{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZUQLYRYLSQDOXWUHY77NQQYHRA","short_pith_number":"pith:ZUQLYRYL","canonical_record":{"source":{"id":"2506.22157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T12:10:57Z","cross_cats_sorted":[],"title_canon_sha256":"90368e8b96c7f88ad0823ec74baf0e2e3b0806bf2dd49f86c3426f935bc8d1e9","abstract_canon_sha256":"c47e1dba7305e1f9f6a472d7998d3d37974e876f52e93ff9bd498d1d811ebddf"},"schema_version":"1.0"},"canonical_sha256":"cd20bc470b9406ebda87c7fed843078821bda247fd61cc574f384ceeca3082bc","source":{"kind":"arxiv","id":"2506.22157","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22157","created_at":"2026-07-05T11:28:22Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22157v1","created_at":"2026-07-05T11:28:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22157","created_at":"2026-07-05T11:28:22Z"},{"alias_kind":"pith_short_12","alias_value":"ZUQLYRYLSQDO","created_at":"2026-07-05T11:28:22Z"},{"alias_kind":"pith_short_16","alias_value":"ZUQLYRYLSQDOXWUH","created_at":"2026-07-05T11:28:22Z"},{"alias_kind":"pith_short_8","alias_value":"ZUQLYRYL","created_at":"2026-07-05T11:28:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZUQLYRYLSQDOXWUHY77NQQYHRA","target":"record","payload":{"canonical_record":{"source":{"id":"2506.22157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T12:10:57Z","cross_cats_sorted":[],"title_canon_sha256":"90368e8b96c7f88ad0823ec74baf0e2e3b0806bf2dd49f86c3426f935bc8d1e9","abstract_canon_sha256":"c47e1dba7305e1f9f6a472d7998d3d37974e876f52e93ff9bd498d1d811ebddf"},"schema_version":"1.0"},"canonical_sha256":"cd20bc470b9406ebda87c7fed843078821bda247fd61cc574f384ceeca3082bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:22.860597Z","signature_b64":"rdcgKYG4a7sXSlxukR2+ljDRlqhfJPiuouq/hu7AucyN4L8YaIuGyLrGye/OZ5N0qYUcBjXOyNlvsEYMlrwqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd20bc470b9406ebda87c7fed843078821bda247fd61cc574f384ceeca3082bc","last_reissued_at":"2026-07-05T11:28:22.860122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:22.860122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.22157","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":"2026-07-05T11:28:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sz5+j3ox1wjyWCuTPELDA3GZhutFuTl/m63InJEA1quuvMdFy1QF1JnY3HjNDSfX/9CqmcwT9yqwIMZ7TXraCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:49:57.737570Z"},"content_sha256":"a4168f26256a252e9bb107d69280a09b9f69ad7454e00eed548d723472ba4b57","schema_version":"1.0","event_id":"sha256:a4168f26256a252e9bb107d69280a09b9f69ad7454e00eed548d723472ba4b57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZUQLYRYLSQDOXWUHY77NQQYHRA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Language Model to Critique for Better Refinement","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bosi Wen, Chao Xiang, Chuxiong Sun, Cunxiang Wang, Jiale Cheng, Li Zhang, Mingchuan Yang, Minlie Huang, Pei Ke, Tianshu Yu, Xinyu Mu","submitted_at":"2025-06-27T12:10:57Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable evaluation and critique capabilities, providing insightful feedback and identifying flaws in various tasks. However, limited research has explored which types of critiques are most effective for improving model responses or how to generate such critiques. To address this gap, we introduce \\textbf{R}efinement-oriented \\textbf{C}ritique \\textbf{O}ptimization (RCO), a novel framework designed to train critic models using refinement signals. RCO uses a feedback loop where critiques, generated by the critic model, guide the actor model in re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22157","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/2506.22157/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":"2026-07-05T11:28:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IioPG2JR1wgyD7y4PSl4xV7D9bctel3Uk3lc+CC75hCXX4Bd8K9qR7+Osj0Sg+HIbcCNTO7lG4bxUGWU9PXaBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:49:57.738063Z"},"content_sha256":"e29ee60849144d9dc0f6fb2a1087310f7f5297c3929a8038165b5999bd395f15","schema_version":"1.0","event_id":"sha256:e29ee60849144d9dc0f6fb2a1087310f7f5297c3929a8038165b5999bd395f15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZUQLYRYLSQDOXWUHY77NQQYHRA/bundle.json","state