{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TRDHATQSROREFI3BYIUSNN43KV","short_pith_number":"pith:TRDHATQS","canonical_record":{"source":{"id":"2210.12719","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-23T12:38:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"98ec5a63f019d154eb2860719b4dd7cb1a39c3ead4444f053b24a973e905895b","abstract_canon_sha256":"59c2efdaca34f452ad2879d2f55a679e90d10d2355f7a09ea4a3b638b3eacb06"},"schema_version":"1.0"},"canonical_sha256":"9c46704e128ba242a361c22926b79b557136c2ef90c87563256319ee939538ac","source":{"kind":"arxiv","id":"2210.12719","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.12719","created_at":"2026-07-05T05:09:32Z"},{"alias_kind":"arxiv_version","alias_value":"2210.12719v1","created_at":"2026-07-05T05:09:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12719","created_at":"2026-07-05T05:09:32Z"},{"alias_kind":"pith_short_12","alias_value":"TRDHATQSRORE","created_at":"2026-07-05T05:09:32Z"},{"alias_kind":"pith_short_16","alias_value":"TRDHATQSROREFI3B","created_at":"2026-07-05T05:09:32Z"},{"alias_kind":"pith_short_8","alias_value":"TRDHATQS","created_at":"2026-07-05T05:09:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TRDHATQSROREFI3BYIUSNN43KV","target":"record","payload":{"canonical_record":{"source":{"id":"2210.12719","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-23T12:38:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"98ec5a63f019d154eb2860719b4dd7cb1a39c3ead4444f053b24a973e905895b","abstract_canon_sha256":"59c2efdaca34f452ad2879d2f55a679e90d10d2355f7a09ea4a3b638b3eacb06"},"schema_version":"1.0"},"canonical_sha256":"9c46704e128ba242a361c22926b79b557136c2ef90c87563256319ee939538ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:32.026713Z","signature_b64":"MApUYqMUg7JBwm+U06E0xl5+qQNUqf+ksFTxClaCK2XnEoDcAkjPA/xcrPpr9iK3RKsy9sqxpAhi7YDpyX4gAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c46704e128ba242a361c22926b79b557136c2ef90c87563256319ee939538ac","last_reissued_at":"2026-07-05T05:09:32.026208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:32.026208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.12719","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":"2026-07-05T05:09:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+57uN29iF9yWmAmo/FmJGZ7PdA6VRrZW6XojJIfxO4x15AsCgobPKGk598LGNGGqWbJpDjzBZH35rsVUSIH7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:08:13.402339Z"},"content_sha256":"8b3739590a58a6a0cbc431e4f23284f7ec6341a58d0954ced6c7ca3b985078e4","schema_version":"1.0","event_id":"sha256:8b3739590a58a6a0cbc431e4f23284f7ec6341a58d0954ced6c7ca3b985078e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TRDHATQSROREFI3BYIUSNN43KV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning General World Models in a Handful of Reward-Free Deployments","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Edward Grefenstette, Jack Parker-Holder, Oleh Rybkin, Philip J. Ball, Stephen J. Roberts, Tim Rockt\\\"aschel, Yingchen Xu","submitted_at":"2022-10-23T12:38:03Z","abstract_excerpt":"Building generally capable agents is a grand challenge for deep reinforcement learning (RL). To approach this challenge practically, we outline two key desiderata: 1) to facilitate generalization, exploration should be task agnostic; 2) to facilitate scalability, exploration policies should collect large quantities of data without costly centralized retraining. Combining these two properties, we introduce the reward-free deployment efficiency setting, a new paradigm for RL research. We then present CASCADE, a novel approach for self-supervised exploration in this new setting. CASCADE seeks to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12719","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/2210.12719/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":"2026-07-05T05:09:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8mLA6qR67jOZNtD9I1CSo6j8ZFh/5U+q246M3+xznxuMgdONUMopB3GlCle/Bte9/XHOQ8BqQq0hBn+ZamRRCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:08:13.404472Z"},"content_sha256":"8613f04fd2ef7f39774743f8fead95d38d7f20ad3761913336824cb1d1c4a4c7","schema_version":"1.0","event_id":"sha256:8613f04fd2ef7f39774743f8fead95d38d7f20ad3761913336824cb1d1c4a4c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TRDHATQSROREFI3BYIUSNN43KV/bundle.json","state_url":"https://pith.science/pith/