{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5MVTTW7V36VE4E2YXKBSZOMN3Z","short_pith_number":"pith:5MVTTW7V","canonical_record":{"source":{"id":"1903.07854","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-19T06:16:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"df07a64d0916f4bfb36d9c27d8fcf51e285710552912d38089eec281e72f6c42","abstract_canon_sha256":"2ecc079053fbc3e74e6f29b7f735421034bb6b3ddd58c7814173fc3dd83a9ba4"},"schema_version":"1.0"},"canonical_sha256":"eb2b39dbf5dfaa4e1358ba832cb98dde45a840519afe1fb4f85cbfa56e62a0fa","source":{"kind":"arxiv","id":"1903.07854","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.07854","created_at":"2026-05-17T23:50:53Z"},{"alias_kind":"arxiv_version","alias_value":"1903.07854v1","created_at":"2026-05-17T23:50:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07854","created_at":"2026-05-17T23:50:53Z"},{"alias_kind":"pith_short_12","alias_value":"5MVTTW7V36VE","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5MVTTW7V36VE4E2Y","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5MVTTW7V","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5MVTTW7V36VE4E2YXKBSZOMN3Z","target":"record","payload":{"canonical_record":{"source":{"id":"1903.07854","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-19T06:16:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"df07a64d0916f4bfb36d9c27d8fcf51e285710552912d38089eec281e72f6c42","abstract_canon_sha256":"2ecc079053fbc3e74e6f29b7f735421034bb6b3ddd58c7814173fc3dd83a9ba4"},"schema_version":"1.0"},"canonical_sha256":"eb2b39dbf5dfaa4e1358ba832cb98dde45a840519afe1fb4f85cbfa56e62a0fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:53.675208Z","signature_b64":"d9rcL371jfRK9ZqZqhIt9gXEL54H1kBjx0QvMCa2Mang28P1IISOw/J6H3fCB3hRERr2+tL7qsAHB3toZNeSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb2b39dbf5dfaa4e1358ba832cb98dde45a840519afe1fb4f85cbfa56e62a0fa","last_reissued_at":"2026-05-17T23:50:53.674535Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:53.674535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.07854","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":"2026-05-17T23:50:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E47IrbB5zeXFEMlFUhKR1FjO7oUSNdsd+KyUn7o3yiXYxOPJ4NR/h/aXABGxnfme/RD6vbPXr9vaSos5MR8/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T02:35:52.681049Z"},"content_sha256":"e587a27d4755d8602bd9e45ad571492f7766b5bc7f19e7bd53da73c436b6fe5a","schema_version":"1.0","event_id":"sha256:e587a27d4755d8602bd9e45ad571492f7766b5bc7f19e7bd53da73c436b6fe5a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5MVTTW7V36VE4E2YXKBSZOMN3Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hindsight Generative Adversarial Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Boyao Li, Naijun Liu, Shuo Wang, Tao Lu, Yinghao Cai","submitted_at":"2019-03-19T06:16:56Z","abstract_excerpt":"Compared to reinforcement learning, imitation learning (IL) is a powerful paradigm for training agents to learn control policies efficiently from expert demonstrations. However, in most cases, obtaining demonstration data is costly and laborious, which poses a significant challenge in some scenarios. A promising alternative is to train agent learning skills via imitation learning without expert demonstrations, which, to some extent, would extremely expand imitation learning areas. To achieve such expectation, in this paper, we propose Hindsight Generative Adversarial Imitation Learning (HGAIL)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07854","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":""},"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":"2026-05-17T23:50:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hn1vSqLRquUOCCdwXSD9MEzQMr+IURZvWw3814vW0t9xyIyIyMw8eISvbytX5RelSVWqSHDw8oZRX1VeQO+pAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T02:35:52.681409Z"},"content_sha256":"57570c7f4ad44178a86492683ed323d0938e5dd021c0c305564e1b6c2e53ac14","schema_version":"1.0","event_id":"sha256:57570c7f4ad44178a86492683ed323d0938e5dd021c0c305564e1b6c2e53ac14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5MVTTW7V36VE4E2YXKBSZOMN3Z/bundle.json","state