{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:A3TIUIZK33MXDD2ZC3UCTO6E73","short_pith_number":"pith:A3TIUIZK","canonical_record":{"source":{"id":"2106.02193","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T00:43:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"afcb02efa35acbf1508b9f9ef666a0afb485474a843e6227db4d1dd5e69a473b","abstract_canon_sha256":"47e0686a7c72f04b1597a01fa076e75a00d177a657bc9260e01c817e5a9ccb71"},"schema_version":"1.0"},"canonical_sha256":"06e68a232aded9718f5916e829bbc4fef55ece521c8b405017206691867c051d","source":{"kind":"arxiv","id":"2106.02193","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:A3TIUIZK33MXDD2ZC3UCTO6E73","target":"record","payload":{"canonical_record":{"source":{"id":"2106.02193","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T00:43:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"afcb02efa35acbf1508b9f9ef666a0afb485474a843e6227db4d1dd5e69a473b","abstract_canon_sha256":"47e0686a7c72f04b1597a01fa076e75a00d177a657bc9260e01c817e5a9ccb71"},"schema_version":"1.0"},"canonical_sha256":"06e68a232aded9718f5916e829bbc4fef55ece521c8b405017206691867c051d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:31.371605Z","signature_b64":"8sOr1viObkVwil8aydwskhZdUJLMOBfJV8T0mG2/RIkPMiLfSrVje69vrip56y7Y8Vd/CmHC2dpwTjwsgdk8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06e68a232aded9718f5916e829bbc4fef55ece521c8b405017206691867c051d","last_reissued_at":"2026-07-05T04:05:31.371060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:31.371060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.02193","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":"2026-07-05T04:05:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0vEmnioR3dC1B0t0LD5qYkbkqABys5dnsyEpQTkxcja2LXbhzcJDxi5Vk53acLyS0P98L3ZTEv0C+Zp5824vDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T04:13:23.641266Z"},"content_sha256":"fbbc3f7db9cdd341608eff9dc61c4c6a9d0081462fb59666504993e03fbbeab3","schema_version":"1.0","event_id":"sha256:fbbc3f7db9cdd341608eff9dc61c4c6a9d0081462fb59666504993e03fbbeab3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:A3TIUIZK33MXDD2ZC3UCTO6E73","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ahmed M. Ahmed, Andrey Kolobov, Bogdan Mazoure, Patrick MacAlpine, R Devon Hjelm","submitted_at":"2021-06-04T00:43:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02193","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/2106.02193/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":"2026-07-05T04:05:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rAf3MxpnuXe2RJ0CebktwpwpRl4ICUiriEUqagwHTAmFC4wvo+lArqkvoCt45/Sc7WgLUuFo1PpKyUIHfVrtAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T04:13:23.641651Z"},"content_sha256":"01e38425ec0c403129aff4ff23dd16da393d58a3d7eef2b323af6db6fc7138c7","schema_version":"1.0","event_id":"sha256:01e38425ec0c403129aff4ff23dd16da393d58a3d7eef2b323af6db6fc7138c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A3TIUIZK33MXDD2ZC3UCTO6E73/bundle.json","state_url":"https://pith.science/pith/A3TIUIZK33MXDD2ZC3UCTO6E73/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A3TIUIZK33MXDD2ZC3UCTO6E73/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":"2026-07-17T04:13:23Z","links":{"resolver":"https://pith.science/pith/A3TIUIZK33MXDD2ZC3UCTO6E73","bundle":"https://pith.science/pith/A3TIUIZK33MXDD2ZC3UCTO6E73/bundle.json","state":"https://pith.science/pith/A3TIUIZK33MXDD2ZC3UCTO6E73/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A3TIUIZK33MXDD2ZC3UCTO6E73/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uoOS7kE1ukFLhnX41Ku7AOXbbdFa6F41DZ6NqKE9Paq9RSqxQaeWWb66lajgHyi3bNUB0t/R7AAgx2jx19TICQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T04:13:23.647736Z","bundle_sha256":"e09c2cad47d57f4e75cfa1778c5f6d4e299d32532bc0c2c693c3d137096768c9"}}