{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:MTPCHG33LSXM4FR3DOQVAZ7CVF","short_pith_number":"pith:MTPCHG33","canonical_record":{"source":{"id":"2212.07486","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T20:07:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"366e92a09711480009398387508bfdc782d938af8c05e7548179b3b4c9734bca","abstract_canon_sha256":"f4bdec4ec4304e0cf9cb357222b05c2487b14855b8b3a3c42f831c884b13f0be"},"schema_version":"1.0"},"canonical_sha256":"64de239b7b5caece163b1ba15067e2a95bae02539ef3323e5ab906740dc89df0","source":{"kind":"arxiv","id":"2212.07486","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.07486","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"arxiv_version","alias_value":"2212.07486v1","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07486","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"pith_short_12","alias_value":"MTPCHG33LSXM","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"pith_short_16","alias_value":"MTPCHG33LSXM4FR3","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"pith_short_8","alias_value":"MTPCHG33","created_at":"2026-07-05T05:25:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:MTPCHG33LSXM4FR3DOQVAZ7CVF","target":"record","payload":{"canonical_record":{"source":{"id":"2212.07486","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T20:07:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"366e92a09711480009398387508bfdc782d938af8c05e7548179b3b4c9734bca","abstract_canon_sha256":"f4bdec4ec4304e0cf9cb357222b05c2487b14855b8b3a3c42f831c884b13f0be"},"schema_version":"1.0"},"canonical_sha256":"64de239b7b5caece163b1ba15067e2a95bae02539ef3323e5ab906740dc89df0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:33.496458Z","signature_b64":"GdbhhpBzY+B1x4DsmKz8JM17oDmmGu39CKS5tFYwJPZDlp5MCXq2OwcZ2KD2OF2VN6ojXn2/cNn2KxCZEoeXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64de239b7b5caece163b1ba15067e2a95bae02539ef3323e5ab906740dc89df0","last_reissued_at":"2026-07-05T05:25:33.495974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:33.495974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.07486","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":"2026-07-05T05:25:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TFgo4sY8I2VBg3xrC5u5F1PieoL7OehHaWnZjtbKSrqMtkT4aTGwlPzXWfmvZZbw7bH0EsXkHyu5VNKtoV2fDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:03:51.581450Z"},"content_sha256":"796c57668b8fe1f662e8b914f6e21a41c4770c5e690e67194285e6694055b0ef","schema_version":"1.0","event_id":"sha256:796c57668b8fe1f662e8b914f6e21a41c4770c5e690e67194285e6694055b0ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:MTPCHG33LSXM4FR3DOQVAZ7CVF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Marginalized Importance Sampling to High-Dimensional State-Spaces via State Abstraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Brahma S. Pavse, Josiah P. Hanna","submitted_at":"2022-12-14T20:07:33Z","abstract_excerpt":"We consider the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where the goal is to estimate the performance of an evaluation policy, $\\pi_e$, using a fixed dataset, $\\mathcal{D}$, collected by one or more policies that may be different from $\\pi_e$. Current OPE algorithms may produce poor OPE estimates under policy distribution shift i.e., when the probability of a particular state-action pair occurring under $\\pi_e$ is very different from the probability of that same pair occurring in $\\mathcal{D}$ (Voloshin et al. 2021, Fu et al. 2021). In this work, we propose to im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07486","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2212.07486/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":"2026-07-05T05:25:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QCnVdH04ernarPeYfU6usmFQjIQQ0nJS7ZkG1MKQXPXSBSJbl8w5yYaRHw0kpbOLIguenee45Ky8C5odHEPADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:03:51.582635Z"},"content_sha256":"eef9c4edc993e435858564c2a30d7463e7814fb5b5f84efa8b76f0c098f738bc","schema_version":"1.0","event_id":"sha256:eef9c4edc993e435858564c2a30d7463e7814fb5b5f84efa8b76f0c098f738bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MTPCHG33LSXM4FR3DOQVAZ7CVF/bundle.json