{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:4UJPE3Q43WI7ZF345KDAJNFJMW","short_pith_number":"pith:4UJPE3Q4","canonical_record":{"source":{"id":"1405.6341","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2014-05-24T20:44:26Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY"],"title_canon_sha256":"24ab196dd3e2c953754f41c00200fcc85908ee2599ea37bfafc09871a98ca33a","abstract_canon_sha256":"ababe1f23980390654a71625f9255ad6cf03af8b1834efa9eede01a8f0852cae"},"schema_version":"1.0"},"canonical_sha256":"e512f26e1cdd91fc977cea8604b4a965b524b2f6d435e761cb5e50dc6273541c","source":{"kind":"arxiv","id":"1405.6341","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.6341","created_at":"2026-05-18T00:42:24Z"},{"alias_kind":"arxiv_version","alias_value":"1405.6341v1","created_at":"2026-05-18T00:42:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.6341","created_at":"2026-05-18T00:42:24Z"},{"alias_kind":"pith_short_12","alias_value":"4UJPE3Q43WI7","created_at":"2026-05-18T12:28:14Z"},{"alias_kind":"pith_short_16","alias_value":"4UJPE3Q43WI7ZF34","created_at":"2026-05-18T12:28:14Z"},{"alias_kind":"pith_short_8","alias_value":"4UJPE3Q4","created_at":"2026-05-18T12:28:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:4UJPE3Q43WI7ZF345KDAJNFJMW","target":"record","payload":{"canonical_record":{"source":{"id":"1405.6341","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2014-05-24T20:44:26Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY"],"title_canon_sha256":"24ab196dd3e2c953754f41c00200fcc85908ee2599ea37bfafc09871a98ca33a","abstract_canon_sha256":"ababe1f23980390654a71625f9255ad6cf03af8b1834efa9eede01a8f0852cae"},"schema_version":"1.0"},"canonical_sha256":"e512f26e1cdd91fc977cea8604b4a965b524b2f6d435e761cb5e50dc6273541c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:24.242532Z","signature_b64":"Vz9VzB8ZVnaResarHbWow7pKqykxBCex4VnpNXyryyhti9QEGAMMHB4JFMvZjudGX3NqevNrNYvKzv3c9dPoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e512f26e1cdd91fc977cea8604b4a965b524b2f6d435e761cb5e50dc6273541c","last_reissued_at":"2026-05-18T00:42:24.241994Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:24.241994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1405.6341","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":"2026-05-18T00:42:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RNZO0dGDziL3VBye2eq10GoeOUs/Esv8VKMs3kSBgRqCdAHLW0EOhlN8m5sqD4SorWtXUnz14Wz3T7F7OqBzCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:17:49.008219Z"},"content_sha256":"ae74e99638900ad3b1581cf7447db92b28d2e61b6cc144a1cb09be30dfbdd32a","schema_version":"1.0","event_id":"sha256:ae74e99638900ad3b1581cf7447db92b28d2e61b6cc144a1cb09be30dfbdd32a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:4UJPE3Q43WI7ZF345KDAJNFJMW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Model Learning for Human-Robot Collaborative Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY"],"primary_cat":"cs.RO","authors_text":"Julie Shah, Keren Gu, Ramya Ramakrishnan, Stefanos Nikolaidis","submitted_at":"2014-05-24T20:44:26Z","abstract_excerpt":"We present a framework for learning human user models from joint-action demonstrations that enables the robot to compute a robust policy for a collaborative task with a human. The learning takes place completely automatically, without any human intervention. First, we describe the clustering of demonstrated action sequences into different human types using an unsupervised learning algorithm. These demonstrated sequences are also used by the robot to learn a reward function that is representative for each type, through the employment of an inverse reinforcement learning algorithm. The learned m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.6341","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":"2026-05-18T00:42:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DV3qer6eH1V4EISJr1HA05DxT/u9I4yNoideCOOJXxXDt9Tkvtrby9tzMwoYUe49tkWWr7EjglZ7oewMy9YACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:17:49.008686Z"},"content_sha256":"439c3ab266cc41a663f555c232d14531859bb05d8fa903531f822f781806a1c4","schema_version":"1.0","event_id":"sha256:439c3ab266cc41a663f555c232d14531859bb05d8fa903531f822f781806a1c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4UJPE3Q43WI7ZF345KDAJNFJMW/bundle.json","state_url":"https://pith.science