{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZSJAO2BZFL4KMOINQLMYXWCCHJ","short_pith_number":"pith:ZSJAO2BZ","canonical_record":{"source":{"id":"2310.17631","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T17:48:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8e2cf349ad0e69f1255636bd9126f6cb5ac0d40e8272f8aecbe9375c824d52b0","abstract_canon_sha256":"63ce418f30910591ef4dc186301fc1e9a4b1a7fbe035695e022f13cf3b93e90a"},"schema_version":"1.0"},"canonical_sha256":"cc920768392af8a6390d82d98bd8423a4df3b4476640162c86f3fca468f4f1a6","source":{"kind":"arxiv","id":"2310.17631","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17631","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17631v2","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17631","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_12","alias_value":"ZSJAO2BZFL4K","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_16","alias_value":"ZSJAO2BZFL4KMOIN","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_8","alias_value":"ZSJAO2BZ","created_at":"2026-07-05T10:21:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZSJAO2BZFL4KMOINQLMYXWCCHJ","target":"record","payload":{"canonical_record":{"source":{"id":"2310.17631","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T17:48:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8e2cf349ad0e69f1255636bd9126f6cb5ac0d40e8272f8aecbe9375c824d52b0","abstract_canon_sha256":"63ce418f30910591ef4dc186301fc1e9a4b1a7fbe035695e022f13cf3b93e90a"},"schema_version":"1.0"},"canonical_sha256":"cc920768392af8a6390d82d98bd8423a4df3b4476640162c86f3fca468f4f1a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:56.379145Z","signature_b64":"zqOilBO5SjzLLeV+B7FJYBPJ8bMZ30h3ERDx+k6mhcvTdbGOr0PWaxZKQMgACa0IZsWa7fHnPDin3mI70rkACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc920768392af8a6390d82d98bd8423a4df3b4476640162c86f3fca468f4f1a6","last_reissued_at":"2026-07-05T10:21:56.378712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:56.378712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.17631","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:21:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0CXU9U5U8SOGZ2iY1ADrqstkomAB3PN29ECvRt4rU6kfPu0fHCKZDZlcNpYXOKNhL2DdQjdEGyfXJAjCG7R+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T07:22:41.950113Z"},"content_sha256":"bb5b7fa050d63c6d4f6f374bbd62ad3add6695b8057730917b458febb84b97cd","schema_version":"1.0","event_id":"sha256:bb5b7fa050d63c6d4f6f374bbd62ad3add6695b8057730917b458febb84b97cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZSJAO2BZFL4KMOINQLMYXWCCHJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"JudgeLM: Fine-tuned Large Language Models are Scalable Judges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lianghui Zhu, Xinggang Wang, Xinlong Wang","submitted_at":"2023-10-26T17:48:58Z","abstract_excerpt":"Evaluating Large Language Models (LLMs) in open-ended scenarios is challenging because existing benchmarks and metrics can not measure them comprehensively. To address this problem, we propose to fine-tune LLMs as scalable judges (JudgeLM) to evaluate LLMs efficiently and effectively in open-ended benchmarks. We first propose a comprehensive, large-scale, high-quality dataset containing task seeds, LLMs-generated answers, and GPT-4-generated judgments for fine-tuning high-performance judges, as well as a new benchmark for evaluating the judges. We train JudgeLM at different scales from 7B, 13B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17631","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/2310.17631/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":"2026-07-05T10:21:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZcYXtZUgQmcsvizmR1gIa3u1pIbClm1PLoYnQB1GzVSHTCHFpxljbrmCznlCRLNDeRDs5CnRuPYWnoEAgMIPCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T07:22:41.950497Z"},"content_sha256":"e3fb197f02456226a28fdcfaec592da3d88f376077e03d2492b91d123efde7ef","schema_version":"1.0","event_id":"sha256:e3fb197f02456226a28fdcfaec592da3d88f376077e03d2492b91d123efde7ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZSJAO2BZFL4KMOINQLMYXWCCHJ/bundle.json","state_url":"https://pith.science/