{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OA5M4F5Z36K4OFHI2QDCBP5QID","short_pith_number":"pith:OA5M4F5Z","canonical_record":{"source":{"id":"2305.12944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-22T11:45:23Z","cross_cats_sorted":[],"title_canon_sha256":"5a32e9f356402de996148d5650eee7bc6d485ecca9d4516e4d6e74c760b8d1f8","abstract_canon_sha256":"4713c3035b763e125deb90de3f7c5c5f9fe7b7e51b5bb01ef1d82067e08cbd91"},"schema_version":"1.0"},"canonical_sha256":"703ace17b9df95c714e8d40620bfb040f3174fd7c59226b842dcc352a1020136","source":{"kind":"arxiv","id":"2305.12944","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12944","created_at":"2026-07-05T06:12:24Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12944v1","created_at":"2026-07-05T06:12:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12944","created_at":"2026-07-05T06:12:24Z"},{"alias_kind":"pith_short_12","alias_value":"OA5M4F5Z36K4","created_at":"2026-07-05T06:12:24Z"},{"alias_kind":"pith_short_16","alias_value":"OA5M4F5Z36K4OFHI","created_at":"2026-07-05T06:12:24Z"},{"alias_kind":"pith_short_8","alias_value":"OA5M4F5Z","created_at":"2026-07-05T06:12:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OA5M4F5Z36K4OFHI2QDCBP5QID","target":"record","payload":{"canonical_record":{"source":{"id":"2305.12944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-22T11:45:23Z","cross_cats_sorted":[],"title_canon_sha256":"5a32e9f356402de996148d5650eee7bc6d485ecca9d4516e4d6e74c760b8d1f8","abstract_canon_sha256":"4713c3035b763e125deb90de3f7c5c5f9fe7b7e51b5bb01ef1d82067e08cbd91"},"schema_version":"1.0"},"canonical_sha256":"703ace17b9df95c714e8d40620bfb040f3174fd7c59226b842dcc352a1020136","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:24.844073Z","signature_b64":"UvJ9CtRu03v6xWnftWzGJgICRfbtkj3Wwh2rLOL4pPTmr20jNwtkI4H23Qw8cuRuNghEPNboLYTbOh9AScZLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"703ace17b9df95c714e8d40620bfb040f3174fd7c59226b842dcc352a1020136","last_reissued_at":"2026-07-05T06:12:24.843616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:24.843616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.12944","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":"2026-07-05T06:12:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"khYPzWtIey0hIFrZ1P8VP0t072ugy86QhdMEKeFnfRv7ohN1pTAQ6klkRITrS5dNNSSzzvFrAVNvGaas9WzTAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T02:30:12.989470Z"},"content_sha256":"75ff13b56a4c8e90d2cbe846c1b04983f44a5dcc826b956fa1de7496e7669b0f","schema_version":"1.0","event_id":"sha256:75ff13b56a4c8e90d2cbe846c1b04983f44a5dcc826b956fa1de7496e7669b0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OA5M4F5Z36K4OFHI2QDCBP5QID","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Primal-Dual Reinforcement Learning for Linear MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gergely Neu, Germano Gabbianelli, Matteo Papini, Nneka Okolo","submitted_at":"2023-05-22T11:45:23Z","abstract_excerpt":"Offline Reinforcement Learning (RL) aims to learn a near-optimal policy from a fixed dataset of transitions collected by another policy. This problem has attracted a lot of attention recently, but most existing methods with strong theoretical guarantees are restricted to finite-horizon or tabular settings. In constrast, few algorithms for infinite-horizon settings with function approximation and minimal assumptions on the dataset are both sample and computationally efficient. Another gap in the current literature is the lack of theoretical analysis for the average-reward setting, which is more"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12944","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/2305.12944/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":"2026-07-05T06:12:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DvkBmSYXt/nVyUqJQMkwnFl0JHmWjYwH+7mQ2jYtv/ViwP4Q/omSlS4ym60tvGVNDG/5L65JpvbFfbqEfOWZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T02:30:12.989982Z"},"content_sha256":"b445385cd3fe7f8d567155291a69548bccf334cb9a8a6ecfc3ca919f41f69ac6","schema_version":"1.0","event_id":"sha256:b445385cd3fe7f8d567155291a69548bccf334cb9a8a6ecfc3ca919f41f69ac6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OA5M4F5Z36K4OFHI2QDCBP5QID/bundle.json","state_url":"https://pith.science/