{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6KITGLWOP6GDVMWY6QKXUVVCBN","short_pith_number":"pith:6KITGLWO","canonical_record":{"source":{"id":"2305.11340","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T23:23:08Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"49cbae1af59efbc3770391f5ab526bd849b9d40121219212a10ebe42d5369191","abstract_canon_sha256":"e607d12ce91129aea33b9aa64bac3516cf69811db3d4d4b36007aa48e1ba14ab"},"schema_version":"1.0"},"canonical_sha256":"f291332ece7f8c3ab2d8f4157a56a20b783eed379a98c17efbebec1940a73476","source":{"kind":"arxiv","id":"2305.11340","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11340","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11340v1","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11340","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"pith_short_12","alias_value":"6KITGLWOP6GD","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"pith_short_16","alias_value":"6KITGLWOP6GDVMWY","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"pith_short_8","alias_value":"6KITGLWO","created_at":"2026-07-05T06:11:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6KITGLWOP6GDVMWY6QKXUVVCBN","target":"record","payload":{"canonical_record":{"source":{"id":"2305.11340","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T23:23:08Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"49cbae1af59efbc3770391f5ab526bd849b9d40121219212a10ebe42d5369191","abstract_canon_sha256":"e607d12ce91129aea33b9aa64bac3516cf69811db3d4d4b36007aa48e1ba14ab"},"schema_version":"1.0"},"canonical_sha256":"f291332ece7f8c3ab2d8f4157a56a20b783eed379a98c17efbebec1940a73476","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:35.901696Z","signature_b64":"LQQaUu7GxAdMMcSLheGIvEad9J7IaljtXvlVlHViupt9MYOqOrUUEU8wkxIDtTpqO2JmlZQdKZJmQxlBFsRZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f291332ece7f8c3ab2d8f4157a56a20b783eed379a98c17efbebec1940a73476","last_reissued_at":"2026-07-05T06:11:35.901275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:35.901275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.11340","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":"2026-07-05T06:11:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G8D3ul+XLWjrSh+g5pOtvQX35Lm+nlF7sthwutmr7Qh7/BJbYuZX5beAxa8raSOJEeVXWJkA/mnN6PUpYnk7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T09:05:47.070372Z"},"content_sha256":"4c3f0cbd0ce047b38691db40f9570a0c9e16a4280d9003c0246b8bc3e94bcfbc","schema_version":"1.0","event_id":"sha256:4c3f0cbd0ce047b38691db40f9570a0c9e16a4280d9003c0246b8bc3e94bcfbc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6KITGLWOP6GDVMWY6QKXUVVCBN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian Reparameterization of Reward-Conditioned Reinforcement Learning with Energy-based Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Ding Zhao, Marco Pavone, Tong Che, Wenhao Ding","submitted_at":"2023-05-18T23:23:08Z","abstract_excerpt":"Recently, reward-conditioned reinforcement learning (RCRL) has gained popularity due to its simplicity, flexibility, and off-policy nature. However, we will show that current RCRL approaches are fundamentally limited and fail to address two critical challenges of RCRL -- improving generalization on high reward-to-go (RTG) inputs, and avoiding out-of-distribution (OOD) RTG queries during testing time. To address these challenges when training vanilla RCRL architectures, we propose Bayesian Reparameterized RCRL (BR-RCRL), a novel set of inductive biases for RCRL inspired by Bayes' theorem. BR-RC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11340","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/2305.11340/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":"2026-07-05T06:11:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MCX1Bq3sQw+eTlLS7JmQnl3kBcWUgPCeUPJwVueaZifX8Lk/G9F8iICmqkgoHv8n/r0O5Z+k+LOY4Xe6U8rxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T09:05:47.070811Z"},"content_sha256":"5819d606bf8ce5eda6f06d11b0776ecc858b21008c97676e23c490b19a5b46ca","schema_version":"1.0","event_id":"sha256:5819d606bf8ce5eda6f06d11b0776ecc858b21008c97676e23c490b19a5b46ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6KITGLWOP6GDVMWY6QKXUVVCBN/bundle.json","state_url":"https://