{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JEKF75WNEGVMTMIGSIX4HEUV5M","short_pith_number":"pith:JEKF75WN","canonical_record":{"source":{"id":"2302.09601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-19T15:47:24Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"142bdda87f705cb9473c78d58397c8b131a69232ffdbc47d27994092d5f86c0b","abstract_canon_sha256":"a24e1915a77e20d3b06242b6d3028d0f15f91d84a19da77d7f536fa8ba5aafeb"},"schema_version":"1.0"},"canonical_sha256":"49145ff6cd21aac9b106922fc39295eb282adf8395ad4cd0994d22cc16279218","source":{"kind":"arxiv","id":"2302.09601","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.09601","created_at":"2026-07-05T05:43:27Z"},{"alias_kind":"arxiv_version","alias_value":"2302.09601v1","created_at":"2026-07-05T05:43:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.09601","created_at":"2026-07-05T05:43:27Z"},{"alias_kind":"pith_short_12","alias_value":"JEKF75WNEGVM","created_at":"2026-07-05T05:43:27Z"},{"alias_kind":"pith_short_16","alias_value":"JEKF75WNEGVMTMIG","created_at":"2026-07-05T05:43:27Z"},{"alias_kind":"pith_short_8","alias_value":"JEKF75WN","created_at":"2026-07-05T05:43:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JEKF75WNEGVMTMIGSIX4HEUV5M","target":"record","payload":{"canonical_record":{"source":{"id":"2302.09601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-19T15:47:24Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"142bdda87f705cb9473c78d58397c8b131a69232ffdbc47d27994092d5f86c0b","abstract_canon_sha256":"a24e1915a77e20d3b06242b6d3028d0f15f91d84a19da77d7f536fa8ba5aafeb"},"schema_version":"1.0"},"canonical_sha256":"49145ff6cd21aac9b106922fc39295eb282adf8395ad4cd0994d22cc16279218","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:27.836788Z","signature_b64":"fC/orsnBmXMLUfbPuEHoeBkJdPBZGiHE96ICt9mR+F0N5rqTehl5nVSYj8gwXH0YxllfCAXBikbv+8R8cI37CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49145ff6cd21aac9b106922fc39295eb282adf8395ad4cd0994d22cc16279218","last_reissued_at":"2026-07-05T05:43:27.836399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:27.836399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.09601","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":"2026-07-05T05:43:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OgXB3DN9unDUoXjavu2LemZ5fQMtg8ZOtv+AX2kAX5IwCvljoDSVQgpiFbi2H44kB2kZwtVJwJPZiy3IPhN/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T15:25:42.005396Z"},"content_sha256":"69c818a4dd611e1c88579777ed5e632aee3ef9946cf1f94d93e835cf802c59d3","schema_version":"1.0","event_id":"sha256:69c818a4dd611e1c88579777ed5e632aee3ef9946cf1f94d93e835cf802c59d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JEKF75WNEGVMTMIGSIX4HEUV5M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalization in Visual Reinforcement Learning with the Reward Sequence Distribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bin Li, Feng Wu, Jie Wang, Mingxuan Ye, Qi Zhou, Rui Yang, Shuiwang Ji, Yongdong Zhang, Zhihao Shi, Zijie Geng","submitted_at":"2023-02-19T15:47:24Z","abstract_excerpt":"Generalization in partially observed markov decision processes (POMDPs) is critical for successful applications of visual reinforcement learning (VRL) in real scenarios. A widely used idea is to learn task-relevant representations that encode task-relevant information of common features in POMDPs, i.e., rewards and transition dynamics. As transition dynamics in the latent state space -- which are task-relevant and invariant to visual distractions -- are unknown to the agents, existing methods alternatively use transition dynamics in the observation space to extract task-relevant information in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.09601","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/2302.09601/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":"2026-07-05T05:43:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GA6pAaxpbqcQjjSVRbWVkudlM0k8YQetB1YiR3FgduAoFDI7uAzaiK4OkTEKkkv73/2irsJ+/xzUKxH0+p7UCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T15:25:42.005778Z"},"content_sha256":"f1627ea09e6b1c7cc4c803b7bbe8c7a7b07f95afe31075fd3dfab565ab7e7d83","schema_version":"1.0","event_id":"sha256:f1627ea09e6b1c7cc4c803b7bbe8c7a7b07f95afe31075fd3dfab565ab7e7d83"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JEKF75WNEGVMTMIGSIX4HEUV5M/bundle.json","state_url":"https://pith.science/pith