{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4MRBSXBUPXVN4BAKASKLZSXESX","short_pith_number":"pith:4MRBSXBU","canonical_record":{"source":{"id":"2004.00530","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-01T15:57:15Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"fd3e7ffacbfe93679213a9285165b8edbfdcb683b0a6f23e3e41784f1757c5f1","abstract_canon_sha256":"c888d583de74fc9af073c7aeed24fa6be053af81f6d0d360894cbe0940dec7cd"},"schema_version":"1.0"},"canonical_sha256":"e322195c347deade040a0494bccae495c11b99361a8e418a95b84f62610d6196","source":{"kind":"arxiv","id":"2004.00530","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.00530","created_at":"2026-07-05T00:52:11Z"},{"alias_kind":"arxiv_version","alias_value":"2004.00530v1","created_at":"2026-07-05T00:52:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.00530","created_at":"2026-07-05T00:52:11Z"},{"alias_kind":"pith_short_12","alias_value":"4MRBSXBUPXVN","created_at":"2026-07-05T00:52:11Z"},{"alias_kind":"pith_short_16","alias_value":"4MRBSXBUPXVN4BAK","created_at":"2026-07-05T00:52:11Z"},{"alias_kind":"pith_short_8","alias_value":"4MRBSXBU","created_at":"2026-07-05T00:52:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4MRBSXBUPXVN4BAKASKLZSXESX","target":"record","payload":{"canonical_record":{"source":{"id":"2004.00530","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-01T15:57:15Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"fd3e7ffacbfe93679213a9285165b8edbfdcb683b0a6f23e3e41784f1757c5f1","abstract_canon_sha256":"c888d583de74fc9af073c7aeed24fa6be053af81f6d0d360894cbe0940dec7cd"},"schema_version":"1.0"},"canonical_sha256":"e322195c347deade040a0494bccae495c11b99361a8e418a95b84f62610d6196","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:11.642308Z","signature_b64":"M2Pcmx4tKQUWm/eZG3MpksnP2HsgpjEkweiOWdzYiqV+UZOp4TMHE2r9OLoGMMpPWFlLR8EGU3jT8OTt0o8IBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e322195c347deade040a0494bccae495c11b99361a8e418a95b84f62610d6196","last_reissued_at":"2026-07-05T00:52:11.641917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:11.641917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.00530","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":"2026-07-05T00:52:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qQMLHG5JiFZWJ8zElecZEaJjMnRYqtFpllI+eT9apd8NEgnOjhBwxEacsizO9F0BEyQgvoy4O2LPLHnFFLJrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T15:37:28.341167Z"},"content_sha256":"95ad31da4c7172d2bd819070663803a3c9ba5c7f3fde8ed73d338fc53f90913e","schema_version":"1.0","event_id":"sha256:95ad31da4c7172d2bd819070663803a3c9ba5c7f3fde8ed73d338fc53f90913e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4MRBSXBUPXVN4BAKASKLZSXESX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Sparse Rewarded Tasks from Sub-Optimal Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Dai, Jiayu Zhou, Kaixiang Lin, Zhuangdi Zhu","submitted_at":"2020-04-01T15:57:15Z","abstract_excerpt":"Model-free deep reinforcement learning (RL) has demonstrated its superiority on many complex sequential decision-making problems. However, heavy dependence on dense rewards and high sample-complexity impedes the wide adoption of these methods in real-world scenarios. On the other hand, imitation learning (IL) learns effectively in sparse-rewarded tasks by leveraging the existing expert demonstrations. In practice, collecting a sufficient amount of expert demonstrations can be prohibitively expensive, and the quality of demonstrations typically limits the performance of the learning policy. In "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.00530","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/2004.00530/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":"2026-07-05T00:52:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0ik93zCd6r0d/vXz7GrIYoSXCc+mxbqqY3x4H0SVCGJTiUK0LnTQZ0UFPBa0qCOrCLIvsHimwy3hsSoSoCFWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T15:37:28.341573Z"},"content_sha256":"bd4e50f2ecd6bcaf45d41a06fa3c6614015f2aab57bf7b9a8f842e7674e5a16b","schema_version":"1.0","event_id":"sha256:bd4e50f2ecd6bcaf45d41a06fa3c6614015f2aab57bf7b9a8f842e7674e5a16b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4MRBSXBUPXVN4BAKASKLZSXESX/bundle.json","state_url":"https://pith.science