","state_url":"https://pith.science/pith/MTPCHG33LSXM4FR3DOQVAZ7CVF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MTPCHG33LSXM4FR3DOQVAZ7CVF/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":"2026-08-17T15:03:51Z","links":{"resolver":"https://pith.science/pith/MTPCHG33LSXM4FR3DOQVAZ7CVF","bundle":"https://pith.science/pith/MTPCHG33LSXM4FR3DOQVAZ7CVF/bundle.json","state":"https://pith.science/pith/MTPCHG33LSXM4FR3DOQVAZ7CVF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MTPCHG33LSXM4FR3DOQVAZ7CVF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MTPCHG33LSXM4FR3DOQVAZ7CVF","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":"f4bdec4ec4304e0cf9cb357222b05c2487b14855b8b3a3c42f831c884b13f0be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T20:07:33Z","title_canon_sha256":"366e92a09711480009398387508bfdc782d938af8c05e7548179b3b4c9734bca"},"schema_version":"1.0","source":{"id":"2212.07486","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.07486","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"arxiv_version","alias_value":"2212.07486v1","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07486","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"pith_short_12","alias_value":"MTPCHG33LSXM","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"pith_short_16","alias_value":"MTPCHG33LSXM4FR3","created_at":"2026-07-05T05:25:33Z"},{"alias_kind":"pith_short_8","alias_value":"MTPCHG33","created_at":"2026-07-05T05:25:33Z"}],"graph_snapshots":[{"event_id":"sha256:eef9c4edc993e435858564c2a30d7463e7814fb5b5f84efa8b76f0c098f738bc","target":"graph","created_at":"2026-07-05T05:25:33Z","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/2212.07486/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where the goal is to estimate the performance of an evaluation policy, $\\pi_e$, using a fixed dataset, $\\mathcal{D}$, collected by one or more policies that may be different from $\\pi_e$. Current OPE algorithms may produce poor OPE estimates under policy distribution shift i.e., when the probability of a particular state-action pair occurring under $\\pi_e$ is very different from the probability of that same pair occurring in $\\mathcal{D}$ (Voloshin et al. 2021, Fu et al. 2021). In this work, we propose to im","authors_text":"Brahma S. Pavse, Josiah P. Hanna","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T20:07:33Z","title":"Scaling Marginalized Importance Sampling to High-Dimensional State-Spaces via State Abstraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07486","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":"sha256:796c57668b8fe1f662e8b914f6e21a41c4770c5e690e67194285e6694055b0ef","target":"record","created_at":"2026-07-05T05:25:33Z","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":"f4bdec4ec4304e0cf9cb357222b05c2487b14855b8b3a3c42f831c884b13f0be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T20:07:33Z","title_canon_sha256":"366e92a09711480009398387508bfdc782d938af8c05e7548179b3b4c9734bca"},"schema_version":"1.0","source":{"id":"2212.07486","kind":"arxiv","version":1}},"canonical_sha256":"64de239b7b5caece163b1ba15067e2a95bae02539ef3323e5ab906740dc89df0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64de239b7b5caece163b1ba15067e2a95bae02539ef3323e5ab906740dc89df0","first_computed_at":"2026-07-05T05:25:33.495974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:25:33.495974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GdbhhpBzY+B1x4DsmKz8JM17oDmmGu39CKS5tFYwJPZDlp5MCXq2OwcZ2KD2OF2VN6ojXn2/cNn2KxCZEoeXBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:25:33.496458Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.07486","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:796c57668b8fe1f662e8b914f6e21a41c4770c5e690e67194285e6694055b0ef","sha256:eef9c4edc993e435858564c2a30d7463e7814fb5b5f84efa8b76f0c098f738bc"],"state_sha256":"a561578c2f8b657a66c257da136ed96750be1a5c2028aac16e210bf47919cc77"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zbUyOG7lU+DReqV+Kbx1UEWnMtrmrHmb2OwpiFsDz+68omIXGoAHidcDVe2ig0D3rRyyCWZ0YE5iV89eQEfUBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T15:03:51.593917Z","bundle_sha256":"b5e6bd5c64a9d8c01ffff1b67e7452cb5bf2c3a31ded041345038b7b3ee2cb0d"}}