{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MQNGCGPXQJOYVBMTTCQKKCHPCM","short_pith_number":"pith:MQNGCGPX","canonical_record":{"source":{"id":"2505.10151","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-15T10:23:56Z","cross_cats_sorted":[],"title_canon_sha256":"6c4723aeef4bf8d245d39e1018dea7f3418ce47114e80be8da5ce467e693cc7c","abstract_canon_sha256":"fac5e0b9112f91881572fce5d5de5b65e907513296ce9533134ec78a8ab0af3e"},"schema_version":"1.0"},"canonical_sha256":"641a6119f7825d8a859398a0a508ef1305aa19a99da002966f664d97cbd6b8ab","source":{"kind":"arxiv","id":"2505.10151","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10151","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10151v1","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10151","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"pith_short_12","alias_value":"MQNGCGPXQJOY","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"pith_short_16","alias_value":"MQNGCGPXQJOYVBMT","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"pith_short_8","alias_value":"MQNGCGPX","created_at":"2026-07-05T11:03:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MQNGCGPXQJOYVBMTTCQKKCHPCM","target":"record","payload":{"canonical_record":{"source":{"id":"2505.10151","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-15T10:23:56Z","cross_cats_sorted":[],"title_canon_sha256":"6c4723aeef4bf8d245d39e1018dea7f3418ce47114e80be8da5ce467e693cc7c","abstract_canon_sha256":"fac5e0b9112f91881572fce5d5de5b65e907513296ce9533134ec78a8ab0af3e"},"schema_version":"1.0"},"canonical_sha256":"641a6119f7825d8a859398a0a508ef1305aa19a99da002966f664d97cbd6b8ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:34.222983Z","signature_b64":"hbt9I8IvT727FJDy8TdufnvUYxqSds6piE138IOdfMurizFnQum1WhseBj09+qnnHuICLlZmyPEx8L+1BbMSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"641a6119f7825d8a859398a0a508ef1305aa19a99da002966f664d97cbd6b8ab","last_reissued_at":"2026-07-05T11:03:34.222347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:34.222347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.10151","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":"2026-07-05T11:03:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KoQ9CI2ySpR4+k0XQc39zwXfu8y1i4v8gsE8bIZ0lbNz3Lw4dhx+LcDC7oCyEta+QelwIfo8h/B5X5O67zO1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:23:59.953029Z"},"content_sha256":"de8b0ea5d81b57845c48c0dec35948e3268dab81164fbe03d8fdebe3cd534dbd","schema_version":"1.0","event_id":"sha256:de8b0ea5d81b57845c48c0dec35948e3268dab81164fbe03d8fdebe3cd534dbd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MQNGCGPXQJOYVBMTTCQKKCHPCM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training People to Reward Robots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Endong Sun, Matthew Howard, Yuqing Zhu","submitted_at":"2025-05-15T10:23:56Z","abstract_excerpt":"Learning from demonstration (LfD) is a technique that allows expert teachers to teach task-oriented skills to robotic systems. However, the most effective way of guiding novice teachers to approach expert-level demonstrations quantitatively for specific teaching tasks remains an open question. To this end, this paper investigates the use of machine teaching (MT) to guide novice teachers to improve their teaching skills based on reinforcement learning from demonstration (RLfD). The paper reports an experiment in which novices receive MT-derived guidance to train their ability to teach a given m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10151","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.10151/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":"2026-07-05T11:03:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+8qx9rlsaxG71nPhB/Ks9o9EMr2ot0JJmgx9wTNJK8uDHNUSMhuEVJGusEUy/OpfT5XQ8ZoKBA86CiN9pvjnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:23:59.953412Z"},"content_sha256":"4e78fe231f0b1f5a577bce86534a9e7105d060ea55f3b7450b4ad7fb672d5130","schema_version":"1.0","event_id":"sha256:4e78fe231f0b1f5a577bce86534a9e7105d060ea55f3b7450b4ad7fb672d5130"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MQNGCGPXQJOYVBMTTCQKKCHPCM/bundle.json","state_url":"https://pith