pith/ZSJAO2BZFL4KMOINQLMYXWCCHJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZSJAO2BZFL4KMOINQLMYXWCCHJ/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":"2026-07-11T07:22:41Z","links":{"resolver":"https://pith.science/pith/ZSJAO2BZFL4KMOINQLMYXWCCHJ","bundle":"https://pith.science/pith/ZSJAO2BZFL4KMOINQLMYXWCCHJ/bundle.json","state":"https://pith.science/pith/ZSJAO2BZFL4KMOINQLMYXWCCHJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZSJAO2BZFL4KMOINQLMYXWCCHJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZSJAO2BZFL4KMOINQLMYXWCCHJ","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":"63ce418f30910591ef4dc186301fc1e9a4b1a7fbe035695e022f13cf3b93e90a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T17:48:58Z","title_canon_sha256":"8e2cf349ad0e69f1255636bd9126f6cb5ac0d40e8272f8aecbe9375c824d52b0"},"schema_version":"1.0","source":{"id":"2310.17631","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17631","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17631v2","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17631","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_12","alias_value":"ZSJAO2BZFL4K","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_16","alias_value":"ZSJAO2BZFL4KMOIN","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_8","alias_value":"ZSJAO2BZ","created_at":"2026-07-05T10:21:56Z"}],"graph_snapshots":[{"event_id":"sha256:e3fb197f02456226a28fdcfaec592da3d88f376077e03d2492b91d123efde7ef","target":"graph","created_at":"2026-07-05T10:21:56Z","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/2310.17631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating Large Language Models (LLMs) in open-ended scenarios is challenging because existing benchmarks and metrics can not measure them comprehensively. To address this problem, we propose to fine-tune LLMs as scalable judges (JudgeLM) to evaluate LLMs efficiently and effectively in open-ended benchmarks. We first propose a comprehensive, large-scale, high-quality dataset containing task seeds, LLMs-generated answers, and GPT-4-generated judgments for fine-tuning high-performance judges, as well as a new benchmark for evaluating the judges. We train JudgeLM at different scales from 7B, 13B","authors_text":"Lianghui Zhu, Xinggang Wang, Xinlong Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T17:48:58Z","title":"JudgeLM: Fine-tuned Large Language Models are Scalable Judges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17631","kind":"arxiv","version":2},"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:bb5b7fa050d63c6d4f6f374bbd62ad3add6695b8057730917b458febb84b97cd","target":"record","created_at":"2026-07-05T10:21:56Z","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":"63ce418f30910591ef4dc186301fc1e9a4b1a7fbe035695e022f13cf3b93e90a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T17:48:58Z","title_canon_sha256":"8e2cf349ad0e69f1255636bd9126f6cb5ac0d40e8272f8aecbe9375c824d52b0"},"schema_version":"1.0","source":{"id":"2310.17631","kind":"arxiv","version":2}},"canonical_sha256":"cc920768392af8a6390d82d98bd8423a4df3b4476640162c86f3fca468f4f1a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc920768392af8a6390d82d98bd8423a4df3b4476640162c86f3fca468f4f1a6","first_computed_at":"2026-07-05T10:21:56.378712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:56.378712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zqOilBO5SjzLLeV+B7FJYBPJ8bMZ30h3ERDx+k6mhcvTdbGOr0PWaxZKQMgACa0IZsWa7fHnPDin3mI70rkACg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:56.379145Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.17631","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb5b7fa050d63c6d4f6f374bbd62ad3add6695b8057730917b458febb84b97cd","sha256:e3fb197f02456226a28fdcfaec592da3d88f376077e03d2492b91d123efde7ef"],"state_sha256":"2c912c1ad73201bd77adf3110e09dfba656fd0df1af02b6e3ca117ec336a5c29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hsuoVskaW20k+WVo+EfUUxlhGeMbq+LGxqqw6TuKtGZSL6+qn+Doralo0ECsDi8dJWEXaNJQVkW4uY0BpmUaAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T07:22:41.952860Z","bundle_sha256":"90fca05931ed185cbc6d55faf05958d8db27504c032ec1c4f04fd882d87a88fa"}}