/pith/4UJPE3Q43WI7ZF345KDAJNFJMW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4UJPE3Q43WI7ZF345KDAJNFJMW/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":"2026-05-25T19:17:49Z","links":{"resolver":"https://pith.science/pith/4UJPE3Q43WI7ZF345KDAJNFJMW","bundle":"https://pith.science/pith/4UJPE3Q43WI7ZF345KDAJNFJMW/bundle.json","state":"https://pith.science/pith/4UJPE3Q43WI7ZF345KDAJNFJMW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4UJPE3Q43WI7ZF345KDAJNFJMW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:4UJPE3Q43WI7ZF345KDAJNFJMW","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":"ababe1f23980390654a71625f9255ad6cf03af8b1834efa9eede01a8f0852cae","cross_cats_sorted":["cs.AI","cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2014-05-24T20:44:26Z","title_canon_sha256":"24ab196dd3e2c953754f41c00200fcc85908ee2599ea37bfafc09871a98ca33a"},"schema_version":"1.0","source":{"id":"1405.6341","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.6341","created_at":"2026-05-18T00:42:24Z"},{"alias_kind":"arxiv_version","alias_value":"1405.6341v1","created_at":"2026-05-18T00:42:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.6341","created_at":"2026-05-18T00:42:24Z"},{"alias_kind":"pith_short_12","alias_value":"4UJPE3Q43WI7","created_at":"2026-05-18T12:28:14Z"},{"alias_kind":"pith_short_16","alias_value":"4UJPE3Q43WI7ZF34","created_at":"2026-05-18T12:28:14Z"},{"alias_kind":"pith_short_8","alias_value":"4UJPE3Q4","created_at":"2026-05-18T12:28:14Z"}],"graph_snapshots":[{"event_id":"sha256:439c3ab266cc41a663f555c232d14531859bb05d8fa903531f822f781806a1c4","target":"graph","created_at":"2026-05-18T00:42:24Z","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":"We present a framework for learning human user models from joint-action demonstrations that enables the robot to compute a robust policy for a collaborative task with a human. The learning takes place completely automatically, without any human intervention. First, we describe the clustering of demonstrated action sequences into different human types using an unsupervised learning algorithm. These demonstrated sequences are also used by the robot to learn a reward function that is representative for each type, through the employment of an inverse reinforcement learning algorithm. The learned m","authors_text":"Julie Shah, Keren Gu, Ramya Ramakrishnan, Stefanos Nikolaidis","cross_cats":["cs.AI","cs.LG","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2014-05-24T20:44:26Z","title":"Efficient Model Learning for Human-Robot Collaborative Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.6341","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:ae74e99638900ad3b1581cf7447db92b28d2e61b6cc144a1cb09be30dfbdd32a","target":"record","created_at":"2026-05-18T00:42:24Z","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":"ababe1f23980390654a71625f9255ad6cf03af8b1834efa9eede01a8f0852cae","cross_cats_sorted":["cs.AI","cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2014-05-24T20:44:26Z","title_canon_sha256":"24ab196dd3e2c953754f41c00200fcc85908ee2599ea37bfafc09871a98ca33a"},"schema_version":"1.0","source":{"id":"1405.6341","kind":"arxiv","version":1}},"canonical_sha256":"e512f26e1cdd91fc977cea8604b4a965b524b2f6d435e761cb5e50dc6273541c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e512f26e1cdd91fc977cea8604b4a965b524b2f6d435e761cb5e50dc6273541c","first_computed_at":"2026-05-18T00:42:24.241994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:24.241994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vz9VzB8ZVnaResarHbWow7pKqykxBCex4VnpNXyryyhti9QEGAMMHB4JFMvZjudGX3NqevNrNYvKzv3c9dPoCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:24.242532Z","signed_message":"canonical_sha256_bytes"},"source_id":"1405.6341","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae74e99638900ad3b1581cf7447db92b28d2e61b6cc144a1cb09be30dfbdd32a","sha256:439c3ab266cc41a663f555c232d14531859bb05d8fa903531f822f781806a1c4"],"state_sha256":"76b466682ec2a3f20cd24d940dcd0e398f8137475dba28cb786e1dd7815c7bd9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4xZXZRjMRpIJohIDTQ1Cgl08irvJaxGS8Mm4J0kvUfEntfcaJH6xYsM8NdhYxYqzYQacBKfs7iPc1CTGMbE4Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:17:49.011756Z","bundle_sha256":"68ac5225c8c8efb82f1b8c402173a881c8eb380df5e4349be3dd36a5c99c506e"}}