{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:N6I3QBF6QEQTWOCVTMPKIHBRM6","short_pith_number":"pith:N6I3QBF6","canonical_record":{"source":{"id":"1707.07907","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-07-25T10:43:35Z","cross_cats_sorted":[],"title_canon_sha256":"3a9e1c8ca853a8c2b33fa4f58625d1b1bfbdd41216ac288011afd3f6337a1279","abstract_canon_sha256":"30400bc8b7de2d02b8c34252387ee94f9e8512cdc8a422ddd8d8f9479aa5a50f"},"schema_version":"1.0"},"canonical_sha256":"6f91b804be81213b38559b1ea41c31679d27fc5a039fe5cfdfcbf2bc438f99bf","source":{"kind":"arxiv","id":"1707.07907","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.07907","created_at":"2026-05-18T00:34:12Z"},{"alias_kind":"arxiv_version","alias_value":"1707.07907v3","created_at":"2026-05-18T00:34:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.07907","created_at":"2026-05-18T00:34:12Z"},{"alias_kind":"pith_short_12","alias_value":"N6I3QBF6QEQT","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"N6I3QBF6QEQTWOCV","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"N6I3QBF6","created_at":"2026-05-18T12:31:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:N6I3QBF6QEQTWOCVTMPKIHBRM6","target":"record","payload":{"canonical_record":{"source":{"id":"1707.07907","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-07-25T10:43:35Z","cross_cats_sorted":[],"title_canon_sha256":"3a9e1c8ca853a8c2b33fa4f58625d1b1bfbdd41216ac288011afd3f6337a1279","abstract_canon_sha256":"30400bc8b7de2d02b8c34252387ee94f9e8512cdc8a422ddd8d8f9479aa5a50f"},"schema_version":"1.0"},"canonical_sha256":"6f91b804be81213b38559b1ea41c31679d27fc5a039fe5cfdfcbf2bc438f99bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:12.874477Z","signature_b64":"TAhF/zFVhhH37KvJZ9BBgHYMEg2Y9fa4tpX1CVkxT+C5oBXwxKoiSezm4TGpCxAxusXXQpgK0iAjlMCnwMVWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f91b804be81213b38559b1ea41c31679d27fc5a039fe5cfdfcbf2bc438f99bf","last_reissued_at":"2026-05-18T00:34:12.873937Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:12.873937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.07907","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":"2026-05-18T00:34:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QIbuYR0dl93Nzd2mEZYBOWhnJ3mcezaWBQqNVM1vV3zEwSXXbRI70mHQtxXMiiC+E6M5TpZxfmqnpLZfFU0zAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T06:53:02.865166Z"},"content_sha256":"073f2582b700481c0cf9f57839d083d4641f98f711c99fe3e13bf26e8b7e0522","schema_version":"1.0","event_id":"sha256:073f2582b700481c0cf9f57839d083d4641f98f711c99fe3e13bf26e8b7e0522"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:N6I3QBF6QEQTWOCVTMPKIHBRM6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mutual Alignment Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ingmar Posner, Markus Wulfmeier, Pieter Abbeel","submitted_at":"2017-07-25T10:43:35Z","abstract_excerpt":"Training robots for operation in the real world is a complex, time consuming and potentially expensive task. Despite significant success of reinforcement learning in games and simulations, research in real robot applications has not been able to match similar progress. While sample complexity can be reduced by training policies in simulation, such policies can perform sub-optimally on the real platform given imperfect calibration of model dynamics. We present an approach -- supplemental to fine tuning on the real robot -- to further benefit from parallel access to a simulator during training a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.07907","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":""},"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":"2026-05-18T00:34:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X/Uw2UoIkfEe4dFdlUHQHADEiY1qEt3ELslHwNVcIxPBhyvB1vbhRmOIZLh83qB9nbXU3U0EAWCVoiACKkLABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T06:53:02.865524Z"},"content_sha256":"28eba474671349d844e7643c5c055b142e8c59ef1fd823543e1b5954afbd3994","schema_version":"1.0","event_id":"sha256:28eba474671349d844e7643c5c055b142e8c59ef1fd823543e1b5954afbd3994"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N6I3QBF6QEQTWOCVTMPKIHBRM6/bundle.json","state_url":"https://