{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QSVFPS6FBLYFIQ5W4K3WSA3JKV","short_pith_number":"pith:QSVFPS6F","canonical_record":{"source":{"id":"1905.11108","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T10:29:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fdb70c5c114be41d1ab6fa074dea78bcb8282462f44308c66900ad03b9749eeb","abstract_canon_sha256":"df88fd9967bea8e463806e3501ce441b1649eeefe91e918be4a9db03ae196258"},"schema_version":"1.0"},"canonical_sha256":"84aa57cbc50af05443b6e2b7690369554c5d5e298a2aed894e469122eea75a43","source":{"kind":"arxiv","id":"1905.11108","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.11108","created_at":"2026-07-05T00:07:23Z"},{"alias_kind":"arxiv_version","alias_value":"1905.11108v3","created_at":"2026-07-05T00:07:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11108","created_at":"2026-07-05T00:07:23Z"},{"alias_kind":"pith_short_12","alias_value":"QSVFPS6FBLYF","created_at":"2026-07-05T00:07:23Z"},{"alias_kind":"pith_short_16","alias_value":"QSVFPS6FBLYFIQ5W","created_at":"2026-07-05T00:07:23Z"},{"alias_kind":"pith_short_8","alias_value":"QSVFPS6F","created_at":"2026-07-05T00:07:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QSVFPS6FBLYFIQ5W4K3WSA3JKV","target":"record","payload":{"canonical_record":{"source":{"id":"1905.11108","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T10:29:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fdb70c5c114be41d1ab6fa074dea78bcb8282462f44308c66900ad03b9749eeb","abstract_canon_sha256":"df88fd9967bea8e463806e3501ce441b1649eeefe91e918be4a9db03ae196258"},"schema_version":"1.0"},"canonical_sha256":"84aa57cbc50af05443b6e2b7690369554c5d5e298a2aed894e469122eea75a43","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:23.477801Z","signature_b64":"oYuH9d3c7aUek8ldr5fogjny4DQrYt3o+l8Abq4BS8vUxVPlg7+QWj+GmxD1NKNBTgnNohK23Pog7KUndRcmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84aa57cbc50af05443b6e2b7690369554c5d5e298a2aed894e469122eea75a43","last_reissued_at":"2026-07-05T00:07:23.477323Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:23.477323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.11108","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":"2026-07-05T00:07:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Zi8cc39wNks2dcKKfZwZK4/2Epl0qUWENQ9swuq8vqMGEDeFNtxc2R1Bs9DAiKeOmgKBPNI+5EjadqJbuypBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:48:05.609167Z"},"content_sha256":"f0c8f305840cd17739103a34e73a68f1c50e89c2ba42a3203459ea1d173ae584","schema_version":"1.0","event_id":"sha256:f0c8f305840cd17739103a34e73a68f1c50e89c2ba42a3203459ea1d173ae584"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QSVFPS6FBLYFIQ5W4K3WSA3JKV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anca D. Dragan, Sergey Levine, Siddharth Reddy","submitted_at":"2019-05-27T10:29:31Z","abstract_excerpt":"Learning to imitate expert behavior from demonstrations can be challenging, especially in environments with high-dimensional, continuous observations and unknown dynamics. Supervised learning methods based on behavioral cloning (BC) suffer from distribution shift: because the agent greedily imitates demonstrated actions, it can drift away from demonstrated states due to error accumulation. Recent methods based on reinforcement learning (RL), such as inverse RL and generative adversarial imitation learning (GAIL), overcome this issue by training an RL agent to match the demonstrations over a lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11108","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/1905.11108/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":"2026-07-05T00:07:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YdC1ohLAx0py7XgXyHlZbviSqdV49B2V45uzh87NI1c3RtnxSdAPbNKN1hEJ8UmtsM6hiAm2vwEX3WrRC37iCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:48:05.610153Z"},"content_sha256":"6a99dbca083e3724aa2055ff28abfaff9cfde568d96fd043d0608e0b9445d947","schema_version":"1.0","event_id":"sha256:6a99dbca083e3724aa2055ff28abfaff9cfde568d96fd043d0608e0b9445d947"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QSVFPS6FBLYFIQ5W4K3WSA3JKV/bundle.json","state_url":"https://pith.science/pith/QSVFPS6