{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:YDHNFVQMD3VR5Q6M6EOH5VLE55","short_pith_number":"pith:YDHNFVQM","canonical_record":{"source":{"id":"1804.05259","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-04-14T18:22:29Z","cross_cats_sorted":[],"title_canon_sha256":"7d7d2c7ba5032507d408dbea15c6da285fa9fb29245b4ca16827e697930253ff","abstract_canon_sha256":"837a7106de351ad4c7a8b32836ae4f707ddacab875be4f321066c135bade0c85"},"schema_version":"1.0"},"canonical_sha256":"c0ced2d60c1eeb1ec3ccf11c7ed564ef4e1bc055df9acbce7d3460972690bcb0","source":{"kind":"arxiv","id":"1804.05259","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.05259","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"1804.05259v1","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05259","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"YDHNFVQMD3VR","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YDHNFVQMD3VR5Q6M","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YDHNFVQM","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:YDHNFVQMD3VR5Q6M6EOH5VLE55","target":"record","payload":{"canonical_record":{"source":{"id":"1804.05259","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-04-14T18:22:29Z","cross_cats_sorted":[],"title_canon_sha256":"7d7d2c7ba5032507d408dbea15c6da285fa9fb29245b4ca16827e697930253ff","abstract_canon_sha256":"837a7106de351ad4c7a8b32836ae4f707ddacab875be4f321066c135bade0c85"},"schema_version":"1.0"},"canonical_sha256":"c0ced2d60c1eeb1ec3ccf11c7ed564ef4e1bc055df9acbce7d3460972690bcb0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:28.489350Z","signature_b64":"oD7OgMp6KB2avpY0hkC68Nn05qcRCHHXzenDY9AxoZ8HuUzRsgste1yH5JCRX/R1VkFAwsLWUVEA0+nWXMZuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0ced2d60c1eeb1ec3ccf11c7ed564ef4e1bc055df9acbce7d3460972690bcb0","last_reissued_at":"2026-05-18T00:18:28.488539Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:28.488539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.05259","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lSYFo5mApscS1ah2F+maQSbG9l8XixYba6XZ9m5/E7VQEJo78cHwzWlgFHPM2Gap9TbmK6LLEXs6Uo7DR57WCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:52:35.422822Z"},"content_sha256":"1fa9643984791c82c4b0af12fc441c7714480718eec8ea0c9d30eec976ca5433","schema_version":"1.0","event_id":"sha256:1fa9643984791c82c4b0af12fc441c7714480718eec8ea0c9d30eec976ca5433"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:YDHNFVQMD3VR5Q6M6EOH5VLE55","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Intrinsically motivated reinforcement learning for human-robot interaction in the real-world","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ahmed Hussain Qureshi, Hiroshi Ishiguro, Yuichiro Yoshikawa, Yutaka Nakamura","submitted_at":"2018-04-14T18:22:29Z","abstract_excerpt":"For a natural social human-robot interaction, it is essential for a robot to learn the human-like social skills. However, learning such skills is notoriously hard due to the limited availability of direct instructions from people to teach a robot. In this paper, we propose an intrinsically motivated reinforcement learning framework in which an agent gets the intrinsic motivation-based rewards through the action-conditional predictive model. By using the proposed method, the robot learned the social skills from the human-robot interaction experiences gathered in the real uncontrolled environmen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05259","kind":"arxiv","version":1},"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":"2026-05-18T00:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8N9nljDMtsnzTAnsi8OPgAR7CuOLGzGMnQx7vN2mAlqkQExo5TZp2uMQroqTu7hu2An9UCXkF1eCps6Vt6KrBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:52:35.423160Z"},"content_sha256":"a982dd98510e6ead41f7ff455bb863f1af6c694ccfb4f626eccf9eef5b9110af","schema_version":"1.0","event_id":"sha256:a982dd98510e6ead41f7ff455bb863f1af6c694ccfb4f626eccf9eef5b9110af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YDHNFVQMD3VR5Q6M6EOH5VLE55/bundle.json","state_url":"https://pith.science/pith/YDHNFVQMD3VR5Q6M6EOH