{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LM3KQWEOPABNZ23C4QDEQDSPFP","short_pith_number":"pith:LM3KQWEO","canonical_record":{"source":{"id":"2406.06606","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T15:23:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"198d143955f71b6a76f513201135050a9e29c6b50b7dbd63c0f751e536ff28fc","abstract_canon_sha256":"c15e458849caeb990654a4c6219904c29090e15b38f640c8f6fcb55197535412"},"schema_version":"1.0"},"canonical_sha256":"5b36a8588e7802dceb62e406480e4f2bd04628cf82f0c88069f2289c4c74d538","source":{"kind":"arxiv","id":"2406.06606","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LM3KQWEOPABNZ23C4QDEQDSPFP","target":"record","payload":{"canonical_record":{"source":{"id":"2406.06606","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T15:23:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"198d143955f71b6a76f513201135050a9e29c6b50b7dbd63c0f751e536ff28fc","abstract_canon_sha256":"c15e458849caeb990654a4c6219904c29090e15b38f640c8f6fcb55197535412"},"schema_version":"1.0"},"canonical_sha256":"5b36a8588e7802dceb62e406480e4f2bd04628cf82f0c88069f2289c4c74d538","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:03.808230Z","signature_b64":"MyCVmY3mce+Nl/NWBYdOsvaNZg8ena9IFkJ3+lzh622neBolIrQNjrMRD0B2CVZd8zD3C5HaC75pQIzz+M29AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b36a8588e7802dceb62e406480e4f2bd04628cf82f0c88069f2289c4c74d538","last_reissued_at":"2026-07-05T08:41:03.807745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:03.807745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.06606","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:41:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OR9gPg7cqFSht95m3ou75xUZ7fq9UcuIcLrIF8JI9lj/98QpClBwlN7n1ToPKfnjFROp0U5znoT2jAOtg/5ZAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:15:21.476030Z"},"content_sha256":"aecaf00e157e8b8c8ee0366a6ce9253ef3dceed14598dce583c889c7656de648","schema_version":"1.0","event_id":"sha256:aecaf00e157e8b8c8ee0366a6ce9253ef3dceed14598dce583c889c7656de648"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LM3KQWEOPABNZ23C4QDEQDSPFP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prototypical Reward Network for Data-Efficient RLHF","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Changyu Chen, Jinghan Zhang, Kunpeng Liu, Xinhao Zhang, Xiting Wang, Yiqiao Jin","submitted_at":"2024-06-06T15:23:30Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06606","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/2406.06606/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:41:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HQYiOvY8BEpI5yHwVUaj1e2um3upoArZGMT6rqQfxpHGe/vlApGmKOeR/DxV0gCi+gM9XkSipTrYE5bSSnoAAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:15:21.476557Z"},"content_sha256":"0e28771ff65025091dfc7f9b7456a9726bbdc54763b759a986d97a944e6cd84f","schema_version":"1.0","event_id":"sha256:0e28771ff65025091dfc7f9b7456a9726bbdc54763b759a986d97a944e6cd84f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LM3KQWEOPABNZ23C4QDEQDSPFP/bundle.json","state_url":"https://pith.science/pith/LM3KQWEOPABNZ23C4QDEQDSPFP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LM3KQWEOPABNZ23C4QDEQDSPFP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T08:15:21Z","links":{"resolver":"https://pith.science/pith/LM3KQWEOPABNZ23C4QDEQDSPFP","bundle":"https://pith.science/pith/LM3KQWEOPABNZ23C4QDEQDSPFP/bundle.json","state":"https://pith.science/pith/LM3KQWEOPABNZ23C4QDEQDSPFP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LM3KQWEOPABNZ23C4QDEQDSPFP/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lkIVHnsGxzId8+uODVj6HsjjsXn6zGkr0e21Tj+A0zXNxJB34eW5UNl+VQDOaGeYddsbNNRCdygBUG993g/9Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:15:21.480600Z","bundle_sha256":"a5ebb6bce04efab8289f26234dc2f7696d7d4dc7b41c7a49f6a421859505cb54"}}