{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7SE4E5U5IPYF2QQ5WK4BE5ZU3Q","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":"efa5df24452797b320638ca9c768e8456b77f56f6984049e5da91cea903c8465","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-23T02:19:10Z","title_canon_sha256":"e8900bf64cc18104a95c0ff8a33bd33b25c6267756b7fd0f872ace2eaf256337"},"schema_version":"1.0","source":{"id":"2208.10687","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.10687","created_at":"2026-07-05T05:49:29Z"},{"alias_kind":"arxiv_version","alias_value":"2208.10687v2","created_at":"2026-07-05T05:49:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.10687","created_at":"2026-07-05T05:49:29Z"},{"alias_kind":"pith_short_12","alias_value":"7SE4E5U5IPYF","created_at":"2026-07-05T05:49:29Z"},{"alias_kind":"pith_short_16","alias_value":"7SE4E5U5IPYF2QQ5","created_at":"2026-07-05T05:49:29Z"},{"alias_kind":"pith_short_8","alias_value":"7SE4E5U5","created_at":"2026-07-05T05:49:29Z"}],"graph_snapshots":[{"event_id":"sha256:6b8f7953907a3e344e801c983d0d40b265cb484356d44cf6815c8385ef799946","target":"graph","created_at":"2026-07-05T05:49:29Z","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/2208.10687/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When inferring reward functions from human behavior (be it demonstrations, comparisons, physical corrections, or e-stops), it has proven useful to model the human as making noisy-rational choices, with a \"rationality coefficient\" capturing how much noise or entropy we expect to see in the human behavior. Prior work typically sets the rationality level to a constant value, regardless of the type, or quality, of human feedback. However, in many settings, giving one type of feedback (e.g. a demonstration) may be much more difficult than a different type of feedback (e.g. answering a comparison qu","authors_text":"Anca D. Dragan, Daniel S. Brown, Gaurav R. Ghosal, Matthew Zurek","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-23T02:19:10Z","title":"The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.10687","kind":"arxiv","version":2},"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":"sha256:3946338778461fd7796ca727b2e2c5bd2604fe497b3abbe348ce86bc1625199d","target":"record","created_at":"2026-07-05T05:49:29Z","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":"efa5df24452797b320638ca9c768e8456b77f56f6984049e5da91cea903c8465","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-23T02:19:10Z","title_canon_sha256":"e8900bf64cc18104a95c0ff8a33bd33b25c6267756b7fd0f872ace2eaf256337"},"schema_version":"1.0","source":{"id":"2208.10687","kind":"arxiv","version":2}},"canonical_sha256":"fc89c2769d43f05d421db2b8127734dc2626602068fd7aef8d5e4acf98fc0d4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc89c2769d43f05d421db2b8127734dc2626602068fd7aef8d5e4acf98fc0d4a","first_computed_at":"2026-07-05T05:49:29.641333Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:49:29.641333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4sbv6otV3wYJ0cELlOjj2QsEfs7DqLXOzfMDYq7j7KQgnL9nl7TnNlE7UwWOHXuzuLTs/olEE4F1X0zpeSm+CA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:49:29.641717Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.10687","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3946338778461fd7796ca727b2e2c5bd2604fe497b3abbe348ce86bc1625199d","sha256:6b8f7953907a3e344e801c983d0d40b265cb484356d44cf6815c8385ef799946"],"state_sha256":"7873a66d0f9ec25b383e06b40426e991e639d94c2d0034230bc8de652f033755"}