{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YVKZGV7UIPHPV4BWYZJVOOI52V","short_pith_number":"pith:YVKZGV7U","canonical_record":{"source":{"id":"2109.10502","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-22T03:36:51Z","cross_cats_sorted":[],"title_canon_sha256":"982f99738e463e81000aa0cfede12cf1f97978959461d881d1d22b509b2f00f6","abstract_canon_sha256":"254dfec8c6ba177b55c4fdb36c10d2cf86c30b06cb946e894df0c664513c79ad"},"schema_version":"1.0"},"canonical_sha256":"c5559357f443cefaf036c65357391dd57899ec1b5f469fd4b338ddebca2cb025","source":{"kind":"arxiv","id":"2109.10502","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.10502","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"arxiv_version","alias_value":"2109.10502v1","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10502","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"pith_short_12","alias_value":"YVKZGV7UIPHP","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"pith_short_16","alias_value":"YVKZGV7UIPHPV4BW","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"pith_short_8","alias_value":"YVKZGV7U","created_at":"2026-07-05T03:16:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YVKZGV7UIPHPV4BWYZJVOOI52V","target":"record","payload":{"canonical_record":{"source":{"id":"2109.10502","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-22T03:36:51Z","cross_cats_sorted":[],"title_canon_sha256":"982f99738e463e81000aa0cfede12cf1f97978959461d881d1d22b509b2f00f6","abstract_canon_sha256":"254dfec8c6ba177b55c4fdb36c10d2cf86c30b06cb946e894df0c664513c79ad"},"schema_version":"1.0"},"canonical_sha256":"c5559357f443cefaf036c65357391dd57899ec1b5f469fd4b338ddebca2cb025","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:16:37.093428Z","signature_b64":"Xe6VKGgHQ8r4p7ipJ9CIsPiH/S83PrDLKgTTZJfdlrOqkZKdGBmoQ/8ULtGHw+ljDjoTd3r5eXUZ1RWMPcR1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5559357f443cefaf036c65357391dd57899ec1b5f469fd4b338ddebca2cb025","last_reissued_at":"2026-07-05T03:16:37.092752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:16:37.092752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.10502","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":"2026-07-05T03:16:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m6OPtw0KUyMgvIwOeHTi0BZ12oShp4IGDNnKMsVFR5KuGxTCXgJvJ7MyvQ2GAE/9dH2IwW2xS30VUNGWo4W1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:51:37.901202Z"},"content_sha256":"8661c53d985799ccca81e0dd97b8909c97d92521aceba4abada9b8b4ef2421aa","schema_version":"1.0","event_id":"sha256:8661c53d985799ccca81e0dd97b8909c97d92521aceba4abada9b8b4ef2421aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YVKZGV7UIPHPV4BWYZJVOOI52V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Spectral Approach to Off-Policy Evaluation for POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Nan Jiang, Yash Nair","submitted_at":"2021-09-22T03:36:51Z","abstract_excerpt":"We consider off-policy evaluation (OPE) in Partially Observable Markov Decision Processes, where the evaluation policy depends only on observable variables but the behavior policy depends on latent states (Tennenholtz et al. (2020a)). Prior work on this problem uses a causal identification strategy based on one-step observable proxies of the hidden state, which relies on the invertibility of certain one-step moment matrices. In this work, we relax this requirement by using spectral methods and extending one-step proxies both into the past and future. We empirically compare our OPE methods to e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10502","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/2109.10502/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":"2026-07-05T03:16:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N3dSFL+yzBpHfj4++Vgy5gfa2KWyp5S+sLczJBoSAOEMwutcxr9K6ooVIutnx87/D5a+fSVMSX3eE5n7oZN8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:51:37.901838Z"},"content_sha256":"6a8ac957bda68d4bb4b860b8060547d5261775c5d7d38cccc83c0954bf7fef53","schema_version":"1.0","event_id":"sha256:6a8ac957bda68d4bb4b860b8060547d5261775c5d7d38cccc83c0954bf7fef53"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YVKZGV7UIPHPV4BWYZJVOOI52V/bundle.json","state_url":"https://pith.science