{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LM3KQWEOPABNZ23C4QDEQDSPFP","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":"c15e458849caeb990654a4c6219904c29090e15b38f640c8f6fcb55197535412","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T15:23:30Z","title_canon_sha256":"198d143955f71b6a76f513201135050a9e29c6b50b7dbd63c0f751e536ff28fc"},"schema_version":"1.0","source":{"id":"2406.06606","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06606","created_at":"2026-07-05T08:41:03Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06606v2","created_at":"2026-07-05T08:41:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06606","created_at":"2026-07-05T08:41:03Z"},{"alias_kind":"pith_short_12","alias_value":"LM3KQWEOPABN","created_at":"2026-07-05T08:41:03Z"},{"alias_kind":"pith_short_16","alias_value":"LM3KQWEOPABNZ23C","created_at":"2026-07-05T08:41:03Z"},{"alias_kind":"pith_short_8","alias_value":"LM3KQWEO","created_at":"2026-07-05T08:41:03Z"}],"graph_snapshots":[{"event_id":"sha256:0e28771ff65025091dfc7f9b7456a9726bbdc54763b759a986d97a944e6cd84f","target":"graph","created_at":"2026-07-05T08:41:03Z","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/2406.06606/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The reward model for Reinforcement Learning from Human Feedback (RLHF) has proven effective in fine-tuning Large Language Models (LLMs). Notably, collecting human feedback for RLHF can be resource-intensive and lead to scalability issues for LLMs and complex tasks. Our proposed framework Proto-RM leverages prototypical networks to enhance reward models under limited human feedback. By enabling stable and reliable structural learning from fewer samples, Proto-RM significantly enhances LLMs' adaptability and accuracy in interpreting human preferences. Extensive experiments on various datasets de","authors_text":"Changyu Chen, Jinghan Zhang, Kunpeng Liu, Xinhao Zhang, Xiting Wang, Yiqiao Jin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T15:23:30Z","title":"Prototypical Reward Network for Data-Efficient RLHF"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06606","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:aecaf00e157e8b8c8ee0366a6ce9253ef3dceed14598dce583c889c7656de648","target":"record","created_at":"2026-07-05T08:41:03Z","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":"c15e458849caeb990654a4c6219904c29090e15b38f640c8f6fcb55197535412","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T15:23:30Z","title_canon_sha256":"198d143955f71b6a76f513201135050a9e29c6b50b7dbd63c0f751e536ff28fc"},"schema_version":"1.0","source":{"id":"2406.06606","kind":"arxiv","version":2}},"canonical_sha256":"5b36a8588e7802dceb62e406480e4f2bd04628cf82f0c88069f2289c4c74d538","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b36a8588e7802dceb62e406480e4f2bd04628cf82f0c88069f2289c4c74d538","first_computed_at":"2026-07-05T08:41:03.807745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:41:03.807745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MyCVmY3mce+Nl/NWBYdOsvaNZg8ena9IFkJ3+lzh622neBolIrQNjrMRD0B2CVZd8zD3C5HaC75pQIzz+M29AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:41:03.808230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06606","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aecaf00e157e8b8c8ee0366a6ce9253ef3dceed14598dce583c889c7656de648","sha256:0e28771ff65025091dfc7f9b7456a9726bbdc54763b759a986d97a944e6cd84f"],"state_sha256":"7fdb2f7a1cc85c13bd3c15e87e7477cbc33c7e222b6fc20bd3668c2a8d954d06"}