{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZAVCFJOTZLUMYB4O7BMCXCTIRC","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":"ba8b33de2e53a4ad64656442819fef29e22095e4725565ab7b4413c46ecd3cce","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-06-21T03:00:36Z","title_canon_sha256":"2bb2f312496df5de7628d2aa467f338b31a090c5a73c84cbec939255c13d5fa5"},"schema_version":"1.0","source":{"id":"1906.08928","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08928","created_at":"2026-05-17T23:42:47Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08928v1","created_at":"2026-05-17T23:42:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08928","created_at":"2026-05-17T23:42:47Z"},{"alias_kind":"pith_short_12","alias_value":"ZAVCFJOTZLUM","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZAVCFJOTZLUMYB4O","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZAVCFJOT","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:d8e906fd1020a0e071fe95f6ef5cd8803b3b363801b4b4d37d05cea0d4975ebc","target":"graph","created_at":"2026-05-17T23:42:47Z","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":"Our goal is to accurately and efficiently learn reward functions for autonomous robots. Current approaches to this problem include inverse reinforcement learning (IRL), which uses expert demonstrations, and preference-based learning, which iteratively queries the user for her preferences between trajectories. In robotics however, IRL often struggles because it is difficult to get high-quality demonstrations; conversely, preference-based learning is very inefficient since it attempts to learn a continuous, high-dimensional function from binary feedback. We propose a new framework for reward lea","authors_text":"Dorsa Sadigh, Gleb Shevchuk, Malayandi Palan, Nicholas C. Landolfi","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-06-21T03:00:36Z","title":"Learning Reward Functions by Integrating Human Demonstrations and Preferences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08928","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":"sha256:445a9b2493e62da52d8f690ab853ed072d949c3927be7fe9c2e3e1e4d6b30130","target":"record","created_at":"2026-05-17T23:42:47Z","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":"ba8b33de2e53a4ad64656442819fef29e22095e4725565ab7b4413c46ecd3cce","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-06-21T03:00:36Z","title_canon_sha256":"2bb2f312496df5de7628d2aa467f338b31a090c5a73c84cbec939255c13d5fa5"},"schema_version":"1.0","source":{"id":"1906.08928","kind":"arxiv","version":1}},"canonical_sha256":"c82a22a5d3cae8cc078ef8582b8a68889cf4eb0a04c3ea1486aa2fb74163b055","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c82a22a5d3cae8cc078ef8582b8a68889cf4eb0a04c3ea1486aa2fb74163b055","first_computed_at":"2026-05-17T23:42:47.376672Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:47.376672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XUteongKia8n3NJ3BEY6K28P8GBBI2QTRvVeWETF/zEkQMfYg04xvM2pF1ZBmuUQJ9hvvRWKZDhX+ZXpuQ9hDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:47.377351Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.08928","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:445a9b2493e62da52d8f690ab853ed072d949c3927be7fe9c2e3e1e4d6b30130","sha256:d8e906fd1020a0e071fe95f6ef5cd8803b3b363801b4b4d37d05cea0d4975ebc"],"state_sha256":"36a72a64eebcb9b7435bc22e7058d7234e52316b352f85ce4b7ccfef88f6e040"}