FBLYFIQ5W4K3WSA3JKV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QSVFPS6FBLYFIQ5W4K3WSA3JKV/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":"2026-08-09T19:48:05Z","links":{"resolver":"https://pith.science/pith/QSVFPS6FBLYFIQ5W4K3WSA3JKV","bundle":"https://pith.science/pith/QSVFPS6FBLYFIQ5W4K3WSA3JKV/bundle.json","state":"https://pith.science/pith/QSVFPS6FBLYFIQ5W4K3WSA3JKV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QSVFPS6FBLYFIQ5W4K3WSA3JKV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QSVFPS6FBLYFIQ5W4K3WSA3JKV","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":"df88fd9967bea8e463806e3501ce441b1649eeefe91e918be4a9db03ae196258","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T10:29:31Z","title_canon_sha256":"fdb70c5c114be41d1ab6fa074dea78bcb8282462f44308c66900ad03b9749eeb"},"schema_version":"1.0","source":{"id":"1905.11108","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.11108","created_at":"2026-07-05T00:07:23Z"},{"alias_kind":"arxiv_version","alias_value":"1905.11108v3","created_at":"2026-07-05T00:07:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11108","created_at":"2026-07-05T00:07:23Z"},{"alias_kind":"pith_short_12","alias_value":"QSVFPS6FBLYF","created_at":"2026-07-05T00:07:23Z"},{"alias_kind":"pith_short_16","alias_value":"QSVFPS6FBLYFIQ5W","created_at":"2026-07-05T00:07:23Z"},{"alias_kind":"pith_short_8","alias_value":"QSVFPS6F","created_at":"2026-07-05T00:07:23Z"}],"graph_snapshots":[{"event_id":"sha256:6a99dbca083e3724aa2055ff28abfaff9cfde568d96fd043d0608e0b9445d947","target":"graph","created_at":"2026-07-05T00:07:23Z","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/1905.11108/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to imitate expert behavior from demonstrations can be challenging, especially in environments with high-dimensional, continuous observations and unknown dynamics. Supervised learning methods based on behavioral cloning (BC) suffer from distribution shift: because the agent greedily imitates demonstrated actions, it can drift away from demonstrated states due to error accumulation. Recent methods based on reinforcement learning (RL), such as inverse RL and generative adversarial imitation learning (GAIL), overcome this issue by training an RL agent to match the demonstrations over a lo","authors_text":"Anca D. Dragan, Sergey Levine, Siddharth Reddy","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T10:29:31Z","title":"SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11108","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:f0c8f305840cd17739103a34e73a68f1c50e89c2ba42a3203459ea1d173ae584","target":"record","created_at":"2026-07-05T00:07:23Z","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":"df88fd9967bea8e463806e3501ce441b1649eeefe91e918be4a9db03ae196258","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T10:29:31Z","title_canon_sha256":"fdb70c5c114be41d1ab6fa074dea78bcb8282462f44308c66900ad03b9749eeb"},"schema_version":"1.0","source":{"id":"1905.11108","kind":"arxiv","version":3}},"canonical_sha256":"84aa57cbc50af05443b6e2b7690369554c5d5e298a2aed894e469122eea75a43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84aa57cbc50af05443b6e2b7690369554c5d5e298a2aed894e469122eea75a43","first_computed_at":"2026-07-05T00:07:23.477323Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:07:23.477323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oYuH9d3c7aUek8ldr5fogjny4DQrYt3o+l8Abq4BS8vUxVPlg7+QWj+GmxD1NKNBTgnNohK23Pog7KUndRcmCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:07:23.477801Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.11108","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0c8f305840cd17739103a34e73a68f1c50e89c2ba42a3203459ea1d173ae584","sha256:6a99dbca083e3724aa2055ff28abfaff9cfde568d96fd043d0608e0b9445d947"],"state_sha256":"1b9674077ef17de45aca07dffa47ccfa9632d82b3b43f83f8588b42ab730e86c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z0RUQylkBLbqfac4m6xNbmDxHwKVokSjGVNyv91LUhibThR01ddmwNe6QeGbelgaJ1BaQc6qR+cVu1QfrJeZCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:48:05.615522Z","bundle_sha256":"ee2eb2bb13e97d57cbf76c4b5514b4fd67e968f6c50f05ef0931f1348fb18244"}}