{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3B54YSARSKYSBYAAKQTM7HVJ6B","short_pith_number":"pith:3B54YSAR","canonical_record":{"source":{"id":"2506.22316","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T15:25:23Z","cross_cats_sorted":[],"title_canon_sha256":"eb7f2862f4197c3e4e334cdf15e7706e7e197e80013403fc1e407f784dfa8e4e","abstract_canon_sha256":"ec54702453ebdc278664a0cb29f0721e801cb2489811b05a0bd154ee523af03d"},"schema_version":"1.0"},"canonical_sha256":"d87bcc481192b120e0005426cf9ea9f0599d37ddc9d7b479e445757250abb806","source":{"kind":"arxiv","id":"2506.22316","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22316","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22316v4","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22316","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_12","alias_value":"3B54YSARSKYS","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_16","alias_value":"3B54YSARSKYSBYAA","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_8","alias_value":"3B54YSAR","created_at":"2026-05-22T01:03:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3B54YSARSKYSBYAAKQTM7HVJ6B","target":"record","payload":{"canonical_record":{"source":{"id":"2506.22316","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T15:25:23Z","cross_cats_sorted":[],"title_canon_sha256":"eb7f2862f4197c3e4e334cdf15e7706e7e197e80013403fc1e407f784dfa8e4e","abstract_canon_sha256":"ec54702453ebdc278664a0cb29f0721e801cb2489811b05a0bd154ee523af03d"},"schema_version":"1.0"},"canonical_sha256":"d87bcc481192b120e0005426cf9ea9f0599d37ddc9d7b479e445757250abb806","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:43.870577Z","signature_b64":"asQF+86iiWGs0c3rRhx5dyEA3BtvLHRwFj7feC5E+WLsL39siWPENvE9smp388HCva4n//TC4wh8gn5f6qbOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d87bcc481192b120e0005426cf9ea9f0599d37ddc9d7b479e445757250abb806","last_reissued_at":"2026-05-22T01:03:43.869877Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:43.869877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.22316","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:03:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wz0VfggAhwOtad41pLkYPBtsQeuTd0J/ar3Q9tNDYu7VmQXFQG3e0zYsxNBHKmS0dbOPwwxVabOOrW/V/eKZBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T23:35:02.108215Z"},"content_sha256":"e02305e66401bee3cefd845a5fdc4c761a7021a3d2f95a242da91fb2ef034ab3","schema_version":"1.0","event_id":"sha256:e02305e66401bee3cefd845a5fdc4c761a7021a3d2f95a242da91fb2ef034ab3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3B54YSARSKYSBYAAKQTM7HVJ6B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Scoring Bias in LLM-as-a-Judge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Chen, Haixiang Hu, Kailai Shao, Qingquan Li, Shaoyu Dou","submitted_at":"2025-06-27T15:25:23Z","abstract_excerpt":"The \"LLM-as-a-Judge\" paradigm, using Large Language Models (LLMs) as automated evaluators, is pivotal to LLM development, offering scalable feedback for complex tasks. However, the reliability of these judges is compromised by various biases. Existing research has heavily concentrated on biases in comparative evaluations. In contrast, scoring-based evaluations-which assign an absolute score and are often more practical in industrial applications-remain under-investigated. To address this gap, we undertake the first dedicated examination of scoring bias in LLM judges. We shift the focus from bi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22316","kind":"arxiv","version":4},"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/2506.22316/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":"2026-05-22T01:03:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j5MQtkK0x9dnH7TTJwP8AkVqhPygMyXk5U7/CDhH1Y6kR5XtP4lfMxzJptsDIm4f1WTi+8dsT6E51OMHw1VEAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T23:35:02.108949Z"},"content_sha256":"25591c4a0606f81594a5a8efcb0d6ac5eb088a500de184ee5e7aea6d66746d4f","schema_version":"1.0","event_id":"sha256:25591c4a0606f81594a5a8efcb0d6ac5eb088a500de184ee5e7aea6d66746d4f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3B54YSARSKYSBYAAKQTM7HVJ6B/bundle.json","state_url":"https://pith.science/pith/3