{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:DXZF5BUNDU52LV74XDVYJVKFY6","short_pith_number":"pith:DXZF5BUN","canonical_record":{"source":{"id":"2005.05960","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-12T17:59:45Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE","cs.RO","stat.ML"],"title_canon_sha256":"595e4b396e4ae7608a264cbcd1b34b4aeae845a234c46b1a9319c1b71075370b","abstract_canon_sha256":"c6f13e5c2ded2d55975df5a7519b1c5a49fa07271e9c8ca4c4e9d327fe79e638"},"schema_version":"1.0"},"canonical_sha256":"1df25e868d1d3ba5d7fcb8eb84d545c7a7a7c5aeacdc6ad65c5ce9f4bfcf4207","source":{"kind":"arxiv","id":"2005.05960","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.05960","created_at":"2026-07-05T01:15:25Z"},{"alias_kind":"arxiv_version","alias_value":"2005.05960v2","created_at":"2026-07-05T01:15:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.05960","created_at":"2026-07-05T01:15:25Z"},{"alias_kind":"pith_short_12","alias_value":"DXZF5BUNDU52","created_at":"2026-07-05T01:15:25Z"},{"alias_kind":"pith_short_16","alias_value":"DXZF5BUNDU52LV74","created_at":"2026-07-05T01:15:25Z"},{"alias_kind":"pith_short_8","alias_value":"DXZF5BUN","created_at":"2026-07-05T01:15:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:DXZF5BUNDU52LV74XDVYJVKFY6","target":"record","payload":{"canonical_record":{"source":{"id":"2005.05960","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-12T17:59:45Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE","cs.RO","stat.ML"],"title_canon_sha256":"595e4b396e4ae7608a264cbcd1b34b4aeae845a234c46b1a9319c1b71075370b","abstract_canon_sha256":"c6f13e5c2ded2d55975df5a7519b1c5a49fa07271e9c8ca4c4e9d327fe79e638"},"schema_version":"1.0"},"canonical_sha256":"1df25e868d1d3ba5d7fcb8eb84d545c7a7a7c5aeacdc6ad65c5ce9f4bfcf4207","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:15:25.797541Z","signature_b64":"IYIBa78elzb40ZFR+XTqVUULJamIkVmtm1MwaZ/wKmuLjJrDSUD5LwFVfDgXd3SYAR84FtGar7ryFquXqm0iBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1df25e868d1d3ba5d7fcb8eb84d545c7a7a7c5aeacdc6ad65c5ce9f4bfcf4207","last_reissued_at":"2026-07-05T01:15:25.797056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:15:25.797056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.05960","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":"2026-07-05T01:15:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/ZMtEIiTzDYUtbPAPMNK/QV9cwgCqQIJNmTRUmSt0JCkAwfmwAn7OTra1O9y5CV3gE24VvUxOe6dq0B/EuOxBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:53:08.765595Z"},"content_sha256":"93c33acf24d336dd880116b68ba9e1b40ad5633b20526e60b2b85acf63f440c7","schema_version":"1.0","event_id":"sha256:93c33acf24d336dd880116b68ba9e1b40ad5633b20526e60b2b85acf63f440c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:DXZF5BUNDU52LV74XDVYJVKFY6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Planning to Explore via Self-Supervised World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Danijar Hafner, Deepak Pathak, Kostas Daniilidis, Oleh Rybkin, Pieter Abbeel, Ramanan Sekar","submitted_at":"2020-05-12T17:59:45Z","abstract_excerpt":"Reinforcement learning allows solving complex tasks, however, the learning tends to be task-specific and the sample efficiency remains a challenge. We present Plan2Explore, a self-supervised reinforcement learning agent that tackles both these challenges through a new approach to self-supervised exploration and fast adaptation to new tasks, which need not be known during exploration. During exploration, unlike prior methods which retrospectively compute the novelty of observations after the agent has already reached them, our agent acts efficiently by leveraging planning to seek out expected f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.05960","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/2005.05960/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":"2026-07-05T01:15:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ulwmJiXVbRSizEIlDuJ+C2iUS38tuugIUBL6xAIygRLZjkJ8rxredDQumlg1oKZyYC9i2LVLZ8he/vnkATgZBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:53:08.766100Z"},"content_sha256":"8019431e67bc29f43a118b4a4033a41f3679274144078d9b9b68e4575be60c5d","schema_version":"1.0","event_id":"sha256:8019431e67bc29f43a118b4a4033a41f3679274144078d9b9b68e4575be60c5d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DXZF5BUNDU52LV74XDVYJVKFY6/bundle.json","state_url":"https://pith.science/pith