{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IR72YOXH32XCGIIWKMAHZMTZCR","short_pith_number":"pith:IR72YOXH","canonical_record":{"source":{"id":"2605.22986","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T19:34:14Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"e1bbf1056017fe0611250577c4913c9ce17a58df7fc09d575cbe839c28fef99c","abstract_canon_sha256":"b5a5fc6889597550e058590aea3827fcabb4ed1cb0fab852c9a644a6986a0f88"},"schema_version":"1.0"},"canonical_sha256":"447fac3ae7deae23211653007cb279144f2ca395bbcb352b137bcb483124ae00","source":{"kind":"arxiv","id":"2605.22986","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22986","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22986v1","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22986","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"pith_short_12","alias_value":"IR72YOXH32XC","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"pith_short_16","alias_value":"IR72YOXH32XCGIIW","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"pith_short_8","alias_value":"IR72YOXH","created_at":"2026-05-25T02:01:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IR72YOXH32XCGIIWKMAHZMTZCR","target":"record","payload":{"canonical_record":{"source":{"id":"2605.22986","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T19:34:14Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"e1bbf1056017fe0611250577c4913c9ce17a58df7fc09d575cbe839c28fef99c","abstract_canon_sha256":"b5a5fc6889597550e058590aea3827fcabb4ed1cb0fab852c9a644a6986a0f88"},"schema_version":"1.0"},"canonical_sha256":"447fac3ae7deae23211653007cb279144f2ca395bbcb352b137bcb483124ae00","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:33.293698Z","signature_b64":"wbTHS5jpV9+gtELec/S17Cf2I5UPVJlm3kepYbO0Hbccc0gM0w7jhDu3OGptgn+w87Jl72VTp0u7PxjJYTINAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"447fac3ae7deae23211653007cb279144f2ca395bbcb352b137bcb483124ae00","last_reissued_at":"2026-05-25T02:01:33.292980Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:33.292980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.22986","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":"2026-05-25T02:01:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SVijJma9t0byRJSyZgHcRi6aOPXQfWbC1L+0L4w884tNKHMtx2Na6SFSdjPrlOoVaHKpqslOoBMkYnLtRrqnBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T00:26:14.066530Z"},"content_sha256":"e2750d56fcac9e89892ed37d739b89c62addd7f100786f33f9253cfe5899bbbc","schema_version":"1.0","event_id":"sha256:e2750d56fcac9e89892ed37d739b89c62addd7f100786f33f9253cfe5899bbbc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IR72YOXH32XCGIIWKMAHZMTZCR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robots That Know What to Ask: Recovering Misaligned Rewards through Targeted Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.RO","authors_text":"Andreea Bobu, Helena Merker, Nick Walker","submitted_at":"2026-05-21T19:34:14Z","abstract_excerpt":"Learning reward functions from demonstrations assumes that demonstrations provide adequate supervision over all features -- or task-relevant aspects of behavior. In practice, demonstrations are often imperfect: humans may under-emphasize certain features due to cognitive load or physical difficulty, or the training regime may fail to sufficiently cover all relevant situations. In either case, important features may be underspecified, leading to ambiguity in the learned reward function and misaligned behavior at deployment. We propose a framework that detects such underspecified features and ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22986","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/2605.22986/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":"2026-05-25T02:01:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v8cBY7cOEGXFZA1YK3rOW3YkKREhpyb3FAkyDx6AWC9knjQswNr/Q7MqV6eWLPmcSsevtG03yZ7pG/EYR9oCCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T00:26:14.067051Z"},"content_sha256":"c9b87731fd998a8754ecdba5f4a9327fe8ee56a87978956a8922d09a0a366c9b","schema_version":"1.0","event_id":"sha256:c9b87731fd998a8754ecdba5f4a9327fe8ee56a87978956a8922d09a0a366c9b"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:IR72YOXH32XCGIIWKMAHZMTZCR","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1016/0364-0213(88) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"John