{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:TSHIGJRK42Y652YGRX35N66W3C","short_pith_number":"pith:TSHIGJRK","canonical_record":{"source":{"id":"2010.11876","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T17:13:31Z","cross_cats_sorted":[],"title_canon_sha256":"7c523bf02ba59d5a45dd76046584654843aecd7c280421b32a1945aac938fd46","abstract_canon_sha256":"96bcbfa68c7a95102a5da10aea4d17dda327ecffd87abfd3fac02ede512dc2a7"},"schema_version":"1.0"},"canonical_sha256":"9c8e83262ae6b1eeeb068df7d6fbd6d8b07d618fc68d7fb9bf142abad2ab858f","source":{"kind":"arxiv","id":"2010.11876","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.11876","created_at":"2026-07-05T01:45:21Z"},{"alias_kind":"arxiv_version","alias_value":"2010.11876v1","created_at":"2026-07-05T01:45:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11876","created_at":"2026-07-05T01:45:21Z"},{"alias_kind":"pith_short_12","alias_value":"TSHIGJRK42Y6","created_at":"2026-07-05T01:45:21Z"},{"alias_kind":"pith_short_16","alias_value":"TSHIGJRK42Y652YG","created_at":"2026-07-05T01:45:21Z"},{"alias_kind":"pith_short_8","alias_value":"TSHIGJRK","created_at":"2026-07-05T01:45:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:TSHIGJRK42Y652YGRX35N66W3C","target":"record","payload":{"canonical_record":{"source":{"id":"2010.11876","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T17:13:31Z","cross_cats_sorted":[],"title_canon_sha256":"7c523bf02ba59d5a45dd76046584654843aecd7c280421b32a1945aac938fd46","abstract_canon_sha256":"96bcbfa68c7a95102a5da10aea4d17dda327ecffd87abfd3fac02ede512dc2a7"},"schema_version":"1.0"},"canonical_sha256":"9c8e83262ae6b1eeeb068df7d6fbd6d8b07d618fc68d7fb9bf142abad2ab858f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:21.782253Z","signature_b64":"8NqFKjR7EO/MqbUrOXqDn9QZcNJaQv/4n3xBBPnyyjJ4Rtl3Lif/1Gug7ZFvpX0lSM+In93sKdkq6frLv+TtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c8e83262ae6b1eeeb068df7d6fbd6d8b07d618fc68d7fb9bf142abad2ab858f","last_reissued_at":"2026-07-05T01:45:21.781812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:21.781812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.11876","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:45:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EYTWV7lY2nXKdd3FtdEDilO/JmaWJThW/O5fA6XPpUuaBoVrSRQvrOiuC0A1FDNU+OKLtMctBkvKTpFDVFFcDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:27:40.002435Z"},"content_sha256":"8131c49d5d11197b4531ccb959ad6c8e295cafd3f4cc21e100f75d910cd7c9c5","schema_version":"1.0","event_id":"sha256:8131c49d5d11197b4531ccb959ad6c8e295cafd3f4cc21e100f75d910cd7c9c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:TSHIGJRK42Y652YGRX35N66W3C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Error Bounds of Imitating Policies and Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Tian Xu, Yang Yu, Ziniu Li","submitted_at":"2020-10-22T17:13:31Z","abstract_excerpt":"Imitation learning trains a policy by mimicking expert demonstrations. Various imitation methods were proposed and empirically evaluated, meanwhile, their theoretical understanding needs further studies. In this paper, we firstly analyze the value gap between the expert policy and imitated policies by two imitation methods, behavioral cloning and generative adversarial imitation. The results support that generative adversarial imitation can reduce the compounding errors compared to behavioral cloning, and thus has a better sample complexity. Noticed that by considering the environment transiti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11876","kind":"arxiv","version":1},"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/2010.11876/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":"2026-07-05T01:45:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jZmuzEOS05NvPHwDG55xSYMaZSdXgw6+Sp2NbLb4x4w3bBWgHsPmV35h1MwALEHUW+65S/zf3s1XWyb8cUfsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:27:40.002940Z"},"content_sha256":"93d805b534b38717ef5d5d64046bbf5cec93dde17b9e66665afa9cc3a19d2486","schema_version":"1.0","event_id":"sha256:93d805b534b38717ef5d5d64046bbf5cec93dde17b9e66665afa9cc3a19d2486"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TSHIGJRK42Y652YGRX35N66W3C/bundle.json","state_url":"https://pith.science