{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:SRUBPYC7CC2RPMXKJTNODKHLLF","short_pith_number":"pith:SRUBPYC7","canonical_record":{"source":{"id":"2108.04763","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-08-10T16:14:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f1577fe436114dd4f38305c237117cea30479ed3b12aa0c4f7811131a6bcc03c","abstract_canon_sha256":"6e2d9b6ce316416659c35fe56191e17228a79a217cc34a239d306bd76d60a47e"},"schema_version":"1.0"},"canonical_sha256":"946817e05f10b517b2ea4cdae1a8eb5976ea5fa6fb77753fdd98545a28160ea2","source":{"kind":"arxiv","id":"2108.04763","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.04763","created_at":"2026-07-05T04:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2108.04763v2","created_at":"2026-07-05T04:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04763","created_at":"2026-07-05T04:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"SRUBPYC7CC2R","created_at":"2026-07-05T04:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"SRUBPYC7CC2RPMXK","created_at":"2026-07-05T04:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"SRUBPYC7","created_at":"2026-07-05T04:05:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:SRUBPYC7CC2RPMXKJTNODKHLLF","target":"record","payload":{"canonical_record":{"source":{"id":"2108.04763","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-08-10T16:14:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f1577fe436114dd4f38305c237117cea30479ed3b12aa0c4f7811131a6bcc03c","abstract_canon_sha256":"6e2d9b6ce316416659c35fe56191e17228a79a217cc34a239d306bd76d60a47e"},"schema_version":"1.0"},"canonical_sha256":"946817e05f10b517b2ea4cdae1a8eb5976ea5fa6fb77753fdd98545a28160ea2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:12.602220Z","signature_b64":"/luxQLtE9Pvb1wbkgvyaTNm81c3S7Y4MU/tSHKeUKHJxS3Iu0cORRGQ/k+xhhHTXHjTqM8PQmNOby7KYpE9VBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"946817e05f10b517b2ea4cdae1a8eb5976ea5fa6fb77753fdd98545a28160ea2","last_reissued_at":"2026-07-05T04:05:12.601768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:12.601768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.04763","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":"2026-07-05T04:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wXiji2gmNel1eklFuN79XH6TCRqgDevWfg6AIlb66ZfqKHjoVqOoq/KfFfQ8ZWc+EzV3GXzolCdee8ouWOn6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T04:53:08.598199Z"},"content_sha256":"1633550af13a0c5b84190dafba09b92bcf7ef3785f04b925f15c5be6bf63d5c1","schema_version":"1.0","event_id":"sha256:1633550af13a0c5b84190dafba09b92bcf7ef3785f04b925f15c5be6bf63d5c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:SRUBPYC7CC2RPMXKJTNODKHLLF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Imitation Learning by Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Kamil Ciosek","submitted_at":"2021-08-10T16:14:41Z","abstract_excerpt":"Imitation learning algorithms learn a policy from demonstrations of expert behavior. We show that, for deterministic experts, imitation learning can be done by reduction to reinforcement learning with a stationary reward. Our theoretical analysis both certifies the recovery of expert reward and bounds the total variation distance between the expert and the imitation learner, showing a link to adversarial imitation learning. We conduct experiments which confirm that our reduction works well in practice for continuous control tasks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.04763","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/2108.04763/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":"2026-07-05T04:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"og+hiu+5DsajI1VLOCsoz/bCoWZQzKXnvQqlPCYCW3/spUTJMdDz31kr+7OOQJOqNu31J2V3nRmsgfpMsE5TBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T04:53:08.598578Z"},"content_sha256":"fa4c04d868557eb59e4d3207faf78f2ca96a0cd013309271c0c8c801a58c5ed0","schema_version":"1.0","event_id":"sha256:fa4c04d868557eb59e4d3207faf78f2ca96a0cd013309271c0c8c801a58c5ed0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SRUBPYC7CC2RPMXKJTNODKHLLF/bundle.json","state_url":"https://pith.science