{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CUD2XLWBM5AFYAKCK4HU4L7O53","short_pith_number":"pith:CUD2XLWB","schema_version":"1.0","canonical_sha256":"1507abaec167405c0142570f4e2feeeef118494b92071b016c4a101177530b31","source":{"kind":"arxiv","id":"2412.07207","version":2},"attestation_state":"computed","paper":{"title":"MAPLE: A Framework for Active Preference Learning Guided by Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Mason Nakamura, Saaduddin Mahmud, Shlomo Zilberstein","submitted_at":"2024-12-10T05:55:14Z","abstract_excerpt":"The advent of large language models (LLMs) has sparked significant interest in using natural language for preference learning. However, existing methods often suffer from high computational burdens, taxing human supervision, and lack of interpretability. To address these issues, we introduce MAPLE, a framework for large language model-guided Bayesian active preference learning. MAPLE leverages LLMs to model the distribution over preference functions, conditioning it on both natural language feedback and conventional preference learning feedback, such as pairwise trajectory rankings. MAPLE also"},"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":"2412.07207","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-10T05:55:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"3f31385fd0cf41b384d3d0c33010ab7e6e208c054569dfa801eb0a525d4930d3","abstract_canon_sha256":"4b329c6b14738ec6c440c6ef4e81d2566aed2ce516d1304ec515b9ac8b3f5e39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:18.974692Z","signature_b64":"blyTNJopnDkye/3QhdWJxrYD378XnXtBmpttYdZdD7NJD9J72zDLIkkiI47YFZ4bObHCCfl1bnbJIc7MRLfgCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1507abaec167405c0142570f4e2feeeef118494b92071b016c4a101177530b31","last_reissued_at":"2026-07-05T09:52:18.974173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:18.974173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAPLE: A Framework for Active Preference Learning Guided by Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Mason Nakamura, Saaduddin Mahmud, Shlomo Zilberstein","submitted_at":"2024-12-10T05:55:14Z","abstract_excerpt":"The advent of large language models (LLMs) has sparked significant interest in using natural language for preference learning. However, existing methods often suffer from high computational burdens, taxing human supervision, and lack of interpretability. To address these issues, we introduce MAPLE, a framework for large language model-guided Bayesian active preference learning. MAPLE leverages LLMs to model the distribution over preference functions, conditioning it on both natural language feedback and conventional preference learning feedback, such as pairwise trajectory rankings. MAPLE also"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07207","kind":"arxiv","version":2},"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/2412.07207/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":"2412.07207","created_at":"2026-07-05T09:52:18.974229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07207v2","created_at":"2026-07-05T09:52:18.974229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07207","created_at":"2026-07-05T09:52:18.974229+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUD2XLWBM5AF","created_at":"2026-07-05T09:52:18.974229+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUD2XLWBM5AFYAKC","created_at":"2026-07-05T09:52:18.974229+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUD2XLWB","created_at":"2026-07-05T09:52:18.974229+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03717","citing_title":"Efficiently Generating Expressive Quadruped Behaviors via Language-Guided Preference Learning","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUD2XLWBM5AFYAKCK4HU4L7O53","json":"https://pith.science/pith/CUD2XLWBM5AFYAKCK4HU4L7O53.json","graph_json":"https://pith.science/api/pith-number/CUD2XLWBM5AFYAKCK4HU4L7O53/graph.json","events_json":"https://pith.science/api/pith-number/CUD2XLWBM5AFYAKCK4HU4L7O53/events.json","paper":"https://pith.science/paper/CUD2XLWB"},"agent_actions":{"view_html":"https://pith.science/pith/CUD2XLWBM5AFYAKCK4HU4L7O53","download_json":"https://pith.science/pith/CUD2XLWBM5AFYAKCK4HU4L7O53.json","view_paper":"https://pith.science/paper/CUD2XLWB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07207&json=true","fetch_graph":"https://pith.science/api/pith-number/CUD2XLWBM5AFYAKCK4HU4L7O53/graph.json","fetch_events":"https://pith.science/api/pith-number/CUD2XLWBM5AFYAKCK4HU4L7O53/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUD2XLWBM5AFYAKCK4HU4L7O53/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUD2XLWBM5AFYAKCK4HU4L7O53/action/storage_attestation","attest_author":"https://pith.science/pith/CUD2XLWBM5AFYAKCK4HU4L7O53/action/author_attestation","sign_citation":"https://pith.science/pith/CUD2XLWBM5AFYAKCK4HU4L7O53/action/citation_signature","submit_replication":"https://pith.science/pith/CUD2XLWBM5AFYAKCK4HU4L7O53/action/replication_record"}},"created_at":"2026-07-05T09:52:18.974229+00:00","updated_at":"2026-07-05T09:52:18.974229+00:00"}