{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:SVR3O4NPPGLVB5WVN6RQRKSAOW","short_pith_number":"pith:SVR3O4NP","canonical_record":{"source":{"id":"2010.11723","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-10-17T04:18:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"23c3b804b900f15486c9cb62f5aa1a2f9c94e1aa06005fa849d6fbbf493427fc","abstract_canon_sha256":"4839737b2e29b4a79706b592d195a92ceb244ba8f100118a1bde8425e389d9b9"},"schema_version":"1.0"},"canonical_sha256":"9563b771af799750f6d56fa308aa407584869fcea87196dc0ebec6c21fa29d4e","source":{"kind":"arxiv","id":"2010.11723","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:SVR3O4NPPGLVB5WVN6RQRKSAOW","target":"record","payload":{"canonical_record":{"source":{"id":"2010.11723","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-10-17T04:18:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"23c3b804b900f15486c9cb62f5aa1a2f9c94e1aa06005fa849d6fbbf493427fc","abstract_canon_sha256":"4839737b2e29b4a79706b592d195a92ceb244ba8f100118a1bde8425e389d9b9"},"schema_version":"1.0"},"canonical_sha256":"9563b771af799750f6d56fa308aa407584869fcea87196dc0ebec6c21fa29d4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:39.583391Z","signature_b64":"S8vkULNse91JezkhNy9QDrJ00DJfasDs41nOekKJfRKGehXKQPImKHCyvFV3nO4wzzLeYli9bU+Kheq/9QBMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9563b771af799750f6d56fa308aa407584869fcea87196dc0ebec6c21fa29d4e","last_reissued_at":"2026-07-05T01:53:39.582980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:39.582980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.11723","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:53:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UxJXLzpAk8n3K3sPq19cfITZ+IGfG6b8CPQ8yUiCS0emxpd5W+8oZ4+HPMUaCGa8v3vUrTyAUZmFgtPs82bOBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:02:33.902329Z"},"content_sha256":"6c15052fc2ddf8594f78db10e7bf479646aa70e6a17fa99c3e8e93d262195587","schema_version":"1.0","event_id":"sha256:6c15052fc2ddf8594f78db10e7bf479646aa70e6a17fa99c3e8e93d262195587"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:SVR3O4NPPGLVB5WVN6RQRKSAOW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning from Suboptimal Demonstration via Self-Supervised Reward Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Letian Chen, Matthew Gombolay, Rohan Paleja","submitted_at":"2020-10-17T04:18:04Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11723","kind":"arxiv","version":3},"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/2010.11723/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":"2026-07-05T01:53:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z0L8NNg0Ey0B3Ol6SqySWht3lOkRIYaqurDfYxjFGYsHKnzTU9vybfwq9oHgmnUtaILvUQIJ+Of6tKRpQN6lBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:02:33.903262Z"},"content_sha256":"cc14b67496592087dc22402d12240d61b053aa36d2f7ee891e3157c290ed4f33","schema_version":"1.0","event_id":"sha256:cc14b67496592087dc22402d12240d61b053aa36d2f7ee891e3157c290ed4f33"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SVR3O4NPPGLVB5WVN6RQRKSAOW/bundle.json","state_url":"https://pith.science/pith/SVR3O4NPPGLVB5WVN6RQRKSAOW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SVR3O4NPPGLVB5WVN6RQRKSAOW/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":"2026-08-09T11:02:33Z","links":{"resolver":"https://pith.science/pith/SVR3O4NPPGLVB5WVN6RQRKSAOW","bundle":"https://pith.science/pith/SVR3O4NPPGLVB5WVN6RQRKSAOW/bundle.json","state":"https://pith.science/pith/SVR3O4NPPGLVB5WVN6RQRKSAOW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SVR3O4NPPGLVB5WVN6RQRKSAOW/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EiFPOGyDhNxEzwJVBLAxqWbkQLU01Hzz+Floss2RBGbemwgUAUN72sbrRZMx54pCFnPguIwf4YQma+JeB4fIDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:02:33.909068Z","bundle_sha256":"7ff887d3bcaff09a70df6d00a23bc70357fcb5a2b7152ccb03e5f2b7914a23bf"}}