{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CRGJFHQ2YGXDQOUFNO5KWROJJD","short_pith_number":"pith:CRGJFHQ2","canonical_record":{"source":{"id":"2202.11960","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-24T08:44:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"06c0c6bcdcfef71393e164f050287c8aede4f742afa66dd024b9043a5d61616b","abstract_canon_sha256":"c982ac60c0f3e1d72cedb1db2f540a000692201aaaa763c4a0ffcb438cd387eb"},"schema_version":"1.0"},"canonical_sha256":"144c929e1ac1ae383a856bbaab45c948c3457adbe1aaf13229427c792e098a39","source":{"kind":"arxiv","id":"2202.11960","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.11960","created_at":"2026-07-05T03:59:48Z"},{"alias_kind":"arxiv_version","alias_value":"2202.11960v1","created_at":"2026-07-05T03:59:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.11960","created_at":"2026-07-05T03:59:48Z"},{"alias_kind":"pith_short_12","alias_value":"CRGJFHQ2YGXD","created_at":"2026-07-05T03:59:48Z"},{"alias_kind":"pith_short_16","alias_value":"CRGJFHQ2YGXDQOUF","created_at":"2026-07-05T03:59:48Z"},{"alias_kind":"pith_short_8","alias_value":"CRGJFHQ2","created_at":"2026-07-05T03:59:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CRGJFHQ2YGXDQOUFNO5KWROJJD","target":"record","payload":{"canonical_record":{"source":{"id":"2202.11960","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-24T08:44:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"06c0c6bcdcfef71393e164f050287c8aede4f742afa66dd024b9043a5d61616b","abstract_canon_sha256":"c982ac60c0f3e1d72cedb1db2f540a000692201aaaa763c4a0ffcb438cd387eb"},"schema_version":"1.0"},"canonical_sha256":"144c929e1ac1ae383a856bbaab45c948c3457adbe1aaf13229427c792e098a39","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:48.081895Z","signature_b64":"zRlA0s/ebnU9t1gd+QS8qc0YqmRDXDi4T5twywN3yHnRGj+xULjQVnyJ0RBrzIgGfEzr1drZdUpkzJqWD9VlAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"144c929e1ac1ae383a856bbaab45c948c3457adbe1aaf13229427c792e098a39","last_reissued_at":"2026-07-05T03:59:48.081515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:48.081515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.11960","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":"2026-07-05T03:59:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pbife0bngQgKd8ZN7XE1LoDZX1pu7Bp0hKs+dW35H9iI5sn+awmrMHr6FnyLrc1SJ5sIffdqipmEKgQMr/tVCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:53:10.335439Z"},"content_sha256":"6917ded69d144451120cb7980521037d21773427322ddb96bd0d3894c16acbac","schema_version":"1.0","event_id":"sha256:6917ded69d144451120cb7980521037d21773427322ddb96bd0d3894c16acbac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CRGJFHQ2YGXDQOUFNO5KWROJJD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dylan R. Ashley, J\\\"urgen Schmidhuber, Kai Arulkumaran, Rupesh K. Srivastava","submitted_at":"2022-02-24T08:44:11Z","abstract_excerpt":"Upside down reinforcement learning (UDRL) flips the conventional use of the return in the objective function in RL upside down, by taking returns as input and predicting actions. UDRL is based purely on supervised learning, and bypasses some prominent issues in RL: bootstrapping, off-policy corrections, and discount factors. While previous work with UDRL demonstrated it in a traditional online RL setting, here we show that this single algorithm can also work in the imitation learning and offline RL settings, be extended to the goal-conditioned RL setting, and even the meta-RL setting. With a g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.11960","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/2202.11960/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":"2026-07-05T03:59:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EER2J40PsMM83dQiJHyJcqKus9NWXO6FpOCWScrlU7nD+SZmdmGTv7EAUPx0u+okC9eieTBUPTj75DMyBPPRAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:53:10.335940Z"},"content_sha256":"a88a072c1ef8bc2f8ac6740dbd4b1762fad1dd3116d996d068eec55ab50d372e","schema_version":"1.0","event_id":"sha256:a88a072c1ef8bc2f8ac6740dbd4b1762fad1dd3116d996d068eec55ab50d372e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CRGJFHQ2YGXDQOUFNO5KWROJJD/bundle.json","state_url":"https://pith.science/pith/CRGJFHQ2YGXDQOUFNO5KWROJJD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CRGJFHQ2YGXDQOUFNO5KWROJJD/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":"2026-08-09T18:53:10Z","links":{"resolver":"https://pith.science/pith/CRGJFHQ2YGXDQOUFNO5KWROJJD","bundle":"https://pith.science/pith/CRGJFHQ2YGXDQOUFNO5KWROJJD/bundle.json","state":"https://pith.science/pith/CRGJFHQ2YGXDQOUFNO5KWROJJD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CRGJFHQ2YGXDQOUFNO5KWROJJD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CRGJFHQ2YGXDQOUFNO5KWROJJD","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":"c982ac60c0f3e1d72cedb1db2f540a000692201aaaa763c4a0ffcb438cd387eb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-24T08:44:11Z","title_canon_sha256":"06c0c6bcdcfef71393e164f050287c8aede4f742afa66dd024b9043a5d61616b"},"schema_version":"1.0","source":{"id":"2202.11960","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.11960","created_at":"2026-07-05T03:59:48Z"},{"alias_kind":"arxiv_version","alias_value":"2202.11960v1","created_at":"2026-07-05T03:59:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.11960","created_at":"2026-07-05T03:59:48Z"},{"alias_kind":"pith_short_12","alias_value":"CRGJFHQ2YGXD","created_at":"2026-07-05T03:59:48Z"},{"alias_kind":"pith_short_16","alias_value":"CRGJFHQ2YGXDQOUF","created_at":"2026-07-05T03:59:48Z"},{"alias_kind":"pith_short_8","alias_value":"CRGJFHQ2","created_at":"2026-07-05T03:59:48Z"}],"graph_snapshots":[{"event_id":"sha256:a88a072c1ef8bc2f8ac6740dbd4b1762fad1dd3116d996d068eec55ab50d372e","target":"graph","created_at":"2026-07-05T03:59:48Z","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/2202.11960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Upside down reinforcement learning (UDRL) flips the conventional use of the return in the objective function in RL upside down, by taking returns as input and predicting actions. UDRL is based purely on supervised learning, and bypasses some prominent issues in RL: bootstrapping, off-policy corrections, and discount factors. While previous work with UDRL demonstrated it in a traditional online RL setting, here we show that this single algorithm can also work in the imitation learning and offline RL settings, be extended to the goal-conditioned RL setting, and even the meta-RL setting. With a g","authors_text":"Dylan R. Ashley, J\\\"urgen Schmidhuber, Kai Arulkumaran, Rupesh K. Srivastava","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-24T08:44:11Z","title":"All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.11960","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":"sha256:6917ded69d144451120cb7980521037d21773427322ddb96bd0d3894c16acbac","target":"record","created_at":"2026-07-05T03:59:48Z","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":"c982ac60c0f3e1d72cedb1db2f540a000692201aaaa763c4a0ffcb438cd387eb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-24T08:44:11Z","title_canon_sha256":"06c0c6bcdcfef71393e164f050287c8aede4f742afa66dd024b9043a5d61616b"},"schema_version":"1.0","source":{"id":"2202.11960","kind":"arxiv","version":1}},"canonical_sha256":"144c929e1ac1ae383a856bbaab45c948c3457adbe1aaf13229427c792e098a39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"144c929e1ac1ae383a856bbaab45c948c3457adbe1aaf13229427c792e098a39","first_computed_at":"2026-07-05T03:59:48.081515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:59:48.081515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zRlA0s/ebnU9t1gd+QS8qc0YqmRDXDi4T5twywN3yHnRGj+xULjQVnyJ0RBrzIgGfEzr1drZdUpkzJqWD9VlAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:59:48.081895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.11960","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6917ded69d144451120cb7980521037d21773427322ddb96bd0d3894c16acbac","sha256:a88a072c1ef8bc2f8ac6740dbd4b1762fad1dd3116d996d068eec55ab50d372e"],"state_sha256":"5bccebe81a3171392bbc60cf46a5d639f49569095788f2dd568f76b934b1f40f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L6KX+oAc3+2awfHVRwrjKfMZP6aDLOqJM6Ym5KbMNoG+tKTSqoNSYyRSuRB3Y4QrCDVnbgjfVa+ja9vU3EHxBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:53:10.339165Z","bundle_sha256":"4af2d0c0183b3cd5023d90aad54515266b0c07b3bbc95a68508e49238449bca9"}}