{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KG3JFTDVGGHQP7D4727O3ITZ7F","short_pith_number":"pith:KG3JFTDV","schema_version":"1.0","canonical_sha256":"51b692cc75318f07fc7cfebeeda279f946f58ac206fc5314f10706d95139b497","source":{"kind":"arxiv","id":"2402.10500","version":3},"attestation_state":"computed","paper":{"title":"Active Preference Optimization for Sample Efficient RLHF","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Nirjhar Das, Sayak Ray Chowdhury, Souradip Chakraborty","submitted_at":"2024-02-16T08:19:34Z","abstract_excerpt":"Large Language Models (LLMs) aligned using Reinforcement Learning from Human Feedback (RLHF) have shown remarkable generation abilities in numerous tasks. However, collecting high-quality human preferences creates costly bottlenecks in practical deployments, and hence, training data are often budgeted. In these scenarios, it is crucial to collect training data (e.g., contexts, a pair of generations for each context, and a preference indicating which generation is better) carefully, yet most of the existing methods sample contexts uniformly at random from a given collection. Given this, under t"},"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":"2402.10500","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-16T08:19:34Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"015aa8dc3627db77ab3d889a2418647adb7ef31bc4ac6eab96eb7c03c0a4375f","abstract_canon_sha256":"6a51cfd1cb54dd5ec5314b06aec003b21e41aea93d7bed2d1ad2233f37454065"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:31.979661Z","signature_b64":"U5yM2Et1Ntn9WmsN85l/wM7VqHGLyEOl0LTFEXTP5gvTc7xGvL8HccMDvSOG8nOP6qIUBbEZjzlx0XeRb6MCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51b692cc75318f07fc7cfebeeda279f946f58ac206fc5314f10706d95139b497","last_reissued_at":"2026-07-05T11:17:31.979186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:31.979186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Preference Optimization for Sample Efficient RLHF","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Nirjhar Das, Sayak Ray Chowdhury, Souradip Chakraborty","submitted_at":"2024-02-16T08:19:34Z","abstract_excerpt":"Large Language Models (LLMs) aligned using Reinforcement Learning from Human Feedback (RLHF) have shown remarkable generation abilities in numerous tasks. However, collecting high-quality human preferences creates costly bottlenecks in practical deployments, and hence, training data are often budgeted. In these scenarios, it is crucial to collect training data (e.g., contexts, a pair of generations for each context, and a preference indicating which generation is better) carefully, yet most of the existing methods sample contexts uniformly at random from a given collection. Given this, under t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10500","kind":"arxiv","version":3},"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/2402.10500/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":"2402.10500","created_at":"2026-07-05T11:17:31.979244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10500v3","created_at":"2026-07-05T11:17:31.979244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10500","created_at":"2026-07-05T11:17:31.979244+00:00"},{"alias_kind":"pith_short_12","alias_value":"KG3JFTDVGGHQ","created_at":"2026-07-05T11:17:31.979244+00:00"},{"alias_kind":"pith_short_16","alias_value":"KG3JFTDVGGHQP7D4","created_at":"2026-07-05T11:17:31.979244+00:00"},{"alias_kind":"pith_short_8","alias_value":"KG3JFTDV","created_at":"2026-07-05T11:17:31.979244+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24803","citing_title":"Active Learning for Stochastic Contextual Linear Bandits","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2602.06239","citing_title":"Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20408","citing_title":"Spectral Souping: A Unified Framework for Online Preference Alignment","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2602.03452","citing_title":"Beyond Variance: Prompt-Efficient RLVR via Rare-Event Amplification and Bidirectional Pairing","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2602.06239","citing_title":"Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2504.20571","citing_title":"Reinforcement Learning for Reasoning in Large Language Models with One Training Example","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02507","citing_title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10784","citing_title":"MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00155","citing_title":"Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KG3JFTDVGGHQP7D4727O3ITZ7F","json":"https://pith.science/pith/KG3JFTDVGGHQP7D4727O3ITZ7F.json","graph_json":"https://pith.science/api/pith-number/KG3JFTDVGGHQP7D4727O3ITZ7F/graph.json","events_json":"https://pith.science/api/pith-number/KG3JFTDVGGHQP7D4727O3ITZ7F/events.json","paper":"https://pith.science/paper/KG3JFTDV"},"agent_actions":{"view_html":"https://pith.science/pith/KG3JFTDVGGHQP7D4727O3ITZ7F","download_json":"https://pith.science/pith/KG3JFTDVGGHQP7D4727O3ITZ7F.json","view_paper":"https://pith.science/paper/KG3JFTDV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10500&json=true","fetch_graph":"https://pith.science/api/pith-number/KG3JFTDVGGHQP7D4727O3ITZ7F/graph.json","fetch_events":"https://pith.science/api/pith-number/KG3JFTDVGGHQP7D4727O3ITZ7F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KG3JFTDVGGHQP7D4727O3ITZ7F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KG3JFTDVGGHQP7D4727O3ITZ7F/action/storage_attestation","attest_author":"https://pith.science/pith/KG3JFTDVGGHQP7D4727O3ITZ7F/action/author_attestation","sign_citation":"https://pith.science/pith/KG3JFTDVGGHQP7D4727O3ITZ7F/action/citation_signature","submit_replication":"https://pith.science/pith/KG3JFTDVGGHQP7D4727O3ITZ7F/action/replication_record"}},"created_at":"2026-07-05T11:17:31.979244+00:00","updated_at":"2026-07-05T11:17:31.979244+00:00"}