{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UJ77VRQ7YAQWRAWW6D3YGDEJ45","short_pith_number":"pith:UJ77VRQ7","canonical_record":{"source":{"id":"2405.19763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T07:19:31Z","cross_cats_sorted":[],"title_canon_sha256":"8af3fe52b8d7421efebeb4996ed3851c0fa6114d2376300f27d1c12a550e41fa","abstract_canon_sha256":"293badccf6180afb61ff785a18f18a521de71ee00b54d57d46bf7a708ba0725d"},"schema_version":"1.0"},"canonical_sha256":"a27ffac61fc0216882d6f0f7830c89e753828056ce0ab675aa8878b8b031e26c","source":{"kind":"arxiv","id":"2405.19763","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19763","created_at":"2026-07-05T08:25:12Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19763v1","created_at":"2026-07-05T08:25:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19763","created_at":"2026-07-05T08:25:12Z"},{"alias_kind":"pith_short_12","alias_value":"UJ77VRQ7YAQW","created_at":"2026-07-05T08:25:12Z"},{"alias_kind":"pith_short_16","alias_value":"UJ77VRQ7YAQWRAWW","created_at":"2026-07-05T08:25:12Z"},{"alias_kind":"pith_short_8","alias_value":"UJ77VRQ7","created_at":"2026-07-05T08:25:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UJ77VRQ7YAQWRAWW6D3YGDEJ45","target":"record","payload":{"canonical_record":{"source":{"id":"2405.19763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T07:19:31Z","cross_cats_sorted":[],"title_canon_sha256":"8af3fe52b8d7421efebeb4996ed3851c0fa6114d2376300f27d1c12a550e41fa","abstract_canon_sha256":"293badccf6180afb61ff785a18f18a521de71ee00b54d57d46bf7a708ba0725d"},"schema_version":"1.0"},"canonical_sha256":"a27ffac61fc0216882d6f0f7830c89e753828056ce0ab675aa8878b8b031e26c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:12.074799Z","signature_b64":"Cc9/zqXtNG3Nt3JU99RKpUCPypCLn/ilQN98r1NOxTr4+u0RZdzKFGMUxzkoay/Oz6YYGF1BLSd0Q6u3m00DAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a27ffac61fc0216882d6f0f7830c89e753828056ce0ab675aa8878b8b031e26c","last_reissued_at":"2026-07-05T08:25:12.074370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:12.074370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.19763","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:25:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mPcklmGLn9G9f8O8nzpg4U7xDikpk0HrvwO2Yd2nm3n4Mrb7NKVYOgI48Pw7wK86M076TasOWphiRzHWjHAKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:24:11.743458Z"},"content_sha256":"1c83271232fd1afb838a31a86a88d80a5ba86111b601139615a2c369fd0a550d","schema_version":"1.0","event_id":"sha256:1c83271232fd1afb838a31a86a88d80a5ba86111b601139615a2c369fd0a550d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UJ77VRQ7YAQWRAWW6D3YGDEJ45","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengguo Yin, Honglin Han, Kuo Liao, Liqun Liu, Mengge Xue, Meng Zhao, Shuang Li, Zhenyu Hu","submitted_at":"2024-05-30T07:19:31Z","abstract_excerpt":"Recent strides in large language models (LLMs) have yielded remarkable performance, leveraging reinforcement learning from human feedback (RLHF) to significantly enhance generation and alignment capabilities. However, RLHF encounters numerous challenges, including the objective mismatch issue, leading to suboptimal performance in Natural Language Understanding (NLU) tasks. To address this limitation, we propose a novel Reinforcement Learning framework enhanced with Label-sensitive Reward (RLLR) to amplify the performance of LLMs in NLU tasks. By incorporating label-sensitive pairs into reinfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19763","kind":"arxiv","version":1},"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/2405.19763/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":"2026-07-05T08:25:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8PMLr/ae3n7E+niwhOYjEsGLnMH9V/OcmtmK+dzxCL2hx+zubvEHOrb2nbuWNFus+Kf8ImzqUvNrlcFZHx/LBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:24:11.744396Z"},"content_sha256":"4a01151201f3f42cb2c8f88ad22c765703b0f3ede40b628abcca52305732e686","schema_version":"1.0","event_id":"sha256:4a01151201f3f42cb2c8f88ad22c765703b0f3ede40b628abcca52305732e686"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UJ77VRQ7YAQWRAWW6D3YGDEJ45/bundle.json","state_url":"https://pith.science/pith/UJ77VRQ7YAQWRAWW6D3YGDEJ45/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UJ77VRQ7YAQWRAWW6D3YGDEJ45/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":"2026-08-18T14:24:11Z","links":{"resolver":"https://pith.science/pith/UJ77VRQ7YAQWRAWW6D3YGDEJ45","bundle":"https://pith.science/pith/UJ77VRQ7YAQWRAWW6D3YGDEJ45/bundle.json","state":"https://pith.science/pith/UJ77VRQ7YAQWRAWW6D3YGDEJ45/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UJ77VRQ7YAQWRAWW6D3YGDEJ45/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UJ77VRQ7YAQWRAWW6D3YGDEJ45","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":"293badccf6180afb61ff785a18f18a521de71ee00b54d57d46bf7a708ba0725d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T07:19:31Z","title_canon_sha256":"8af3fe52b8d7421efebeb4996ed3851c0fa6114d2376300f27d1c12a550e41fa"},"schema_version":"1.0","source":{"id":"2405.19763","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19763","created_at":"2026-07-05T08:25:12Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19763v1","created_at":"2026-07-05T08:25:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19763","created_at":"2026-07-05T08:25:12Z"},{"alias_kind":"pith_short_12","alias_value":"UJ77VRQ7YAQW","created_at":"2026-07-05T08:25:12Z"},{"alias_kind":"pith_short_16","alias_value":"UJ77VRQ7YAQWRAWW","created_at":"2026-07-05T08:25:12Z"},{"alias_kind":"pith_short_8","alias_value":"UJ77VRQ7","created_at":"2026-07-05T08:25:12Z"}],"graph_snapshots":[{"event_id":"sha256:4a01151201f3f42cb2c8f88ad22c765703b0f3ede40b628abcca52305732e686","target":"graph","created_at":"2026-07-05T08:25:12Z","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/2405.19763/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent strides in large language models (LLMs) have yielded remarkable performance, leveraging reinforcement learning from human feedback (RLHF) to significantly enhance generation and alignment capabilities. However, RLHF encounters numerous challenges, including the objective mismatch issue, leading to suboptimal performance in Natural Language Understanding (NLU) tasks. To address this limitation, we propose a novel Reinforcement Learning framework enhanced with Label-sensitive Reward (RLLR) to amplify the performance of LLMs in NLU tasks. By incorporating label-sensitive pairs into reinfor","authors_text":"Chengguo Yin, Honglin Han, Kuo Liao, Liqun Liu, Mengge Xue, Meng Zhao, Shuang Li, Zhenyu Hu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T07:19:31Z","title":"Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19763","kind":"arxiv","version":1},"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":"sha256:1c83271232fd1afb838a31a86a88d80a5ba86111b601139615a2c369fd0a550d","target":"record","created_at":"2026-07-05T08:25:12Z","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":"293badccf6180afb61ff785a18f18a521de71ee00b54d57d46bf7a708ba0725d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T07:19:31Z","title_canon_sha256":"8af3fe52b8d7421efebeb4996ed3851c0fa6114d2376300f27d1c12a550e41fa"},"schema_version":"1.0","source":{"id":"2405.19763","kind":"arxiv","version":1}},"canonical_sha256":"a27ffac61fc0216882d6f0f7830c89e753828056ce0ab675aa8878b8b031e26c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a27ffac61fc0216882d6f0f7830c89e753828056ce0ab675aa8878b8b031e26c","first_computed_at":"2026-07-05T08:25:12.074370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:12.074370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cc9/zqXtNG3Nt3JU99RKpUCPypCLn/ilQN98r1NOxTr4+u0RZdzKFGMUxzkoay/Oz6YYGF1BLSd0Q6u3m00DAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:12.074799Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19763","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c83271232fd1afb838a31a86a88d80a5ba86111b601139615a2c369fd0a550d","sha256:4a01151201f3f42cb2c8f88ad22c765703b0f3ede40b628abcca52305732e686"],"state_sha256":"1da8901f2863cb4ed8d68ba1872063213dd4254107661f3bcbe7b4009c8d81e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2bwqLZPTc+FCyz6QBO4O06COdlEOVYuI05KsRN5jBkMbpXg5T3PNgpsz4pHzwIkWz0F1eFvSky/DT4fFlZ7JDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T14:24:11.756296Z","bundle_sha256":"15de91bbabf9f22c5b9cdd3e41a6b9aea881b462372cb0525b55e4e56c78c976"}}