{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SVR3O4NPPGLVB5WVN6RQRKSAOW","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":"4839737b2e29b4a79706b592d195a92ceb244ba8f100118a1bde8425e389d9b9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-10-17T04:18:04Z","title_canon_sha256":"23c3b804b900f15486c9cb62f5aa1a2f9c94e1aa06005fa849d6fbbf493427fc"},"schema_version":"1.0","source":{"id":"2010.11723","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.11723","created_at":"2026-07-05T01:53:39Z"},{"alias_kind":"arxiv_version","alias_value":"2010.11723v3","created_at":"2026-07-05T01:53:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11723","created_at":"2026-07-05T01:53:39Z"},{"alias_kind":"pith_short_12","alias_value":"SVR3O4NPPGLV","created_at":"2026-07-05T01:53:39Z"},{"alias_kind":"pith_short_16","alias_value":"SVR3O4NPPGLVB5WV","created_at":"2026-07-05T01:53:39Z"},{"alias_kind":"pith_short_8","alias_value":"SVR3O4NP","created_at":"2026-07-05T01:53:39Z"}],"graph_snapshots":[{"event_id":"sha256:cc14b67496592087dc22402d12240d61b053aa36d2f7ee891e3157c290ed4f33","target":"graph","created_at":"2026-07-05T01:53:39Z","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/2010.11723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning from Demonstration (LfD) seeks to democratize robotics by enabling non-roboticist end-users to teach robots to perform a task by providing a human demonstration. However, modern LfD techniques, e.g. inverse reinforcement learning (IRL), assume users provide at least stochastically optimal demonstrations. This assumption fails to hold in most real-world scenarios. Recent attempts to learn from sub-optimal demonstration leverage pairwise rankings and following the Luce-Shepard rule. However, we show these approaches make incorrect assumptions and thus suffer from brittle, degraded perfo","authors_text":"Letian Chen, Matthew Gombolay, Rohan Paleja","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-10-17T04:18:04Z","title":"Learning from Suboptimal Demonstration via Self-Supervised Reward Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11723","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":"sha256:6c15052fc2ddf8594f78db10e7bf479646aa70e6a17fa99c3e8e93d262195587","target":"record","created_at":"2026-07-05T01:53:39Z","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":"4839737b2e29b4a79706b592d195a92ceb244ba8f100118a1bde8425e389d9b9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-10-17T04:18:04Z","title_canon_sha256":"23c3b804b900f15486c9cb62f5aa1a2f9c94e1aa06005fa849d6fbbf493427fc"},"schema_version":"1.0","source":{"id":"2010.11723","kind":"arxiv","version":3}},"canonical_sha256":"9563b771af799750f6d56fa308aa407584869fcea87196dc0ebec6c21fa29d4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9563b771af799750f6d56fa308aa407584869fcea87196dc0ebec6c21fa29d4e","first_computed_at":"2026-07-05T01:53:39.582980Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:53:39.582980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S8vkULNse91JezkhNy9QDrJ00DJfasDs41nOekKJfRKGehXKQPImKHCyvFV3nO4wzzLeYli9bU+Kheq/9QBMDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:53:39.583391Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.11723","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c15052fc2ddf8594f78db10e7bf479646aa70e6a17fa99c3e8e93d262195587","sha256:cc14b67496592087dc22402d12240d61b053aa36d2f7ee891e3157c290ed4f33"],"state_sha256":"b5f718eb43e8400712ff77df684a42923d23123224f23b37e3af12f94404ffed"}