{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XQ6DRVXQV3HDHKWLDQB54PG4IJ","short_pith_number":"pith:XQ6DRVXQ","canonical_record":{"source":{"id":"2212.08765","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-17T00:26:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"37a6e12cda55246fbf6e27868a5f4bd793e30355ecbe12e33f525304c1dfb7cc","abstract_canon_sha256":"6509b35255ff51a0dc222be50c093c0c1b01c4deedccb157b676cd63198c7667"},"schema_version":"1.0"},"canonical_sha256":"bc3c38d6f0aece33aacb1c03de3cdc4254a6778cd2af2fab73e96747eb6ca1db","source":{"kind":"arxiv","id":"2212.08765","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08765","created_at":"2026-07-05T05:48:45Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08765v2","created_at":"2026-07-05T05:48:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08765","created_at":"2026-07-05T05:48:45Z"},{"alias_kind":"pith_short_12","alias_value":"XQ6DRVXQV3HD","created_at":"2026-07-05T05:48:45Z"},{"alias_kind":"pith_short_16","alias_value":"XQ6DRVXQV3HDHKWL","created_at":"2026-07-05T05:48:45Z"},{"alias_kind":"pith_short_8","alias_value":"XQ6DRVXQ","created_at":"2026-07-05T05:48:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XQ6DRVXQV3HDHKWLDQB54PG4IJ","target":"record","payload":{"canonical_record":{"source":{"id":"2212.08765","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-17T00:26:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"37a6e12cda55246fbf6e27868a5f4bd793e30355ecbe12e33f525304c1dfb7cc","abstract_canon_sha256":"6509b35255ff51a0dc222be50c093c0c1b01c4deedccb157b676cd63198c7667"},"schema_version":"1.0"},"canonical_sha256":"bc3c38d6f0aece33aacb1c03de3cdc4254a6778cd2af2fab73e96747eb6ca1db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:45.998443Z","signature_b64":"WJXFWz7EiRsEIrfhjo3QI0+nZC6yPic3STm8BuA3VAoLO39UM2PhRYRUhpMYPMKjuAMDrPMoOEgjGxmR00AeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc3c38d6f0aece33aacb1c03de3cdc4254a6778cd2af2fab73e96747eb6ca1db","last_reissued_at":"2026-07-05T05:48:45.997973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:45.997973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.08765","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":"2026-07-05T05:48:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lCpDu+ZC3oV1aNUyiheAdx/bmOM9OOUTGWrSjvPnxoFJA8hjzNmIkeWAMtVM31lldOCuKbeGsUlHxE7X4+DBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T18:29:23.773929Z"},"content_sha256":"34536f6aa5f26b62be4aa9c0c5ff25730e14bacd8956dba8970bb1e757f9777b","schema_version":"1.0","event_id":"sha256:34536f6aa5f26b62be4aa9c0c5ff25730e14bacd8956dba8970bb1e757f9777b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XQ6DRVXQV3HDHKWLDQB54PG4IJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Latent Variable Representation for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Dai, Chenjun Xiao, Dale Schuurmans, Na Li, Sujay Sanghavi, Tianjun Zhang, Tongzheng Ren, Zhaoran Wang","submitted_at":"2022-12-17T00:26:31Z","abstract_excerpt":"Deep latent variable models have achieved significant empirical successes in model-based reinforcement learning (RL) due to their expressiveness in modeling complex transition dynamics. On the other hand, it remains unclear theoretically and empirically how latent variable models may facilitate learning, planning, and exploration to improve the sample efficiency of RL. In this paper, we provide a representation view of the latent variable models for state-action value functions, which allows both tractable variational learning algorithm and effective implementation of the optimism/pessimism pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08765","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/2212.08765/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":"2026-07-05T05:48:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OKbsOW+ub37vMoyfnaFef9F2wqNv0YByynmaWlIe3+IhU+VHuoGsg/nm4ARv/5uB5vOQ727DoDOIJY1gBJy8DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T18:29:23.774653Z"},"content_sha256":"a819264cd56f3fd868f834a500f252c70f29967704f5d33e02631201272f8ea9","schema_version":"1.0","event_id":"sha256:a819264cd56f3fd868f834a500f252c70f29967704f5d33e02631201272f8ea9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XQ6DRVXQV3HDHKWLDQB54PG4IJ/bundle.json","state_url":"https://pith.science