_url":"https://pith.science/pith/ZUQLYRYLSQDOXWUHY77NQQYHRA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZUQLYRYLSQDOXWUHY77NQQYHRA/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":"2026-08-08T11:49:57Z","links":{"resolver":"https://pith.science/pith/ZUQLYRYLSQDOXWUHY77NQQYHRA","bundle":"https://pith.science/pith/ZUQLYRYLSQDOXWUHY77NQQYHRA/bundle.json","state":"https://pith.science/pith/ZUQLYRYLSQDOXWUHY77NQQYHRA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZUQLYRYLSQDOXWUHY77NQQYHRA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZUQLYRYLSQDOXWUHY77NQQYHRA","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":"c47e1dba7305e1f9f6a472d7998d3d37974e876f52e93ff9bd498d1d811ebddf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T12:10:57Z","title_canon_sha256":"90368e8b96c7f88ad0823ec74baf0e2e3b0806bf2dd49f86c3426f935bc8d1e9"},"schema_version":"1.0","source":{"id":"2506.22157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22157","created_at":"2026-07-05T11:28:22Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22157v1","created_at":"2026-07-05T11:28:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22157","created_at":"2026-07-05T11:28:22Z"},{"alias_kind":"pith_short_12","alias_value":"ZUQLYRYLSQDO","created_at":"2026-07-05T11:28:22Z"},{"alias_kind":"pith_short_16","alias_value":"ZUQLYRYLSQDOXWUH","created_at":"2026-07-05T11:28:22Z"},{"alias_kind":"pith_short_8","alias_value":"ZUQLYRYL","created_at":"2026-07-05T11:28:22Z"}],"graph_snapshots":[{"event_id":"sha256:e29ee60849144d9dc0f6fb2a1087310f7f5297c3929a8038165b5999bd395f15","target":"graph","created_at":"2026-07-05T11:28:22Z","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/2506.22157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable evaluation and critique capabilities, providing insightful feedback and identifying flaws in various tasks. However, limited research has explored which types of critiques are most effective for improving model responses or how to generate such critiques. To address this gap, we introduce \\textbf{R}efinement-oriented \\textbf{C}ritique \\textbf{O}ptimization (RCO), a novel framework designed to train critic models using refinement signals. RCO uses a feedback loop where critiques, generated by the critic model, guide the actor model in re","authors_text":"Bosi Wen, Chao Xiang, Chuxiong Sun, Cunxiang Wang, Jiale Cheng, Li Zhang, Mingchuan Yang, Minlie Huang, Pei Ke, Tianshu Yu, Xinyu Mu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T12:10:57Z","title":"Training Language Model to Critique for Better Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22157","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:a4168f26256a252e9bb107d69280a09b9f69ad7454e00eed548d723472ba4b57","target":"record","created_at":"2026-07-05T11:28:22Z","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":"c47e1dba7305e1f9f6a472d7998d3d37974e876f52e93ff9bd498d1d811ebddf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T12:10:57Z","title_canon_sha256":"90368e8b96c7f88ad0823ec74baf0e2e3b0806bf2dd49f86c3426f935bc8d1e9"},"schema_version":"1.0","source":{"id":"2506.22157","kind":"arxiv","version":1}},"canonical_sha256":"cd20bc470b9406ebda87c7fed843078821bda247fd61cc574f384ceeca3082bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd20bc470b9406ebda87c7fed843078821bda247fd61cc574f384ceeca3082bc","first_computed_at":"2026-07-05T11:28:22.860122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:22.860122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rdcgKYG4a7sXSlxukR2+ljDRlqhfJPiuouq/hu7AucyN4L8YaIuGyLrGye/OZ5N0qYUcBjXOyNlvsEYMlrwqDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:22.860597Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.22157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4168f26256a252e9bb107d69280a09b9f69ad7454e00eed548d723472ba4b57","sha256:e29ee60849144d9dc0f6fb2a1087310f7f5297c3929a8038165b5999bd395f15"],"state_sha256":"2750f5307f581d458de9c052e8ae0350d96a35bcac09f634551dd25b98b524cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4D2IFO4nWoh5AkVHtRTNzwbJDgbR0KO7c9niitiqcqnfg1ABWmHgJxJZFyDqvCo5wfSQFlFTS9EBHUjF5PSYBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:49:57.743675Z","bundle_sha256":"e55cb5d25c1d5acbd379deec92063255f73045a5d5f58833494fb3116fd1a87c"}}