{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:67ODNOK56KGUAGS72DUDCU33N5","short_pith_number":"pith:67ODNOK5","canonical_record":{"source":{"id":"1908.09357","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-25T16:22:04Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"021aea021c7d905d2d17112351173b3673e6bec4d19679ed51d559653e3813e4","abstract_canon_sha256":"0cbea72d6437270ba86747a60350c18fed9ee818c36012c34f55db48d0b167c7"},"schema_version":"1.0"},"canonical_sha256":"f7dc36b95df28d401a5fd0e831537b6f480a92f75b6ea91c565df41f31475e1f","source":{"kind":"arxiv","id":"1908.09357","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.09357","created_at":"2026-07-05T00:33:15Z"},{"alias_kind":"arxiv_version","alias_value":"1908.09357v3","created_at":"2026-07-05T00:33:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09357","created_at":"2026-07-05T00:33:15Z"},{"alias_kind":"pith_short_12","alias_value":"67ODNOK56KGU","created_at":"2026-07-05T00:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"67ODNOK56KGUAGS7","created_at":"2026-07-05T00:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"67ODNOK5","created_at":"2026-07-05T00:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:67ODNOK56KGUAGS72DUDCU33N5","target":"record","payload":{"canonical_record":{"source":{"id":"1908.09357","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-25T16:22:04Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"021aea021c7d905d2d17112351173b3673e6bec4d19679ed51d559653e3813e4","abstract_canon_sha256":"0cbea72d6437270ba86747a60350c18fed9ee818c36012c34f55db48d0b167c7"},"schema_version":"1.0"},"canonical_sha256":"f7dc36b95df28d401a5fd0e831537b6f480a92f75b6ea91c565df41f31475e1f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:33:15.488476Z","signature_b64":"dR8rnjSNJAiVTZavbHkMYJjmoPmG+Oa07mKaO+jMcOmcm5jQiLDx+JhyUG+tOF4y6YZaYVFR1d3n3UvmD44yDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7dc36b95df28d401a5fd0e831537b6f480a92f75b6ea91c565df41f31475e1f","last_reissued_at":"2026-07-05T00:33:15.488007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:33:15.488007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.09357","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":"2026-07-05T00:33:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9TL/FGQejEh6eC7GBCk+2IROA/B3P2ndX/1bmcOzxAQhfC8ytIoEBgnzA2kDAvlC4yiSZhQtcv2UnJfAS2h0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:06:21.600216Z"},"content_sha256":"065b4ef70c8e5c1088074bf5cf892ffc390425690412baeeafdd23e45dc7f2eb","schema_version":"1.0","event_id":"sha256:065b4ef70c8e5c1088074bf5cf892ffc390425690412baeeafdd23e45dc7f2eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:67ODNOK56KGUAGS72DUDCU33N5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamics-aware Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhinav Gupta, Kyunghyun Cho, Rajat Agarwal, William Whitney","submitted_at":"2019-08-25T16:22:04Z","abstract_excerpt":"In this paper we consider self-supervised representation learning to improve sample efficiency in reinforcement learning (RL). We propose a forward prediction objective for simultaneously learning embeddings of states and action sequences. These embeddings capture the structure of the environment's dynamics, enabling efficient policy learning. We demonstrate that our action embeddings alone improve the sample efficiency and peak performance of model-free RL on control from low-dimensional states. By combining state and action embeddings, we achieve efficient learning of high-quality policies o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09357","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/1908.09357/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":"2026-07-05T00:33:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4cvZL32JuOrJ5vAhQowlcEELQhW2l9OHiuW6dNPyOZPNIw9+29Ue2WW/VlSnIAQWOB88Y5ihVjQuYgB9vxc0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:06:21.600730Z"},"content_sha256":"ed528bef261acb3e98c993604ba16f8f961a7517cedb1f5f53d1c9ae31c49d78","schema_version":"1.0","event_id":"sha256:ed528bef261acb3e98c993604ba16f8f961a7517cedb1f5f53d1c9ae31c49d78"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/67ODNOK56KGUAGS72DUDCU33N5/bundle.json","state_url":"https://pith.