{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GNCCMZXRBFODL4PHJKTZA6Y732","short_pith_number":"pith:GNCCMZXR","schema_version":"1.0","canonical_sha256":"33442666f1095c35f1e74aa7907b1fde817a2382c495d04b22ca6f45f26407a1","source":{"kind":"arxiv","id":"2310.05470","version":2},"attestation_state":"computed","paper":{"title":"Generative Judge for Evaluating Alignment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Junlong Li, Pengfei Liu, Run-Ze Fan, Shichao Sun, Weizhe Yuan","submitted_at":"2023-10-09T07:27:15Z","abstract_excerpt":"The rapid development of Large Language Models (LLMs) has substantially expanded the range of tasks they can address. In the field of Natural Language Processing (NLP), researchers have shifted their focus from conventional NLP tasks (e.g., sequence tagging and parsing) towards tasks that revolve around aligning with human needs (e.g., brainstorming and email writing). This shift in task distribution imposes new requirements on evaluating these aligned models regarding generality (i.e., assessing performance across diverse scenarios), flexibility (i.e., examining under different protocols), an"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.05470","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T07:27:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cae87f51c5a87cab213c557b763b7f03cadbd27c928532318d17eb167afdb073","abstract_canon_sha256":"f90d6f0e1897c3c093954d6c3003607af2778d507d592faaa290af2d9221a885"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:28.389165Z","signature_b64":"6lqVvyhrRL+gMrZdwgWpRdEuJi7j7cZG2WNd87PaldwM1HbBhWbpMY4yamjLz5rs2poLW9M44BZoyHFfsbWcDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33442666f1095c35f1e74aa7907b1fde817a2382c495d04b22ca6f45f26407a1","last_reissued_at":"2026-07-05T07:21:28.388682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:28.388682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Judge for Evaluating Alignment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Junlong Li, Pengfei Liu, Run-Ze Fan, Shichao Sun, Weizhe Yuan","submitted_at":"2023-10-09T07:27:15Z","abstract_excerpt":"The rapid development of Large Language Models (LLMs) has substantially expanded the range of tasks they can address. In the field of Natural Language Processing (NLP), researchers have shifted their focus from conventional NLP tasks (e.g., sequence tagging and parsing) towards tasks that revolve around aligning with human needs (e.g., brainstorming and email writing). This shift in task distribution imposes new requirements on evaluating these aligned models regarding generality (i.e., assessing performance across diverse scenarios), flexibility (i.e., examining under different protocols), an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05470","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/2310.05470/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.05470","created_at":"2026-07-05T07:21:28.388750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.05470v2","created_at":"2026-07-05T07:21:28.388750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05470","created_at":"2026-07-05T07:21:28.388750+00:00"},{"alias_kind":"pith_short_12","alias_value":"GNCCMZXRBFOD","created_at":"2026-07-05T07:21:28.388750+00:00"},{"alias_kind":"pith_short_16","alias_value":"GNCCMZXRBFODL4PH","created_at":"2026-07-05T07:21:28.388750+00:00"},{"alias_kind":"pith_short_8","alias_value":"GNCCMZXR","created_at":"2026-07-05T07:21:28.388750+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01249","citing_title":"Trust Region On-Policy Distillation","ref_index":149,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00093","citing_title":"Agreement Metrics for LLM-as-Judge Evaluation: What to Report and Why","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15594","citing_title":"A Survey on LLM-as-a-Judge","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19237","citing_title":"Sensorimotor Self-Recognition in Multimodal Large Language Model-Driven Robots","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2509.08827","citing_title":"A Survey of Reinforcement Learning for Large Reasoning Models","ref_index":276,"is_internal_anchor":false},{"citing_arxiv_id":"2502.03387","citing_title":"LIMO: Less is More for Reasoning","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16335","citing_title":"Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2501.13918","citing_title":"Improving Video Generation with Human Feedback","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27727","citing_title":"LLM-as-a-Judge for Human-AI Co-Creation: A Reliability-Aware Evaluation Framework for Coding","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23178","citing_title":"Judging the Judges: A Systematic Evaluation of Bias Mitigation Strategies in LLM-as-a-Judge Pipelines","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GNCCMZXRBFODL4PHJKTZA6Y732","json":"https://pith.science/pith/GNCCMZXRBFODL4PHJKTZA6Y732.json","graph_json":"https://pith.science/api/pith-number/GNCCMZXRBFODL4PHJKTZA6Y732/graph.json","events_json":"https://pith.science/api/pith-number/GNCCMZXRBFODL4PHJKTZA6Y732/events.json","paper":"https://pith.science/paper/GNCCMZXR"},"agent_actions":{"view_html":"https://pith.science/pith/GNCCMZXRBFODL4PHJKTZA6Y732","download_json":"https://pith.science/pith/GNCCMZXRBFODL4PHJKTZA6Y732.json","view_paper":"https://pith.science/paper/GNCCMZXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.05470&json=true","fetch_graph":"https://pith.science/api/pith-number/GNCCMZXRBFODL4PHJKTZA6Y732/graph.json","fetch_events":"https://pith.science/api/pith-number/GNCCMZXRBFODL4PHJKTZA6Y732/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GNCCMZXRBFODL4PHJKTZA6Y732/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GNCCMZXRBFODL4PHJKTZA6Y732/action/storage_attestation","attest_author":"https://pith.science/pith/GNCCMZXRBFODL4PHJKTZA6Y732/action/author_attestation","sign_citation":"https://pith.science/pith/GNCCMZXRBFODL4PHJKTZA6Y732/action/citation_signature","submit_replication":"https://pith.science/pith/GNCCMZXRBFODL4PHJKTZA6Y732/action/replication_record"}},"created_at":"2026-07-05T07:21:28.388750+00:00","updated_at":"2026-07-05T07:21:28.388750+00:00"}