{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:U6UKN3K4PHJ2WSLR25TPVQOER2","short_pith_number":"pith:U6UKN3K4","canonical_record":{"source":{"id":"2402.15754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-24T08:01:32Z","cross_cats_sorted":[],"title_canon_sha256":"fa7173e2c13c5dc8af351427183b02869e542f1f4aa77c09813ed4ed84fc2c28","abstract_canon_sha256":"f8dc9b2dfaf5c5c02e848e5bd1fb836dba3be396bb126cfb20476a5e27b1113a"},"schema_version":"1.0"},"canonical_sha256":"a7a8a6ed5c79d3ab4971d766fac1c48e9fbc77df692e9477fe1a902dc444c773","source":{"kind":"arxiv","id":"2402.15754","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15754","created_at":"2026-07-05T07:48:57Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15754v1","created_at":"2026-07-05T07:48:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15754","created_at":"2026-07-05T07:48:57Z"},{"alias_kind":"pith_short_12","alias_value":"U6UKN3K4PHJ2","created_at":"2026-07-05T07:48:57Z"},{"alias_kind":"pith_short_16","alias_value":"U6UKN3K4PHJ2WSLR","created_at":"2026-07-05T07:48:57Z"},{"alias_kind":"pith_short_8","alias_value":"U6UKN3K4","created_at":"2026-07-05T07:48:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:U6UKN3K4PHJ2WSLR25TPVQOER2","target":"record","payload":{"canonical_record":{"source":{"id":"2402.15754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-24T08:01:32Z","cross_cats_sorted":[],"title_canon_sha256":"fa7173e2c13c5dc8af351427183b02869e542f1f4aa77c09813ed4ed84fc2c28","abstract_canon_sha256":"f8dc9b2dfaf5c5c02e848e5bd1fb836dba3be396bb126cfb20476a5e27b1113a"},"schema_version":"1.0"},"canonical_sha256":"a7a8a6ed5c79d3ab4971d766fac1c48e9fbc77df692e9477fe1a902dc444c773","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:57.619812Z","signature_b64":"eCt9AeHM8H5SlmlhuQIca+yr9FIvyso76JK8R6QVc2BK87V+ESY1WnT8JvQtpR30I/y1Z1pEn2bYrXDmadV3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7a8a6ed5c79d3ab4971d766fac1c48e9fbc77df692e9477fe1a902dc444c773","last_reissued_at":"2026-07-05T07:48:57.619376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:57.619376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.15754","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":"2026-07-05T07:48:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8fSzFdyQLhILMBbRWmC1N8btI/BNnfg9USTWn42bUTGzyYYLEJ1lV8y5WMq0prTiLbACJwAU5e+PdUCWFEDOCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:53:13.062412Z"},"content_sha256":"a00ebf77a9b7e1e348d7a6ca587d758d42535c35fb19a2d0f4596ea72163395f","schema_version":"1.0","event_id":"sha256:a00ebf77a9b7e1e348d7a6ca587d758d42535c35fb19a2d0f4596ea72163395f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:U6UKN3K4PHJ2WSLR25TPVQOER2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Feng Sun, Furu Wei, Haizhen Huang, Qi Zhang, Shaohan Huang, Tianchi Yang, Weiwei Deng, Yuxuan Liu, Zihan Zhang","submitted_at":"2024-02-24T08:01:32Z","abstract_excerpt":"Large language models (LLMs) have emerged as a promising alternative to expensive human evaluations. However, the alignment and coverage of LLM-based evaluations are often limited by the scope and potential bias of the evaluation prompts and criteria. To address this challenge, we propose HD-Eval, a novel framework that iteratively aligns LLM-based evaluators with human preference via Hierarchical Criteria Decomposition. HD-Eval inherits the essence from the evaluation mindset of human experts and enhances the alignment of LLM-based evaluators by decomposing a given evaluation task into finer-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15754","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/2402.15754/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":"2026-07-05T07:48:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sequ3LJh9Y7qa5BdMpkIa9vlJmlWa0ujph3KkbGurU0sYqPYf2/goQO4qr+gLOsfoZX28A4Wkq9tej+M0wqWDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:53:13.062982Z"},"content_sha256":"b23e0472d4bb42e9d02d5760a9ba99d2ce37b9834cb2a3fdd4b6b24554167480","schema_version":"1.0","event_id":"sha256:b23e0472d4bb42e9d02d5760a9ba99d2ce37b9834cb2a3fdd4b6b24554167480"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U6UKN3K4PHJ2WSLR25TPVQOER2/bundle.json","state_url":"https://pith.science