{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CZZACCOSEZ7W3AE36OMK2MICSR","short_pith_number":"pith:CZZACCOS","canonical_record":{"source":{"id":"2410.12735","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T16:51:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f4f208ccb249ecbe735f8ff32f1e16671de382a66f408fc42d61f67e20d34cb9","abstract_canon_sha256":"91bfe10e1a8769057bb23a67ebfd195529efaf692a3bd3f5b811091e5818f2d0"},"schema_version":"1.0"},"canonical_sha256":"16720109d2267f6d809bf398ad31029467b27e419581270c767ebee599367f2f","source":{"kind":"arxiv","id":"2410.12735","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12735","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12735v5","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12735","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"pith_short_12","alias_value":"CZZACCOSEZ7W","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"pith_short_16","alias_value":"CZZACCOSEZ7W3AE3","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"pith_short_8","alias_value":"CZZACCOS","created_at":"2026-07-05T10:54:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CZZACCOSEZ7W3AE36OMK2MICSR","target":"record","payload":{"canonical_record":{"source":{"id":"2410.12735","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T16:51:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f4f208ccb249ecbe735f8ff32f1e16671de382a66f408fc42d61f67e20d34cb9","abstract_canon_sha256":"91bfe10e1a8769057bb23a67ebfd195529efaf692a3bd3f5b811091e5818f2d0"},"schema_version":"1.0"},"canonical_sha256":"16720109d2267f6d809bf398ad31029467b27e419581270c767ebee599367f2f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:37.991507Z","signature_b64":"mTYn9Ufqbz1CC4yjVrXDZDIyN4LRS3UaBK5lrDacjF6h3DptsG9rs0j54boLgsG0JuXvy+1MsC+xFdujCUzCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16720109d2267f6d809bf398ad31029467b27e419581270c767ebee599367f2f","last_reissued_at":"2026-07-05T10:54:37.991016Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:37.991016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.12735","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:54:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"srOXAqF3xX2U7q4tcEyXPo83vn+fWJOxV+BloIoSRCu8tNpWdgbsn7XcD0tNLm8JqCit774vojPXfbHT6W8jCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:03:37.011910Z"},"content_sha256":"bd269d359820b12845ead50a8af339d58b93949c0ecee52a92429f2f5bacf92f","schema_version":"1.0","event_id":"sha256:bd269d359820b12845ead50a8af339d58b93949c0ecee52a92429f2f5bacf92f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CZZACCOSEZ7W3AE36OMK2MICSR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CREAM: Consistency Regularized Self-Rewarding Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Chetan Bansal, Huaxiu Yao, Weilei He, Weitong Zhang, Xuchao Zhang, Ying Wei, Zhaoyang Wang, Zhiyuan Liang","submitted_at":"2024-10-16T16:51:01Z","abstract_excerpt":"Recent self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to iteratively improve the alignment performance without the need of human annotations for preference data. These methods commonly utilize the same LLM to act as both the policy model (which generates responses) and the reward model (which scores and ranks those responses). The ranked responses are then used as preference pairs to train the LLM via direct alignment technologies (e.g. DPO). However, it is noteworthy that throughout this process, there is no guarantee of accuracy in the rewarding and ranki"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12735","kind":"arxiv","version":5},"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/2410.12735/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":"2026-07-05T10:54:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sUxMzTTZPBsn1W3HvhyR1SQqAAccvaj8whYn7FDA0V5TH2L+sj5HrFFh7wLUYLu7UfY8mWcXbA9f3m5OgzJxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:03:37.012683Z"},"content_sha256":"3c682f62652fa37c6d0e1d0d4996b5393aad02f2fa9e673f141463ec1846d6b7","schema_version":"1.0","event_id":"sha256:3c682f62652fa37c6d0e1d0d4996b5393aad02f2fa9e673f141463ec1846d6b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CZZACCOSEZ7W3AE36OMK2MICSR/bundle