B54YSARSKYSBYAAKQTM7HVJ6B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3B54YSARSKYSBYAAKQTM7HVJ6B/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":"2026-05-26T23:35:02Z","links":{"resolver":"https://pith.science/pith/3B54YSARSKYSBYAAKQTM7HVJ6B","bundle":"https://pith.science/pith/3B54YSARSKYSBYAAKQTM7HVJ6B/bundle.json","state":"https://pith.science/pith/3B54YSARSKYSBYAAKQTM7HVJ6B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3B54YSARSKYSBYAAKQTM7HVJ6B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3B54YSARSKYSBYAAKQTM7HVJ6B","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":"ec54702453ebdc278664a0cb29f0721e801cb2489811b05a0bd154ee523af03d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T15:25:23Z","title_canon_sha256":"eb7f2862f4197c3e4e334cdf15e7706e7e197e80013403fc1e407f784dfa8e4e"},"schema_version":"1.0","source":{"id":"2506.22316","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22316","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22316v4","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22316","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_12","alias_value":"3B54YSARSKYS","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_16","alias_value":"3B54YSARSKYSBYAA","created_at":"2026-05-22T01:03:43Z"},{"alias_kind":"pith_short_8","alias_value":"3B54YSAR","created_at":"2026-05-22T01:03:43Z"}],"graph_snapshots":[{"event_id":"sha256:25591c4a0606f81594a5a8efcb0d6ac5eb088a500de184ee5e7aea6d66746d4f","target":"graph","created_at":"2026-05-22T01:03:43Z","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/2506.22316/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The \"LLM-as-a-Judge\" paradigm, using Large Language Models (LLMs) as automated evaluators, is pivotal to LLM development, offering scalable feedback for complex tasks. However, the reliability of these judges is compromised by various biases. Existing research has heavily concentrated on biases in comparative evaluations. In contrast, scoring-based evaluations-which assign an absolute score and are often more practical in industrial applications-remain under-investigated. To address this gap, we undertake the first dedicated examination of scoring bias in LLM judges. We shift the focus from bi","authors_text":"Chao Chen, Haixiang Hu, Kailai Shao, Qingquan Li, Shaoyu Dou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T15:25:23Z","title":"Evaluating Scoring Bias in LLM-as-a-Judge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22316","kind":"arxiv","version":4},"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:e02305e66401bee3cefd845a5fdc4c761a7021a3d2f95a242da91fb2ef034ab3","target":"record","created_at":"2026-05-22T01:03:43Z","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":"ec54702453ebdc278664a0cb29f0721e801cb2489811b05a0bd154ee523af03d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T15:25:23Z","title_canon_sha256":"eb7f2862f4197c3e4e334cdf15e7706e7e197e80013403fc1e407f784dfa8e4e"},"schema_version":"1.0","source":{"id":"2506.22316","kind":"arxiv","version":4}},"canonical_sha256":"d87bcc481192b120e0005426cf9ea9f0599d37ddc9d7b479e445757250abb806","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d87bcc481192b120e0005426cf9ea9f0599d37ddc9d7b479e445757250abb806","first_computed_at":"2026-05-22T01:03:43.869877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:43.869877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"asQF+86iiWGs0c3rRhx5dyEA3BtvLHRwFj7feC5E+WLsL39siWPENvE9smp388HCva4n//TC4wh8gn5f6qbOBA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:43.870577Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.22316","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e02305e66401bee3cefd845a5fdc4c761a7021a3d2f95a242da91fb2ef034ab3","sha256:25591c4a0606f81594a5a8efcb0d6ac5eb088a500de184ee5e7aea6d66746d4f"],"state_sha256":"740f688a6d5341abae568c06d6b341110fc73af529ce16d1a7f18ce0ddc63f6c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VMaghW/ItDbla2AsSqLWmm3PYjJPzqD3ovNUrfirXjjAzGziBai6mHjL+/iBYMstETZSPpJoGirnFeon0xy7Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T23:35:02.112335Z","bundle_sha256":"95201d711bd54e9a3023b5975e0cc41c5a8738722230d1343b4423c98bf484d0"}}