{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YOJW7Y3OE65D7SXXPCIZJIFKDI","short_pith_number":"pith:YOJW7Y3O","canonical_record":{"source":{"id":"2209.14935","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T16:54:05Z","cross_cats_sorted":[],"title_canon_sha256":"d21237c6ee638ae0e10d321108dfb628adf41b98e98fa54fb37667fe5be1c1c7","abstract_canon_sha256":"e8b8938eb754d35a8435e72ef855bc33b2ee0e6d9b54cc2398d037a851651322"},"schema_version":"1.0"},"canonical_sha256":"c3936fe36e27ba3fcaf7789194a0aa1a30e46e6d3b1e0f963543c16b8297b70d","source":{"kind":"arxiv","id":"2209.14935","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14935","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14935v2","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14935","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"pith_short_12","alias_value":"YOJW7Y3OE65D","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"pith_short_16","alias_value":"YOJW7Y3OE65D7SXX","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"pith_short_8","alias_value":"YOJW7Y3O","created_at":"2026-07-05T05:47:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YOJW7Y3OE65D7SXXPCIZJIFKDI","target":"record","payload":{"canonical_record":{"source":{"id":"2209.14935","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T16:54:05Z","cross_cats_sorted":[],"title_canon_sha256":"d21237c6ee638ae0e10d321108dfb628adf41b98e98fa54fb37667fe5be1c1c7","abstract_canon_sha256":"e8b8938eb754d35a8435e72ef855bc33b2ee0e6d9b54cc2398d037a851651322"},"schema_version":"1.0"},"canonical_sha256":"c3936fe36e27ba3fcaf7789194a0aa1a30e46e6d3b1e0f963543c16b8297b70d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:04.118835Z","signature_b64":"nzt6sAdT1aSUIa6AMygJFPwGhdqoYm3paJR3H0DNiEvl7HlYZalDvRvpfuiGAj/k4MA3SZNXzkwQMOFem2AyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3936fe36e27ba3fcaf7789194a0aa1a30e46e6d3b1e0f963543c16b8297b70d","last_reissued_at":"2026-07-05T05:47:04.118327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:04.118327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.14935","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":"2026-07-05T05:47:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YAN0Fokf97JPVllqnlzu6ETSGGyzkbJu+jP5PQ1BITHV7hY3WJNWKe9VzNFtp+R7a/WNlEqVyUzwhar8fiwiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:50:13.598452Z"},"content_sha256":"9372921d62063b4d5f73d3a52f05eda50489e18382917c078e876a9d9cd07150","schema_version":"1.0","event_id":"sha256:9372921d62063b4d5f73d3a52f05eda50489e18382917c078e876a9d9cd07150"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YOJW7Y3OE65D7SXXPCIZJIFKDI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Does Zero-Shot Reinforcement Learning Exist?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ahmed Touati, J\\'er\\'emy Rapin, Yann Ollivier","submitted_at":"2022-09-29T16:54:05Z","abstract_excerpt":"A zero-shot RL agent is an agent that can solve any RL task in a given environment, instantly with no additional planning or learning, after an initial reward-free learning phase. This marks a shift from the reward-centric RL paradigm towards \"controllable\" agents that can follow arbitrary instructions in an environment. Current RL agents can solve families of related tasks at best, or require planning anew for each task. Strategies for approximate zero-shot RL ave been suggested using successor features (SFs) [BBQ+ 18] or forward-backward (FB) representations [TO21], but testing has been limi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14935","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/2209.14935/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":"2026-07-05T05:47:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A3aCVDGHD4zWHkelp/qmDOzL8mF/otUREK9FLEpFI8QQftmyjHm6qXeMtHT5QxR394HtNpG6dbmjM7NRyeudDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:50:13.598960Z"},"content_sha256":"d67a66ab74f38f361379ab0941afa97708baaee9631fa79b4f9e9b86e4dd6f08","schema_version":"1.0","event_id":"sha256:d67a66ab74f38f361379ab0941afa97708baaee9631fa79b4f9e9b86e4dd6f08"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YOJW7Y3OE65D7SXXPCIZJIFKDI/bundle.json","state_url":"https://pith.science