{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:62SZW72YDARDYLWB6LIYSCKEGM","short_pith_number":"pith:62SZW72Y","canonical_record":{"source":{"id":"1904.06387","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-12T19:34:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"94629d2e5117df8269e8db35152cd2f6070d55cad20c750b041949446ff8c999","abstract_canon_sha256":"21196885823e6a131448a971742824da7ccfb033bcbefbf107582c3b087e6f1c"},"schema_version":"1.0"},"canonical_sha256":"f6a59b7f5818223c2ec1f2d1890944330180042c9cf112abd5cdead44b229afe","source":{"kind":"arxiv","id":"1904.06387","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.06387","created_at":"2026-05-17T23:41:09Z"},{"alias_kind":"arxiv_version","alias_value":"1904.06387v5","created_at":"2026-05-17T23:41:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06387","created_at":"2026-05-17T23:41:09Z"},{"alias_kind":"pith_short_12","alias_value":"62SZW72YDARD","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"62SZW72YDARDYLWB","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"62SZW72Y","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:62SZW72YDARDYLWB6LIYSCKEGM","target":"record","payload":{"canonical_record":{"source":{"id":"1904.06387","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-12T19:34:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"94629d2e5117df8269e8db35152cd2f6070d55cad20c750b041949446ff8c999","abstract_canon_sha256":"21196885823e6a131448a971742824da7ccfb033bcbefbf107582c3b087e6f1c"},"schema_version":"1.0"},"canonical_sha256":"f6a59b7f5818223c2ec1f2d1890944330180042c9cf112abd5cdead44b229afe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:09.056486Z","signature_b64":"oJGjZ6eUsgpEIwxzuh3KLzBkQSF7IUfDwmKdhhcZum9ReTQmUmIoIpCkMXQrQVxJvuT2GqJEOHkWgPvY25cAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6a59b7f5818223c2ec1f2d1890944330180042c9cf112abd5cdead44b229afe","last_reissued_at":"2026-05-17T23:41:09.055783Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:09.055783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.06387","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7TZWI6VmAigtd7fTxHSkxtJ8QO3kj+3UTHISR6QceRF7gEzCLEpGzj87UugnsfOweba82oyGKgOwrZt/zXokDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:42:29.376019Z"},"content_sha256":"0f9fcfc4b45f0e24bda99c1dbaeba87cc82a4819dbfe646676769b55dc568d5f","schema_version":"1.0","event_id":"sha256:0f9fcfc4b45f0e24bda99c1dbaeba87cc82a4819dbfe646676769b55dc568d5f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:62SZW72YDARDYLWB6LIYSCKEGM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel S. Brown, Prabhat Nagarajan, Scott Niekum, Wonjoon Goo","submitted_at":"2019-04-12T19:34:43Z","abstract_excerpt":"A critical flaw of existing inverse reinforcement learning (IRL) methods is their inability to significantly outperform the demonstrator. This is because IRL typically seeks a reward function that makes the demonstrator appear near-optimal, rather than inferring the underlying intentions of the demonstrator that may have been poorly executed in practice. In this paper, we introduce a novel reward-learning-from-observation algorithm, Trajectory-ranked Reward EXtrapolation (T-REX), that extrapolates beyond a set of (approximately) ranked demonstrations in order to infer high-quality reward funct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06387","kind":"arxiv","version":5},"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":"2026-05-17T23:41:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lVi2a8Hlubw1+IxLDV9mWEuYihp+lgoBpKGVHdhto0qxbjRKNl3cC7g2mYZM08R5tQx40D+Mk5c8krdX8kKqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:42:29.376480Z"},"content_sha256":"a6ba7af442f1c4572b5681deba86504305ffe66fbd7af611a906f633a2c12495","schema_version":"1.0","event_id":"sha256:a6ba7af442f1c4572b5681deba86504305ffe66fbd7af611a906f633a2c12495"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/62SZW72YDARDYLWB6LIYSCKEGM/bundle.json","state_url":"https://pith.science/pith/62SZW72YDARDYLWB6LIYSCKEGM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