/pith/XQ6DRVXQV3HDHKWLDQB54PG4IJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XQ6DRVXQV3HDHKWLDQB54PG4IJ/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":"2026-08-22T18:29:23Z","links":{"resolver":"https://pith.science/pith/XQ6DRVXQV3HDHKWLDQB54PG4IJ","bundle":"https://pith.science/pith/XQ6DRVXQV3HDHKWLDQB54PG4IJ/bundle.json","state":"https://pith.science/pith/XQ6DRVXQV3HDHKWLDQB54PG4IJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XQ6DRVXQV3HDHKWLDQB54PG4IJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XQ6DRVXQV3HDHKWLDQB54PG4IJ","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":"6509b35255ff51a0dc222be50c093c0c1b01c4deedccb157b676cd63198c7667","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-17T00:26:31Z","title_canon_sha256":"37a6e12cda55246fbf6e27868a5f4bd793e30355ecbe12e33f525304c1dfb7cc"},"schema_version":"1.0","source":{"id":"2212.08765","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08765","created_at":"2026-07-05T05:48:45Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08765v2","created_at":"2026-07-05T05:48:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08765","created_at":"2026-07-05T05:48:45Z"},{"alias_kind":"pith_short_12","alias_value":"XQ6DRVXQV3HD","created_at":"2026-07-05T05:48:45Z"},{"alias_kind":"pith_short_16","alias_value":"XQ6DRVXQV3HDHKWL","created_at":"2026-07-05T05:48:45Z"},{"alias_kind":"pith_short_8","alias_value":"XQ6DRVXQ","created_at":"2026-07-05T05:48:45Z"}],"graph_snapshots":[{"event_id":"sha256:a819264cd56f3fd868f834a500f252c70f29967704f5d33e02631201272f8ea9","target":"graph","created_at":"2026-07-05T05:48:45Z","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/2212.08765/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep latent variable models have achieved significant empirical successes in model-based reinforcement learning (RL) due to their expressiveness in modeling complex transition dynamics. On the other hand, it remains unclear theoretically and empirically how latent variable models may facilitate learning, planning, and exploration to improve the sample efficiency of RL. In this paper, we provide a representation view of the latent variable models for state-action value functions, which allows both tractable variational learning algorithm and effective implementation of the optimism/pessimism pr","authors_text":"Bo Dai, Chenjun Xiao, Dale Schuurmans, Na Li, Sujay Sanghavi, Tianjun Zhang, Tongzheng Ren, Zhaoran Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-17T00:26:31Z","title":"Latent Variable Representation for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08765","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":"sha256:34536f6aa5f26b62be4aa9c0c5ff25730e14bacd8956dba8970bb1e757f9777b","target":"record","created_at":"2026-07-05T05:48:45Z","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":"6509b35255ff51a0dc222be50c093c0c1b01c4deedccb157b676cd63198c7667","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-17T00:26:31Z","title_canon_sha256":"37a6e12cda55246fbf6e27868a5f4bd793e30355ecbe12e33f525304c1dfb7cc"},"schema_version":"1.0","source":{"id":"2212.08765","kind":"arxiv","version":2}},"canonical_sha256":"bc3c38d6f0aece33aacb1c03de3cdc4254a6778cd2af2fab73e96747eb6ca1db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc3c38d6f0aece33aacb1c03de3cdc4254a6778cd2af2fab73e96747eb6ca1db","first_computed_at":"2026-07-05T05:48:45.997973Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:48:45.997973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WJXFWz7EiRsEIrfhjo3QI0+nZC6yPic3STm8BuA3VAoLO39UM2PhRYRUhpMYPMKjuAMDrPMoOEgjGxmR00AeAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:48:45.998443Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.08765","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34536f6aa5f26b62be4aa9c0c5ff25730e14bacd8956dba8970bb1e757f9777b","sha256:a819264cd56f3fd868f834a500f252c70f29967704f5d33e02631201272f8ea9"],"state_sha256":"c64defad87e03c1409f2dd795d37c933f82efdaaf864c2fdaabfc469d2f4c536"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qTE4IqZqdlAoHYI0gdS+i8B1KO+XiggC9p+6PedMriMMmgqXmLeV78LBU5N89O952o4PIEu1WnSS2nf7CnnzDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T18:29:23.780082Z","bundle_sha256":"dfb9387db609c82ee08933a1fbee8f10fb5bbdcec71ab0c1fa1416459f9e6fe5"}}