{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ODDX3BV4ZRYVT44AQ77YUEVQKM","short_pith_number":"pith:ODDX3BV4","canonical_record":{"source":{"id":"2503.04360","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T12:04:29Z","cross_cats_sorted":[],"title_canon_sha256":"dd681026f745716921f7bb276d5986b3bce8aecd290e86caf2a3e7ae116cf77a","abstract_canon_sha256":"2d2964b70141e330ea9d33c617bab661ad753e927d4eafc0c8e257fefea40777"},"schema_version":"1.0"},"canonical_sha256":"70c77d86bccc7159f38087ff8a12b0530033024f861011e8cb3d80ef6ef0c582","source":{"kind":"arxiv","id":"2503.04360","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04360","created_at":"2026-07-05T10:25:36Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04360v1","created_at":"2026-07-05T10:25:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04360","created_at":"2026-07-05T10:25:36Z"},{"alias_kind":"pith_short_12","alias_value":"ODDX3BV4ZRYV","created_at":"2026-07-05T10:25:36Z"},{"alias_kind":"pith_short_16","alias_value":"ODDX3BV4ZRYVT44A","created_at":"2026-07-05T10:25:36Z"},{"alias_kind":"pith_short_8","alias_value":"ODDX3BV4","created_at":"2026-07-05T10:25:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ODDX3BV4ZRYVT44AQ77YUEVQKM","target":"record","payload":{"canonical_record":{"source":{"id":"2503.04360","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T12:04:29Z","cross_cats_sorted":[],"title_canon_sha256":"dd681026f745716921f7bb276d5986b3bce8aecd290e86caf2a3e7ae116cf77a","abstract_canon_sha256":"2d2964b70141e330ea9d33c617bab661ad753e927d4eafc0c8e257fefea40777"},"schema_version":"1.0"},"canonical_sha256":"70c77d86bccc7159f38087ff8a12b0530033024f861011e8cb3d80ef6ef0c582","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:36.728860Z","signature_b64":"jdwEMysOMCYFvS1wozB8FcRUbigH9aTkDunnFWZYRIVDf3hwg7nbFIW8Z1u9peqJfbshF5waU+XheoA4+AYHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70c77d86bccc7159f38087ff8a12b0530033024f861011e8cb3d80ef6ef0c582","last_reissued_at":"2026-07-05T10:25:36.727926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:36.727926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.04360","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":"2026-07-05T10:25:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nfouTDc5+nWvQOMF7eKAZMDDZgynlpGuDOm05v/IvedFZwXMuPYEasdP4CRsGH8PujM/0h1ATaCCPIpokaSbCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:40:37.328591Z"},"content_sha256":"926fcb6081bbc00a94f0a151279a31fff6306163cbe344ec58d488d551432fd0","schema_version":"1.0","event_id":"sha256:926fcb6081bbc00a94f0a151279a31fff6306163cbe344ec58d488d551432fd0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ODDX3BV4ZRYVT44AQ77YUEVQKM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring the Multilingual NLG Evaluation Abilities of LLM-Based Evaluators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiayi Chang, Mingqi Gao, Xiaojun Wan, Xinyu Hu","submitted_at":"2025-03-06T12:04:29Z","abstract_excerpt":"Previous research has shown that LLMs have potential in multilingual NLG evaluation tasks. However, existing research has not fully explored the differences in the evaluation capabilities of LLMs across different languages. To this end, this study provides a comprehensive analysis of the multilingual evaluation performance of 10 recent LLMs, spanning high-resource and low-resource languages through correlation analysis, perturbation attacks, and fine-tuning. We found that 1) excluding the reference answer from the prompt and using large-parameter LLM-based evaluators leads to better performanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04360","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/2503.04360/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":"2026-07-05T10:25:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gWNqlfSqdosOfWFw8I1yHaSx3vN40SNvZx+Qy4LPmEq733i5fOOL6BXuf0+4kM5yPz3uElr1YFccZThXyIVAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:40:37.329099Z"},"content_sha256":"5afc5ab0766059f522f0b51629252e7839314d7f15d155c047687039af8a7990","schema_version":"1.0","event_id":"sha256:5afc5ab0766059f522f0b51629252e7839314d7f15d155c047687039af8a7990"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ODDX3BV4ZRYVT44AQ77YUEVQKM/bundle.json","state_url":"https://pith.science