{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WBRSQ7UHHLI5BEBVP6G6RY5EPQ","short_pith_number":"pith:WBRSQ7UH","canonical_record":{"source":{"id":"2410.12784","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-16T17:58:19Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"397aaa25030d0a9eba6e331062873b61db47e2cf1902bd5e4d27a7f34f4f88e7","abstract_canon_sha256":"3d84c5f3f302ddd28fe40cbe37ee6ddc65caa237fde722582d2f6060a7f39b70"},"schema_version":"1.0"},"canonical_sha256":"b063287e873ad1d090357f8de8e3a47c073865e8d1a36361c8ae05de181061e7","source":{"kind":"arxiv","id":"2410.12784","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12784","created_at":"2026-05-18T01:18:21Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12784v2","created_at":"2026-05-18T01:18:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12784","created_at":"2026-05-18T01:18:21Z"},{"alias_kind":"pith_short_12","alias_value":"WBRSQ7UHHLI5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"WBRSQ7UHHLI5BEBV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"WBRSQ7UH","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WBRSQ7UHHLI5BEBVP6G6RY5EPQ","target":"record","payload":{"canonical_record":{"source":{"id":"2410.12784","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-16T17:58:19Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"397aaa25030d0a9eba6e331062873b61db47e2cf1902bd5e4d27a7f34f4f88e7","abstract_canon_sha256":"3d84c5f3f302ddd28fe40cbe37ee6ddc65caa237fde722582d2f6060a7f39b70"},"schema_version":"1.0"},"canonical_sha256":"b063287e873ad1d090357f8de8e3a47c073865e8d1a36361c8ae05de181061e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:18:21.885904Z","signature_b64":"3Nv6dvTIIAi2Dp9TjRkFsfXJ8c9H0FKfSa+yQ222TpQgRW0TuMXf50+4GDnsZqbkexPW5v0tGF4u53En66RzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b063287e873ad1d090357f8de8e3a47c073865e8d1a36361c8ae05de181061e7","last_reissued_at":"2026-05-18T01:18:21.885230Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:18:21.885230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.12784","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":"2026-05-18T01:18:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rwTcCpuTNuiB8s+XrC6iHqzvraE+Gg+Kvp3qk0WE1rx7EHFtK7f8TJByZqVSdgCWOwIiaKFOs8ZGNbM8APWbCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T08:40:56.537310Z"},"content_sha256":"59504c07c2db0ec8e08ecc246f7dd77c3ee2a67545b2c1245b24250a326b1d9a","schema_version":"1.0","event_id":"sha256:59504c07c2db0ec8e08ecc246f7dd77c3ee2a67545b2c1245b24250a326b1d9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WBRSQ7UHHLI5BEBVP6G6RY5EPQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Alejandro Cuadron, Chenguang Wang, Ion Stoica, Kyle Montgomery, Raluca Ada Popa, Sijun Tan, Siyuan Zhuang, William Y. Tang","submitted_at":"2024-10-16T17:58:19Z","abstract_excerpt":"LLM-based judges have emerged as a scalable alternative to human evaluation and are increasingly used to assess, compare, and improve models. However, the reliability of LLM-based judges themselves is rarely scrutinized. As LLMs become more advanced, their responses grow more sophisticated, requiring stronger judges to evaluate them. Existing benchmarks primarily focus on a judge's alignment with human preferences, but often fail to account for more challenging tasks where crowdsourced human preference is a poor indicator of factual and logical correctness. To address this, we propose a novel "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12784","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":""},"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":"2026-05-18T01:18:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T96xA7LEBkO0PNaVPetz9oxorJ3yFpkWhGbN8ZHAyAei9p79k60XABfmgdqD3cSt7T2d7tbXbJNNxywzv5oeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T08:40:56.537829Z"},"content_sha256":"c6ded7310145959f80808f94d404fd4edb0ecd31a8eefdb20838e75670075f49","schema_version":"1.0","event_id":"sha256:c6ded7310145959f80808f94d404fd4edb0ecd31a8eefdb20838e75670075f49"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WBRSQ7UHHLI5BEBVP6G6RY5EPQ/bundle.json","state_url":"https://pith.science