pith/OA5M4F5Z36K4OFHI2QDCBP5QID/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OA5M4F5Z36K4OFHI2QDCBP5QID/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":"2026-08-16T02:30:12Z","links":{"resolver":"https://pith.science/pith/OA5M4F5Z36K4OFHI2QDCBP5QID","bundle":"https://pith.science/pith/OA5M4F5Z36K4OFHI2QDCBP5QID/bundle.json","state":"https://pith.science/pith/OA5M4F5Z36K4OFHI2QDCBP5QID/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OA5M4F5Z36K4OFHI2QDCBP5QID/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OA5M4F5Z36K4OFHI2QDCBP5QID","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":"4713c3035b763e125deb90de3f7c5c5f9fe7b7e51b5bb01ef1d82067e08cbd91","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-22T11:45:23Z","title_canon_sha256":"5a32e9f356402de996148d5650eee7bc6d485ecca9d4516e4d6e74c760b8d1f8"},"schema_version":"1.0","source":{"id":"2305.12944","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12944","created_at":"2026-07-05T06:12:24Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12944v1","created_at":"2026-07-05T06:12:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12944","created_at":"2026-07-05T06:12:24Z"},{"alias_kind":"pith_short_12","alias_value":"OA5M4F5Z36K4","created_at":"2026-07-05T06:12:24Z"},{"alias_kind":"pith_short_16","alias_value":"OA5M4F5Z36K4OFHI","created_at":"2026-07-05T06:12:24Z"},{"alias_kind":"pith_short_8","alias_value":"OA5M4F5Z","created_at":"2026-07-05T06:12:24Z"}],"graph_snapshots":[{"event_id":"sha256:b445385cd3fe7f8d567155291a69548bccf334cb9a8a6ecfc3ca919f41f69ac6","target":"graph","created_at":"2026-07-05T06:12:24Z","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/2305.12944/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline Reinforcement Learning (RL) aims to learn a near-optimal policy from a fixed dataset of transitions collected by another policy. This problem has attracted a lot of attention recently, but most existing methods with strong theoretical guarantees are restricted to finite-horizon or tabular settings. In constrast, few algorithms for infinite-horizon settings with function approximation and minimal assumptions on the dataset are both sample and computationally efficient. Another gap in the current literature is the lack of theoretical analysis for the average-reward setting, which is more","authors_text":"Gergely Neu, Germano Gabbianelli, Matteo Papini, Nneka Okolo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-22T11:45:23Z","title":"Offline Primal-Dual Reinforcement Learning for Linear MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12944","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":"sha256:75ff13b56a4c8e90d2cbe846c1b04983f44a5dcc826b956fa1de7496e7669b0f","target":"record","created_at":"2026-07-05T06:12:24Z","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":"4713c3035b763e125deb90de3f7c5c5f9fe7b7e51b5bb01ef1d82067e08cbd91","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-22T11:45:23Z","title_canon_sha256":"5a32e9f356402de996148d5650eee7bc6d485ecca9d4516e4d6e74c760b8d1f8"},"schema_version":"1.0","source":{"id":"2305.12944","kind":"arxiv","version":1}},"canonical_sha256":"703ace17b9df95c714e8d40620bfb040f3174fd7c59226b842dcc352a1020136","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"703ace17b9df95c714e8d40620bfb040f3174fd7c59226b842dcc352a1020136","first_computed_at":"2026-07-05T06:12:24.843616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:24.843616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UvJ9CtRu03v6xWnftWzGJgICRfbtkj3Wwh2rLOL4pPTmr20jNwtkI4H23Qw8cuRuNghEPNboLYTbOh9AScZLAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:24.844073Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.12944","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75ff13b56a4c8e90d2cbe846c1b04983f44a5dcc826b956fa1de7496e7669b0f","sha256:b445385cd3fe7f8d567155291a69548bccf334cb9a8a6ecfc3ca919f41f69ac6"],"state_sha256":"7ffd5e2d34dbdd55ddbda8c8c194db83b86c0b2bd2c4c15dd3238205ccc0487a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EJTX8r+hreRU5YugPV2J2QchJKmeUuL3p7h28QDu1KGF/poMofvNrbEoh8mvGurglcWpMx+PP/lJu8RJKs8oCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T02:30:12.997836Z","bundle_sha256":"e9f178612292ee48ffaa2fd31966ea9bc49d615f514d6daed38359b17cae04e6"}}