{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:73LAUBWKU2VLAS6MQ3RIU3PBJL","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":"2be02e1837b0d7616845fd1fd8a56f16eb1e152c0f2f6a590e189e02c0606b50","cross_cats_sorted":["cs.AI","cs.IT","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-27T01:10:17Z","title_canon_sha256":"11e9833cc3d27161f96640f28c438d7a27251401caa9b48fe8700549c3480bc8"},"schema_version":"1.0","source":{"id":"2412.19396","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19396","created_at":"2026-07-05T09:54:34Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19396v1","created_at":"2026-07-05T09:54:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19396","created_at":"2026-07-05T09:54:34Z"},{"alias_kind":"pith_short_12","alias_value":"73LAUBWKU2VL","created_at":"2026-07-05T09:54:34Z"},{"alias_kind":"pith_short_16","alias_value":"73LAUBWKU2VLAS6M","created_at":"2026-07-05T09:54:34Z"},{"alias_kind":"pith_short_8","alias_value":"73LAUBWK","created_at":"2026-07-05T09:54:34Z"}],"graph_snapshots":[{"event_id":"sha256:f644627d12de1e18e8f772c46bc374e1d0855e6e52b57d899145044992ca20fe","target":"graph","created_at":"2026-07-05T09:54:34Z","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/2412.19396/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study learning of human preferences from a limited comparison feedback. This task is ubiquitous in machine learning. Its applications such as reinforcement learning from human feedback, have been transformational. We formulate this problem as learning a Plackett-Luce model over a universe of $N$ choices from $K$-way comparison feedback, where typically $K \\ll N$. Our solution is the D-optimal design for the Plackett-Luce objective. The design defines a data logging policy that elicits comparison feedback for a small collection of optimally chosen points from all ${N \\choose K}$ feasible sub","authors_text":"Branislav Kveton, Gaurush Hiranandani, Kiran Koshy Thekumparampil, Kousha Kalantari, Shoham Sabach","cross_cats":["cs.AI","cs.IT","math.IT","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-27T01:10:17Z","title":"Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19396","kind":"arxiv","version":1},"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":"sha256:34056b3a2579b9674c3b044408557cd145dfffbc31c40eccb4abf8131185f054","target":"record","created_at":"2026-07-05T09:54:34Z","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":"2be02e1837b0d7616845fd1fd8a56f16eb1e152c0f2f6a590e189e02c0606b50","cross_cats_sorted":["cs.AI","cs.IT","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-27T01:10:17Z","title_canon_sha256":"11e9833cc3d27161f96640f28c438d7a27251401caa9b48fe8700549c3480bc8"},"schema_version":"1.0","source":{"id":"2412.19396","kind":"arxiv","version":1}},"canonical_sha256":"fed60a06caa6aab04bcc86e28a6de14ade16c85c3e3c0e753cf77e70d0749f89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fed60a06caa6aab04bcc86e28a6de14ade16c85c3e3c0e753cf77e70d0749f89","first_computed_at":"2026-07-05T09:54:34.917835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:34.917835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I7jzPD1h7npOyL1L/+ls//OO5w+pGLvVDGzfjGlnfNNh9aaLN/XAXtiwcz75YNu/zWq+uAaCA2uSE4cdQnqZAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:34.918338Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19396","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34056b3a2579b9674c3b044408557cd145dfffbc31c40eccb4abf8131185f054","sha256:f644627d12de1e18e8f772c46bc374e1d0855e6e52b57d899145044992ca20fe"],"state_sha256":"c82641e761922e1fdc520f3f1a6b53d25398b1cf99400ca8ab148b9a287bd131"}