{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:RFME6KYUGJXUIHAPCA6OKULXI7","short_pith_number":"pith:RFME6KYU","canonical_record":{"source":{"id":"1912.02875","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-12-05T21:10:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ef0265bf1724762dec779753e2c9ef82b51dcc8975f1a3ddd69ac5b6d8fc6f8a","abstract_canon_sha256":"82b3905583ec42d98e915d113a3ec763d970e104fdaca11ad2f8f6dfb655fd6a"},"schema_version":"1.0"},"canonical_sha256":"89584f2b14326f441c0f103ce5517747f7ac002eeb7364e7182a3ff8a3f9fe38","source":{"kind":"arxiv","id":"1912.02875","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.02875","created_at":"2026-07-05T01:12:29Z"},{"alias_kind":"arxiv_version","alias_value":"1912.02875v2","created_at":"2026-07-05T01:12:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.02875","created_at":"2026-07-05T01:12:29Z"},{"alias_kind":"pith_short_12","alias_value":"RFME6KYUGJXU","created_at":"2026-07-05T01:12:29Z"},{"alias_kind":"pith_short_16","alias_value":"RFME6KYUGJXUIHAP","created_at":"2026-07-05T01:12:29Z"},{"alias_kind":"pith_short_8","alias_value":"RFME6KYU","created_at":"2026-07-05T01:12:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:RFME6KYUGJXUIHAPCA6OKULXI7","target":"record","payload":{"canonical_record":{"source":{"id":"1912.02875","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-12-05T21:10:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ef0265bf1724762dec779753e2c9ef82b51dcc8975f1a3ddd69ac5b6d8fc6f8a","abstract_canon_sha256":"82b3905583ec42d98e915d113a3ec763d970e104fdaca11ad2f8f6dfb655fd6a"},"schema_version":"1.0"},"canonical_sha256":"89584f2b14326f441c0f103ce5517747f7ac002eeb7364e7182a3ff8a3f9fe38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:12:29.756856Z","signature_b64":"voyS/9V6cOnZiogHPj8h3xhZ5sPTfndlHapgb1mISW5jep0tTlvhoNoNhrwlCrT8YRTc/ZtTh43pHarvOvTuBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89584f2b14326f441c0f103ce5517747f7ac002eeb7364e7182a3ff8a3f9fe38","last_reissued_at":"2026-07-05T01:12:29.756400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:12:29.756400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.02875","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":"2026-07-05T01:12:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LSPaKG9f7AAgY0je3b9b/3yUHFjpqJGzcmV3Md1CxVgafKCO2AeiECoZFCWlsFHA4myYI75tYqiF6P0RpwDAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:45:04.821449Z"},"content_sha256":"ad41ed8f455f3c8d829e633fa5bc3bb44f9a0093f66f63b808c29f0f65981bdb","schema_version":"1.0","event_id":"sha256:ad41ed8f455f3c8d829e633fa5bc3bb44f9a0093f66f63b808c29f0f65981bdb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:RFME6KYUGJXUIHAPCA6OKULXI7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Juergen Schmidhuber","submitted_at":"2019-12-05T21:10:08Z","abstract_excerpt":"We transform reinforcement learning (RL) into a form of supervised learning (SL) by turning traditional RL on its head, calling this Upside Down RL (UDRL). Standard RL predicts rewards, while UDRL instead uses rewards as task-defining inputs, together with representations of time horizons and other computable functions of historic and desired future data. UDRL learns to interpret these input observations as commands, mapping them to actions (or action probabilities) through SL on past (possibly accidental) experience. UDRL generalizes to achieve high rewards or other goals, through input comma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.02875","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/1912.02875/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":"2026-07-05T01:12:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GV3nYf7dOQZ2p4B2A/nwj0EX7sDEucMgKfu/vWixx8KbHHrW1Q/bWldbSuzQ+grHyne6HH5cvdi4YW5eBbRjBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:45:04.822508Z"},"content_sha256":"6b198d49c31beee1841c9235bad41f2c5c052deac52274970e4fc63c7e23a19f","schema_version":"1.0","event_id":"sha256:6b198d49c31beee1841c9235bad41f2c5c052deac52274970e4fc63c7e23a19f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RFME6KYUGJXUIHAPCA6OKULXI7/bundle.json","state_url":"https://pith.science/pith/RFME6KYUGJXUIHAPCA6OKULXI7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RFME6KYUGJXUIHAPCA6OKULXI7/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":"2026-08-06T22:45:04Z","links":{"resolver":"https://pith.science/pith/RFME6KYUGJXUIHAPCA6OKULXI7","bundle":"https://pith.science/pith/RFME6KYUGJXUIHAPCA6OKULXI7/bundle.json","state":"https://pith.science/pith/RFME6KYUGJXUIHAPCA6OKULXI7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RFME6KYUGJXUIHAPCA6OKULXI7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RFME6KYUGJXUIHAPCA6OKULXI7","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":"82b3905583ec42d98e915d113a3ec763d970e104fdaca11ad2f8f6dfb655fd6a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-12-05T21:10:08Z","title_canon_sha256":"ef0265bf1724762dec779753e2c9ef82b51dcc8975f1a3ddd69ac5b6d8fc6f8a"},"schema_version":"1.0","source":{"id":"1912.02875","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.02875","created_at":"2026-07-05T01:12:29Z"},{"alias_kind":"arxiv_version","alias_value":"1912.02875v2","created_at":"2026-07-05T01:12:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.02875","created_at":"2026-07-05T01:12:29Z"},{"alias_kind":"pith_short_12","alias_value":"RFME6KYUGJXU","created_at":"2026-07-05T01:12:29Z"},{"alias_kind":"pith_short_16","alias_value":"RFME6KYUGJXUIHAP","created_at":"2026-07-05T01:12:29Z"},{"alias_kind":"pith_short_8","alias_value":"RFME6KYU","created_at":"2026-07-05T01:12:29Z"}],"graph_snapshots":[{"event_id":"sha256:6b198d49c31beee1841c9235bad41f2c5c052deac52274970e4fc63c7e23a19f","target":"graph","created_at":"2026-07-05T01:12:29Z","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/1912.02875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We transform reinforcement learning (RL) into a form of supervised learning (SL) by turning traditional RL on its head, calling this Upside Down RL (UDRL). Standard RL predicts rewards, while UDRL instead uses rewards as task-defining inputs, together with representations of time horizons and other computable functions of historic and desired future data. UDRL learns to interpret these input observations as commands, mapping them to actions (or action probabilities) through SL on past (possibly accidental) experience. UDRL generalizes to achieve high rewards or other goals, through input comma","authors_text":"Juergen Schmidhuber","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-12-05T21:10:08Z","title":"Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.02875","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:ad41ed8f455f3c8d829e633fa5bc3bb44f9a0093f66f63b808c29f0f65981bdb","target":"record","created_at":"2026-07-05T01:12:29Z","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":"82b3905583ec42d98e915d113a3ec763d970e104fdaca11ad2f8f6dfb655fd6a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-12-05T21:10:08Z","title_canon_sha256":"ef0265bf1724762dec779753e2c9ef82b51dcc8975f1a3ddd69ac5b6d8fc6f8a"},"schema_version":"1.0","source":{"id":"1912.02875","kind":"arxiv","version":2}},"canonical_sha256":"89584f2b14326f441c0f103ce5517747f7ac002eeb7364e7182a3ff8a3f9fe38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89584f2b14326f441c0f103ce5517747f7ac002eeb7364e7182a3ff8a3f9fe38","first_computed_at":"2026-07-05T01:12:29.756400Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:12:29.756400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"voyS/9V6cOnZiogHPj8h3xhZ5sPTfndlHapgb1mISW5jep0tTlvhoNoNhrwlCrT8YRTc/ZtTh43pHarvOvTuBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:12:29.756856Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.02875","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad41ed8f455f3c8d829e633fa5bc3bb44f9a0093f66f63b808c29f0f65981bdb","sha256:6b198d49c31beee1841c9235bad41f2c5c052deac52274970e4fc63c7e23a19f"],"state_sha256":"90fd322d6eafeea12aa1776f098614dbfd1c4b86eb6e714ed7c1fafeaf6fb7be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dB3ZZ9D+vSzQXes19+FNm45hQDePNp2qamUuiq2rbY9grjeqjcqnQAkA4ft/60TjYgPBzVthzVuQFFhKpDGKBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T22:45:04.829420Z","bundle_sha256":"947d8dec4310648f071cbeb076699de69910fdfaee873ae2b895fceed73a0426"}}