Sweller. Cognitive load during problem solving: Effects on learning.Cognitive Science, 12(2):257– 285, 1988. ISSN 0364-0213.DOI: 10.1016/0364- 0213(88)90023-7","arxiv_id":"2605.22986","detector":"doi_compliance","evidence":{"ref_index":43,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"John Sweller. Cognitive load during problem solving: Effects on learning.Cognitive Science, 12(2):257– 285, 1988. ISSN 0364-0213.DOI: 10.1016/0364- 0213(88)90023-7","reconstructed_doi":"10.1016/0364-0213(88"},"severity":"advisory","ref_index":43,"audited_at":"2026-05-25T05:39:07.482685Z","event_type":"pith.integrity.v1","detected_doi":"10.1016/0364-0213(88","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"16c5f5414f74bd3f08bcc7be9608a25eee979ba822169569f55e1d1c9a067b26","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":7467,"payload_sha256":"d96462fc15490a17681907b4232840fad885a4b547b99747fe19b8507aac123b","signature_b64":"sv6Wj1JQ1ZgA/4/K542Y+xs6YmeX/36UHmtMPC0iMWvGxbZ7zzaoJ/p/++r8/OkHAiwnYLE0YmOVX6IIW+TuDA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T05:39:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aH+WjgJdqjQFuOUlc8x08BAA9K5KqAfwc/49/OeTLz4HRUaZIvXmSEey4BJpTCPhePieQC2cJmK1jdPUc9ZrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T00:26:14.068505Z"},"content_sha256":"5ad8553575732e3f2096d445d51c8d8dfb329510698c2903be53de3a904eac69","schema_version":"1.0","event_id":"sha256:5ad8553575732e3f2096d445d51c8d8dfb329510698c2903be53de3a904eac69"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:IR72YOXH32XCGIIWKMAHZMTZCR","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/DE-VLRN.2010.5578865) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Maya Cakmak and Andrea L. Thomaz. Optimal- ity of human teachers for robot learners. In2010 IEEE 9th International Conference on Development and Learning, pages 64–69, 2010.DOI: 10.1109/DE- VLRN.2010.5578865","arxiv_id":"2605.22986","detector":"doi_compliance","evidence":{"ref_index":16,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Maya Cakmak and Andrea L. Thomaz. Optimal- ity of human teachers for robot learners. In2010 IEEE 9th International Conference on Development and Learning, pages 64–69, 2010.DOI: 10.1109/DE- VLRN.2010.5578865","reconstructed_doi":"10.1109/DE-VLRN.2010.5578865"},"severity":"advisory","ref_index":16,"audited_at":"2026-05-25T05:39:07.482685Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/DE-VLRN.2010.5578865","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"ba8747e330dd6153e8244886491754387a58ea9f3a278c7ac0fbcabc53448f50","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":7466,"payload_sha256":"5a3af9f27a24c63e6649262e572d721bf8ce2969227e28677d5f3aa9112a8278","signature_b64":"dmNIonNIqOxaoU+PIty4/V0Qfjl+hP4IFWQ7tvNthVtJlxOs3fgFhwnrdt3m5rX3/bQRk7Ryr6Xf3EA9eoZdCw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T05:39:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"urp6jdYxcV9+V8uI7NPD9sF21Qow9SSPIEVT4Yf30kIr6G1Afrkx768Pdaor9ueeTI4O5P8upKTJaVt+HbEzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T00:26:14.069002Z"},"content_sha256":"e4ca629de816f6901154bf3e951a54f689c17239fa394f35e5f920e83b7369a3","schema_version":"1.0","event_id":"sha256:e4ca629de816f6901154bf3e951a54f689c17239fa394f35e5f920e83b7369a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IR72YOXH32XCGIIWKMAHZMTZCR/bundle.json","state_url":"https://pith.science/pith/IR72YOXH32XCGIIWKMAHZMTZCR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IR72YOXH32XCGIIWKMAHZMTZCR/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":"2026-05-27T00:26:14Z","links":{"resolver":"https://pith.science/pith/IR72YOXH32XCGIIWKMAHZMTZCR","bundle":"https://pith.science/pith/IR72YOXH32XCGIIWKMAHZMTZCR/bundle.json","state":"https://pith.science/pith/IR72