{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:CT7FONS2XFZ5LWOY7RW6NE4DKG","short_pith_number":"pith:CT7FONS2","canonical_record":{"source":{"id":"1807.06919","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-18T13:28:59Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f0d481f317a0de2b2680fa8a7799cb97dca6319605a4f650cdbbb0e0aba3ac1e","abstract_canon_sha256":"0a7b0d99d0c6fbc078dd7b4860bd1a7f91750f92db0c72ca979b8c36f607072e"},"schema_version":"1.0"},"canonical_sha256":"14fe57365ab973d5d9d8fc6de6938351a68758f204748727e0d65996df7f1c40","source":{"kind":"arxiv","id":"1807.06919","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.06919","created_at":"2026-07-05T04:16:33Z"},{"alias_kind":"arxiv_version","alias_value":"1807.06919v5","created_at":"2026-07-05T04:16:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06919","created_at":"2026-07-05T04:16:33Z"},{"alias_kind":"pith_short_12","alias_value":"CT7FONS2XFZ5","created_at":"2026-07-05T04:16:33Z"},{"alias_kind":"pith_short_16","alias_value":"CT7FONS2XFZ5LWOY","created_at":"2026-07-05T04:16:33Z"},{"alias_kind":"pith_short_8","alias_value":"CT7FONS2","created_at":"2026-07-05T04:16:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:CT7FONS2XFZ5LWOY7RW6NE4DKG","target":"record","payload":{"canonical_record":{"source":{"id":"1807.06919","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-18T13:28:59Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f0d481f317a0de2b2680fa8a7799cb97dca6319605a4f650cdbbb0e0aba3ac1e","abstract_canon_sha256":"0a7b0d99d0c6fbc078dd7b4860bd1a7f91750f92db0c72ca979b8c36f607072e"},"schema_version":"1.0"},"canonical_sha256":"14fe57365ab973d5d9d8fc6de6938351a68758f204748727e0d65996df7f1c40","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:33.603583Z","signature_b64":"kpus7Xo12SyFZ3HSyH4+JPdnTx6GwFwysKl++Fgn7dLsX9/9Hx54HHyPu5/964xY7lu3Xx4GVuM6PC70qZ49DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14fe57365ab973d5d9d8fc6de6938351a68758f204748727e0d65996df7f1c40","last_reissued_at":"2026-07-05T04:16:33.603088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:33.603088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.06919","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:16:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nBQ6YbIRCyWrI+Eyj9SXDBfj1aNK34dfDgyI3tNh3SnBGAO0eC692WyIY9LQY7lyM5znqW4aRPpGmHYwN2FtBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T06:50:45.551619Z"},"content_sha256":"8d18714e8821e0dc03b9d6bf2fcd2b545e4ae264eb09d341e0b73873e9ef0c2c","schema_version":"1.0","event_id":"sha256:8d18714e8821e0dc03b9d6bf2fcd2b545e4ae264eb09d341e0b73873e9ef0c2c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:CT7FONS2XFZ5LWOY7RW6NE4DKG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Backplay: \"Man muss immer umkehren\"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Peysakhovich, Cinjon Resnick, Joan Bruna, Kyunghyun Cho, Roberta Raileanu, Sanyam Kapoor","submitted_at":"2018-07-18T13:28:59Z","abstract_excerpt":"Model-free reinforcement learning (RL) requires a large number of trials to learn a good policy, especially in environments with sparse rewards. We explore a method to improve the sample efficiency when we have access to demonstrations. Our approach, Backplay, uses a single demonstration to construct a curriculum for a given task. Rather than starting each training episode in the environment's fixed initial state, we start the agent near the end of the demonstration and move the starting point backwards during the course of training until we reach the initial state. Our contributions are that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06919","kind":"arxiv","version":5},"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/1807.06919/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":"2026-07-05T04:16:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0fHjv4mB2+UF4VkY7IBXOvYAXp1eSJHAM5vc7DsdW+xDZxXKLPGYEGPO0YQke1RM8uUr84/HUFzZeF7bQWKzDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T06:50:45.553167Z"},"content_sha256":"3b9435605c5407134ed6a5aeeb4db77dfce0334937e71724c48d0929b0dab2b0","schema_version":"1.0","event_id":"sha256:3b9435605c5407134ed6a5aeeb4db77dfce0334937e71724c48d0929b0dab2b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CT7FONS2XFZ5LWOY7RW6NE4DKG/bundle.json","state_url":"https://pith.science/