{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XY7KON7NUNNCW425TSTDLG4KXI","short_pith_number":"pith:XY7KON7N","canonical_record":{"source":{"id":"2111.09794","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-18T16:53:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"443dc01b529d399abe2cbe72f19303300ca011189e7c80b40235eed258ed7cb0","abstract_canon_sha256":"af2933a9f10806b0fe5cd67c052da33043ed830f90f678b6c6485b9d9d775c11"},"schema_version":"1.0"},"canonical_sha256":"be3ea737eda35a2b735d9ca6359b8aba32c26507b6581b404d4350cfa690fcbf","source":{"kind":"arxiv","id":"2111.09794","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.09794","created_at":"2026-07-05T05:34:14Z"},{"alias_kind":"arxiv_version","alias_value":"2111.09794v6","created_at":"2026-07-05T05:34:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09794","created_at":"2026-07-05T05:34:14Z"},{"alias_kind":"pith_short_12","alias_value":"XY7KON7NUNNC","created_at":"2026-07-05T05:34:14Z"},{"alias_kind":"pith_short_16","alias_value":"XY7KON7NUNNCW425","created_at":"2026-07-05T05:34:14Z"},{"alias_kind":"pith_short_8","alias_value":"XY7KON7N","created_at":"2026-07-05T05:34:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XY7KON7NUNNCW425TSTDLG4KXI","target":"record","payload":{"canonical_record":{"source":{"id":"2111.09794","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-18T16:53:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"443dc01b529d399abe2cbe72f19303300ca011189e7c80b40235eed258ed7cb0","abstract_canon_sha256":"af2933a9f10806b0fe5cd67c052da33043ed830f90f678b6c6485b9d9d775c11"},"schema_version":"1.0"},"canonical_sha256":"be3ea737eda35a2b735d9ca6359b8aba32c26507b6581b404d4350cfa690fcbf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:14.188818Z","signature_b64":"nawQMv1t6q3Bx9atwhQdngxVl1e6+JpkRCxxpteN62bPdNNeH7+zIUvQnDHRa5446R6HB1q9xgQSIPbhtqknAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be3ea737eda35a2b735d9ca6359b8aba32c26507b6581b404d4350cfa690fcbf","last_reissued_at":"2026-07-05T05:34:14.188303Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:14.188303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.09794","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:34:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ddXw270N8SFolgk6be3zQeVuNyAHfhlnbRJTpNt5Nk4Mi4pDOLfrpeCC5kGAEDNuu3/lRQ1VuOJ/E79NtiXmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:54:16.926945Z"},"content_sha256":"42440115011665c60446c609655f5d17adb40fa6d69f6e10d8e983466d1dccd8","schema_version":"1.0","event_id":"sha256:42440115011665c60446c609655f5d17adb40fa6d69f6e10d8e983466d1dccd8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XY7KON7NUNNCW425TSTDLG4KXI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amy Zhang, Edward Grefenstette, Robert Kirk, Tim Rockt\\\"aschel","submitted_at":"2021-11-18T16:53:02Z","abstract_excerpt":"The study of zero-shot generalisation (ZSG) in deep Reinforcement Learning (RL) aims to produce RL algorithms whose policies generalise well to novel unseen situations at deployment time, avoiding overfitting to their training environments. Tackling this is vital if we are to deploy reinforcement learning algorithms in real world scenarios, where the environment will be diverse, dynamic and unpredictable. This survey is an overview of this nascent field. We rely on a unifying formalism and terminology for discussing different ZSG problems, building upon previous works. We go on to categorise e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09794","kind":"arxiv","version":6},"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/2111.09794/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":"2026-07-05T05:34:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZPf+H7N+RsARddeLmYbYylyr2lWoaSp/UhL3P1AxvpM0RBWjx6vyesYKVltJiqwes3gnoWmjrzJvXn6seImoAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:54:16.927467Z"},"content_sha256":"70da1734764140f9e5a2db08c55d82ca319aef83b41c696f08e99a2008a00e3f","schema_version":"1.0","event_id":"sha256:70da1734764140f9e5a2db08c55d82ca319aef83b41c696f08e99a2008a00e3f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XY7KON7NUNNCW425TSTDLG4KXI/bundle.json","state_url":"https://pith.science/pith/XY7KON7NUNNCW425TSTDLG4KXI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XY7KON7NUNNCW425TSTDLG4KXI/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":"2026-08-08T13:54:16Z","links":{"resolver":"https://pith.science/pith/XY7KON7NUNNCW425TSTDLG4KXI","bundle":"https://pith.science/pith/XY7KON7NUNNCW425TSTDLG4KXI/bundle.json","state":"https://pith.science/pith/XY7KON7NUNNCW425TSTDLG4KXI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XY7KON7NUNNCW425TSTDLG4KXI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XY7KON7NUNNCW425TSTDLG4KXI","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":"af2933a9f10806b0fe5cd67c052da33043ed830f90f678b6c6485b9d9d775c11","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-18T16:53:02Z","title_canon_sha256":"443dc01b529d399abe2cbe72f19303300ca011189e7c80b40235eed258ed7cb0"},"schema_version":"1.0","source":{"id":"2111.09794","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.09794","created_at":"2026-07-05T05:34:14Z"},{"alias_kind":"arxiv_version","alias_value":"2111.09794v6","created_at":"2026-07-05T05:34:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09794","created_at":"2026-07-05T05:34:14Z"},{"alias_kind":"pith_short_12","alias_value":"XY7KON7NUNNC","created_at":"2026-07-05T05:34:14Z"},{"alias_kind":"pith_short_16","alias_value":"XY7KON7NUNNCW425","created_at":"2026-07-05T05:34:14Z"},{"alias_kind":"pith_short_8","alias_value":"XY7KON7N","created_at":"2026-07-05T05:34:14Z"}],"graph_snapshots":[{"event_id":"sha256:70da1734764140f9e5a2db08c55d82ca319aef83b41c696f08e99a2008a00e3f","target":"graph","created_at":"2026-07-05T05:34:14Z","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/2111.09794/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The study of zero-shot generalisation (ZSG) in deep Reinforcement Learning (RL) aims to produce RL algorithms whose policies generalise well to novel unseen situations at deployment time, avoiding overfitting to their training environments. Tackling this is vital if we are to deploy reinforcement learning algorithms in real world scenarios, where the environment will be diverse, dynamic and unpredictable. This survey is an overview of this nascent field. We rely on a unifying formalism and terminology for discussing different ZSG problems, building upon previous works. We go on to categorise e","authors_text":"Amy Zhang, Edward Grefenstette, Robert Kirk, Tim Rockt\\\"aschel","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-18T16:53:02Z","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09794","kind":"arxiv","version":6},"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":"sha256:42440115011665c60446c609655f5d17adb40fa6d69f6e10d8e983466d1dccd8","target":"record","created_at":"2026-07-05T05:34:14Z","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":"af2933a9f10806b0fe5cd67c052da33043ed830f90f678b6c6485b9d9d775c11","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-18T16:53:02Z","title_canon_sha256":"443dc01b529d399abe2cbe72f19303300ca011189e7c80b40235eed258ed7cb0"},"schema_version":"1.0","source":{"id":"2111.09794","kind":"arxiv","version":6}},"canonical_sha256":"be3ea737eda35a2b735d9ca6359b8aba32c26507b6581b404d4350cfa690fcbf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be3ea737eda35a2b735d9ca6359b8aba32c26507b6581b404d4350cfa690fcbf","first_computed_at":"2026-07-05T05:34:14.188303Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:34:14.188303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nawQMv1t6q3Bx9atwhQdngxVl1e6+JpkRCxxpteN62bPdNNeH7+zIUvQnDHRa5446R6HB1q9xgQSIPbhtqknAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:34:14.188818Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.09794","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42440115011665c60446c609655f5d17adb40fa6d69f6e10d8e983466d1dccd8","sha256:70da1734764140f9e5a2db08c55d82ca319aef83b41c696f08e99a2008a00e3f"],"state_sha256":"270cc26ad5d4a5b6fbdddd04a1c1c8ff443cf9c5ec7d2a47641b7173849ba96d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZtBh7oirScm/AvW8fw7mrzVWGePYJyjmbB0Q14NZTaAYKikxNFV+ayUg2WBkRBSSF1Q/7Af89ZmtjJXC18K5AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:54:16.932588Z","bundle_sha256":"330c05b1ef4cdb7f1f693785decc9ec41a008ea1961b30204a3aeca9b22ac4fc"}}