5VLE55/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YDHNFVQMD3VR5Q6M6EOH5VLE55/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":"2026-08-06T13:52:35Z","links":{"resolver":"https://pith.science/pith/YDHNFVQMD3VR5Q6M6EOH5VLE55","bundle":"https://pith.science/pith/YDHNFVQMD3VR5Q6M6EOH5VLE55/bundle.json","state":"https://pith.science/pith/YDHNFVQMD3VR5Q6M6EOH5VLE55/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YDHNFVQMD3VR5Q6M6EOH5VLE55/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YDHNFVQMD3VR5Q6M6EOH5VLE55","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":"837a7106de351ad4c7a8b32836ae4f707ddacab875be4f321066c135bade0c85","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-04-14T18:22:29Z","title_canon_sha256":"7d7d2c7ba5032507d408dbea15c6da285fa9fb29245b4ca16827e697930253ff"},"schema_version":"1.0","source":{"id":"1804.05259","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.05259","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"1804.05259v1","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05259","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"YDHNFVQMD3VR","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YDHNFVQMD3VR5Q6M","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YDHNFVQM","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:a982dd98510e6ead41f7ff455bb863f1af6c694ccfb4f626eccf9eef5b9110af","target":"graph","created_at":"2026-05-18T00:18:28Z","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":"For a natural social human-robot interaction, it is essential for a robot to learn the human-like social skills. However, learning such skills is notoriously hard due to the limited availability of direct instructions from people to teach a robot. In this paper, we propose an intrinsically motivated reinforcement learning framework in which an agent gets the intrinsic motivation-based rewards through the action-conditional predictive model. By using the proposed method, the robot learned the social skills from the human-robot interaction experiences gathered in the real uncontrolled environmen","authors_text":"Ahmed Hussain Qureshi, Hiroshi Ishiguro, Yuichiro Yoshikawa, Yutaka Nakamura","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-04-14T18:22:29Z","title":"Intrinsically motivated reinforcement learning for human-robot interaction in the real-world"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05259","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":"sha256:1fa9643984791c82c4b0af12fc441c7714480718eec8ea0c9d30eec976ca5433","target":"record","created_at":"2026-05-18T00:18:28Z","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":"837a7106de351ad4c7a8b32836ae4f707ddacab875be4f321066c135bade0c85","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-04-14T18:22:29Z","title_canon_sha256":"7d7d2c7ba5032507d408dbea15c6da285fa9fb29245b4ca16827e697930253ff"},"schema_version":"1.0","source":{"id":"1804.05259","kind":"arxiv","version":1}},"canonical_sha256":"c0ced2d60c1eeb1ec3ccf11c7ed564ef4e1bc055df9acbce7d3460972690bcb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0ced2d60c1eeb1ec3ccf11c7ed564ef4e1bc055df9acbce7d3460972690bcb0","first_computed_at":"2026-05-18T00:18:28.488539Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:28.488539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oD7OgMp6KB2avpY0hkC68Nn05qcRCHHXzenDY9AxoZ8HuUzRsgste1yH5JCRX/R1VkFAwsLWUVEA0+nWXMZuCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:28.489350Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.05259","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fa9643984791c82c4b0af12fc441c7714480718eec8ea0c9d30eec976ca5433","sha256:a982dd98510e6ead41f7ff455bb863f1af6c694ccfb4f626eccf9eef5b9110af"],"state_sha256":"9ed9d24464ed1d92d76e77db9ea6f89ee1311cd067bfbf04c555c0adbeec48e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jpb2KyttlI/wprkwGPjk1pL8JtZjnITnwBqesVqwx6oVanQ0iYKz3h9IgWsca0aUXqzvXQxcKNGWzhFDxPm5Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T13:52:35.425572Z","bundle_sha256":"98143f6253f0f4558bb0cc0de01b06fb2c441dbb2a6291f62f5f3bd94720615f"}}