pith/CT7FONS2XFZ5LWOY7RW6NE4DKG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CT7FONS2XFZ5LWOY7RW6NE4DKG/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":"2026-08-11T06:50:45Z","links":{"resolver":"https://pith.science/pith/CT7FONS2XFZ5LWOY7RW6NE4DKG","bundle":"https://pith.science/pith/CT7FONS2XFZ5LWOY7RW6NE4DKG/bundle.json","state":"https://pith.science/pith/CT7FONS2XFZ5LWOY7RW6NE4DKG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CT7FONS2XFZ5LWOY7RW6NE4DKG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CT7FONS2XFZ5LWOY7RW6NE4DKG","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":"0a7b0d99d0c6fbc078dd7b4860bd1a7f91750f92db0c72ca979b8c36f607072e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-18T13:28:59Z","title_canon_sha256":"f0d481f317a0de2b2680fa8a7799cb97dca6319605a4f650cdbbb0e0aba3ac1e"},"schema_version":"1.0","source":{"id":"1807.06919","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.06919","created_at":"2026-07-05T04:16:33Z"},{"alias_kind":"arxiv_version","alias_value":"1807.06919v5","created_at":"2026-07-05T04:16:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06919","created_at":"2026-07-05T04:16:33Z"},{"alias_kind":"pith_short_12","alias_value":"CT7FONS2XFZ5","created_at":"2026-07-05T04:16:33Z"},{"alias_kind":"pith_short_16","alias_value":"CT7FONS2XFZ5LWOY","created_at":"2026-07-05T04:16:33Z"},{"alias_kind":"pith_short_8","alias_value":"CT7FONS2","created_at":"2026-07-05T04:16:33Z"}],"graph_snapshots":[{"event_id":"sha256:3b9435605c5407134ed6a5aeeb4db77dfce0334937e71724c48d0929b0dab2b0","target":"graph","created_at":"2026-07-05T04:16:33Z","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/1807.06919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-free reinforcement learning (RL) requires a large number of trials to learn a good policy, especially in environments with sparse rewards. We explore a method to improve the sample efficiency when we have access to demonstrations. Our approach, Backplay, uses a single demonstration to construct a curriculum for a given task. Rather than starting each training episode in the environment's fixed initial state, we start the agent near the end of the demonstration and move the starting point backwards during the course of training until we reach the initial state. Our contributions are that ","authors_text":"Alexander Peysakhovich, Cinjon Resnick, Joan Bruna, Kyunghyun Cho, Roberta Raileanu, Sanyam Kapoor","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-18T13:28:59Z","title":"Backplay: \"Man muss immer umkehren\""},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06919","kind":"arxiv","version":5},"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":"sha256:8d18714e8821e0dc03b9d6bf2fcd2b545e4ae264eb09d341e0b73873e9ef0c2c","target":"record","created_at":"2026-07-05T04:16:33Z","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":"0a7b0d99d0c6fbc078dd7b4860bd1a7f91750f92db0c72ca979b8c36f607072e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-18T13:28:59Z","title_canon_sha256":"f0d481f317a0de2b2680fa8a7799cb97dca6319605a4f650cdbbb0e0aba3ac1e"},"schema_version":"1.0","source":{"id":"1807.06919","kind":"arxiv","version":5}},"canonical_sha256":"14fe57365ab973d5d9d8fc6de6938351a68758f204748727e0d65996df7f1c40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14fe57365ab973d5d9d8fc6de6938351a68758f204748727e0d65996df7f1c40","first_computed_at":"2026-07-05T04:16:33.603088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:16:33.603088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kpus7Xo12SyFZ3HSyH4+JPdnTx6GwFwysKl++Fgn7dLsX9/9Hx54HHyPu5/964xY7lu3Xx4GVuM6PC70qZ49DA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:16:33.603583Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.06919","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d18714e8821e0dc03b9d6bf2fcd2b545e4ae264eb09d341e0b73873e9ef0c2c","sha256:3b9435605c5407134ed6a5aeeb4db77dfce0334937e71724c48d0929b0dab2b0"],"state_sha256":"c2c7f1e74c73bd6f15dec75cffa6e2c890f259e0c631bea8abdcb18b79a13d0a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HjYPjdYESvjyM2YS989zK50B8WhgsKSMJGXOA5izww/vyY4LPY+4pGsWTyLqVOGJOxP7YKoRnVLNZeYYQRp7BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T06:50:45.621137Z","bundle_sha256":"982a3b22836c80f5f0e2d4132ae0ad251e763c5447e5ca97226701d1f290a171"}}