.json","state_url":"https://pith.science/pith/CZZACCOSEZ7W3AE36OMK2MICSR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CZZACCOSEZ7W3AE36OMK2MICSR/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":"2026-08-04T17:03:37Z","links":{"resolver":"https://pith.science/pith/CZZACCOSEZ7W3AE36OMK2MICSR","bundle":"https://pith.science/pith/CZZACCOSEZ7W3AE36OMK2MICSR/bundle.json","state":"https://pith.science/pith/CZZACCOSEZ7W3AE36OMK2MICSR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CZZACCOSEZ7W3AE36OMK2MICSR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CZZACCOSEZ7W3AE36OMK2MICSR","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":"91bfe10e1a8769057bb23a67ebfd195529efaf692a3bd3f5b811091e5818f2d0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T16:51:01Z","title_canon_sha256":"f4f208ccb249ecbe735f8ff32f1e16671de382a66f408fc42d61f67e20d34cb9"},"schema_version":"1.0","source":{"id":"2410.12735","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12735","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12735v5","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12735","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"pith_short_12","alias_value":"CZZACCOSEZ7W","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"pith_short_16","alias_value":"CZZACCOSEZ7W3AE3","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"pith_short_8","alias_value":"CZZACCOS","created_at":"2026-07-05T10:54:37Z"}],"graph_snapshots":[{"event_id":"sha256:3c682f62652fa37c6d0e1d0d4996b5393aad02f2fa9e673f141463ec1846d6b7","target":"graph","created_at":"2026-07-05T10:54:37Z","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/2410.12735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to iteratively improve the alignment performance without the need of human annotations for preference data. These methods commonly utilize the same LLM to act as both the policy model (which generates responses) and the reward model (which scores and ranks those responses). The ranked responses are then used as preference pairs to train the LLM via direct alignment technologies (e.g. DPO). However, it is noteworthy that throughout this process, there is no guarantee of accuracy in the rewarding and ranki","authors_text":"Chetan Bansal, Huaxiu Yao, Weilei He, Weitong Zhang, Xuchao Zhang, Ying Wei, Zhaoyang Wang, Zhiyuan Liang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T16:51:01Z","title":"CREAM: Consistency Regularized Self-Rewarding Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12735","kind":"arxiv","version":5},"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:bd269d359820b12845ead50a8af339d58b93949c0ecee52a92429f2f5bacf92f","target":"record","created_at":"2026-07-05T10:54:37Z","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":"91bfe10e1a8769057bb23a67ebfd195529efaf692a3bd3f5b811091e5818f2d0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T16:51:01Z","title_canon_sha256":"f4f208ccb249ecbe735f8ff32f1e16671de382a66f408fc42d61f67e20d34cb9"},"schema_version":"1.0","source":{"id":"2410.12735","kind":"arxiv","version":5}},"canonical_sha256":"16720109d2267f6d809bf398ad31029467b27e419581270c767ebee599367f2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16720109d2267f6d809bf398ad31029467b27e419581270c767ebee599367f2f","first_computed_at":"2026-07-05T10:54:37.991016Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:37.991016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mTYn9Ufqbz1CC4yjVrXDZDIyN4LRS3UaBK5lrDacjF6h3DptsG9rs0j54boLgsG0JuXvy+1MsC+xFdujCUzCCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:37.991507Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12735","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd269d359820b12845ead50a8af339d58b93949c0ecee52a92429f2f5bacf92f","sha256:3c682f62652fa37c6d0e1d0d4996b5393aad02f2fa9e673f141463ec1846d6b7"],"state_sha256":"4d98c0276dfd903021e6c6be253cdfaa3a3ab067408695bfdf38206137839d18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kJGZnNKUueL+0X9R7U+Kgc9OpR6rEKEHHFNFSeshMLgRGq3q0xwZTr3UeBAnZnPUKzcgCK+Yj9dbOAhaYsnSAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:03:37.019264Z","bundle_sha256":"fe45e9ad35cb2d3f71c1caee5095f996553997293af224e6db610d49625ee567"}}