{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AOAZSDKLYTCTSVOURIJ33WTC2K","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":"bb2c4f91bef268ed8cd236f5a6438388ecf9b12b84d8478a8c6634d4e8d302bd","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-02T16:04:21Z","title_canon_sha256":"8aff62f8117c8d01404d67924207b71b88aae7256d9d7d61e4be5dbb931724a6"},"schema_version":"1.0","source":{"id":"2001.00503","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.00503","created_at":"2026-07-05T01:53:36Z"},{"alias_kind":"arxiv_version","alias_value":"2001.00503v3","created_at":"2026-07-05T01:53:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00503","created_at":"2026-07-05T01:53:36Z"},{"alias_kind":"pith_short_12","alias_value":"AOAZSDKLYTCT","created_at":"2026-07-05T01:53:36Z"},{"alias_kind":"pith_short_16","alias_value":"AOAZSDKLYTCTSVOU","created_at":"2026-07-05T01:53:36Z"},{"alias_kind":"pith_short_8","alias_value":"AOAZSDKL","created_at":"2026-07-05T01:53:36Z"}],"graph_snapshots":[{"event_id":"sha256:e9ac9b317016448bd6948e82d15379e974dd31044fb605fefcd9a502814f2c8a","target":"graph","created_at":"2026-07-05T01:53:36Z","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/2001.00503/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has achieved tremendous success as a general framework for learning how to make decisions. However, this success relies on the interactive hand-tuning of a reward function by RL experts. On the other hand, inverse reinforcement learning (IRL) seeks to learn a reward function from readily-obtained human demonstrations. Yet, IRL suffers from two major limitations: 1) reward ambiguity - there are an infinite number of possible reward functions that could explain an expert's demonstration and 2) heterogeneity - human experts adopt varying strategies and preferences, whi","authors_text":"Letian Chen, Matthew Gombolay, Muyleng Ghuy, Rohan Paleja","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-02T16:04:21Z","title":"Joint Goal and Strategy Inference across Heterogeneous Demonstrators via Reward Network Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00503","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":"sha256:120cfd55fff3a58959a131dfbb1e6fe22b2e0b9984be45a1983a46bf6261180a","target":"record","created_at":"2026-07-05T01:53:36Z","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":"bb2c4f91bef268ed8cd236f5a6438388ecf9b12b84d8478a8c6634d4e8d302bd","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-02T16:04:21Z","title_canon_sha256":"8aff62f8117c8d01404d67924207b71b88aae7256d9d7d61e4be5dbb931724a6"},"schema_version":"1.0","source":{"id":"2001.00503","kind":"arxiv","version":3}},"canonical_sha256":"0381990d4bc4c53955d48a13bdda62d2852f8aac07498edd453ec0e2de0c98d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0381990d4bc4c53955d48a13bdda62d2852f8aac07498edd453ec0e2de0c98d2","first_computed_at":"2026-07-05T01:53:36.805132Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:53:36.805132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"21G20C1AqJ1Tg2np7Ew7Zno8WjM/asdnjT6nPqW8mKiIfBHRGQTBJHnA9Yua6P9BECl8YUK2+XolocoBzthnAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:53:36.805593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.00503","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:120cfd55fff3a58959a131dfbb1e6fe22b2e0b9984be45a1983a46bf6261180a","sha256:e9ac9b317016448bd6948e82d15379e974dd31044fb605fefcd9a502814f2c8a"],"state_sha256":"e54d3d614a5c23615d98e4bea4bf255777994c839cf1fa576856df838ce251ca"}