/DXZF5BUNDU52LV74XDVYJVKFY6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DXZF5BUNDU52LV74XDVYJVKFY6/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":"2026-08-10T10:53:08Z","links":{"resolver":"https://pith.science/pith/DXZF5BUNDU52LV74XDVYJVKFY6","bundle":"https://pith.science/pith/DXZF5BUNDU52LV74XDVYJVKFY6/bundle.json","state":"https://pith.science/pith/DXZF5BUNDU52LV74XDVYJVKFY6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DXZF5BUNDU52LV74XDVYJVKFY6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DXZF5BUNDU52LV74XDVYJVKFY6","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":"c6f13e5c2ded2d55975df5a7519b1c5a49fa07271e9c8ca4c4e9d327fe79e638","cross_cats_sorted":["cs.AI","cs.CV","cs.NE","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-12T17:59:45Z","title_canon_sha256":"595e4b396e4ae7608a264cbcd1b34b4aeae845a234c46b1a9319c1b71075370b"},"schema_version":"1.0","source":{"id":"2005.05960","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.05960","created_at":"2026-07-05T01:15:25Z"},{"alias_kind":"arxiv_version","alias_value":"2005.05960v2","created_at":"2026-07-05T01:15:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.05960","created_at":"2026-07-05T01:15:25Z"},{"alias_kind":"pith_short_12","alias_value":"DXZF5BUNDU52","created_at":"2026-07-05T01:15:25Z"},{"alias_kind":"pith_short_16","alias_value":"DXZF5BUNDU52LV74","created_at":"2026-07-05T01:15:25Z"},{"alias_kind":"pith_short_8","alias_value":"DXZF5BUN","created_at":"2026-07-05T01:15:25Z"}],"graph_snapshots":[{"event_id":"sha256:8019431e67bc29f43a118b4a4033a41f3679274144078d9b9b68e4575be60c5d","target":"graph","created_at":"2026-07-05T01:15:25Z","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/2005.05960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning allows solving complex tasks, however, the learning tends to be task-specific and the sample efficiency remains a challenge. We present Plan2Explore, a self-supervised reinforcement learning agent that tackles both these challenges through a new approach to self-supervised exploration and fast adaptation to new tasks, which need not be known during exploration. During exploration, unlike prior methods which retrospectively compute the novelty of observations after the agent has already reached them, our agent acts efficiently by leveraging planning to seek out expected f","authors_text":"Danijar Hafner, Deepak Pathak, Kostas Daniilidis, Oleh Rybkin, Pieter Abbeel, Ramanan Sekar","cross_cats":["cs.AI","cs.CV","cs.NE","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-12T17:59:45Z","title":"Planning to Explore via Self-Supervised World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.05960","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":"sha256:93c33acf24d336dd880116b68ba9e1b40ad5633b20526e60b2b85acf63f440c7","target":"record","created_at":"2026-07-05T01:15:25Z","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":"c6f13e5c2ded2d55975df5a7519b1c5a49fa07271e9c8ca4c4e9d327fe79e638","cross_cats_sorted":["cs.AI","cs.CV","cs.NE","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-12T17:59:45Z","title_canon_sha256":"595e4b396e4ae7608a264cbcd1b34b4aeae845a234c46b1a9319c1b71075370b"},"schema_version":"1.0","source":{"id":"2005.05960","kind":"arxiv","version":2}},"canonical_sha256":"1df25e868d1d3ba5d7fcb8eb84d545c7a7a7c5aeacdc6ad65c5ce9f4bfcf4207","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1df25e868d1d3ba5d7fcb8eb84d545c7a7a7c5aeacdc6ad65c5ce9f4bfcf4207","first_computed_at":"2026-07-05T01:15:25.797056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:15:25.797056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IYIBa78elzb40ZFR+XTqVUULJamIkVmtm1MwaZ/wKmuLjJrDSUD5LwFVfDgXd3SYAR84FtGar7ryFquXqm0iBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:15:25.797541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.05960","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93c33acf24d336dd880116b68ba9e1b40ad5633b20526e60b2b85acf63f440c7","sha256:8019431e67bc29f43a118b4a4033a41f3679274144078d9b9b68e4575be60c5d"],"state_sha256":"2a843cc35215e037dcfc68ad85f800c4daa8eedb82b3c68c3f4d203b1bac60af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"82L/vfRTNCv7sRuVMTVf6DeRW6AuauoSQlL9/fVYVaYjszaO2uB/fPeVvhBDpkyg5b+g4NIX1LP/EquK1yw2CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T10:53:08.769541Z","bundle_sha256":"2eca513ac466b86661d78a6f77eb8c4554271b1a0fe579408199e9bc93ef5b01"}}