/pith/YOJW7Y3OE65D7SXXPCIZJIFKDI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YOJW7Y3OE65D7SXXPCIZJIFKDI/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":"2026-08-09T12:50:13Z","links":{"resolver":"https://pith.science/pith/YOJW7Y3OE65D7SXXPCIZJIFKDI","bundle":"https://pith.science/pith/YOJW7Y3OE65D7SXXPCIZJIFKDI/bundle.json","state":"https://pith.science/pith/YOJW7Y3OE65D7SXXPCIZJIFKDI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YOJW7Y3OE65D7SXXPCIZJIFKDI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YOJW7Y3OE65D7SXXPCIZJIFKDI","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":"e8b8938eb754d35a8435e72ef855bc33b2ee0e6d9b54cc2398d037a851651322","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T16:54:05Z","title_canon_sha256":"d21237c6ee638ae0e10d321108dfb628adf41b98e98fa54fb37667fe5be1c1c7"},"schema_version":"1.0","source":{"id":"2209.14935","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14935","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14935v2","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14935","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"pith_short_12","alias_value":"YOJW7Y3OE65D","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"pith_short_16","alias_value":"YOJW7Y3OE65D7SXX","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"pith_short_8","alias_value":"YOJW7Y3O","created_at":"2026-07-05T05:47:04Z"}],"graph_snapshots":[{"event_id":"sha256:d67a66ab74f38f361379ab0941afa97708baaee9631fa79b4f9e9b86e4dd6f08","target":"graph","created_at":"2026-07-05T05:47:04Z","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/2209.14935/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A zero-shot RL agent is an agent that can solve any RL task in a given environment, instantly with no additional planning or learning, after an initial reward-free learning phase. This marks a shift from the reward-centric RL paradigm towards \"controllable\" agents that can follow arbitrary instructions in an environment. Current RL agents can solve families of related tasks at best, or require planning anew for each task. Strategies for approximate zero-shot RL ave been suggested using successor features (SFs) [BBQ+ 18] or forward-backward (FB) representations [TO21], but testing has been limi","authors_text":"Ahmed Touati, J\\'er\\'emy Rapin, Yann Ollivier","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T16:54:05Z","title":"Does Zero-Shot Reinforcement Learning Exist?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14935","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":"sha256:9372921d62063b4d5f73d3a52f05eda50489e18382917c078e876a9d9cd07150","target":"record","created_at":"2026-07-05T05:47:04Z","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":"e8b8938eb754d35a8435e72ef855bc33b2ee0e6d9b54cc2398d037a851651322","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T16:54:05Z","title_canon_sha256":"d21237c6ee638ae0e10d321108dfb628adf41b98e98fa54fb37667fe5be1c1c7"},"schema_version":"1.0","source":{"id":"2209.14935","kind":"arxiv","version":2}},"canonical_sha256":"c3936fe36e27ba3fcaf7789194a0aa1a30e46e6d3b1e0f963543c16b8297b70d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3936fe36e27ba3fcaf7789194a0aa1a30e46e6d3b1e0f963543c16b8297b70d","first_computed_at":"2026-07-05T05:47:04.118327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:04.118327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nzt6sAdT1aSUIa6AMygJFPwGhdqoYm3paJR3H0DNiEvl7HlYZalDvRvpfuiGAj/k4MA3SZNXzkwQMOFem2AyDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:04.118835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.14935","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9372921d62063b4d5f73d3a52f05eda50489e18382917c078e876a9d9cd07150","sha256:d67a66ab74f38f361379ab0941afa97708baaee9631fa79b4f9e9b86e4dd6f08"],"state_sha256":"75f61ebcbd44561deea5a74166afc9547b13ee920e58d5206a22b46f6df6e98e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"syoj7c3QeWKUsMjr4QOR2ppMLof0H81t5Yu1IfVIZGl6lTK+Y8ooRnLfhkl4Fal7HMe5DUp1dPxmkaHXv0CtCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T12:50:13.604533Z","bundle_sha256":"c9eb0c0f6407404e05b8a32f206c891db2ae0324f06a24550b5194ce9edb2ffb"}}