/JEKF75WNEGVMTMIGSIX4HEUV5M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JEKF75WNEGVMTMIGSIX4HEUV5M/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":"2026-07-20T15:25:42Z","links":{"resolver":"https://pith.science/pith/JEKF75WNEGVMTMIGSIX4HEUV5M","bundle":"https://pith.science/pith/JEKF75WNEGVMTMIGSIX4HEUV5M/bundle.json","state":"https://pith.science/pith/JEKF75WNEGVMTMIGSIX4HEUV5M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JEKF75WNEGVMTMIGSIX4HEUV5M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JEKF75WNEGVMTMIGSIX4HEUV5M","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":"a24e1915a77e20d3b06242b6d3028d0f15f91d84a19da77d7f536fa8ba5aafeb","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-19T15:47:24Z","title_canon_sha256":"142bdda87f705cb9473c78d58397c8b131a69232ffdbc47d27994092d5f86c0b"},"schema_version":"1.0","source":{"id":"2302.09601","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.09601","created_at":"2026-07-05T05:43:27Z"},{"alias_kind":"arxiv_version","alias_value":"2302.09601v1","created_at":"2026-07-05T05:43:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.09601","created_at":"2026-07-05T05:43:27Z"},{"alias_kind":"pith_short_12","alias_value":"JEKF75WNEGVM","created_at":"2026-07-05T05:43:27Z"},{"alias_kind":"pith_short_16","alias_value":"JEKF75WNEGVMTMIG","created_at":"2026-07-05T05:43:27Z"},{"alias_kind":"pith_short_8","alias_value":"JEKF75WN","created_at":"2026-07-05T05:43:27Z"}],"graph_snapshots":[{"event_id":"sha256:f1627ea09e6b1c7cc4c803b7bbe8c7a7b07f95afe31075fd3dfab565ab7e7d83","target":"graph","created_at":"2026-07-05T05:43:27Z","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/2302.09601/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generalization in partially observed markov decision processes (POMDPs) is critical for successful applications of visual reinforcement learning (VRL) in real scenarios. A widely used idea is to learn task-relevant representations that encode task-relevant information of common features in POMDPs, i.e., rewards and transition dynamics. As transition dynamics in the latent state space -- which are task-relevant and invariant to visual distractions -- are unknown to the agents, existing methods alternatively use transition dynamics in the observation space to extract task-relevant information in","authors_text":"Bin Li, Feng Wu, Jie Wang, Mingxuan Ye, Qi Zhou, Rui Yang, Shuiwang Ji, Yongdong Zhang, Zhihao Shi, Zijie Geng","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-19T15:47:24Z","title":"Generalization in Visual Reinforcement Learning with the Reward Sequence Distribution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.09601","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":"sha256:69c818a4dd611e1c88579777ed5e632aee3ef9946cf1f94d93e835cf802c59d3","target":"record","created_at":"2026-07-05T05:43:27Z","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":"a24e1915a77e20d3b06242b6d3028d0f15f91d84a19da77d7f536fa8ba5aafeb","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-19T15:47:24Z","title_canon_sha256":"142bdda87f705cb9473c78d58397c8b131a69232ffdbc47d27994092d5f86c0b"},"schema_version":"1.0","source":{"id":"2302.09601","kind":"arxiv","version":1}},"canonical_sha256":"49145ff6cd21aac9b106922fc39295eb282adf8395ad4cd0994d22cc16279218","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"49145ff6cd21aac9b106922fc39295eb282adf8395ad4cd0994d22cc16279218","first_computed_at":"2026-07-05T05:43:27.836399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:43:27.836399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fC/orsnBmXMLUfbPuEHoeBkJdPBZGiHE96ICt9mR+F0N5rqTehl5nVSYj8gwXH0YxllfCAXBikbv+8R8cI37CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:43:27.836788Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.09601","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69c818a4dd611e1c88579777ed5e632aee3ef9946cf1f94d93e835cf802c59d3","sha256:f1627ea09e6b1c7cc4c803b7bbe8c7a7b07f95afe31075fd3dfab565ab7e7d83"],"state_sha256":"e0bbacf0ac945a7553dde1a603a76f1ea3dc2b15098f0ac476fbd25b256d6766"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/jhq5RUyDEzqe04zwQ35QxFXJ/tqi+PoClJGYqT3mkMNjcK8IMMm9wthafjPsIZ6TJvwcboqTSB2Znt0Aq4mAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T15:25:42.007963Z","bundle_sha256":"c6729303f0e129ba1d6d683fbe7abc771616819de16b3d74326d69e555e0b9de"}}