{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4P5XPPGT34NNX4JBXIBDBAJTEE","short_pith_number":"pith:4P5XPPGT","canonical_record":{"source":{"id":"2506.01692","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-02T13:52:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6a10ee1a862147779c215bc17d93c904d2a67102d9bedd5baa08742cf9dd9426","abstract_canon_sha256":"addf39ec5673ddb5ee455b4a182d6c94da62873a50ec90ca99c7c1509b12055c"},"schema_version":"1.0"},"canonical_sha256":"e3fb77bcd3df1adbf121ba023081332135e43686821e54f8e4b9c8adc4485bd2","source":{"kind":"arxiv","id":"2506.01692","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01692","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01692v1","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01692","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"pith_short_12","alias_value":"4P5XPPGT34NN","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"pith_short_16","alias_value":"4P5XPPGT34NNX4JB","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"pith_short_8","alias_value":"4P5XPPGT","created_at":"2026-07-05T11:14:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4P5XPPGT34NNX4JBXIBDBAJTEE","target":"record","payload":{"canonical_record":{"source":{"id":"2506.01692","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-02T13:52:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6a10ee1a862147779c215bc17d93c904d2a67102d9bedd5baa08742cf9dd9426","abstract_canon_sha256":"addf39ec5673ddb5ee455b4a182d6c94da62873a50ec90ca99c7c1509b12055c"},"schema_version":"1.0"},"canonical_sha256":"e3fb77bcd3df1adbf121ba023081332135e43686821e54f8e4b9c8adc4485bd2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:17.971374Z","signature_b64":"hgoPxfNaGcsvHEKURfZc5YeM52j9ZUgDPSfPKMkkEjksmJIDsaMevqSXF9V+Uid1+VaX8xttWTEXlgTnW/NUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3fb77bcd3df1adbf121ba023081332135e43686821e54f8e4b9c8adc4485bd2","last_reissued_at":"2026-07-05T11:14:17.970897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:17.970897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.01692","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":"2026-07-05T11:14:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xaVHsa9tWfcRzl5nMsG6StbZm2lAGeyse0M/8WO/mZWref1S5VOJiXXW5NaaTraTj94vdOmDnZFPoi20h6UiBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:54:08.243724Z"},"content_sha256":"3fd79a6b5465b8292f252a4e597d23072ac2a1b432f44f0570f030c4f5a2624f","schema_version":"1.0","event_id":"sha256:3fd79a6b5465b8292f252a4e597d23072ac2a1b432f44f0570f030c4f5a2624f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4P5XPPGT34NNX4JBXIBDBAJTEE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Descriptive and Normative Theory of Human Beliefs in RLHF","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Frank Chiu, Scott Niekum, Shripad Deshmukh, Sylee Dandekar, W. Bradley Knox","submitted_at":"2025-06-02T13:52:55Z","abstract_excerpt":"Human preferences in RLHF are typically modeled as a function of the human's reward function or corresponding optimal state-action values. In this work, we propose that human beliefs about the capabilities of the agent being trained also play a key role in preference generation. We examine two questions related to this hypothesis, one descriptive and one normative, respectively: Do human labelers' beliefs about agent capabilities affect the preferences that they provide? And what is the ideal set of beliefs about an agent -- and resulting preferences -- for humans to have? We propose a new pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01692","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/2506.01692/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":"2026-07-05T11:14:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mRZp+HtuXkVPp6Y4nYef/BYfb0yxgRfgb3ZFxqxmi0WgH+zu+6aXEBNmIvAzZT6KatafRhVOHkuvtdkmT1v4BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:54:08.244498Z"},"content_sha256":"a4eab5a3c7d7a3950f0a79b6cfe18300d0e8325ed71ca04144008d16ed814213","schema_version":"1.0","event_id":"sha256:a4eab5a3c7d7a3950f0a79b6cfe18300d0e8325ed71ca04144008d16ed814213"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4P5XPPGT34NNX4JBXIBDBAJTEE/bundle.json","state_url":"https://pith