{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QJRZIRK4OXHDEFAQ4UE6Z562QI","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":"5f5f86b356be7717a87613262c4a3c0cd744400710856cb3cef4dd53f2e53cf3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T04:52:22Z","title_canon_sha256":"d476aa709e4d3da3b4b9f3f748fc16a44ff065cb891c56aeb55fccf1508117dc"},"schema_version":"1.0","source":{"id":"2410.22690","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22690","created_at":"2026-07-05T09:53:06Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22690v3","created_at":"2026-07-05T09:53:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22690","created_at":"2026-07-05T09:53:06Z"},{"alias_kind":"pith_short_12","alias_value":"QJRZIRK4OXHD","created_at":"2026-07-05T09:53:06Z"},{"alias_kind":"pith_short_16","alias_value":"QJRZIRK4OXHDEFAQ","created_at":"2026-07-05T09:53:06Z"},{"alias_kind":"pith_short_8","alias_value":"QJRZIRK4","created_at":"2026-07-05T09:53:06Z"}],"graph_snapshots":[{"event_id":"sha256:7a90f9a4f09bd0a45a3329b759d3f5898db92a9af8f5eabc465d9f8d88dc9685","target":"graph","created_at":"2026-07-05T09:53:06Z","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/2410.22690/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As AI agents generate increasingly sophisticated behaviors, manually encoding human preferences to guide these agents becomes more challenging. To address this, it has been suggested that agents instead learn preferences from human choice data. This approach requires a model of choice behavior that the agent can use to interpret the data. For choices between partial trajectories of states and actions, previous models assume choice probabilities are determined by the partial return or the cumulative advantage.\n  We consider an alternative model based instead on the bootstrapped return, which ad","authors_text":"Benjamin Van Roy, Henrik Marklund","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T04:52:22Z","title":"Choice Between Partial Trajectories: Disentangling Goals from Beliefs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22690","kind":"arxiv","version":3},"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":"sha256:02f25a06085713ed2236cff30d3ffe1970d3f33dd8cf3cd19b78e6887eff5c21","target":"record","created_at":"2026-07-05T09:53:06Z","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":"5f5f86b356be7717a87613262c4a3c0cd744400710856cb3cef4dd53f2e53cf3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T04:52:22Z","title_canon_sha256":"d476aa709e4d3da3b4b9f3f748fc16a44ff065cb891c56aeb55fccf1508117dc"},"schema_version":"1.0","source":{"id":"2410.22690","kind":"arxiv","version":3}},"canonical_sha256":"826394455c75ce321410e509ecf7da823aa7f72419baa36898667b93b26acb32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"826394455c75ce321410e509ecf7da823aa7f72419baa36898667b93b26acb32","first_computed_at":"2026-07-05T09:53:06.912112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:06.912112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i+0QUqWf/Y1x0CPmFC0THDX9CRlU1KEjdGJ67IlxjryakqRdftMqBajLAwx/J+Kaq5ecxajziPAOLGB1OGrrAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:06.912597Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.22690","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02f25a06085713ed2236cff30d3ffe1970d3f33dd8cf3cd19b78e6887eff5c21","sha256:7a90f9a4f09bd0a45a3329b759d3f5898db92a9af8f5eabc465d9f8d88dc9685"],"state_sha256":"3fa47142e825039179dfa0d1c31ee74083a25029f33c751bae0847a0dad9a6ea"}