{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GTA2XHGD4ZXVWI63PGR5ADNTKO","short_pith_number":"pith:GTA2XHGD","schema_version":"1.0","canonical_sha256":"34c1ab9cc3e66f5b23db79a3d00db35394b1f23b9cd8043143236ff4008e2a5a","source":{"kind":"arxiv","id":"2308.04571","version":1},"attestation_state":"computed","paper":{"title":"Optimizing Algorithms From Pairwise User Preferences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.HC"],"primary_cat":"cs.RO","authors_text":"Aaron Steinfeld, Katherine Shih, Leonid Keselman, Martial Hebert","submitted_at":"2023-08-08T20:36:59Z","abstract_excerpt":"Typical black-box optimization approaches in robotics focus on learning from metric scores. However, that is not always possible, as not all developers have ground truth available. Learning appropriate robot behavior in human-centric contexts often requires querying users, who typically cannot provide precise metric scores. Existing approaches leverage human feedback in an attempt to model an implicit reward function; however, this reward may be difficult or impossible to effectively capture. In this work, we introduce SortCMA to optimize algorithm parameter configurations in high dimensions b"},"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":"2308.04571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-08-08T20:36:59Z","cross_cats_sorted":["cs.CV","cs.HC"],"title_canon_sha256":"1449ea49fe6e7af60717a5676036b1c55eee71c707f94ef13e2661af48df8bbb","abstract_canon_sha256":"63cdf6f35c00e05ad92fb4574d4effdd67efadff880d17c4fce8661cd21ff556"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:39.660811Z","signature_b64":"ZMFRo8YoWtq8gX6Ynd4r6ASVu9RyXW5yfrTaxwbyeUApfU9/P9ONItiW0IDWqJsWZbbiwjNNZRmkDpNGOQUrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34c1ab9cc3e66f5b23db79a3d00db35394b1f23b9cd8043143236ff4008e2a5a","last_reissued_at":"2026-07-05T06:39:39.660321Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:39.660321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Algorithms From Pairwise User Preferences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.HC"],"primary_cat":"cs.RO","authors_text":"Aaron Steinfeld, Katherine Shih, Leonid Keselman, Martial Hebert","submitted_at":"2023-08-08T20:36:59Z","abstract_excerpt":"Typical black-box optimization approaches in robotics focus on learning from metric scores. However, that is not always possible, as not all developers have ground truth available. Learning appropriate robot behavior in human-centric contexts often requires querying users, who typically cannot provide precise metric scores. Existing approaches leverage human feedback in an attempt to model an implicit reward function; however, this reward may be difficult or impossible to effectively capture. In this work, we introduce SortCMA to optimize algorithm parameter configurations in high dimensions b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04571","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/2308.04571/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":"2308.04571","created_at":"2026-07-05T06:39:39.660380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.04571v1","created_at":"2026-07-05T06:39:39.660380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04571","created_at":"2026-07-05T06:39:39.660380+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTA2XHGD4ZXV","created_at":"2026-07-05T06:39:39.660380+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTA2XHGD4ZXVWI63","created_at":"2026-07-05T06:39:39.660380+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTA2XHGD","created_at":"2026-07-05T06:39:39.660380+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11999","citing_title":"Generative Representational Learning of Foundation Models for Recommendation","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GTA2XHGD4ZXVWI63PGR5ADNTKO","json":"https://pith.science/pith/GTA2XHGD4ZXVWI63PGR5ADNTKO.json","graph_json":"https://pith.science/api/pith-number/GTA2XHGD4ZXVWI63PGR5ADNTKO/graph.json","events_json":"https://pith.science/api/pith-number/GTA2XHGD4ZXVWI63PGR5ADNTKO/events.json","paper":"https://pith.science/paper/GTA2XHGD"},"agent_actions":{"view_html":"https://pith.science/pith/GTA2XHGD4ZXVWI63PGR5ADNTKO","download_json":"https://pith.science/pith/GTA2XHGD4ZXVWI63PGR5ADNTKO.json","view_paper":"https://pith.science/paper/GTA2XHGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.04571&json=true","fetch_graph":"https://pith.science/api/pith-number/GTA2XHGD4ZXVWI63PGR5ADNTKO/graph.json","fetch_events":"https://pith.science/api/pith-number/GTA2XHGD4ZXVWI63PGR5ADNTKO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTA2XHGD4ZXVWI63PGR5ADNTKO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTA2XHGD4ZXVWI63PGR5ADNTKO/action/storage_attestation","attest_author":"https://pith.science/pith/GTA2XHGD4ZXVWI63PGR5ADNTKO/action/author_attestation","sign_citation":"https://pith.science/pith/GTA2XHGD4ZXVWI63PGR5ADNTKO/action/citation_signature","submit_replication":"https://pith.science/pith/GTA2XHGD4ZXVWI63PGR5ADNTKO/action/replication_record"}},"created_at":"2026-07-05T06:39:39.660380+00:00","updated_at":"2026-07-05T06:39:39.660380+00:00"}