{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:G3QHYBHTGTXLTU3DYKIKFVYWIN","short_pith_number":"pith:G3QHYBHT","canonical_record":{"source":{"id":"2008.02430","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T02:25:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d7cad5828001e6025f70baaf96dea3f28a964c77d375d9c05735c10908b82bef","abstract_canon_sha256":"88eaad04b796ebccb085623f9d8f915dcb643a5c41f23d0f8e4edbf51d96ae2d"},"schema_version":"1.0"},"canonical_sha256":"36e07c04f334eeb9d363c290a2d716434dbdf76e5a2999ff461224264ce5de70","source":{"kind":"arxiv","id":"2008.02430","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.02430","created_at":"2026-07-05T01:49:54Z"},{"alias_kind":"arxiv_version","alias_value":"2008.02430v2","created_at":"2026-07-05T01:49:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02430","created_at":"2026-07-05T01:49:54Z"},{"alias_kind":"pith_short_12","alias_value":"G3QHYBHTGTXL","created_at":"2026-07-05T01:49:54Z"},{"alias_kind":"pith_short_16","alias_value":"G3QHYBHTGTXLTU3D","created_at":"2026-07-05T01:49:54Z"},{"alias_kind":"pith_short_8","alias_value":"G3QHYBHT","created_at":"2026-07-05T01:49:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:G3QHYBHTGTXLTU3DYKIKFVYWIN","target":"record","payload":{"canonical_record":{"source":{"id":"2008.02430","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T02:25:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d7cad5828001e6025f70baaf96dea3f28a964c77d375d9c05735c10908b82bef","abstract_canon_sha256":"88eaad04b796ebccb085623f9d8f915dcb643a5c41f23d0f8e4edbf51d96ae2d"},"schema_version":"1.0"},"canonical_sha256":"36e07c04f334eeb9d363c290a2d716434dbdf76e5a2999ff461224264ce5de70","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:54.037208Z","signature_b64":"cAYvIJi98kEaTaJRxNK+nLtRNhCPei7iylOozCfBiI3+M4fXTtZshi9ivXGAZuJaqFnr3YqqoJsoX1/RO6R9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36e07c04f334eeb9d363c290a2d716434dbdf76e5a2999ff461224264ce5de70","last_reissued_at":"2026-07-05T01:49:54.036828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:54.036828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.02430","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":"2026-07-05T01:49:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k5/sZQKDwTPP7XEmGmhmYk0DozzVh5zqT0JlCY/Q7Dkfc8rvGp92tfWOX3wWnTlCTYwOs2Q4E1h93YUfJAQhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:08:14.471153Z"},"content_sha256":"c45d5059a7ff9b3e9babf8c69a414563cec4bd7ebaabc1c98621c36ac8648d52","schema_version":"1.0","event_id":"sha256:c45d5059a7ff9b3e9babf8c69a414563cec4bd7ebaabc1c98621c36ac8648d52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:G3QHYBHTGTXLTU3DYKIKFVYWIN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contrastive Variational Reinforcement Learning for Complex Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Hsu, Siwei Chen, Wee Sun Lee, Xiao Ma","submitted_at":"2020-08-06T02:25:51Z","abstract_excerpt":"Deep reinforcement learning (DRL) has achieved significant success in various robot tasks: manipulation, navigation, etc. However, complex visual observations in natural environments remains a major challenge. This paper presents Contrastive Variational Reinforcement Learning (CVRL), a model-based method that tackles complex visual observations in DRL. CVRL learns a contrastive variational model by maximizing the mutual information between latent states and observations discriminatively, through contrastive learning. It avoids modeling the complex observation space unnecessarily, as the common"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02430","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/2008.02430/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":"2026-07-05T01:49:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0/bOItKUa+Rj+F5sK08iemXCehaUAkyGb4BnTiHsO707Yt8bW3Y1m3OoI10K3Frubo/KNnoNs+/rQtwpRNMcBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:08:14.471958Z"},"content_sha256":"d10f9cb951c9cc1d8584d039dcde22730889e4f4d01f13e66f09f5800824171e","schema_version":"1.0","event_id":"sha256:d10f9cb951c9cc1d8584d039dcde22730889e4f4d01f13e66f09f5800824171e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G3QHYBHTGTXLTU3DYKIKFVYWIN/bundle.json","state_url":"https