TRDHATQSROREFI3BYIUSNN43KV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TRDHATQSROREFI3BYIUSNN43KV/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":"2026-08-15T17:08:13Z","links":{"resolver":"https://pith.science/pith/TRDHATQSROREFI3BYIUSNN43KV","bundle":"https://pith.science/pith/TRDHATQSROREFI3BYIUSNN43KV/bundle.json","state":"https://pith.science/pith/TRDHATQSROREFI3BYIUSNN43KV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TRDHATQSROREFI3BYIUSNN43KV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TRDHATQSROREFI3BYIUSNN43KV","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":"59c2efdaca34f452ad2879d2f55a679e90d10d2355f7a09ea4a3b638b3eacb06","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-23T12:38:03Z","title_canon_sha256":"98ec5a63f019d154eb2860719b4dd7cb1a39c3ead4444f053b24a973e905895b"},"schema_version":"1.0","source":{"id":"2210.12719","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.12719","created_at":"2026-07-05T05:09:32Z"},{"alias_kind":"arxiv_version","alias_value":"2210.12719v1","created_at":"2026-07-05T05:09:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12719","created_at":"2026-07-05T05:09:32Z"},{"alias_kind":"pith_short_12","alias_value":"TRDHATQSRORE","created_at":"2026-07-05T05:09:32Z"},{"alias_kind":"pith_short_16","alias_value":"TRDHATQSROREFI3B","created_at":"2026-07-05T05:09:32Z"},{"alias_kind":"pith_short_8","alias_value":"TRDHATQS","created_at":"2026-07-05T05:09:32Z"}],"graph_snapshots":[{"event_id":"sha256:8613f04fd2ef7f39774743f8fead95d38d7f20ad3761913336824cb1d1c4a4c7","target":"graph","created_at":"2026-07-05T05:09:32Z","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/2210.12719/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building generally capable agents is a grand challenge for deep reinforcement learning (RL). To approach this challenge practically, we outline two key desiderata: 1) to facilitate generalization, exploration should be task agnostic; 2) to facilitate scalability, exploration policies should collect large quantities of data without costly centralized retraining. Combining these two properties, we introduce the reward-free deployment efficiency setting, a new paradigm for RL research. We then present CASCADE, a novel approach for self-supervised exploration in this new setting. CASCADE seeks to ","authors_text":"Aldo Pacchiano, Edward Grefenstette, Jack Parker-Holder, Oleh Rybkin, Philip J. Ball, Stephen J. Roberts, Tim Rockt\\\"aschel, Yingchen Xu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-23T12:38:03Z","title":"Learning General World Models in a Handful of Reward-Free Deployments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12719","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":"sha256:8b3739590a58a6a0cbc431e4f23284f7ec6341a58d0954ced6c7ca3b985078e4","target":"record","created_at":"2026-07-05T05:09:32Z","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":"59c2efdaca34f452ad2879d2f55a679e90d10d2355f7a09ea4a3b638b3eacb06","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-23T12:38:03Z","title_canon_sha256":"98ec5a63f019d154eb2860719b4dd7cb1a39c3ead4444f053b24a973e905895b"},"schema_version":"1.0","source":{"id":"2210.12719","kind":"arxiv","version":1}},"canonical_sha256":"9c46704e128ba242a361c22926b79b557136c2ef90c87563256319ee939538ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c46704e128ba242a361c22926b79b557136c2ef90c87563256319ee939538ac","first_computed_at":"2026-07-05T05:09:32.026208Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:09:32.026208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MApUYqMUg7JBwm+U06E0xl5+qQNUqf+ksFTxClaCK2XnEoDcAkjPA/xcrPpr9iK3RKsy9sqxpAhi7YDpyX4gAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:09:32.026713Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.12719","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b3739590a58a6a0cbc431e4f23284f7ec6341a58d0954ced6c7ca3b985078e4","sha256:8613f04fd2ef7f39774743f8fead95d38d7f20ad3761913336824cb1d1c4a4c7"],"state_sha256":"274fe14e02c861e93926c6e45bcfddd6386c1891e29f3b914497a5886b31bec0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"abu+kFtn3gvrKOTeah1tLAulXMasE1pQJ0q7ZEX9j12APWslC/yWJ2V4gkk3Ol4BxBCKzxLB0904lu3ziUXkAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:08:13.410241Z","bundle_sha256":"ae06acd32d6f138642d6e835ed8e01169f17ed822a978afa7b165608f8afadd9"}}