pith.science/pith/6KITGLWOP6GDVMWY6QKXUVVCBN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6KITGLWOP6GDVMWY6QKXUVVCBN/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":"2026-07-11T09:05:47Z","links":{"resolver":"https://pith.science/pith/6KITGLWOP6GDVMWY6QKXUVVCBN","bundle":"https://pith.science/pith/6KITGLWOP6GDVMWY6QKXUVVCBN/bundle.json","state":"https://pith.science/pith/6KITGLWOP6GDVMWY6QKXUVVCBN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6KITGLWOP6GDVMWY6QKXUVVCBN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6KITGLWOP6GDVMWY6QKXUVVCBN","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":"e607d12ce91129aea33b9aa64bac3516cf69811db3d4d4b36007aa48e1ba14ab","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T23:23:08Z","title_canon_sha256":"49cbae1af59efbc3770391f5ab526bd849b9d40121219212a10ebe42d5369191"},"schema_version":"1.0","source":{"id":"2305.11340","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11340","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11340v1","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11340","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"pith_short_12","alias_value":"6KITGLWOP6GD","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"pith_short_16","alias_value":"6KITGLWOP6GDVMWY","created_at":"2026-07-05T06:11:35Z"},{"alias_kind":"pith_short_8","alias_value":"6KITGLWO","created_at":"2026-07-05T06:11:35Z"}],"graph_snapshots":[{"event_id":"sha256:5819d606bf8ce5eda6f06d11b0776ecc858b21008c97676e23c490b19a5b46ca","target":"graph","created_at":"2026-07-05T06:11:35Z","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/2305.11340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, reward-conditioned reinforcement learning (RCRL) has gained popularity due to its simplicity, flexibility, and off-policy nature. However, we will show that current RCRL approaches are fundamentally limited and fail to address two critical challenges of RCRL -- improving generalization on high reward-to-go (RTG) inputs, and avoiding out-of-distribution (OOD) RTG queries during testing time. To address these challenges when training vanilla RCRL architectures, we propose Bayesian Reparameterized RCRL (BR-RCRL), a novel set of inductive biases for RCRL inspired by Bayes' theorem. BR-RC","authors_text":"Ding Zhao, Marco Pavone, Tong Che, Wenhao Ding","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T23:23:08Z","title":"Bayesian Reparameterization of Reward-Conditioned Reinforcement Learning with Energy-based Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11340","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":"sha256:4c3f0cbd0ce047b38691db40f9570a0c9e16a4280d9003c0246b8bc3e94bcfbc","target":"record","created_at":"2026-07-05T06:11:35Z","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":"e607d12ce91129aea33b9aa64bac3516cf69811db3d4d4b36007aa48e1ba14ab","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T23:23:08Z","title_canon_sha256":"49cbae1af59efbc3770391f5ab526bd849b9d40121219212a10ebe42d5369191"},"schema_version":"1.0","source":{"id":"2305.11340","kind":"arxiv","version":1}},"canonical_sha256":"f291332ece7f8c3ab2d8f4157a56a20b783eed379a98c17efbebec1940a73476","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f291332ece7f8c3ab2d8f4157a56a20b783eed379a98c17efbebec1940a73476","first_computed_at":"2026-07-05T06:11:35.901275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:35.901275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LQQaUu7GxAdMMcSLheGIvEad9J7IaljtXvlVlHViupt9MYOqOrUUEU8wkxIDtTpqO2JmlZQdKZJmQxlBFsRZBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:35.901696Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.11340","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c3f0cbd0ce047b38691db40f9570a0c9e16a4280d9003c0246b8bc3e94bcfbc","sha256:5819d606bf8ce5eda6f06d11b0776ecc858b21008c97676e23c490b19a5b46ca"],"state_sha256":"763a9571426c7015f0d152c064370b4452d3390a09096e3baa4a30e96bf591d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wbI44LBIhyyl8O3oULtyh2wQ8uSbFW2xFO7aoFgxLh2UODCG3USGjqXO1D8czjhFIS4+CpQJS1Cv/E+fGNS+DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T09:05:47.073954Z","bundle_sha256":"a74227515a297b0d002c9bb528229a84d85daf43b86e16f1551d5b4812e29f3a"}}