{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:FEH73ABTMOOREENAPXVS7LRTDA","short_pith_number":"pith:FEH73ABT","canonical_record":{"source":{"id":"2011.07193","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-14T02:03:08Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"1c2e660de01161dfb8aad8007d53f0d5095c8516deec2bc3dca0fd620ec8634c","abstract_canon_sha256":"b962420ef23306a58583489d6a5b97e82e9aaeb9a659942d6bd10aac7163a785"},"schema_version":"1.0"},"canonical_sha256":"290ffd8033639d1211a07deb2fae331829ab986ce59226b344dd5389f0b99ba4","source":{"kind":"arxiv","id":"2011.07193","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.07193","created_at":"2026-07-05T02:15:34Z"},{"alias_kind":"arxiv_version","alias_value":"2011.07193v2","created_at":"2026-07-05T02:15:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.07193","created_at":"2026-07-05T02:15:34Z"},{"alias_kind":"pith_short_12","alias_value":"FEH73ABTMOOR","created_at":"2026-07-05T02:15:34Z"},{"alias_kind":"pith_short_16","alias_value":"FEH73ABTMOOREENA","created_at":"2026-07-05T02:15:34Z"},{"alias_kind":"pith_short_8","alias_value":"FEH73ABT","created_at":"2026-07-05T02:15:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:FEH73ABTMOOREENAPXVS7LRTDA","target":"record","payload":{"canonical_record":{"source":{"id":"2011.07193","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-14T02:03:08Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"1c2e660de01161dfb8aad8007d53f0d5095c8516deec2bc3dca0fd620ec8634c","abstract_canon_sha256":"b962420ef23306a58583489d6a5b97e82e9aaeb9a659942d6bd10aac7163a785"},"schema_version":"1.0"},"canonical_sha256":"290ffd8033639d1211a07deb2fae331829ab986ce59226b344dd5389f0b99ba4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:34.803961Z","signature_b64":"+wJ5eOeR0SpJIXC6DMfJU8PN/VKHZtbZ6Vu8xx8zYz0SC/LQ83yi/2jMAqyleJjuqD4kOgEVV/cyZEcTE/mdBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"290ffd8033639d1211a07deb2fae331829ab986ce59226b344dd5389f0b99ba4","last_reissued_at":"2026-07-05T02:15:34.803441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:34.803441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.07193","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":"2026-07-05T02:15:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RRJ7ruunU+9zNfLchSJxWV1hNP9TzbEL07TD2pyhYUJRfeE04hQ+oUDPe0l+AmUugiYV18NVh8lx7nKVYMw1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:13:55.195192Z"},"content_sha256":"afe6596bc8f35595e62c3adf18f05ee80e619b2e62eb2388ab49d0df14bdf6d9","schema_version":"1.0","event_id":"sha256:afe6596bc8f35595e62c3adf18f05ee80e619b2e62eb2388ab49d0df14bdf6d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:FEH73ABTMOOREENAPXVS7LRTDA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data-Efficient Learning for Complex and Real-Time Physical Problem Solving using Augmented Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Alan Sullivan, Daniel Nikovski, Devesh K. Jha, Diego Romeres, Jeroen van Baar, Joshua B. Tenenbaum, Kei Ota, Kevin A. Smith, Takayuki Semitsu, Tomoaki Oiki","submitted_at":"2020-11-14T02:03:08Z","abstract_excerpt":"Humans quickly solve tasks in novel systems with complex dynamics, without requiring much interaction. While deep reinforcement learning algorithms have achieved tremendous success in many complex tasks, these algorithms need a large number of samples to learn meaningful policies. In this paper, we present a task for navigating a marble to the center of a circular maze. While this system is very intuitive and easy for humans to solve, it can be very difficult and inefficient for standard reinforcement learning algorithms to learn meaningful policies. We present a model that learns to move a ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.07193","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/2011.07193/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":"2026-07-05T02:15:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SmMeuIHRAkRG0JyLs/9cerxa28i8Gev1pQowaIc2V+fF9a4rhc249JMjRtwejhJHmTRk7NsKKru50IxiiKw2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:13:55.195589Z"},"content_sha256":"2f1a6ad963d19ef7e51ad2cbd392099815ceb74bc5b4453689a5a67d6c41bdc8","schema_version":"1.0","event_id":"sha256:2f1a6ad963d19ef7e51ad2cbd392099815ceb74bc5b4453689a5a67d6c41bdc8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FEH73ABTMOOREENAPXVS7LRTDA/bundle.json","state_url":"https://pith.