/pith/SRUBPYC7CC2RPMXKJTNODKHLLF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SRUBPYC7CC2RPMXKJTNODKHLLF/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":"2026-08-23T04:53:08Z","links":{"resolver":"https://pith.science/pith/SRUBPYC7CC2RPMXKJTNODKHLLF","bundle":"https://pith.science/pith/SRUBPYC7CC2RPMXKJTNODKHLLF/bundle.json","state":"https://pith.science/pith/SRUBPYC7CC2RPMXKJTNODKHLLF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SRUBPYC7CC2RPMXKJTNODKHLLF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SRUBPYC7CC2RPMXKJTNODKHLLF","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":"6e2d9b6ce316416659c35fe56191e17228a79a217cc34a239d306bd76d60a47e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-08-10T16:14:41Z","title_canon_sha256":"f1577fe436114dd4f38305c237117cea30479ed3b12aa0c4f7811131a6bcc03c"},"schema_version":"1.0","source":{"id":"2108.04763","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.04763","created_at":"2026-07-05T04:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2108.04763v2","created_at":"2026-07-05T04:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04763","created_at":"2026-07-05T04:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"SRUBPYC7CC2R","created_at":"2026-07-05T04:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"SRUBPYC7CC2RPMXK","created_at":"2026-07-05T04:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"SRUBPYC7","created_at":"2026-07-05T04:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:fa4c04d868557eb59e4d3207faf78f2ca96a0cd013309271c0c8c801a58c5ed0","target":"graph","created_at":"2026-07-05T04:05:12Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2108.04763/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imitation learning algorithms learn a policy from demonstrations of expert behavior. We show that, for deterministic experts, imitation learning can be done by reduction to reinforcement learning with a stationary reward. Our theoretical analysis both certifies the recovery of expert reward and bounds the total variation distance between the expert and the imitation learner, showing a link to adversarial imitation learning. We conduct experiments which confirm that our reduction works well in practice for continuous control tasks.","authors_text":"Kamil Ciosek","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-08-10T16:14:41Z","title":"Imitation Learning by Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.04763","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":"sha256:1633550af13a0c5b84190dafba09b92bcf7ef3785f04b925f15c5be6bf63d5c1","target":"record","created_at":"2026-07-05T04:05:12Z","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":"6e2d9b6ce316416659c35fe56191e17228a79a217cc34a239d306bd76d60a47e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-08-10T16:14:41Z","title_canon_sha256":"f1577fe436114dd4f38305c237117cea30479ed3b12aa0c4f7811131a6bcc03c"},"schema_version":"1.0","source":{"id":"2108.04763","kind":"arxiv","version":2}},"canonical_sha256":"946817e05f10b517b2ea4cdae1a8eb5976ea5fa6fb77753fdd98545a28160ea2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"946817e05f10b517b2ea4cdae1a8eb5976ea5fa6fb77753fdd98545a28160ea2","first_computed_at":"2026-07-05T04:05:12.601768Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:12.601768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/luxQLtE9Pvb1wbkgvyaTNm81c3S7Y4MU/tSHKeUKHJxS3Iu0cORRGQ/k+xhhHTXHjTqM8PQmNOby7KYpE9VBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:12.602220Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.04763","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1633550af13a0c5b84190dafba09b92bcf7ef3785f04b925f15c5be6bf63d5c1","sha256:fa4c04d868557eb59e4d3207faf78f2ca96a0cd013309271c0c8c801a58c5ed0"],"state_sha256":"bf35a45bb0aeded9cbbd6f5afe274718c6a90614ac3129777764f838a22287de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qpqMZP2e7lBYdZZz6NwVDJMXfg1ecUH3e/RSE5y/I59w7q9q/85maVXi59G4stPLvOa8cPry5yqy2CXECbThDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T04:53:08.601292Z","bundle_sha256":"1868e2b6bb9a9415c607d7db51138a9dfefd24339d17c71ddad8decd929dfd06"}}