{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:SGIN5CWNARMKQLI5IRFOT3ZQTF","short_pith_number":"pith:SGIN5CWN","canonical_record":{"source":{"id":"1701.02369","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2017-01-09T22:03:18Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"fde05aac0cc570b7fa4051cf62cd5af1562e08bfb1e0b3b88bf78f6eec92e508","abstract_canon_sha256":"f7a6fa9f50cfb8a9a8b5d52fae4f95d3b8c9b504b0a82b748fd14f028ca9d156"},"schema_version":"1.0"},"canonical_sha256":"9190de8acd0458a82d1d444ae9ef309954646899782ee7d0e549c397ae0a5b9d","source":{"kind":"arxiv","id":"1701.02369","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.02369","created_at":"2026-05-18T00:52:03Z"},{"alias_kind":"arxiv_version","alias_value":"1701.02369v3","created_at":"2026-05-18T00:52:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.02369","created_at":"2026-05-18T00:52:03Z"},{"alias_kind":"pith_short_12","alias_value":"SGIN5CWNARMK","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SGIN5CWNARMKQLI5","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SGIN5CWN","created_at":"2026-05-18T12:31:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:SGIN5CWNARMKQLI5IRFOT3ZQTF","target":"record","payload":{"canonical_record":{"source":{"id":"1701.02369","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2017-01-09T22:03:18Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"fde05aac0cc570b7fa4051cf62cd5af1562e08bfb1e0b3b88bf78f6eec92e508","abstract_canon_sha256":"f7a6fa9f50cfb8a9a8b5d52fae4f95d3b8c9b504b0a82b748fd14f028ca9d156"},"schema_version":"1.0"},"canonical_sha256":"9190de8acd0458a82d1d444ae9ef309954646899782ee7d0e549c397ae0a5b9d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:03.585937Z","signature_b64":"9l5Tft43+lAlYWitOGScQVTTdoL77nB+tZVUav1bF2Vs5WOi4UkeFuYfQNFOvX2sYgGTP4UNK53NaNMFar3NCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9190de8acd0458a82d1d444ae9ef309954646899782ee7d0e549c397ae0a5b9d","last_reissued_at":"2026-05-18T00:52:03.585481Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:03.585481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1701.02369","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":"2026-05-18T00:52:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yOOlpKAb9GIlZimEngILiVTQkvBHHa+OIeFOLZpMG+hItQjpZKjb+uPfIaFcAhN1ItVT8DXjCfehIxnX+PrDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:45:34.181308Z"},"content_sha256":"6e32c1f967bc17c504da10fbf811cf520941d9fec3c4724dd7a6366b9bed3f6e","schema_version":"1.0","event_id":"sha256:6e32c1f967bc17c504da10fbf811cf520941d9fec3c4724dd7a6366b9bed3f6e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:SGIN5CWNARMKQLI5IRFOT3ZQTF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning based Embodied Agents Modelling Human Users Through Interaction and Multi-Sensory Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.HC","authors_text":"Kory W. Mathewson, Patrick M. Pilarski","submitted_at":"2017-01-09T22:03:18Z","abstract_excerpt":"This paper extends recent work in interactive machine learning (IML) focused on effectively incorporating human feedback. We show how control and feedback signals complement each other in systems which model human reward. We demonstrate that simultaneously incorporating human control and feedback signals can improve interactive robotic systems' performance on a self-mirrored movement control task where an RL-agent controlled right arm attempts to match the preprogrammed movement pattern of the left arm. We illustrate the impact of varying human feedback parameters on task performance by invest"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.02369","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":""},"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":"2026-05-18T00:52:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cg9dMmNKAZzHLNhHZe82OXeI1xFBNm2HblFmgW9hCUYpCa6y+JPWqs/ubh+N5EEFZd6qahrfKYcrQtpEgtFKCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:45:34.181680Z"},"content_sha256":"6bcda9380f68956d4b1dc0d1ba4f2f0c21f00f6f62bb7495608a346d985966a6","schema_version":"1.0","event_id":"sha256:6bcda9380f68956d4b1dc0d1ba4f2f0c21f00f6f62bb7495608a346d985966a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SGIN5CWNARMKQLI5IRFOT3ZQTF/bundle.json","state_url":"https://pith.science/pith/SGIN5CWNARMKQLI5IRFOT3ZQTF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SGIN5CWNARMKQLI5IRFOT3ZQTF/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":"2026-06-01T20:45:34Z","links":{"resolver":"https://pith.science/pith/SGIN5CWNARMKQLI5IRFOT3ZQTF","bundle":"https://pith.science/pith/SGIN5CWNARMKQLI5IRFOT3ZQTF/bundle.json","state":"https://pith.science/pith/SGIN5CWNARMKQLI5IRFOT3ZQTF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SGIN5CWNARMKQLI5IRFOT3ZQTF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:SGIN5CWNARMKQLI5IRFOT3ZQTF","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":"f7a6fa9f50cfb8a9a8b5d52fae4f95d3b8c9b504b0a82b748fd14f028ca9d156","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2017-01-09T22:03:18Z","title_canon_sha256":"fde05aac0cc570b7fa4051cf62cd5af1562e08bfb1e0b3b88bf78f6eec92e508"},"schema_version":"1.0","source":{"id":"1701.02369","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.02369","created_at":"2026-05-18T00:52:03Z"},{"alias_kind":"arxiv_version","alias_value":"1701.02369v3","created_at":"2026-05-18T00:52:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.02369","created_at":"2026-05-18T00:52:03Z"},{"alias_kind":"pith_short_12","alias_value":"SGIN5CWNARMK","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SGIN5CWNARMKQLI5","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SGIN5CWN","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:6bcda9380f68956d4b1dc0d1ba4f2f0c21f00f6f62bb7495608a346d985966a6","target":"graph","created_at":"2026-05-18T00:52:03Z","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":"This paper extends recent work in interactive machine learning (IML) focused on effectively incorporating human feedback. We show how control and feedback signals complement each other in systems which model human reward. We demonstrate that simultaneously incorporating human control and feedback signals can improve interactive robotic systems' performance on a self-mirrored movement control task where an RL-agent controlled right arm attempts to match the preprogrammed movement pattern of the left arm. We illustrate the impact of varying human feedback parameters on task performance by invest","authors_text":"Kory W. Mathewson, Patrick M. Pilarski","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2017-01-09T22:03:18Z","title":"Reinforcement Learning based Embodied Agents Modelling Human Users Through Interaction and Multi-Sensory Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.02369","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":"sha256:6e32c1f967bc17c504da10fbf811cf520941d9fec3c4724dd7a6366b9bed3f6e","target":"record","created_at":"2026-05-18T00:52:03Z","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":"f7a6fa9f50cfb8a9a8b5d52fae4f95d3b8c9b504b0a82b748fd14f028ca9d156","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2017-01-09T22:03:18Z","title_canon_sha256":"fde05aac0cc570b7fa4051cf62cd5af1562e08bfb1e0b3b88bf78f6eec92e508"},"schema_version":"1.0","source":{"id":"1701.02369","kind":"arxiv","version":3}},"canonical_sha256":"9190de8acd0458a82d1d444ae9ef309954646899782ee7d0e549c397ae0a5b9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9190de8acd0458a82d1d444ae9ef309954646899782ee7d0e549c397ae0a5b9d","first_computed_at":"2026-05-18T00:52:03.585481Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:52:03.585481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9l5Tft43+lAlYWitOGScQVTTdoL77nB+tZVUav1bF2Vs5WOi4UkeFuYfQNFOvX2sYgGTP4UNK53NaNMFar3NCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:52:03.585937Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.02369","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e32c1f967bc17c504da10fbf811cf520941d9fec3c4724dd7a6366b9bed3f6e","sha256:6bcda9380f68956d4b1dc0d1ba4f2f0c21f00f6f62bb7495608a346d985966a6"],"state_sha256":"923a79fc356dada30dfead893b4c13d244409d3538ed36ef4870fd783e8a3f4b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tGRuI+AtwwnExdcSFMzAj8ZTXsjPvqOs7icPyLYfdq8da6Y3rcGSPsMxfsH7TYujCLwmJm2VfMQ5Lo/R3t3ZAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T20:45:34.183621Z","bundle_sha256":"d3b2c404866d14af70ea15953b4bbec902a02518169f2bc2a801e93bd561635b"}}