/pith/ODDX3BV4ZRYVT44AQ77YUEVQKM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ODDX3BV4ZRYVT44AQ77YUEVQKM/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":"2026-08-04T12:40:37Z","links":{"resolver":"https://pith.science/pith/ODDX3BV4ZRYVT44AQ77YUEVQKM","bundle":"https://pith.science/pith/ODDX3BV4ZRYVT44AQ77YUEVQKM/bundle.json","state":"https://pith.science/pith/ODDX3BV4ZRYVT44AQ77YUEVQKM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ODDX3BV4ZRYVT44AQ77YUEVQKM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ODDX3BV4ZRYVT44AQ77YUEVQKM","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":"2d2964b70141e330ea9d33c617bab661ad753e927d4eafc0c8e257fefea40777","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T12:04:29Z","title_canon_sha256":"dd681026f745716921f7bb276d5986b3bce8aecd290e86caf2a3e7ae116cf77a"},"schema_version":"1.0","source":{"id":"2503.04360","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04360","created_at":"2026-07-05T10:25:36Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04360v1","created_at":"2026-07-05T10:25:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04360","created_at":"2026-07-05T10:25:36Z"},{"alias_kind":"pith_short_12","alias_value":"ODDX3BV4ZRYV","created_at":"2026-07-05T10:25:36Z"},{"alias_kind":"pith_short_16","alias_value":"ODDX3BV4ZRYVT44A","created_at":"2026-07-05T10:25:36Z"},{"alias_kind":"pith_short_8","alias_value":"ODDX3BV4","created_at":"2026-07-05T10:25:36Z"}],"graph_snapshots":[{"event_id":"sha256:5afc5ab0766059f522f0b51629252e7839314d7f15d155c047687039af8a7990","target":"graph","created_at":"2026-07-05T10:25:36Z","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/2503.04360/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Previous research has shown that LLMs have potential in multilingual NLG evaluation tasks. However, existing research has not fully explored the differences in the evaluation capabilities of LLMs across different languages. To this end, this study provides a comprehensive analysis of the multilingual evaluation performance of 10 recent LLMs, spanning high-resource and low-resource languages through correlation analysis, perturbation attacks, and fine-tuning. We found that 1) excluding the reference answer from the prompt and using large-parameter LLM-based evaluators leads to better performanc","authors_text":"Jiayi Chang, Mingqi Gao, Xiaojun Wan, Xinyu Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T12:04:29Z","title":"Exploring the Multilingual NLG Evaluation Abilities of LLM-Based Evaluators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04360","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":"sha256:926fcb6081bbc00a94f0a151279a31fff6306163cbe344ec58d488d551432fd0","target":"record","created_at":"2026-07-05T10:25:36Z","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":"2d2964b70141e330ea9d33c617bab661ad753e927d4eafc0c8e257fefea40777","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T12:04:29Z","title_canon_sha256":"dd681026f745716921f7bb276d5986b3bce8aecd290e86caf2a3e7ae116cf77a"},"schema_version":"1.0","source":{"id":"2503.04360","kind":"arxiv","version":1}},"canonical_sha256":"70c77d86bccc7159f38087ff8a12b0530033024f861011e8cb3d80ef6ef0c582","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70c77d86bccc7159f38087ff8a12b0530033024f861011e8cb3d80ef6ef0c582","first_computed_at":"2026-07-05T10:25:36.727926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:36.727926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jdwEMysOMCYFvS1wozB8FcRUbigH9aTkDunnFWZYRIVDf3hwg7nbFIW8Z1u9peqJfbshF5waU+XheoA4+AYHDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:36.728860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.04360","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:926fcb6081bbc00a94f0a151279a31fff6306163cbe344ec58d488d551432fd0","sha256:5afc5ab0766059f522f0b51629252e7839314d7f15d155c047687039af8a7990"],"state_sha256":"607d9d6355ae09f6c2986d8e93ab5f5e0c22d4c85234809eae49e4cd5b192d26"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bk56hwIV0ghN8hAJqDXS4a0BVZEa2xN8+tDpjkN6Oc2JeMfQW+xspwxPtC473QeGospnaS6O6N2tcsfs0qOGCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:40:37.332305Z","bundle_sha256":"27eca254f0b5aab02eadfbb75ecb133a34954dd3c5d5a113c50dd37d03b35687"}}