{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4H5OFESRQKCXHKN76YGXK26WFI","short_pith_number":"pith:4H5OFESR","canonical_record":{"source":{"id":"2001.07798","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-21T22:28:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8c05223298de86e829f6c821207ab0ebee61f06595db92632983ed55bbb77191","abstract_canon_sha256":"da229367a4f916bfb8b7e7ebaa9dcf2989ad123e46a655e1df3505b4ba9fb041"},"schema_version":"1.0"},"canonical_sha256":"e1fae29251828573a9bff60d756bd62a281da58c7dc72c4a3f24b760cd33c504","source":{"kind":"arxiv","id":"2001.07798","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.07798","created_at":"2026-07-05T01:50:17Z"},{"alias_kind":"arxiv_version","alias_value":"2001.07798v4","created_at":"2026-07-05T01:50:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.07798","created_at":"2026-07-05T01:50:17Z"},{"alias_kind":"pith_short_12","alias_value":"4H5OFESRQKCX","created_at":"2026-07-05T01:50:17Z"},{"alias_kind":"pith_short_16","alias_value":"4H5OFESRQKCXHKN7","created_at":"2026-07-05T01:50:17Z"},{"alias_kind":"pith_short_8","alias_value":"4H5OFESR","created_at":"2026-07-05T01:50:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4H5OFESRQKCXHKN76YGXK26WFI","target":"record","payload":{"canonical_record":{"source":{"id":"2001.07798","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-21T22:28:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8c05223298de86e829f6c821207ab0ebee61f06595db92632983ed55bbb77191","abstract_canon_sha256":"da229367a4f916bfb8b7e7ebaa9dcf2989ad123e46a655e1df3505b4ba9fb041"},"schema_version":"1.0"},"canonical_sha256":"e1fae29251828573a9bff60d756bd62a281da58c7dc72c4a3f24b760cd33c504","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:50:17.054456Z","signature_b64":"2wigJREUWbHdZsVx0ZFh5qmam79tjjkZ/i46DAoaOrUzC0VioE4kmh+52gxFYd76cxJdoueacet0wh/0VgzABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1fae29251828573a9bff60d756bd62a281da58c7dc72c4a3f24b760cd33c504","last_reissued_at":"2026-07-05T01:50:17.054039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:50:17.054039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.07798","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:50:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UY8xUWnF+rD64JA84lymUgX9ff6ytp/q4kLl6m/d5dVRoSgcm+8kyOJ3FghN4CiLPMSIVlOBvrD+0cP11p0WCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:02:29.725215Z"},"content_sha256":"726b37db9f69756a9d9279c7091691e4fbb208d60608eff157f07e9b2d8e9fc2","schema_version":"1.0","event_id":"sha256:726b37db9f69756a9d9279c7091691e4fbb208d60608eff157f07e9b2d8e9fc2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4H5OFESRQKCXHKN76YGXK26WFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Augmenting GAIL with BC for sample efficient imitation learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Changliu Liu, Katia Sycara, Rohit Jena","submitted_at":"2020-01-21T22:28:50Z","abstract_excerpt":"Imitation learning is the problem of recovering an expert policy without access to a reward signal. Behavior cloning and GAIL are two widely used methods for performing imitation learning. Behavior cloning converges in a few iterations but doesn't achieve peak performance due to its inherent iid assumption about the state-action distribution. GAIL addresses the issue by accounting for the temporal dependencies when performing a state distribution matching between the agent and the expert. Although GAIL is sample efficient in the number of expert trajectories required, it is still not very samp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.07798","kind":"arxiv","version":4},"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/2001.07798/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":"2026-07-05T01:50:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q1mQtSuS8GQr436CYtC3MzfgFbTVbW3jhmoNuQMpYMEAGbB5vVAfuZ+XVpX0EQQ+jSqEX7GcwRTuJJAwsuS7AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:02:29.725723Z"},"content_sha256":"2e45893a042d23906dd59a04226f14c591ece009f8b52532cc73f00ee11c8fcf","schema_version":"1.0","event_id":"sha256:2e45893a042d23906dd59a04226f14c591ece009f8b52532cc73f00ee11c8fcf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4H5OFESRQKCXHKN76YGXK26WFI/bundle.json","state_url":"https://pith.science/pith