science/pith/FEH73ABTMOOREENAPXVS7LRTDA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FEH73ABTMOOREENAPXVS7LRTDA/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":"2026-07-07T12:13:55Z","links":{"resolver":"https://pith.science/pith/FEH73ABTMOOREENAPXVS7LRTDA","bundle":"https://pith.science/pith/FEH73ABTMOOREENAPXVS7LRTDA/bundle.json","state":"https://pith.science/pith/FEH73ABTMOOREENAPXVS7LRTDA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FEH73ABTMOOREENAPXVS7LRTDA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FEH73ABTMOOREENAPXVS7LRTDA","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":"b962420ef23306a58583489d6a5b97e82e9aaeb9a659942d6bd10aac7163a785","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-14T02:03:08Z","title_canon_sha256":"1c2e660de01161dfb8aad8007d53f0d5095c8516deec2bc3dca0fd620ec8634c"},"schema_version":"1.0","source":{"id":"2011.07193","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.07193","created_at":"2026-07-05T02:15:34Z"},{"alias_kind":"arxiv_version","alias_value":"2011.07193v2","created_at":"2026-07-05T02:15:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.07193","created_at":"2026-07-05T02:15:34Z"},{"alias_kind":"pith_short_12","alias_value":"FEH73ABTMOOR","created_at":"2026-07-05T02:15:34Z"},{"alias_kind":"pith_short_16","alias_value":"FEH73ABTMOOREENA","created_at":"2026-07-05T02:15:34Z"},{"alias_kind":"pith_short_8","alias_value":"FEH73ABT","created_at":"2026-07-05T02:15:34Z"}],"graph_snapshots":[{"event_id":"sha256:2f1a6ad963d19ef7e51ad2cbd392099815ceb74bc5b4453689a5a67d6c41bdc8","target":"graph","created_at":"2026-07-05T02:15:34Z","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/2011.07193/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans quickly solve tasks in novel systems with complex dynamics, without requiring much interaction. While deep reinforcement learning algorithms have achieved tremendous success in many complex tasks, these algorithms need a large number of samples to learn meaningful policies. In this paper, we present a task for navigating a marble to the center of a circular maze. While this system is very intuitive and easy for humans to solve, it can be very difficult and inefficient for standard reinforcement learning algorithms to learn meaningful policies. We present a model that learns to move a ma","authors_text":"Alan Sullivan, Daniel Nikovski, Devesh K. Jha, Diego Romeres, Jeroen van Baar, Joshua B. Tenenbaum, Kei Ota, Kevin A. Smith, Takayuki Semitsu, Tomoaki Oiki","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-14T02:03:08Z","title":"Data-Efficient Learning for Complex and Real-Time Physical Problem Solving using Augmented Simulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.07193","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:afe6596bc8f35595e62c3adf18f05ee80e619b2e62eb2388ab49d0df14bdf6d9","target":"record","created_at":"2026-07-05T02:15:34Z","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":"b962420ef23306a58583489d6a5b97e82e9aaeb9a659942d6bd10aac7163a785","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-14T02:03:08Z","title_canon_sha256":"1c2e660de01161dfb8aad8007d53f0d5095c8516deec2bc3dca0fd620ec8634c"},"schema_version":"1.0","source":{"id":"2011.07193","kind":"arxiv","version":2}},"canonical_sha256":"290ffd8033639d1211a07deb2fae331829ab986ce59226b344dd5389f0b99ba4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"290ffd8033639d1211a07deb2fae331829ab986ce59226b344dd5389f0b99ba4","first_computed_at":"2026-07-05T02:15:34.803441Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:15:34.803441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+wJ5eOeR0SpJIXC6DMfJU8PN/VKHZtbZ6Vu8xx8zYz0SC/LQ83yi/2jMAqyleJjuqD4kOgEVV/cyZEcTE/mdBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:15:34.803961Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.07193","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afe6596bc8f35595e62c3adf18f05ee80e619b2e62eb2388ab49d0df14bdf6d9","sha256:2f1a6ad963d19ef7e51ad2cbd392099815ceb74bc5b4453689a5a67d6c41bdc8"],"state_sha256":"6e1e9dcda5238b9c9cc45c5561dfdc4f0b5a0c13c3d7bc7bc1e9f8da87939f5d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xaxIYcO/aQjaSfrEB9Z9ZE/OF5+UXUZLuTk/n84Wduu+nRc6+SYOqz8vC2iC/d0Ez8maXNUtsvBSWtT5XAqtCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:13:55.197590Z","bundle_sha256":"0ca269910ca428b23bdcf3306b9d584d10efc9da0530ae45b7516f8c3678f203"}}