{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:OKBLDLZE7TNLCBDVDUIJ2XVUWD","short_pith_number":"pith:OKBLDLZE","canonical_record":{"source":{"id":"1910.07719","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-17T05:37:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7ccdbbe008f56383a265372efe7837adc8cdb7cda32d336447e9a3d4d444600a","abstract_canon_sha256":"81f4bdb9672876a1bf28526224769e453fed1285b39223c6a7459c71c564f5f7"},"schema_version":"1.0"},"canonical_sha256":"7282b1af24fcdab104751d109d5eb4b0d92ed6e260b29e55d6d52f961bd2190a","source":{"kind":"arxiv","id":"1910.07719","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.07719","created_at":"2026-07-05T00:40:25Z"},{"alias_kind":"arxiv_version","alias_value":"1910.07719v3","created_at":"2026-07-05T00:40:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.07719","created_at":"2026-07-05T00:40:25Z"},{"alias_kind":"pith_short_12","alias_value":"OKBLDLZE7TNL","created_at":"2026-07-05T00:40:25Z"},{"alias_kind":"pith_short_16","alias_value":"OKBLDLZE7TNLCBDV","created_at":"2026-07-05T00:40:25Z"},{"alias_kind":"pith_short_8","alias_value":"OKBLDLZE","created_at":"2026-07-05T00:40:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:OKBLDLZE7TNLCBDVDUIJ2XVUWD","target":"record","payload":{"canonical_record":{"source":{"id":"1910.07719","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-17T05:37:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7ccdbbe008f56383a265372efe7837adc8cdb7cda32d336447e9a3d4d444600a","abstract_canon_sha256":"81f4bdb9672876a1bf28526224769e453fed1285b39223c6a7459c71c564f5f7"},"schema_version":"1.0"},"canonical_sha256":"7282b1af24fcdab104751d109d5eb4b0d92ed6e260b29e55d6d52f961bd2190a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:25.964406Z","signature_b64":"BHNlfYW7AqL5Dz77FeaG+h+1uOy0UmesaHshAL1Sa3ojwd57Dydx4tCxgi/d+2RWJ/IUVpBFxEYoudDZalmXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7282b1af24fcdab104751d109d5eb4b0d92ed6e260b29e55d6d52f961bd2190a","last_reissued_at":"2026-07-05T00:40:25.963934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:25.963934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.07719","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:40:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6wopk7XswwojG22vDb/MmwGsRQLH5whxBeC2d6FvnvNhWBkbJB9VHvdoWY7kuvHgluuxM7SSYhBouNs216YACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:18:55.576144Z"},"content_sha256":"8828d2cb5f0fb7a3203a8b679f8777708705c0e5512ec49c818e82a5c573f985","schema_version":"1.0","event_id":"sha256:8828d2cb5f0fb7a3203a8b679f8777708705c0e5512ec49c818e82a5c573f985"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:OKBLDLZE7TNLCBDVDUIJ2XVUWD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Single Episode Policy Transfer in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Brenden Petersen, Daniel Faissol, Hongyuan Zha, Jiachen Yang","submitted_at":"2019-10-17T05:37:50Z","abstract_excerpt":"Transfer and adaptation to new unknown environmental dynamics is a key challenge for reinforcement learning (RL). An even greater challenge is performing near-optimally in a single attempt at test time, possibly without access to dense rewards, which is not addressed by current methods that require multiple experience rollouts for adaptation. To achieve single episode transfer in a family of environments with related dynamics, we propose a general algorithm that optimizes a probe and an inference model to rapidly estimate underlying latent variables of test dynamics, which are then immediately"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.07719","kind":"arxiv","version":3},"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/1910.07719/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":"2026-07-05T00:40:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YFmkQ4QqSOT6kOQs6Pbi0IQ6DwFTXdFxdajxDcd7zJpXf4NZ8tYLsoNm91NhoMhw+ao/qniLq6OHy/O/cf90DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:18:55.576854Z"},"content_sha256":"9e590adb13c0eafdad8f6d617479206ae556dd925664151a74d4b7124129b995","schema_version":"1.0","event_id":"sha256:9e590adb13c0eafdad8f6d617479206ae556dd925664151a74d4b7124129b995"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OKBLDLZE7TNLCBDVDUIJ2XVUWD/bundle.json","state_url":"https://pith.science