{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:A3TIUIZK33MXDD2ZC3UCTO6E73","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":"47e0686a7c72f04b1597a01fa076e75a00d177a657bc9260e01c817e5a9ccb71","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T00:43:10Z","title_canon_sha256":"afcb02efa35acbf1508b9f9ef666a0afb485474a843e6227db4d1dd5e69a473b"},"schema_version":"1.0","source":{"id":"2106.02193","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.02193","created_at":"2026-07-05T04:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2106.02193v2","created_at":"2026-07-05T04:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02193","created_at":"2026-07-05T04:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"A3TIUIZK33MX","created_at":"2026-07-05T04:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"A3TIUIZK33MXDD2Z","created_at":"2026-07-05T04:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"A3TIUIZK","created_at":"2026-07-05T04:05:31Z"}],"graph_snapshots":[{"event_id":"sha256:01e38425ec0c403129aff4ff23dd16da393d58a3d7eef2b323af6db6fc7138c7","target":"graph","created_at":"2026-07-05T04:05:31Z","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/2106.02193/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A highly desirable property of a reinforcement learning (RL) agent -- and a major difficulty for deep RL approaches -- is the ability to generalize policies learned on a few tasks over a high-dimensional observation space to similar tasks not seen during training. Many promising approaches to this challenge consider RL as a process of training two functions simultaneously: a complex nonlinear encoder that maps high-dimensional observations to a latent representation space, and a simple linear policy over this space. We posit that a superior encoder for zero-shot generalization in RL can be tra","authors_text":"Ahmed M. Ahmed, Andrey Kolobov, Bogdan Mazoure, Patrick MacAlpine, R Devon Hjelm","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T00:43:10Z","title":"Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02193","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:fbbc3f7db9cdd341608eff9dc61c4c6a9d0081462fb59666504993e03fbbeab3","target":"record","created_at":"2026-07-05T04:05:31Z","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":"47e0686a7c72f04b1597a01fa076e75a00d177a657bc9260e01c817e5a9ccb71","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T00:43:10Z","title_canon_sha256":"afcb02efa35acbf1508b9f9ef666a0afb485474a843e6227db4d1dd5e69a473b"},"schema_version":"1.0","source":{"id":"2106.02193","kind":"arxiv","version":2}},"canonical_sha256":"06e68a232aded9718f5916e829bbc4fef55ece521c8b405017206691867c051d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06e68a232aded9718f5916e829bbc4fef55ece521c8b405017206691867c051d","first_computed_at":"2026-07-05T04:05:31.371060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:31.371060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8sOr1viObkVwil8aydwskhZdUJLMOBfJV8T0mG2/RIkPMiLfSrVje69vrip56y7Y8Vd/CmHC2dpwTjwsgdk8Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:31.371605Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.02193","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbbc3f7db9cdd341608eff9dc61c4c6a9d0081462fb59666504993e03fbbeab3","sha256:01e38425ec0c403129aff4ff23dd16da393d58a3d7eef2b323af6db6fc7138c7"],"state_sha256":"2964fbca2c742f15e6d76f05a859f047a0dd39011b03875c9241548ff0b31726"}