.science/pith/4P5XPPGT34NNX4JBXIBDBAJTEE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4P5XPPGT34NNX4JBXIBDBAJTEE/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":"2026-08-08T11:54:08Z","links":{"resolver":"https://pith.science/pith/4P5XPPGT34NNX4JBXIBDBAJTEE","bundle":"https://pith.science/pith/4P5XPPGT34NNX4JBXIBDBAJTEE/bundle.json","state":"https://pith.science/pith/4P5XPPGT34NNX4JBXIBDBAJTEE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4P5XPPGT34NNX4JBXIBDBAJTEE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4P5XPPGT34NNX4JBXIBDBAJTEE","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":"addf39ec5673ddb5ee455b4a182d6c94da62873a50ec90ca99c7c1509b12055c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-02T13:52:55Z","title_canon_sha256":"6a10ee1a862147779c215bc17d93c904d2a67102d9bedd5baa08742cf9dd9426"},"schema_version":"1.0","source":{"id":"2506.01692","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01692","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01692v1","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01692","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"pith_short_12","alias_value":"4P5XPPGT34NN","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"pith_short_16","alias_value":"4P5XPPGT34NNX4JB","created_at":"2026-07-05T11:14:17Z"},{"alias_kind":"pith_short_8","alias_value":"4P5XPPGT","created_at":"2026-07-05T11:14:17Z"}],"graph_snapshots":[{"event_id":"sha256:a4eab5a3c7d7a3950f0a79b6cfe18300d0e8325ed71ca04144008d16ed814213","target":"graph","created_at":"2026-07-05T11:14:17Z","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/2506.01692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human preferences in RLHF are typically modeled as a function of the human's reward function or corresponding optimal state-action values. In this work, we propose that human beliefs about the capabilities of the agent being trained also play a key role in preference generation. We examine two questions related to this hypothesis, one descriptive and one normative, respectively: Do human labelers' beliefs about agent capabilities affect the preferences that they provide? And what is the ideal set of beliefs about an agent -- and resulting preferences -- for humans to have? We propose a new pre","authors_text":"Frank Chiu, Scott Niekum, Shripad Deshmukh, Sylee Dandekar, W. Bradley Knox","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-02T13:52:55Z","title":"A Descriptive and Normative Theory of Human Beliefs in RLHF"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01692","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":"sha256:3fd79a6b5465b8292f252a4e597d23072ac2a1b432f44f0570f030c4f5a2624f","target":"record","created_at":"2026-07-05T11:14:17Z","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":"addf39ec5673ddb5ee455b4a182d6c94da62873a50ec90ca99c7c1509b12055c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-02T13:52:55Z","title_canon_sha256":"6a10ee1a862147779c215bc17d93c904d2a67102d9bedd5baa08742cf9dd9426"},"schema_version":"1.0","source":{"id":"2506.01692","kind":"arxiv","version":1}},"canonical_sha256":"e3fb77bcd3df1adbf121ba023081332135e43686821e54f8e4b9c8adc4485bd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3fb77bcd3df1adbf121ba023081332135e43686821e54f8e4b9c8adc4485bd2","first_computed_at":"2026-07-05T11:14:17.970897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:17.970897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hgoPxfNaGcsvHEKURfZc5YeM52j9ZUgDPSfPKMkkEjksmJIDsaMevqSXF9V+Uid1+VaX8xttWTEXlgTnW/NUCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:17.971374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01692","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fd79a6b5465b8292f252a4e597d23072ac2a1b432f44f0570f030c4f5a2624f","sha256:a4eab5a3c7d7a3950f0a79b6cfe18300d0e8325ed71ca04144008d16ed814213"],"state_sha256":"9e72620af941f83ce92bb9f143faaeaf0651bc504ca2e276ade883511506c07d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gEsXCbebUxk4rJZX1kAZcNin2Y/FaoBgb5uqIc+68taMcfzJxSSfPXTPfdUo9LHcaZcCus2fm6OGROdSsPGJCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:54:08.249843Z","bundle_sha256":"72ade6771322137639f25bd5260ed92b2e8ef34941be77e4ea0dfebec9369e84"}}