/pith/YVKZGV7UIPHPV4BWYZJVOOI52V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YVKZGV7UIPHPV4BWYZJVOOI52V/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":"2026-08-09T07:51:37Z","links":{"resolver":"https://pith.science/pith/YVKZGV7UIPHPV4BWYZJVOOI52V","bundle":"https://pith.science/pith/YVKZGV7UIPHPV4BWYZJVOOI52V/bundle.json","state":"https://pith.science/pith/YVKZGV7UIPHPV4BWYZJVOOI52V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YVKZGV7UIPHPV4BWYZJVOOI52V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YVKZGV7UIPHPV4BWYZJVOOI52V","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":"254dfec8c6ba177b55c4fdb36c10d2cf86c30b06cb946e894df0c664513c79ad","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-22T03:36:51Z","title_canon_sha256":"982f99738e463e81000aa0cfede12cf1f97978959461d881d1d22b509b2f00f6"},"schema_version":"1.0","source":{"id":"2109.10502","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.10502","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"arxiv_version","alias_value":"2109.10502v1","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10502","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"pith_short_12","alias_value":"YVKZGV7UIPHP","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"pith_short_16","alias_value":"YVKZGV7UIPHPV4BW","created_at":"2026-07-05T03:16:37Z"},{"alias_kind":"pith_short_8","alias_value":"YVKZGV7U","created_at":"2026-07-05T03:16:37Z"}],"graph_snapshots":[{"event_id":"sha256:6a8ac957bda68d4bb4b860b8060547d5261775c5d7d38cccc83c0954bf7fef53","target":"graph","created_at":"2026-07-05T03:16:37Z","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/2109.10502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider off-policy evaluation (OPE) in Partially Observable Markov Decision Processes, where the evaluation policy depends only on observable variables but the behavior policy depends on latent states (Tennenholtz et al. (2020a)). Prior work on this problem uses a causal identification strategy based on one-step observable proxies of the hidden state, which relies on the invertibility of certain one-step moment matrices. In this work, we relax this requirement by using spectral methods and extending one-step proxies both into the past and future. We empirically compare our OPE methods to e","authors_text":"Nan Jiang, Yash Nair","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-22T03:36:51Z","title":"A Spectral Approach to Off-Policy Evaluation for POMDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10502","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":"sha256:8661c53d985799ccca81e0dd97b8909c97d92521aceba4abada9b8b4ef2421aa","target":"record","created_at":"2026-07-05T03:16:37Z","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":"254dfec8c6ba177b55c4fdb36c10d2cf86c30b06cb946e894df0c664513c79ad","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-22T03:36:51Z","title_canon_sha256":"982f99738e463e81000aa0cfede12cf1f97978959461d881d1d22b509b2f00f6"},"schema_version":"1.0","source":{"id":"2109.10502","kind":"arxiv","version":1}},"canonical_sha256":"c5559357f443cefaf036c65357391dd57899ec1b5f469fd4b338ddebca2cb025","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5559357f443cefaf036c65357391dd57899ec1b5f469fd4b338ddebca2cb025","first_computed_at":"2026-07-05T03:16:37.092752Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:16:37.092752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xe6VKGgHQ8r4p7ipJ9CIsPiH/S83PrDLKgTTZJfdlrOqkZKdGBmoQ/8ULtGHw+ljDjoTd3r5eXUZ1RWMPcR1AA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:16:37.093428Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.10502","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8661c53d985799ccca81e0dd97b8909c97d92521aceba4abada9b8b4ef2421aa","sha256:6a8ac957bda68d4bb4b860b8060547d5261775c5d7d38cccc83c0954bf7fef53"],"state_sha256":"a92f75e3d214798f6f5e5c3a0690a8a97a705e9b0040db281c99601da066bfca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uB7Gfqxgn0IzucW5gWM6vWNz35lJbHVXepERZKovxUIkCJL/ExWUClmxWPxz+NSYjzkfhlFLzocbTHirQ+Z9BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:51:37.908744Z","bundle_sha256":"43f064526e09b49fb327b7a57e2ff3af1de1b2565f0e22766371457576d37d9a"}}