavior-agnostic data. While these estimators all perform some form of stationary distribution correction, they arise from different derivations and objective functions. In this paper, we unify these estimators as regularized Lagrangians of the same linear program. The unification allows us to expand the space of DICE estimators to new alternatives that demonstrate improved performance. More importantly, by analyzing the expanded space of estimat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03438","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.03438/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:22:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+zbWGJ4nuyK7M+vHjtum35GWPbFf4P+mI22zGGIRpZmW7EbBLDsXR4fPzfB0q53NIdoGDhLzKtqKRXXfQtZUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T06:20:28.859224Z"},"content_sha256":"a8d424bb8a43678988d82def8f8e0bdecbb8d0efff64057e1d99000f503e430f","schema_version":"1.0","event_id":"sha256:a8d424bb8a43678988d82def8f8e0bdecbb8d0efff64057e1d99000f503e430f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/22LQHGSBFXBOJNAEQYXIHGZCYS/bundle.json","state_url":"https://pith.science/pith/22LQHGSBFXBOJNAEQYXIHGZCYS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/22LQHGSBFXBOJNAEQYXIHGZCYS/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":"2026-08-01T06:20:29Z","links":{"resolver":"https://pith.science/pith/22LQHGSBFXBOJNAEQYXIHGZCYS","bundle":"https://pith.science/pith/22LQHGSBFXBOJNAEQYXIHGZCYS/bundle.json","state":"https://pith.science/pith/22LQHGSBFXBOJNAEQYXIHGZCYS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/22LQHGSBFXBOJNAEQYXIHGZCYS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:22LQHGSBFXBOJNAEQYXIHGZCYS","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":"887d1cc064fc14f08244641edb6cfc378d1ce7a97ed836cb545678cbaafb3b63","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T13:45:56Z","title_canon_sha256":"662352abf861c71462cfba9888bb115ff2e916953632c7d752eb1ea9f5633160"},"schema_version":"1.0","source":{"id":"2007.03438","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03438","created_at":"2026-07-05T01:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03438v2","created_at":"2026-07-05T01:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03438","created_at":"2026-07-05T01:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"22LQHGSBFXBO","created_at":"2026-07-05T01:22:02Z"},{"alias_kind":"pith_short_16","alias_value":"22LQHGSBFXBOJNAE","created_at":"2026-07-05T01:22:02Z"},{"alias_kind":"pith_short_8","alias_value":"22LQHGSB","created_at":"2026-07-05T01:22:02Z"}],"graph_snapshots":[{"event_id":"sha256:a8d424bb8a43678988d82def8f8e0bdecbb8d0efff64057e1d99000f503e430f","target":"graph","created_at":"2026-07-05T01:22:02Z","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/2007.03438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recently proposed distribution correction estimation (DICE) family of estimators has advanced the state of the art in off-policy evaluation from behavior-agnostic data. While these estimators all perform some form of stationary distribution correction, they arise from different derivations and objective functions. In this paper, we unify these estimators as regularized Lagrangians of the same linear program. The unification allows us to expand the space of DICE estimators to new alternatives that demonstrate improved performance. More importantly, by analyzing the expanded space of estimat","authors_text":"Bo Dai, Dale Schuurmans, Lihong Li, Mengjiao Yang, Ofir Nachum","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T13:45:56Z","title":"Off-Policy Evaluation via the Regularized Lagrangian"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03438","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":"sha256:2c550a3e88340df8ca46522358a9aa50b11c0666a8d4cf086f3c88afb7aa9f76","target":"record","created_at":"2026-07-05T01:22:02Z","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":"887d1cc064fc14f08244641edb6cfc378d1ce7a97ed836cb545678cbaafb3b63","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T13:45:56Z","title_canon_sha256":"662352abf861c71462cfba9888bb115ff2e916953632c7d752eb1ea9f5633160"},"schema_version":"1.0","source":{"id":"2007.03438","kind":"arxiv","version":2}},"canonical_sha256":"d697039a412dc2e4b404862e839b22c482ae75ab5f41380c31090cc8577ec2c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d697039a412dc2e4b404862e839b22c482ae75ab5f41380c31090cc8577ec2c5","first_computed_at":"2026-07-05T01:22:02.489990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:22:02.489990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ey/5qOxsVs6poL0wfVCVrUOpqPJP3s5T8bkxqaYJHFPQPpe4hdmYRMOohjUxOo6PWo/a5fcxX3tPFIaGoBo6AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:22:02.490407Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.03438","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c550a3e88340df8ca46522358a9aa50b11c0666a8d4cf086f3c88afb7aa9f76","sha256:a8d424bb8a43678988d82def8f8e0bdecbb8d0efff64057e1d99000f503e430f"],"state_sha256":"71e33c37b2ea5da6793f6c2d632283cfd351a5617b4a40d2ef223dd309523478"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VJZCSsnQ8/yY7m3z6zkwc9/LzAEu1MaaMV/m3ducHE6DQM8jxPhmi6+VknhouDqSRe62rbQ4eNBihGLlV+XVCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T06:20:29.041811Z","bundle_sha256":"91ab541358686339c864e0933cdb2a4c81e02bb2bd11d5493246a55bd3fc8b5f"}}