{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WPPVX4YI7CE6SHPVPH7B2PMEA7","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":"6b0087dc40ba152e9bdb003ff46925a5a5fbe4075bc4c62a21014694cba48d1a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-10T13:59:50Z","title_canon_sha256":"4e9420601e7334c01043358ee4a31cae7ee80a6c0cc09ec9a53300e6210de8cc"},"schema_version":"1.0","source":{"id":"2603.09692","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.09692","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2603.09692v2","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.09692","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"WPPVX4YI7CE6","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"WPPVX4YI7CE6SHPV","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"WPPVX4YI","created_at":"2026-06-02T02:04:52Z"}],"graph_snapshots":[{"event_id":"sha256:5fec47d7379ca740edb0d2d4f0e319414b7f62010b9741b3fcc1f00ae158e09c","target":"graph","created_at":"2026-06-02T02:04:52Z","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/2603.09692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) has become the standard for aligning Large Language Models (LLMs), yet its efficacy is bottlenecked by the high cost of acquiring preference data, especially in low-resource and expert domains. To address this, we introduce ACTIVEULTRAFEEDBACK, a modular active learning pipeline that leverages uncertainty estimates to dynamically identify the most informative responses for annotation. Our pipeline facilitates the systematic evaluation of standard response selection methods alongside DOUBLE REVERSE THOMPSON SAMPLING (DRTS) and DELTAUCB, two nove","authors_text":"Andreas Krause, Barna P\\'asztor, Davit Melikidze, Ido Hakimi, Jessica Lam, Marian Schneider, Martin Wertich","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-10T13:59:50Z","title":"ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.09692","kind":"arxiv","version":2},"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:c1dbd38489f0ef2e8ed9bc8444be4932b3e27c9aceffe4cc4c2de1871fabf4bb","target":"record","created_at":"2026-06-02T02:04:52Z","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":"6b0087dc40ba152e9bdb003ff46925a5a5fbe4075bc4c62a21014694cba48d1a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-10T13:59:50Z","title_canon_sha256":"4e9420601e7334c01043358ee4a31cae7ee80a6c0cc09ec9a53300e6210de8cc"},"schema_version":"1.0","source":{"id":"2603.09692","kind":"arxiv","version":2}},"canonical_sha256":"b3df5bf308f889e91df579fe1d3d8407fa18f406d74bb316ecc22ad854e1aa87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3df5bf308f889e91df579fe1d3d8407fa18f406d74bb316ecc22ad854e1aa87","first_computed_at":"2026-06-02T02:04:52.216220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:52.216220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5uIbD+4y5un+CBy9JxASeuNsNt07ERc1CFr7OnQy6uOpIpE9NvFBQrDxXxcQy24f/2kPhBwjThU6U3vgGyRHDg==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:52.216681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.09692","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1dbd38489f0ef2e8ed9bc8444be4932b3e27c9aceffe4cc4c2de1871fabf4bb","sha256:5fec47d7379ca740edb0d2d4f0e319414b7f62010b9741b3fcc1f00ae158e09c"],"state_sha256":"a2a3acc464673f2407ccf18c82834d3ea5d49510d1c3b361a9d1e3f952dddb5f"}