://pith.science/pith/G3QHYBHTGTXLTU3DYKIKFVYWIN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G3QHYBHTGTXLTU3DYKIKFVYWIN/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":"2026-08-21T10:08:14Z","links":{"resolver":"https://pith.science/pith/G3QHYBHTGTXLTU3DYKIKFVYWIN","bundle":"https://pith.science/pith/G3QHYBHTGTXLTU3DYKIKFVYWIN/bundle.json","state":"https://pith.science/pith/G3QHYBHTGTXLTU3DYKIKFVYWIN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G3QHYBHTGTXLTU3DYKIKFVYWIN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:G3QHYBHTGTXLTU3DYKIKFVYWIN","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":"88eaad04b796ebccb085623f9d8f915dcb643a5c41f23d0f8e4edbf51d96ae2d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T02:25:51Z","title_canon_sha256":"d7cad5828001e6025f70baaf96dea3f28a964c77d375d9c05735c10908b82bef"},"schema_version":"1.0","source":{"id":"2008.02430","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.02430","created_at":"2026-07-05T01:49:54Z"},{"alias_kind":"arxiv_version","alias_value":"2008.02430v2","created_at":"2026-07-05T01:49:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02430","created_at":"2026-07-05T01:49:54Z"},{"alias_kind":"pith_short_12","alias_value":"G3QHYBHTGTXL","created_at":"2026-07-05T01:49:54Z"},{"alias_kind":"pith_short_16","alias_value":"G3QHYBHTGTXLTU3D","created_at":"2026-07-05T01:49:54Z"},{"alias_kind":"pith_short_8","alias_value":"G3QHYBHT","created_at":"2026-07-05T01:49:54Z"}],"graph_snapshots":[{"event_id":"sha256:d10f9cb951c9cc1d8584d039dcde22730889e4f4d01f13e66f09f5800824171e","target":"graph","created_at":"2026-07-05T01:49:54Z","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/2008.02430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (DRL) has achieved significant success in various robot tasks: manipulation, navigation, etc. However, complex visual observations in natural environments remains a major challenge. This paper presents Contrastive Variational Reinforcement Learning (CVRL), a model-based method that tackles complex visual observations in DRL. CVRL learns a contrastive variational model by maximizing the mutual information between latent states and observations discriminatively, through contrastive learning. It avoids modeling the complex observation space unnecessarily, as the common","authors_text":"David Hsu, Siwei Chen, Wee Sun Lee, Xiao Ma","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T02:25:51Z","title":"Contrastive Variational Reinforcement Learning for Complex Observations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02430","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:c45d5059a7ff9b3e9babf8c69a414563cec4bd7ebaabc1c98621c36ac8648d52","target":"record","created_at":"2026-07-05T01:49:54Z","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":"88eaad04b796ebccb085623f9d8f915dcb643a5c41f23d0f8e4edbf51d96ae2d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T02:25:51Z","title_canon_sha256":"d7cad5828001e6025f70baaf96dea3f28a964c77d375d9c05735c10908b82bef"},"schema_version":"1.0","source":{"id":"2008.02430","kind":"arxiv","version":2}},"canonical_sha256":"36e07c04f334eeb9d363c290a2d716434dbdf76e5a2999ff461224264ce5de70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36e07c04f334eeb9d363c290a2d716434dbdf76e5a2999ff461224264ce5de70","first_computed_at":"2026-07-05T01:49:54.036828Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:54.036828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cAYvIJi98kEaTaJRxNK+nLtRNhCPei7iylOozCfBiI3+M4fXTtZshi9ivXGAZuJaqFnr3YqqoJsoX1/RO6R9AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:54.037208Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.02430","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c45d5059a7ff9b3e9babf8c69a414563cec4bd7ebaabc1c98621c36ac8648d52","sha256:d10f9cb951c9cc1d8584d039dcde22730889e4f4d01f13e66f09f5800824171e"],"state_sha256":"8783a46b681fa997ac0fb3c393f2bb3d76d7e54874d099f65629b6ca912dc75d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E4r10qDUelBr4Q1cjv8DJirc/2V6rY2ZiyQjH17EkgMpERcrz2Vp9eL6oazBKX4tB3WyhNxA86T76n+3605JAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T10:08:14.476686Z","bundle_sha256":"e0e8b4c17481263641537fd899134627caa2c186aaf39ac4052c1e0e70673bc9"}}