YOXH32XCGIIWKMAHZMTZCR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IR72YOXH32XCGIIWKMAHZMTZCR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IR72YOXH32XCGIIWKMAHZMTZCR","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b5a5fc6889597550e058590aea3827fcabb4ed1cb0fab852c9a644a6986a0f88","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T19:34:14Z","title_canon_sha256":"e1bbf1056017fe0611250577c4913c9ce17a58df7fc09d575cbe839c28fef99c"},"schema_version":"1.0","source":{"id":"2605.22986","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22986","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22986v1","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22986","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"pith_short_12","alias_value":"IR72YOXH32XC","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"pith_short_16","alias_value":"IR72YOXH32XCGIIW","created_at":"2026-05-25T02:01:33Z"},{"alias_kind":"pith_short_8","alias_value":"IR72YOXH","created_at":"2026-05-25T02:01:33Z"}],"graph_snapshots":[{"event_id":"sha256:c9b87731fd998a8754ecdba5f4a9327fe8ee56a87978956a8922d09a0a366c9b","target":"graph","created_at":"2026-05-25T02:01:33Z","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/2605.22986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning reward functions from demonstrations assumes that demonstrations provide adequate supervision over all features -- or task-relevant aspects of behavior. In practice, demonstrations are often imperfect: humans may under-emphasize certain features due to cognitive load or physical difficulty, or the training regime may fail to sufficiently cover all relevant situations. In either case, important features may be underspecified, leading to ambiguity in the learned reward function and misaligned behavior at deployment. We propose a framework that detects such underspecified features and ac","authors_text":"Andreea Bobu, Helena Merker, Nick Walker","cross_cats":["cs.AI","cs.HC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T19:34:14Z","title":"Robots That Know What to Ask: Recovering Misaligned Rewards through Targeted Explanations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22986","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:e2750d56fcac9e89892ed37d739b89c62addd7f100786f33f9253cfe5899bbbc","target":"record","created_at":"2026-05-25T02:01:33Z","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":"b5a5fc6889597550e058590aea3827fcabb4ed1cb0fab852c9a644a6986a0f88","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T19:34:14Z","title_canon_sha256":"e1bbf1056017fe0611250577c4913c9ce17a58df7fc09d575cbe839c28fef99c"},"schema_version":"1.0","source":{"id":"2605.22986","kind":"arxiv","version":1}},"canonical_sha256":"447fac3ae7deae23211653007cb279144f2ca395bbcb352b137bcb483124ae00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"447fac3ae7deae23211653007cb279144f2ca395bbcb352b137bcb483124ae00","first_computed_at":"2026-05-25T02:01:33.292980Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:33.292980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wbTHS5jpV9+gtELec/S17Cf2I5UPVJlm3kepYbO0Hbccc0gM0w7jhDu3OGptgn+w87Jl72VTp0u7PxjJYTINAQ==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:33.293698Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22986","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:5ad8553575732e3f2096d445d51c8d8dfb329510698c2903be53de3a904eac69","sha256:e4ca629de816f6901154bf3e951a54f689c17239fa394f35e5f920e83b7369a3"]}],"invalid_events":[],"applied_event_ids":["sha256:e2750d56fcac9e89892ed37d739b89c62addd7f100786f33f9253cfe5899bbbc","sha256:c9b87731fd998a8754ecdba5f4a9327fe8ee56a87978956a8922d09a0a366c9b"],"state_sha256":"1e53767e6e8029223f0a34d2cefc89bc7e194c01a91c5c7987cb330b3cba3847"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7etW6oS5tjmt6TGr7ZTa0cgX4V6NSvLJK0de3OK+pUqF8ksK2GAQpGmeZiWzIYmChtg4K2uaVpC6BbhdopNqCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T00:26:14.073060Z","bundle_sha256":"58c4301fa446f44ec31d98ff032ae5c73cc0e3e970442af179763cdc44818c1a"}}