science/pith/67ODNOK56KGUAGS72DUDCU33N5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/67ODNOK56KGUAGS72DUDCU33N5/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":"2026-08-11T17:06:21Z","links":{"resolver":"https://pith.science/pith/67ODNOK56KGUAGS72DUDCU33N5","bundle":"https://pith.science/pith/67ODNOK56KGUAGS72DUDCU33N5/bundle.json","state":"https://pith.science/pith/67ODNOK56KGUAGS72DUDCU33N5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/67ODNOK56KGUAGS72DUDCU33N5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:67ODNOK56KGUAGS72DUDCU33N5","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":"0cbea72d6437270ba86747a60350c18fed9ee818c36012c34f55db48d0b167c7","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-25T16:22:04Z","title_canon_sha256":"021aea021c7d905d2d17112351173b3673e6bec4d19679ed51d559653e3813e4"},"schema_version":"1.0","source":{"id":"1908.09357","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.09357","created_at":"2026-07-05T00:33:15Z"},{"alias_kind":"arxiv_version","alias_value":"1908.09357v3","created_at":"2026-07-05T00:33:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09357","created_at":"2026-07-05T00:33:15Z"},{"alias_kind":"pith_short_12","alias_value":"67ODNOK56KGU","created_at":"2026-07-05T00:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"67ODNOK56KGUAGS7","created_at":"2026-07-05T00:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"67ODNOK5","created_at":"2026-07-05T00:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:ed528bef261acb3e98c993604ba16f8f961a7517cedb1f5f53d1c9ae31c49d78","target":"graph","created_at":"2026-07-05T00:33:15Z","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/1908.09357/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we consider self-supervised representation learning to improve sample efficiency in reinforcement learning (RL). We propose a forward prediction objective for simultaneously learning embeddings of states and action sequences. These embeddings capture the structure of the environment's dynamics, enabling efficient policy learning. We demonstrate that our action embeddings alone improve the sample efficiency and peak performance of model-free RL on control from low-dimensional states. By combining state and action embeddings, we achieve efficient learning of high-quality policies o","authors_text":"Abhinav Gupta, Kyunghyun Cho, Rajat Agarwal, William Whitney","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-25T16:22:04Z","title":"Dynamics-aware Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09357","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":"sha256:065b4ef70c8e5c1088074bf5cf892ffc390425690412baeeafdd23e45dc7f2eb","target":"record","created_at":"2026-07-05T00:33:15Z","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":"0cbea72d6437270ba86747a60350c18fed9ee818c36012c34f55db48d0b167c7","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-25T16:22:04Z","title_canon_sha256":"021aea021c7d905d2d17112351173b3673e6bec4d19679ed51d559653e3813e4"},"schema_version":"1.0","source":{"id":"1908.09357","kind":"arxiv","version":3}},"canonical_sha256":"f7dc36b95df28d401a5fd0e831537b6f480a92f75b6ea91c565df41f31475e1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7dc36b95df28d401a5fd0e831537b6f480a92f75b6ea91c565df41f31475e1f","first_computed_at":"2026-07-05T00:33:15.488007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:33:15.488007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dR8rnjSNJAiVTZavbHkMYJjmoPmG+Oa07mKaO+jMcOmcm5jQiLDx+JhyUG+tOF4y6YZaYVFR1d3n3UvmD44yDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:33:15.488476Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.09357","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:065b4ef70c8e5c1088074bf5cf892ffc390425690412baeeafdd23e45dc7f2eb","sha256:ed528bef261acb3e98c993604ba16f8f961a7517cedb1f5f53d1c9ae31c49d78"],"state_sha256":"b3dcd36d6927818db8885038405044410198a67d544bba813fa4674726398d14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YTsDDv/W1Y1tR3wmc1yZKVvlwEIRF5riqSw0bH15XspZhjniEGaPW/9/K5PJaNa5q0l+h2T1ycHusuXFBD1TDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T17:06:21.604732Z","bundle_sha256":"6f80bedfd63315b1a9edea986cb3479205e36ca46634fdc2a852eb3656de3b15"}}