/pith/U6UKN3K4PHJ2WSLR25TPVQOER2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U6UKN3K4PHJ2WSLR25TPVQOER2/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":"2026-08-08T04:53:13Z","links":{"resolver":"https://pith.science/pith/U6UKN3K4PHJ2WSLR25TPVQOER2","bundle":"https://pith.science/pith/U6UKN3K4PHJ2WSLR25TPVQOER2/bundle.json","state":"https://pith.science/pith/U6UKN3K4PHJ2WSLR25TPVQOER2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U6UKN3K4PHJ2WSLR25TPVQOER2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U6UKN3K4PHJ2WSLR25TPVQOER2","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":"f8dc9b2dfaf5c5c02e848e5bd1fb836dba3be396bb126cfb20476a5e27b1113a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-24T08:01:32Z","title_canon_sha256":"fa7173e2c13c5dc8af351427183b02869e542f1f4aa77c09813ed4ed84fc2c28"},"schema_version":"1.0","source":{"id":"2402.15754","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15754","created_at":"2026-07-05T07:48:57Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15754v1","created_at":"2026-07-05T07:48:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15754","created_at":"2026-07-05T07:48:57Z"},{"alias_kind":"pith_short_12","alias_value":"U6UKN3K4PHJ2","created_at":"2026-07-05T07:48:57Z"},{"alias_kind":"pith_short_16","alias_value":"U6UKN3K4PHJ2WSLR","created_at":"2026-07-05T07:48:57Z"},{"alias_kind":"pith_short_8","alias_value":"U6UKN3K4","created_at":"2026-07-05T07:48:57Z"}],"graph_snapshots":[{"event_id":"sha256:b23e0472d4bb42e9d02d5760a9ba99d2ce37b9834cb2a3fdd4b6b24554167480","target":"graph","created_at":"2026-07-05T07:48:57Z","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/2402.15754/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have emerged as a promising alternative to expensive human evaluations. However, the alignment and coverage of LLM-based evaluations are often limited by the scope and potential bias of the evaluation prompts and criteria. To address this challenge, we propose HD-Eval, a novel framework that iteratively aligns LLM-based evaluators with human preference via Hierarchical Criteria Decomposition. HD-Eval inherits the essence from the evaluation mindset of human experts and enhances the alignment of LLM-based evaluators by decomposing a given evaluation task into finer-","authors_text":"Feng Sun, Furu Wei, Haizhen Huang, Qi Zhang, Shaohan Huang, Tianchi Yang, Weiwei Deng, Yuxuan Liu, Zihan Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-24T08:01:32Z","title":"HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15754","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:a00ebf77a9b7e1e348d7a6ca587d758d42535c35fb19a2d0f4596ea72163395f","target":"record","created_at":"2026-07-05T07:48:57Z","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":"f8dc9b2dfaf5c5c02e848e5bd1fb836dba3be396bb126cfb20476a5e27b1113a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-24T08:01:32Z","title_canon_sha256":"fa7173e2c13c5dc8af351427183b02869e542f1f4aa77c09813ed4ed84fc2c28"},"schema_version":"1.0","source":{"id":"2402.15754","kind":"arxiv","version":1}},"canonical_sha256":"a7a8a6ed5c79d3ab4971d766fac1c48e9fbc77df692e9477fe1a902dc444c773","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7a8a6ed5c79d3ab4971d766fac1c48e9fbc77df692e9477fe1a902dc444c773","first_computed_at":"2026-07-05T07:48:57.619376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:57.619376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eCt9AeHM8H5SlmlhuQIca+yr9FIvyso76JK8R6QVc2BK87V+ESY1WnT8JvQtpR30I/y1Z1pEn2bYrXDmadV3Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:57.619812Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15754","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a00ebf77a9b7e1e348d7a6ca587d758d42535c35fb19a2d0f4596ea72163395f","sha256:b23e0472d4bb42e9d02d5760a9ba99d2ce37b9834cb2a3fdd4b6b24554167480"],"state_sha256":"87041059c431c8b56bba9aff7f47651d51d1c322f354b56457126e8cdb5e11d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PvjO4Hcw9xN8KFqNl9TukZh6INCaPa2n3aq9ngCPLtk/0lm4jDcK+CTKPuRM7UYh2DHg6O6JyRbB+lUPsubLBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:53:13.069445Z","bundle_sha256":"b1055c4b736bb3a9e219a5a68e1cfef75b890d76825323621819839804993be6"}}