{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z47JLLHC3ZD6WCCVJLLQKBNKF3","short_pith_number":"pith:Z47JLLHC","schema_version":"1.0","canonical_sha256":"cf3e95ace2de47eb08554ad70505aa2efb3d4a1449de083e483601282387f0cc","source":{"kind":"arxiv","id":"2403.06003","version":1},"attestation_state":"computed","paper":{"title":"A Generalized Acquisition Function for Preference-based Reward Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Anca Dragan, Erdem B{\\i}y{\\i}k, Evan Ellis, Gaurav R. Ghosal, Stuart J. Russell","submitted_at":"2024-03-09T20:32:17Z","abstract_excerpt":"Preference-based reward learning is a popular technique for teaching robots and autonomous systems how a human user wants them to perform a task. Previous works have shown that actively synthesizing preference queries to maximize information gain about the reward function parameters improves data efficiency. The information gain criterion focuses on precisely identifying all parameters of the reward function. This can potentially be wasteful as many parameters may result in the same reward, and many rewards may result in the same behavior in the downstream tasks. Instead, we show that it is po"},"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":"2403.06003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-09T20:32:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4f65393a7e8ed880ac7cb478177281729c119968d06cb81ee4de60638024d1e0","abstract_canon_sha256":"47b997533990ad9498aa2ee0b96a08801ad2f5aeda3542ceec72942d1c9c358a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:16.703781Z","signature_b64":"D+4VCF+isp+iak+YyhZRVFdYtAnsmomCFBO/gZQ/i84b9sNpqm7I+ihA5CXNloenI3atuAP5orvj2pkHCF+FCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf3e95ace2de47eb08554ad70505aa2efb3d4a1449de083e483601282387f0cc","last_reissued_at":"2026-07-05T07:54:16.703411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:16.703411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Generalized Acquisition Function for Preference-based Reward Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Anca Dragan, Erdem B{\\i}y{\\i}k, Evan Ellis, Gaurav R. Ghosal, Stuart J. Russell","submitted_at":"2024-03-09T20:32:17Z","abstract_excerpt":"Preference-based reward learning is a popular technique for teaching robots and autonomous systems how a human user wants them to perform a task. Previous works have shown that actively synthesizing preference queries to maximize information gain about the reward function parameters improves data efficiency. The information gain criterion focuses on precisely identifying all parameters of the reward function. This can potentially be wasteful as many parameters may result in the same reward, and many rewards may result in the same behavior in the downstream tasks. Instead, we show that it is po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06003","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/2403.06003/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":"2403.06003","created_at":"2026-07-05T07:54:16.703464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06003v1","created_at":"2026-07-05T07:54:16.703464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06003","created_at":"2026-07-05T07:54:16.703464+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z47JLLHC3ZD6","created_at":"2026-07-05T07:54:16.703464+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z47JLLHC3ZD6WCCV","created_at":"2026-07-05T07:54:16.703464+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z47JLLHC","created_at":"2026-07-05T07:54:16.703464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z47JLLHC3ZD6WCCVJLLQKBNKF3","json":"https://pith.science/pith/Z47JLLHC3ZD6WCCVJLLQKBNKF3.json","graph_json":"https://pith.science/api/pith-number/Z47JLLHC3ZD6WCCVJLLQKBNKF3/graph.json","events_json":"https://pith.science/api/pith-number/Z47JLLHC3ZD6WCCVJLLQKBNKF3/events.json","paper":"https://pith.science/paper/Z47JLLHC"},"agent_actions":{"view_html":"https://pith.science/pith/Z47JLLHC3ZD6WCCVJLLQKBNKF3","download_json":"https://pith.science/pith/Z47JLLHC3ZD6WCCVJLLQKBNKF3.json","view_paper":"https://pith.science/paper/Z47JLLHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06003&json=true","fetch_graph":"https://pith.science/api/pith-number/Z47JLLHC3ZD6WCCVJLLQKBNKF3/graph.json","fetch_events":"https://pith.science/api/pith-number/Z47JLLHC3ZD6WCCVJLLQKBNKF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z47JLLHC3ZD6WCCVJLLQKBNKF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z47JLLHC3ZD6WCCVJLLQKBNKF3/action/storage_attestation","attest_author":"https://pith.science/pith/Z47JLLHC3ZD6WCCVJLLQKBNKF3/action/author_attestation","sign_citation":"https://pith.science/pith/Z47JLLHC3ZD6WCCVJLLQKBNKF3/action/citation_signature","submit_replication":"https://pith.science/pith/Z47JLLHC3ZD6WCCVJLLQKBNKF3/action/replication_record"}},"created_at":"2026-07-05T07:54:16.703464+00:00","updated_at":"2026-07-05T07:54:16.703464+00:00"}