pith.science/pith/N6I3QBF6QEQTWOCVTMPKIHBRM6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N6I3QBF6QEQTWOCVTMPKIHBRM6/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":"2026-06-03T06:53:02Z","links":{"resolver":"https://pith.science/pith/N6I3QBF6QEQTWOCVTMPKIHBRM6","bundle":"https://pith.science/pith/N6I3QBF6QEQTWOCVTMPKIHBRM6/bundle.json","state":"https://pith.science/pith/N6I3QBF6QEQTWOCVTMPKIHBRM6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N6I3QBF6QEQTWOCVTMPKIHBRM6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:N6I3QBF6QEQTWOCVTMPKIHBRM6","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":"30400bc8b7de2d02b8c34252387ee94f9e8512cdc8a422ddd8d8f9479aa5a50f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-07-25T10:43:35Z","title_canon_sha256":"3a9e1c8ca853a8c2b33fa4f58625d1b1bfbdd41216ac288011afd3f6337a1279"},"schema_version":"1.0","source":{"id":"1707.07907","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.07907","created_at":"2026-05-18T00:34:12Z"},{"alias_kind":"arxiv_version","alias_value":"1707.07907v3","created_at":"2026-05-18T00:34:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.07907","created_at":"2026-05-18T00:34:12Z"},{"alias_kind":"pith_short_12","alias_value":"N6I3QBF6QEQT","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"N6I3QBF6QEQTWOCV","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"N6I3QBF6","created_at":"2026-05-18T12:31:31Z"}],"graph_snapshots":[{"event_id":"sha256:28eba474671349d844e7643c5c055b142e8c59ef1fd823543e1b5954afbd3994","target":"graph","created_at":"2026-05-18T00:34:12Z","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"},"paper":{"abstract_excerpt":"Training robots for operation in the real world is a complex, time consuming and potentially expensive task. Despite significant success of reinforcement learning in games and simulations, research in real robot applications has not been able to match similar progress. While sample complexity can be reduced by training policies in simulation, such policies can perform sub-optimally on the real platform given imperfect calibration of model dynamics. We present an approach -- supplemental to fine tuning on the real robot -- to further benefit from parallel access to a simulator during training a","authors_text":"Ingmar Posner, Markus Wulfmeier, Pieter Abbeel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-07-25T10:43:35Z","title":"Mutual Alignment Transfer Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.07907","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":"sha256:073f2582b700481c0cf9f57839d083d4641f98f711c99fe3e13bf26e8b7e0522","target":"record","created_at":"2026-05-18T00:34:12Z","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":"30400bc8b7de2d02b8c34252387ee94f9e8512cdc8a422ddd8d8f9479aa5a50f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-07-25T10:43:35Z","title_canon_sha256":"3a9e1c8ca853a8c2b33fa4f58625d1b1bfbdd41216ac288011afd3f6337a1279"},"schema_version":"1.0","source":{"id":"1707.07907","kind":"arxiv","version":3}},"canonical_sha256":"6f91b804be81213b38559b1ea41c31679d27fc5a039fe5cfdfcbf2bc438f99bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f91b804be81213b38559b1ea41c31679d27fc5a039fe5cfdfcbf2bc438f99bf","first_computed_at":"2026-05-18T00:34:12.873937Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:34:12.873937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TAhF/zFVhhH37KvJZ9BBgHYMEg2Y9fa4tpX1CVkxT+C5oBXwxKoiSezm4TGpCxAxusXXQpgK0iAjlMCnwMVWAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:34:12.874477Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.07907","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:073f2582b700481c0cf9f57839d083d4641f98f711c99fe3e13bf26e8b7e0522","sha256:28eba474671349d844e7643c5c055b142e8c59ef1fd823543e1b5954afbd3994"],"state_sha256":"e29d9502d458f20f44584a03a59eb16b5a13f7321ca1df3d0622b9c279848933"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+giXgwUtnB08anfdoj8VO8RR6vhcvre31VJV1EIGctmYe4gbJUqcjDi3Z+e0GBTAC6g6OxRgLmOA1hY7Ia6HBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T06:53:02.867418Z","bundle_sha256":"18d891a6b8c3ad8f77a784ed92d307c086218fb6863ad704bf8aa1dbebf1632f"}}