{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:AMR57NMKLUMT3T6BYJV574Y2LK","short_pith_number":"pith:AMR57NMK","canonical_record":{"source":{"id":"2212.04717","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-09T08:16:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"10c3786c9de88b3e9f5bff0cb26565006c5f08b2364ddc5d9ed0addaf08bda90","abstract_canon_sha256":"9e57117cffa71e4ac53e0968467150becb8da4941c59dc6cff7c98dbfdf5ecc0"},"schema_version":"1.0"},"canonical_sha256":"0323dfb58a5d193dcfc1c26bdff31a5a8a5e9e40ecff49a3f4ed76810eba26a0","source":{"kind":"arxiv","id":"2212.04717","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.04717","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"2212.04717v2","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04717","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"AMR57NMKLUMT","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"pith_short_16","alias_value":"AMR57NMKLUMT3T6B","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"pith_short_8","alias_value":"AMR57NMK","created_at":"2026-07-05T07:06:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:AMR57NMKLUMT3T6BYJV574Y2LK","target":"record","payload":{"canonical_record":{"source":{"id":"2212.04717","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-09T08:16:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"10c3786c9de88b3e9f5bff0cb26565006c5f08b2364ddc5d9ed0addaf08bda90","abstract_canon_sha256":"9e57117cffa71e4ac53e0968467150becb8da4941c59dc6cff7c98dbfdf5ecc0"},"schema_version":"1.0"},"canonical_sha256":"0323dfb58a5d193dcfc1c26bdff31a5a8a5e9e40ecff49a3f4ed76810eba26a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:21.750230Z","signature_b64":"Gr8mCCOHzZWCgCDU4cIBQgmkkfHSpX6sLii/WvVGeMhU/Zhu5cwoJogJAH5kNZo/9LwrukZYDWEU+pTQoOJQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0323dfb58a5d193dcfc1c26bdff31a5a8a5e9e40ecff49a3f4ed76810eba26a0","last_reissued_at":"2026-07-05T07:06:21.749799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:21.749799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.04717","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"73q1AD+j2pppyyEKFaBuqqSeX6G/nvnkZtrE6KW6mQD/GOEUDX5iQBCOiHsRdSOW2y49mx4XtxKmbRokJzlQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:22:02.273007Z"},"content_sha256":"866bc74759a52cedbd4f48dc1f880238310d338c560ca59cc8c6d18758397e07","schema_version":"1.0","event_id":"sha256:866bc74759a52cedbd4f48dc1f880238310d338c560ca59cc8c6d18758397e07"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:AMR57NMKLUMT3T6BYJV574Y2LK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Sensitivity of Reward Inference to Misspecified Human Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anca Dragan, Joey Hong, Kush Bhatia","submitted_at":"2022-12-09T08:16:20Z","abstract_excerpt":"Inferring reward functions from human behavior is at the center of value alignment - aligning AI objectives with what we, humans, actually want. But doing so relies on models of how humans behave given their objectives. After decades of research in cognitive science, neuroscience, and behavioral economics, obtaining accurate human models remains an open research topic. This begs the question: how accurate do these models need to be in order for the reward inference to be accurate? On the one hand, if small errors in the model can lead to catastrophic error in inference, the entire framework of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04717","kind":"arxiv","version":2},"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/2212.04717/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":"2026-07-05T07:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hFbfCCXz2fuKwVSFHh2DALsJt+2iZVpopvl3PeoebVKfAD6DW1O7DMPYy9GEikgHLYyTkM9S7qmNoEfvoqdJDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:22:02.273952Z"},"content_sha256":"4310f9962c614dcfeeeec1a8c55ae733bb55892e90f8906b3a3968a493b9fdd7","schema_version":"1.0","event_id":"sha256:4310f9962c614dcfeeeec1a8c55ae733bb55892e90f8906b3a3968a493b9fdd7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AMR57NMKLUMT3T6BYJV574Y2LK/bundle.json","state_url":"https://pith.science/pith/AMR57NMKLUMT3T6BYJV574Y2LK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AMR57NMKLUMT3T6BYJV574Y2LK/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":"2026-08-11T08:22:02Z","links":{"resolver":"https://pith.science/pith/AMR57NMKLUMT3T6BYJV574Y2LK","bundle":"https://pith.science/pith/AMR57NMKLUMT3T6BYJV574Y2LK/bundle.json","state":"https://pith.science/pith/AMR57NMKLUMT3T6BYJV574Y2LK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AMR57NMKLUMT3T6BYJV574Y2LK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AMR57NMKLUMT3T6BYJV574Y2LK","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":"9e57117cffa71e4ac53e0968467150becb8da4941c59dc6cff7c98dbfdf5ecc0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-09T08:16:20Z","title_canon_sha256":"10c3786c9de88b3e9f5bff0cb26565006c5f08b2364ddc5d9ed0addaf08bda90"},"schema_version":"1.0","source":{"id":"2212.04717","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.04717","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"2212.04717v2","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04717","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"AMR57NMKLUMT","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"pith_short_16","alias_value":"AMR57NMKLUMT3T6B","created_at":"2026-07-05T07:06:21Z"},{"alias_kind":"pith_short_8","alias_value":"AMR57NMK","created_at":"2026-07-05T07:06:21Z"}],"graph_snapshots":[{"event_id":"sha256:4310f9962c614dcfeeeec1a8c55ae733bb55892e90f8906b3a3968a493b9fdd7","target":"graph","created_at":"2026-07-05T07:06:21Z","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/2212.04717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inferring reward functions from human behavior is at the center of value alignment - aligning AI objectives with what we, humans, actually want. But doing so relies on models of how humans behave given their objectives. After decades of research in cognitive science, neuroscience, and behavioral economics, obtaining accurate human models remains an open research topic. This begs the question: how accurate do these models need to be in order for the reward inference to be accurate? On the one hand, if small errors in the model can lead to catastrophic error in inference, the entire framework of","authors_text":"Anca Dragan, Joey Hong, Kush Bhatia","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-09T08:16:20Z","title":"On the Sensitivity of Reward Inference to Misspecified Human Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04717","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":"sha256:866bc74759a52cedbd4f48dc1f880238310d338c560ca59cc8c6d18758397e07","target":"record","created_at":"2026-07-05T07:06:21Z","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":"9e57117cffa71e4ac53e0968467150becb8da4941c59dc6cff7c98dbfdf5ecc0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-09T08:16:20Z","title_canon_sha256":"10c3786c9de88b3e9f5bff0cb26565006c5f08b2364ddc5d9ed0addaf08bda90"},"schema_version":"1.0","source":{"id":"2212.04717","kind":"arxiv","version":2}},"canonical_sha256":"0323dfb58a5d193dcfc1c26bdff31a5a8a5e9e40ecff49a3f4ed76810eba26a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0323dfb58a5d193dcfc1c26bdff31a5a8a5e9e40ecff49a3f4ed76810eba26a0","first_computed_at":"2026-07-05T07:06:21.749799Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:21.749799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gr8mCCOHzZWCgCDU4cIBQgmkkfHSpX6sLii/WvVGeMhU/Zhu5cwoJogJAH5kNZo/9LwrukZYDWEU+pTQoOJQAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:21.750230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.04717","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:866bc74759a52cedbd4f48dc1f880238310d338c560ca59cc8c6d18758397e07","sha256:4310f9962c614dcfeeeec1a8c55ae733bb55892e90f8906b3a3968a493b9fdd7"],"state_sha256":"755b050b89552fbc022831ca5916c91925905e16765553d031b18f53f41f5f95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"amcGj6Fwhzato8omrAWHCQ+b56NF9EAlxY+LBNqDlHfqnljkHUJXoUeodo7sky316mPCFZfzTFJGWYVaVyuqAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T08:22:02.280849Z","bundle_sha256":"e2b671163c70bd8c915c755aee46bd6c5fd004d1f977caf253559b52128bae70"}}