/pith/4MRBSXBUPXVN4BAKASKLZSXESX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4MRBSXBUPXVN4BAKASKLZSXESX/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":"2026-07-16T15:37:28Z","links":{"resolver":"https://pith.science/pith/4MRBSXBUPXVN4BAKASKLZSXESX","bundle":"https://pith.science/pith/4MRBSXBUPXVN4BAKASKLZSXESX/bundle.json","state":"https://pith.science/pith/4MRBSXBUPXVN4BAKASKLZSXESX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4MRBSXBUPXVN4BAKASKLZSXESX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4MRBSXBUPXVN4BAKASKLZSXESX","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":"c888d583de74fc9af073c7aeed24fa6be053af81f6d0d360894cbe0940dec7cd","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-01T15:57:15Z","title_canon_sha256":"fd3e7ffacbfe93679213a9285165b8edbfdcb683b0a6f23e3e41784f1757c5f1"},"schema_version":"1.0","source":{"id":"2004.00530","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.00530","created_at":"2026-07-05T00:52:11Z"},{"alias_kind":"arxiv_version","alias_value":"2004.00530v1","created_at":"2026-07-05T00:52:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.00530","created_at":"2026-07-05T00:52:11Z"},{"alias_kind":"pith_short_12","alias_value":"4MRBSXBUPXVN","created_at":"2026-07-05T00:52:11Z"},{"alias_kind":"pith_short_16","alias_value":"4MRBSXBUPXVN4BAK","created_at":"2026-07-05T00:52:11Z"},{"alias_kind":"pith_short_8","alias_value":"4MRBSXBU","created_at":"2026-07-05T00:52:11Z"}],"graph_snapshots":[{"event_id":"sha256:bd4e50f2ecd6bcaf45d41a06fa3c6614015f2aab57bf7b9a8f842e7674e5a16b","target":"graph","created_at":"2026-07-05T00:52:11Z","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/2004.00530/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-free deep reinforcement learning (RL) has demonstrated its superiority on many complex sequential decision-making problems. However, heavy dependence on dense rewards and high sample-complexity impedes the wide adoption of these methods in real-world scenarios. On the other hand, imitation learning (IL) learns effectively in sparse-rewarded tasks by leveraging the existing expert demonstrations. In practice, collecting a sufficient amount of expert demonstrations can be prohibitively expensive, and the quality of demonstrations typically limits the performance of the learning policy. In ","authors_text":"Bo Dai, Jiayu Zhou, Kaixiang Lin, Zhuangdi Zhu","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-01T15:57:15Z","title":"Learning Sparse Rewarded Tasks from Sub-Optimal Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.00530","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":"sha256:95ad31da4c7172d2bd819070663803a3c9ba5c7f3fde8ed73d338fc53f90913e","target":"record","created_at":"2026-07-05T00:52:11Z","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":"c888d583de74fc9af073c7aeed24fa6be053af81f6d0d360894cbe0940dec7cd","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-01T15:57:15Z","title_canon_sha256":"fd3e7ffacbfe93679213a9285165b8edbfdcb683b0a6f23e3e41784f1757c5f1"},"schema_version":"1.0","source":{"id":"2004.00530","kind":"arxiv","version":1}},"canonical_sha256":"e322195c347deade040a0494bccae495c11b99361a8e418a95b84f62610d6196","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e322195c347deade040a0494bccae495c11b99361a8e418a95b84f62610d6196","first_computed_at":"2026-07-05T00:52:11.641917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:52:11.641917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M2Pcmx4tKQUWm/eZG3MpksnP2HsgpjEkweiOWdzYiqV+UZOp4TMHE2r9OLoGMMpPWFlLR8EGU3jT8OTt0o8IBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:52:11.642308Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.00530","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95ad31da4c7172d2bd819070663803a3c9ba5c7f3fde8ed73d338fc53f90913e","sha256:bd4e50f2ecd6bcaf45d41a06fa3c6614015f2aab57bf7b9a8f842e7674e5a16b"],"state_sha256":"744a9216f5668b30b96ab9ccf1e8ac1e8942b278471d6e0f9fb041cc5939539d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lLgUBggfiyPIOgbnIyFk3Fivj5/cNH5Cg4LHi2OKpn4Php13uniu1SmnEppXN/7nLquNxKqyO5U/6dUQSPKCDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T15:37:28.343794Z","bundle_sha256":"061ec82e4f4150a00c6fbbfccbdf3f6c88e13a3b1f25874f18926bc197260324"}}