.science/pith/MQNGCGPXQJOYVBMTTCQKKCHPCM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MQNGCGPXQJOYVBMTTCQKKCHPCM/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":"2026-07-06T12:23:59Z","links":{"resolver":"https://pith.science/pith/MQNGCGPXQJOYVBMTTCQKKCHPCM","bundle":"https://pith.science/pith/MQNGCGPXQJOYVBMTTCQKKCHPCM/bundle.json","state":"https://pith.science/pith/MQNGCGPXQJOYVBMTTCQKKCHPCM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MQNGCGPXQJOYVBMTTCQKKCHPCM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MQNGCGPXQJOYVBMTTCQKKCHPCM","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":"fac5e0b9112f91881572fce5d5de5b65e907513296ce9533134ec78a8ab0af3e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-15T10:23:56Z","title_canon_sha256":"6c4723aeef4bf8d245d39e1018dea7f3418ce47114e80be8da5ce467e693cc7c"},"schema_version":"1.0","source":{"id":"2505.10151","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10151","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10151v1","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10151","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"pith_short_12","alias_value":"MQNGCGPXQJOY","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"pith_short_16","alias_value":"MQNGCGPXQJOYVBMT","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"pith_short_8","alias_value":"MQNGCGPX","created_at":"2026-07-05T11:03:34Z"}],"graph_snapshots":[{"event_id":"sha256:4e78fe231f0b1f5a577bce86534a9e7105d060ea55f3b7450b4ad7fb672d5130","target":"graph","created_at":"2026-07-05T11:03:34Z","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/2505.10151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning from demonstration (LfD) is a technique that allows expert teachers to teach task-oriented skills to robotic systems. However, the most effective way of guiding novice teachers to approach expert-level demonstrations quantitatively for specific teaching tasks remains an open question. To this end, this paper investigates the use of machine teaching (MT) to guide novice teachers to improve their teaching skills based on reinforcement learning from demonstration (RLfD). The paper reports an experiment in which novices receive MT-derived guidance to train their ability to teach a given m","authors_text":"Endong Sun, Matthew Howard, Yuqing Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-15T10:23:56Z","title":"Training People to Reward Robots"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10151","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:de8b0ea5d81b57845c48c0dec35948e3268dab81164fbe03d8fdebe3cd534dbd","target":"record","created_at":"2026-07-05T11:03:34Z","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":"fac5e0b9112f91881572fce5d5de5b65e907513296ce9533134ec78a8ab0af3e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-15T10:23:56Z","title_canon_sha256":"6c4723aeef4bf8d245d39e1018dea7f3418ce47114e80be8da5ce467e693cc7c"},"schema_version":"1.0","source":{"id":"2505.10151","kind":"arxiv","version":1}},"canonical_sha256":"641a6119f7825d8a859398a0a508ef1305aa19a99da002966f664d97cbd6b8ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"641a6119f7825d8a859398a0a508ef1305aa19a99da002966f664d97cbd6b8ab","first_computed_at":"2026-07-05T11:03:34.222347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:34.222347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hbt9I8IvT727FJDy8TdufnvUYxqSds6piE138IOdfMurizFnQum1WhseBj09+qnnHuICLlZmyPEx8L+1BbMSBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:34.222983Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.10151","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de8b0ea5d81b57845c48c0dec35948e3268dab81164fbe03d8fdebe3cd534dbd","sha256:4e78fe231f0b1f5a577bce86534a9e7105d060ea55f3b7450b4ad7fb672d5130"],"state_sha256":"ce177008109fac7d33d3d48e984dd03e89b7691c1a133db389395950fa966c0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i6x/1D7vvjQrFTd5x7TIg0Oyl6cLGdCfGl8TwORYeLmRlImkY7OMsmkSAITr1iSRZva2/pviYRNdQFgI3SOuBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T12:23:59.955349Z","bundle_sha256":"bbd5591ce154afa91e6f4adbd7f733a79d29682fb7d18d510589a7c65cad19cf"}}