/4H5OFESRQKCXHKN76YGXK26WFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4H5OFESRQKCXHKN76YGXK26WFI/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":"2026-08-14T08:02:29Z","links":{"resolver":"https://pith.science/pith/4H5OFESRQKCXHKN76YGXK26WFI","bundle":"https://pith.science/pith/4H5OFESRQKCXHKN76YGXK26WFI/bundle.json","state":"https://pith.science/pith/4H5OFESRQKCXHKN76YGXK26WFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4H5OFESRQKCXHKN76YGXK26WFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4H5OFESRQKCXHKN76YGXK26WFI","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":"da229367a4f916bfb8b7e7ebaa9dcf2989ad123e46a655e1df3505b4ba9fb041","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-21T22:28:50Z","title_canon_sha256":"8c05223298de86e829f6c821207ab0ebee61f06595db92632983ed55bbb77191"},"schema_version":"1.0","source":{"id":"2001.07798","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.07798","created_at":"2026-07-05T01:50:17Z"},{"alias_kind":"arxiv_version","alias_value":"2001.07798v4","created_at":"2026-07-05T01:50:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.07798","created_at":"2026-07-05T01:50:17Z"},{"alias_kind":"pith_short_12","alias_value":"4H5OFESRQKCX","created_at":"2026-07-05T01:50:17Z"},{"alias_kind":"pith_short_16","alias_value":"4H5OFESRQKCXHKN7","created_at":"2026-07-05T01:50:17Z"},{"alias_kind":"pith_short_8","alias_value":"4H5OFESR","created_at":"2026-07-05T01:50:17Z"}],"graph_snapshots":[{"event_id":"sha256:2e45893a042d23906dd59a04226f14c591ece009f8b52532cc73f00ee11c8fcf","target":"graph","created_at":"2026-07-05T01:50:17Z","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/2001.07798/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imitation learning is the problem of recovering an expert policy without access to a reward signal. Behavior cloning and GAIL are two widely used methods for performing imitation learning. Behavior cloning converges in a few iterations but doesn't achieve peak performance due to its inherent iid assumption about the state-action distribution. GAIL addresses the issue by accounting for the temporal dependencies when performing a state distribution matching between the agent and the expert. Although GAIL is sample efficient in the number of expert trajectories required, it is still not very samp","authors_text":"Changliu Liu, Katia Sycara, Rohit Jena","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-21T22:28:50Z","title":"Augmenting GAIL with BC for sample efficient imitation learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.07798","kind":"arxiv","version":4},"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":"sha256:726b37db9f69756a9d9279c7091691e4fbb208d60608eff157f07e9b2d8e9fc2","target":"record","created_at":"2026-07-05T01:50:17Z","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":"da229367a4f916bfb8b7e7ebaa9dcf2989ad123e46a655e1df3505b4ba9fb041","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-21T22:28:50Z","title_canon_sha256":"8c05223298de86e829f6c821207ab0ebee61f06595db92632983ed55bbb77191"},"schema_version":"1.0","source":{"id":"2001.07798","kind":"arxiv","version":4}},"canonical_sha256":"e1fae29251828573a9bff60d756bd62a281da58c7dc72c4a3f24b760cd33c504","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1fae29251828573a9bff60d756bd62a281da58c7dc72c4a3f24b760cd33c504","first_computed_at":"2026-07-05T01:50:17.054039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:50:17.054039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2wigJREUWbHdZsVx0ZFh5qmam79tjjkZ/i46DAoaOrUzC0VioE4kmh+52gxFYd76cxJdoueacet0wh/0VgzABQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:50:17.054456Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.07798","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:726b37db9f69756a9d9279c7091691e4fbb208d60608eff157f07e9b2d8e9fc2","sha256:2e45893a042d23906dd59a04226f14c591ece009f8b52532cc73f00ee11c8fcf"],"state_sha256":"94121bf49126dc6b89f445d24abe2ba8f38d0db922228cb41d27b508ad348808"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YDO7KS2j3fkHxLtrWQyzpnxPousOMKPy/U9PyQWbItJMih6baH3KCm3CFyzFb8+P6rs3EiRiyqUb9bfK57K4Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:02:29.730099Z","bundle_sha256":"37c3058553c504254b9e48d00dc5582a3523bd5c3b3020c6e0fd4594888c47f1"}}