/pith/OKBLDLZE7TNLCBDVDUIJ2XVUWD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OKBLDLZE7TNLCBDVDUIJ2XVUWD/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":"2026-07-06T16:18:55Z","links":{"resolver":"https://pith.science/pith/OKBLDLZE7TNLCBDVDUIJ2XVUWD","bundle":"https://pith.science/pith/OKBLDLZE7TNLCBDVDUIJ2XVUWD/bundle.json","state":"https://pith.science/pith/OKBLDLZE7TNLCBDVDUIJ2XVUWD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OKBLDLZE7TNLCBDVDUIJ2XVUWD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:OKBLDLZE7TNLCBDVDUIJ2XVUWD","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":"81f4bdb9672876a1bf28526224769e453fed1285b39223c6a7459c71c564f5f7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-17T05:37:50Z","title_canon_sha256":"7ccdbbe008f56383a265372efe7837adc8cdb7cda32d336447e9a3d4d444600a"},"schema_version":"1.0","source":{"id":"1910.07719","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.07719","created_at":"2026-07-05T00:40:25Z"},{"alias_kind":"arxiv_version","alias_value":"1910.07719v3","created_at":"2026-07-05T00:40:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.07719","created_at":"2026-07-05T00:40:25Z"},{"alias_kind":"pith_short_12","alias_value":"OKBLDLZE7TNL","created_at":"2026-07-05T00:40:25Z"},{"alias_kind":"pith_short_16","alias_value":"OKBLDLZE7TNLCBDV","created_at":"2026-07-05T00:40:25Z"},{"alias_kind":"pith_short_8","alias_value":"OKBLDLZE","created_at":"2026-07-05T00:40:25Z"}],"graph_snapshots":[{"event_id":"sha256:9e590adb13c0eafdad8f6d617479206ae556dd925664151a74d4b7124129b995","target":"graph","created_at":"2026-07-05T00:40:25Z","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/1910.07719/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transfer and adaptation to new unknown environmental dynamics is a key challenge for reinforcement learning (RL). An even greater challenge is performing near-optimally in a single attempt at test time, possibly without access to dense rewards, which is not addressed by current methods that require multiple experience rollouts for adaptation. To achieve single episode transfer in a family of environments with related dynamics, we propose a general algorithm that optimizes a probe and an inference model to rapidly estimate underlying latent variables of test dynamics, which are then immediately","authors_text":"Brenden Petersen, Daniel Faissol, Hongyuan Zha, Jiachen Yang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-17T05:37:50Z","title":"Single Episode Policy Transfer in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.07719","kind":"arxiv","version":3},"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":"sha256:8828d2cb5f0fb7a3203a8b679f8777708705c0e5512ec49c818e82a5c573f985","target":"record","created_at":"2026-07-05T00:40:25Z","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":"81f4bdb9672876a1bf28526224769e453fed1285b39223c6a7459c71c564f5f7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-17T05:37:50Z","title_canon_sha256":"7ccdbbe008f56383a265372efe7837adc8cdb7cda32d336447e9a3d4d444600a"},"schema_version":"1.0","source":{"id":"1910.07719","kind":"arxiv","version":3}},"canonical_sha256":"7282b1af24fcdab104751d109d5eb4b0d92ed6e260b29e55d6d52f961bd2190a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7282b1af24fcdab104751d109d5eb4b0d92ed6e260b29e55d6d52f961bd2190a","first_computed_at":"2026-07-05T00:40:25.963934Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:40:25.963934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BHNlfYW7AqL5Dz77FeaG+h+1uOy0UmesaHshAL1Sa3ojwd57Dydx4tCxgi/d+2RWJ/IUVpBFxEYoudDZalmXAw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:40:25.964406Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.07719","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8828d2cb5f0fb7a3203a8b679f8777708705c0e5512ec49c818e82a5c573f985","sha256:9e590adb13c0eafdad8f6d617479206ae556dd925664151a74d4b7124129b995"],"state_sha256":"99b6e06681c36a08bf533d2d0a6897d98d90665763c1d4fee523e1f939003b7c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PZOEQQCIRfGtvIsDSsZYWOwwzLj4lHXQFaX3oyhdXRHOrIjE5+zMpEiittDJx8F8NmPIQ/FG/dWfN0WssnUUCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:18:55.578819Z","bundle_sha256":"0da358f5c903cca2eadd4af8a08149a45224c11a715eea2cbce00884a8fa92a9"}}