/pith/TSHIGJRK42Y652YGRX35N66W3C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TSHIGJRK42Y652YGRX35N66W3C/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":"2026-08-09T07:27:40Z","links":{"resolver":"https://pith.science/pith/TSHIGJRK42Y652YGRX35N66W3C","bundle":"https://pith.science/pith/TSHIGJRK42Y652YGRX35N66W3C/bundle.json","state":"https://pith.science/pith/TSHIGJRK42Y652YGRX35N66W3C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TSHIGJRK42Y652YGRX35N66W3C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TSHIGJRK42Y652YGRX35N66W3C","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":"96bcbfa68c7a95102a5da10aea4d17dda327ecffd87abfd3fac02ede512dc2a7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T17:13:31Z","title_canon_sha256":"7c523bf02ba59d5a45dd76046584654843aecd7c280421b32a1945aac938fd46"},"schema_version":"1.0","source":{"id":"2010.11876","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.11876","created_at":"2026-07-05T01:45:21Z"},{"alias_kind":"arxiv_version","alias_value":"2010.11876v1","created_at":"2026-07-05T01:45:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11876","created_at":"2026-07-05T01:45:21Z"},{"alias_kind":"pith_short_12","alias_value":"TSHIGJRK42Y6","created_at":"2026-07-05T01:45:21Z"},{"alias_kind":"pith_short_16","alias_value":"TSHIGJRK42Y652YG","created_at":"2026-07-05T01:45:21Z"},{"alias_kind":"pith_short_8","alias_value":"TSHIGJRK","created_at":"2026-07-05T01:45:21Z"}],"graph_snapshots":[{"event_id":"sha256:93d805b534b38717ef5d5d64046bbf5cec93dde17b9e66665afa9cc3a19d2486","target":"graph","created_at":"2026-07-05T01:45:21Z","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/2010.11876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imitation learning trains a policy by mimicking expert demonstrations. Various imitation methods were proposed and empirically evaluated, meanwhile, their theoretical understanding needs further studies. In this paper, we firstly analyze the value gap between the expert policy and imitated policies by two imitation methods, behavioral cloning and generative adversarial imitation. The results support that generative adversarial imitation can reduce the compounding errors compared to behavioral cloning, and thus has a better sample complexity. Noticed that by considering the environment transiti","authors_text":"Tian Xu, Yang Yu, Ziniu Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T17:13:31Z","title":"Error Bounds of Imitating Policies and Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11876","kind":"arxiv","version":1},"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":"sha256:8131c49d5d11197b4531ccb959ad6c8e295cafd3f4cc21e100f75d910cd7c9c5","target":"record","created_at":"2026-07-05T01:45:21Z","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":"96bcbfa68c7a95102a5da10aea4d17dda327ecffd87abfd3fac02ede512dc2a7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T17:13:31Z","title_canon_sha256":"7c523bf02ba59d5a45dd76046584654843aecd7c280421b32a1945aac938fd46"},"schema_version":"1.0","source":{"id":"2010.11876","kind":"arxiv","version":1}},"canonical_sha256":"9c8e83262ae6b1eeeb068df7d6fbd6d8b07d618fc68d7fb9bf142abad2ab858f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c8e83262ae6b1eeeb068df7d6fbd6d8b07d618fc68d7fb9bf142abad2ab858f","first_computed_at":"2026-07-05T01:45:21.781812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:21.781812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8NqFKjR7EO/MqbUrOXqDn9QZcNJaQv/4n3xBBPnyyjJ4Rtl3Lif/1Gug7ZFvpX0lSM+In93sKdkq6frLv+TtDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:21.782253Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.11876","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8131c49d5d11197b4531ccb959ad6c8e295cafd3f4cc21e100f75d910cd7c9c5","sha256:93d805b534b38717ef5d5d64046bbf5cec93dde17b9e66665afa9cc3a19d2486"],"state_sha256":"02b3a8dde027438b35743a54b2b178fe884d46cd90d9221a86d977b1357880c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DerhSY8NhnMghKhy2zS6z2ibRpF5U20oTjn6GMpFpKoQMGs/W8kU4nRQtizbmzR588Vwiq6V6MKFo+ZEf1giCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:27:40.006986Z","bundle_sha256":"7e72b2d8d7303e9ae986e85d07e59bf3e109e5409146d4dedc50bdfe930ba782"}}