_url":"https://pith.science/pith/5MVTTW7V36VE4E2YXKBSZOMN3Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5MVTTW7V36VE4E2YXKBSZOMN3Z/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":"2026-06-09T02:35:52Z","links":{"resolver":"https://pith.science/pith/5MVTTW7V36VE4E2YXKBSZOMN3Z","bundle":"https://pith.science/pith/5MVTTW7V36VE4E2YXKBSZOMN3Z/bundle.json","state":"https://pith.science/pith/5MVTTW7V36VE4E2YXKBSZOMN3Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5MVTTW7V36VE4E2YXKBSZOMN3Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5MVTTW7V36VE4E2YXKBSZOMN3Z","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":"2ecc079053fbc3e74e6f29b7f735421034bb6b3ddd58c7814173fc3dd83a9ba4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-19T06:16:56Z","title_canon_sha256":"df07a64d0916f4bfb36d9c27d8fcf51e285710552912d38089eec281e72f6c42"},"schema_version":"1.0","source":{"id":"1903.07854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.07854","created_at":"2026-05-17T23:50:53Z"},{"alias_kind":"arxiv_version","alias_value":"1903.07854v1","created_at":"2026-05-17T23:50:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07854","created_at":"2026-05-17T23:50:53Z"},{"alias_kind":"pith_short_12","alias_value":"5MVTTW7V36VE","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5MVTTW7V36VE4E2Y","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5MVTTW7V","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:57570c7f4ad44178a86492683ed323d0938e5dd021c0c305564e1b6c2e53ac14","target":"graph","created_at":"2026-05-17T23:50:53Z","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"},"paper":{"abstract_excerpt":"Compared to reinforcement learning, imitation learning (IL) is a powerful paradigm for training agents to learn control policies efficiently from expert demonstrations. However, in most cases, obtaining demonstration data is costly and laborious, which poses a significant challenge in some scenarios. A promising alternative is to train agent learning skills via imitation learning without expert demonstrations, which, to some extent, would extremely expand imitation learning areas. To achieve such expectation, in this paper, we propose Hindsight Generative Adversarial Imitation Learning (HGAIL)","authors_text":"Boyao Li, Naijun Liu, Shuo Wang, Tao Lu, Yinghao Cai","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-19T06:16:56Z","title":"Hindsight Generative Adversarial Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07854","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:e587a27d4755d8602bd9e45ad571492f7766b5bc7f19e7bd53da73c436b6fe5a","target":"record","created_at":"2026-05-17T23:50:53Z","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":"2ecc079053fbc3e74e6f29b7f735421034bb6b3ddd58c7814173fc3dd83a9ba4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-19T06:16:56Z","title_canon_sha256":"df07a64d0916f4bfb36d9c27d8fcf51e285710552912d38089eec281e72f6c42"},"schema_version":"1.0","source":{"id":"1903.07854","kind":"arxiv","version":1}},"canonical_sha256":"eb2b39dbf5dfaa4e1358ba832cb98dde45a840519afe1fb4f85cbfa56e62a0fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb2b39dbf5dfaa4e1358ba832cb98dde45a840519afe1fb4f85cbfa56e62a0fa","first_computed_at":"2026-05-17T23:50:53.674535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:53.674535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d9rcL371jfRK9ZqZqhIt9gXEL54H1kBjx0QvMCa2Mang28P1IISOw/J6H3fCB3hRERr2+tL7qsAHB3toZNeSBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:53.675208Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.07854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e587a27d4755d8602bd9e45ad571492f7766b5bc7f19e7bd53da73c436b6fe5a","sha256:57570c7f4ad44178a86492683ed323d0938e5dd021c0c305564e1b6c2e53ac14"],"state_sha256":"ae5ac6fc7a7d057e81e26f991d5f00af42be6646fb78a6af188da855bfa238a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HzOj84cl1lHkynUv85FpbgmWoGqjbKRTkuYvFfLM/pOpYdqLQyLFC1i/zPiQ1F6cH5zScesitjPre+/L2mbBAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T02:35:52.683965Z","bundle_sha256":"87f6471b230b5d1b5549ed71136e8c74c4d74096f8b42e7bc38711b4bc13250c"}}