{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KIVRZK7KTWDMGRUZRIPQVESAT7","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":"f1c56b0bbcc450dae8ea4e57f9ad7cd26c70278f6e8deadef8daad5ecfa2ba2e","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-19T16:34:20Z","title_canon_sha256":"b3cb5072de7b019621db66ca9dd808393f36fe8db6bfbc36f183f87d7b606526"},"schema_version":"1.0","source":{"id":"2103.10897","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.10897","created_at":"2026-07-05T02:56:57Z"},{"alias_kind":"arxiv_version","alias_value":"2103.10897v3","created_at":"2026-07-05T02:56:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10897","created_at":"2026-07-05T02:56:57Z"},{"alias_kind":"pith_short_12","alias_value":"KIVRZK7KTWDM","created_at":"2026-07-05T02:56:57Z"},{"alias_kind":"pith_short_16","alias_value":"KIVRZK7KTWDMGRUZ","created_at":"2026-07-05T02:56:57Z"},{"alias_kind":"pith_short_8","alias_value":"KIVRZK7K","created_at":"2026-07-05T02:56:57Z"}],"graph_snapshots":[{"event_id":"sha256:bb3c512d99e26e9cf7949bf33186f72a268adb8af4e378b4b0de260138d4ba66","target":"graph","created_at":"2026-07-05T02:56:57Z","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/2103.10897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work introduces Bilinear Classes, a new structural framework, which permit generalization in reinforcement learning in a wide variety of settings through the use of function approximation. The framework incorporates nearly all existing models in which a polynomial sample complexity is achievable, and, notably, also includes new models, such as the Linear $Q^*/V^*$ model in which both the optimal $Q$-function and the optimal $V$-function are linear in some known feature space. Our main result provides an RL algorithm which has polynomial sample complexity for Bilinear Classes; notably, thi","authors_text":"Gaurav Mahajan, Jason D. Lee, Ruosong Wang, Shachar Lovett, Sham M. Kakade, Simon S. Du, Wen Sun","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-19T16:34:20Z","title":"Bilinear Classes: A Structural Framework for Provable Generalization in RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10897","kind":"arxiv","version":3},"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":"sha256:30d97bb43f9edb48515c1dbecf3a10db80c595b062c09b045c72a58756fad8f0","target":"record","created_at":"2026-07-05T02:56:57Z","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":"f1c56b0bbcc450dae8ea4e57f9ad7cd26c70278f6e8deadef8daad5ecfa2ba2e","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-19T16:34:20Z","title_canon_sha256":"b3cb5072de7b019621db66ca9dd808393f36fe8db6bfbc36f183f87d7b606526"},"schema_version":"1.0","source":{"id":"2103.10897","kind":"arxiv","version":3}},"canonical_sha256":"522b1cabea9d86c346998a1f0a92409fcffa957cdbd388b52b1c7f0801670405","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"522b1cabea9d86c346998a1f0a92409fcffa957cdbd388b52b1c7f0801670405","first_computed_at":"2026-07-05T02:56:57.479411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:56:57.479411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4QzXHHTiFwEowFwkVUaoiR1B00sNsUDuX4vGqUfWhrs+djf+a5LZTihvPqD94QHSHjylRlgg9CoL3jP1spvWDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:56:57.480035Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.10897","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30d97bb43f9edb48515c1dbecf3a10db80c595b062c09b045c72a58756fad8f0","sha256:bb3c512d99e26e9cf7949bf33186f72a268adb8af4e378b4b0de260138d4ba66"],"state_sha256":"876deb1c0f70ebdc43757d66a12d2e5be47476fe32f8887be153864a863ce960"}