/62SZW72YDARDYLWB6LIYSCKEGM/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":"2026-08-11T10:42:29Z","links":{"resolver":"https://pith.science/pith/62SZW72YDARDYLWB6LIYSCKEGM","bundle":"https://pith.science/pith/62SZW72YDARDYLWB6LIYSCKEGM/bundle.json","state":"https://pith.science/pith/62SZW72YDARDYLWB6LIYSCKEGM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/62SZW72YDARDYLWB6LIYSCKEGM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:62SZW72YDARDYLWB6LIYSCKEGM","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":"21196885823e6a131448a971742824da7ccfb033bcbefbf107582c3b087e6f1c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-12T19:34:43Z","title_canon_sha256":"94629d2e5117df8269e8db35152cd2f6070d55cad20c750b041949446ff8c999"},"schema_version":"1.0","source":{"id":"1904.06387","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.06387","created_at":"2026-05-17T23:41:09Z"},{"alias_kind":"arxiv_version","alias_value":"1904.06387v5","created_at":"2026-05-17T23:41:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06387","created_at":"2026-05-17T23:41:09Z"},{"alias_kind":"pith_short_12","alias_value":"62SZW72YDARD","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"62SZW72YDARDYLWB","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"62SZW72Y","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:a6ba7af442f1c4572b5681deba86504305ffe66fbd7af611a906f633a2c12495","target":"graph","created_at":"2026-05-17T23:41:09Z","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":"A critical flaw of existing inverse reinforcement learning (IRL) methods is their inability to significantly outperform the demonstrator. This is because IRL typically seeks a reward function that makes the demonstrator appear near-optimal, rather than inferring the underlying intentions of the demonstrator that may have been poorly executed in practice. In this paper, we introduce a novel reward-learning-from-observation algorithm, Trajectory-ranked Reward EXtrapolation (T-REX), that extrapolates beyond a set of (approximately) ranked demonstrations in order to infer high-quality reward funct","authors_text":"Daniel S. Brown, Prabhat Nagarajan, Scott Niekum, Wonjoon Goo","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-12T19:34:43Z","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06387","kind":"arxiv","version":5},"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":"sha256:0f9fcfc4b45f0e24bda99c1dbaeba87cc82a4819dbfe646676769b55dc568d5f","target":"record","created_at":"2026-05-17T23:41:09Z","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":"21196885823e6a131448a971742824da7ccfb033bcbefbf107582c3b087e6f1c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-12T19:34:43Z","title_canon_sha256":"94629d2e5117df8269e8db35152cd2f6070d55cad20c750b041949446ff8c999"},"schema_version":"1.0","source":{"id":"1904.06387","kind":"arxiv","version":5}},"canonical_sha256":"f6a59b7f5818223c2ec1f2d1890944330180042c9cf112abd5cdead44b229afe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6a59b7f5818223c2ec1f2d1890944330180042c9cf112abd5cdead44b229afe","first_computed_at":"2026-05-17T23:41:09.055783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:09.055783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oJGjZ6eUsgpEIwxzuh3KLzBkQSF7IUfDwmKdhhcZum9ReTQmUmIoIpCkMXQrQVxJvuT2GqJEOHkWgPvY25cAAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:09.056486Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.06387","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f9fcfc4b45f0e24bda99c1dbaeba87cc82a4819dbfe646676769b55dc568d5f","sha256:a6ba7af442f1c4572b5681deba86504305ffe66fbd7af611a906f633a2c12495"],"state_sha256":"4e6e2654262195fd6d8a0e8377510e4ba96a62b33c03ef70f28b4572b7213164"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4huS3qrO1bSaEXh+dqlPH1fGNghtqmrvic1RyviM2q8hhYPZ8wICVq9kLo8Aw7rJBpmz5xbVeIuQUk9mo4KzBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T10:42:29.381371Z","bundle_sha256":"c6c58549ae9e9b2bbdb0f5d48cdcf11bffeaaf9dd0aa1c4edbd4e9f9ec2a8d3d"}}