{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GAHHQY7LQVBNZMQLOYVFSJ2EBO","short_pith_number":"pith:GAHHQY7L","schema_version":"1.0","canonical_sha256":"300e7863eb8542dcb20b762a5927440bacbc6df51e610124fa321343bec4639b","source":{"kind":"arxiv","id":"2101.07691","version":1},"attestation_state":"computed","paper":{"title":"Choice Set Misspecification in Reward Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Anca Dragan, Rachel Freedman, Rohin Shah","submitted_at":"2021-01-19T15:35:30Z","abstract_excerpt":"Specifying reward functions for robots that operate in environments without a natural reward signal can be challenging, and incorrectly specified rewards can incentivise degenerate or dangerous behavior. A promising alternative to manually specifying reward functions is to enable robots to infer them from human feedback, like demonstrations or corrections. To interpret this feedback, robots treat as approximately optimal a choice the person makes from a choice set, like the set of possible trajectories they could have demonstrated or possible corrections they could have made. In this work, we "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2101.07691","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-01-19T15:35:30Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"1ada033e0435055f548a74064cead67beaf8f00a54744a42613af71320d0de2a","abstract_canon_sha256":"135b41ee861dde7c68b561e71fd0b225871891e7d917bc0e1428b121ed17dfae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:08:00.329114Z","signature_b64":"MRQgvNcVm6VP/EGkNYIX68Cy9mn/PN8feRtl35Tgfyxokg+sdArnqf/Hi8jg+/55Q9exums+P6SekcOm+8hhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"300e7863eb8542dcb20b762a5927440bacbc6df51e610124fa321343bec4639b","last_reissued_at":"2026-07-05T02:08:00.328648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:08:00.328648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Choice Set Misspecification in Reward Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Anca Dragan, Rachel Freedman, Rohin Shah","submitted_at":"2021-01-19T15:35:30Z","abstract_excerpt":"Specifying reward functions for robots that operate in environments without a natural reward signal can be challenging, and incorrectly specified rewards can incentivise degenerate or dangerous behavior. A promising alternative to manually specifying reward functions is to enable robots to infer them from human feedback, like demonstrations or corrections. To interpret this feedback, robots treat as approximately optimal a choice the person makes from a choice set, like the set of possible trajectories they could have demonstrated or possible corrections they could have made. In this work, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.07691","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/2101.07691/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2101.07691","created_at":"2026-07-05T02:08:00.328718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.07691v1","created_at":"2026-07-05T02:08:00.328718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.07691","created_at":"2026-07-05T02:08:00.328718+00:00"},{"alias_kind":"pith_short_12","alias_value":"GAHHQY7LQVBN","created_at":"2026-07-05T02:08:00.328718+00:00"},{"alias_kind":"pith_short_16","alias_value":"GAHHQY7LQVBNZMQL","created_at":"2026-07-05T02:08:00.328718+00:00"},{"alias_kind":"pith_short_8","alias_value":"GAHHQY7L","created_at":"2026-07-05T02:08:00.328718+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.15288","citing_title":"Active teacher selection for reward learning","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GAHHQY7LQVBNZMQLOYVFSJ2EBO","json":"https://pith.science/pith/GAHHQY7LQVBNZMQLOYVFSJ2EBO.json","graph_json":"https://pith.science/api/pith-number/GAHHQY7LQVBNZMQLOYVFSJ2EBO/graph.json","events_json":"https://pith.science/api/pith-number/GAHHQY7LQVBNZMQLOYVFSJ2EBO/events.json","paper":"https://pith.science/paper/GAHHQY7L"},"agent_actions":{"view_html":"https://pith.science/pith/GAHHQY7LQVBNZMQLOYVFSJ2EBO","download_json":"https://pith.science/pith/GAHHQY7LQVBNZMQLOYVFSJ2EBO.json","view_paper":"https://pith.science/paper/GAHHQY7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.07691&json=true","fetch_graph":"https://pith.science/api/pith-number/GAHHQY7LQVBNZMQLOYVFSJ2EBO/graph.json","fetch_events":"https://pith.science/api/pith-number/GAHHQY7LQVBNZMQLOYVFSJ2EBO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GAHHQY7LQVBNZMQLOYVFSJ2EBO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GAHHQY7LQVBNZMQLOYVFSJ2EBO/action/storage_attestation","attest_author":"https://pith.science/pith/GAHHQY7LQVBNZMQLOYVFSJ2EBO/action/author_attestation","sign_citation":"https://pith.science/pith/GAHHQY7LQVBNZMQLOYVFSJ2EBO/action/citation_signature","submit_replication":"https://pith.science/pith/GAHHQY7LQVBNZMQLOYVFSJ2EBO/action/replication_record"}},"created_at":"2026-07-05T02:08:00.328718+00:00","updated_at":"2026-07-05T02:08:00.328718+00:00"}