/pith/WBRSQ7UHHLI5BEBVP6G6RY5EPQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WBRSQ7UHHLI5BEBVP6G6RY5EPQ/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":"2026-05-27T08:40:56Z","links":{"resolver":"https://pith.science/pith/WBRSQ7UHHLI5BEBVP6G6RY5EPQ","bundle":"https://pith.science/pith/WBRSQ7UHHLI5BEBVP6G6RY5EPQ/bundle.json","state":"https://pith.science/pith/WBRSQ7UHHLI5BEBVP6G6RY5EPQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WBRSQ7UHHLI5BEBVP6G6RY5EPQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WBRSQ7UHHLI5BEBVP6G6RY5EPQ","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":"3d84c5f3f302ddd28fe40cbe37ee6ddc65caa237fde722582d2f6060a7f39b70","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-16T17:58:19Z","title_canon_sha256":"397aaa25030d0a9eba6e331062873b61db47e2cf1902bd5e4d27a7f34f4f88e7"},"schema_version":"1.0","source":{"id":"2410.12784","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12784","created_at":"2026-05-18T01:18:21Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12784v2","created_at":"2026-05-18T01:18:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12784","created_at":"2026-05-18T01:18:21Z"},{"alias_kind":"pith_short_12","alias_value":"WBRSQ7UHHLI5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"WBRSQ7UHHLI5BEBV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"WBRSQ7UH","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c6ded7310145959f80808f94d404fd4edb0ecd31a8eefdb20838e75670075f49","target":"graph","created_at":"2026-05-18T01:18:21Z","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"},"paper":{"abstract_excerpt":"LLM-based judges have emerged as a scalable alternative to human evaluation and are increasingly used to assess, compare, and improve models. However, the reliability of LLM-based judges themselves is rarely scrutinized. As LLMs become more advanced, their responses grow more sophisticated, requiring stronger judges to evaluate them. Existing benchmarks primarily focus on a judge's alignment with human preferences, but often fail to account for more challenging tasks where crowdsourced human preference is a poor indicator of factual and logical correctness. To address this, we propose a novel ","authors_text":"Alejandro Cuadron, Chenguang Wang, Ion Stoica, Kyle Montgomery, Raluca Ada Popa, Sijun Tan, Siyuan Zhuang, William Y. Tang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-16T17:58:19Z","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12784","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":"sha256:59504c07c2db0ec8e08ecc246f7dd77c3ee2a67545b2c1245b24250a326b1d9a","target":"record","created_at":"2026-05-18T01:18:21Z","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":"3d84c5f3f302ddd28fe40cbe37ee6ddc65caa237fde722582d2f6060a7f39b70","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-16T17:58:19Z","title_canon_sha256":"397aaa25030d0a9eba6e331062873b61db47e2cf1902bd5e4d27a7f34f4f88e7"},"schema_version":"1.0","source":{"id":"2410.12784","kind":"arxiv","version":2}},"canonical_sha256":"b063287e873ad1d090357f8de8e3a47c073865e8d1a36361c8ae05de181061e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b063287e873ad1d090357f8de8e3a47c073865e8d1a36361c8ae05de181061e7","first_computed_at":"2026-05-18T01:18:21.885230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:18:21.885230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3Nv6dvTIIAi2Dp9TjRkFsfXJ8c9H0FKfSa+yQ222TpQgRW0TuMXf50+4GDnsZqbkexPW5v0tGF4u53En66RzAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:18:21.885904Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12784","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59504c07c2db0ec8e08ecc246f7dd77c3ee2a67545b2c1245b24250a326b1d9a","sha256:c6ded7310145959f80808f94d404fd4edb0ecd31a8eefdb20838e75670075f49"],"state_sha256":"c008e83e4bf6f3b47ba5dc86ab2bd485201ccca16909e6b1c5563154b16cf1fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TZ+BvDfQChw9Wf531ij0EjnhaIQsSSZzCom3OVonRixGmKwcWeGhAks/vP+55IF+w/66VFN7iz2PgHhf5kzkDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T08:40:56.541617Z","bundle_sha256":"c24a21ab7c67957e9a846c5d299c7134f8e81c77d04b8540ff5f25b54afee37b"}}