{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3ALB7XMRWXIPXE5NE7YOTENQ3S","short_pith_number":"pith:3ALB7XMR","canonical_record":{"source":{"id":"2310.19740","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T17:04:35Z","cross_cats_sorted":[],"title_canon_sha256":"ad921c7c2e23938c7cd59e57acdad2373fb9848fa649e28accfee761e3370b1a","abstract_canon_sha256":"6ec54b336a01a0b7694b39f6c09402f5cf0b092de5e3c7154b60b16c9fe2bb47"},"schema_version":"1.0"},"canonical_sha256":"d8161fdd91b5d0fb93ad27f0e991b0dc9d30c5c3a88c83d8e70abd5924b50732","source":{"kind":"arxiv","id":"2310.19740","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19740","created_at":"2026-07-05T10:02:21Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19740v2","created_at":"2026-07-05T10:02:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19740","created_at":"2026-07-05T10:02:21Z"},{"alias_kind":"pith_short_12","alias_value":"3ALB7XMRWXIP","created_at":"2026-07-05T10:02:21Z"},{"alias_kind":"pith_short_16","alias_value":"3ALB7XMRWXIPXE5N","created_at":"2026-07-05T10:02:21Z"},{"alias_kind":"pith_short_8","alias_value":"3ALB7XMR","created_at":"2026-07-05T10:02:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3ALB7XMRWXIPXE5NE7YOTENQ3S","target":"record","payload":{"canonical_record":{"source":{"id":"2310.19740","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T17:04:35Z","cross_cats_sorted":[],"title_canon_sha256":"ad921c7c2e23938c7cd59e57acdad2373fb9848fa649e28accfee761e3370b1a","abstract_canon_sha256":"6ec54b336a01a0b7694b39f6c09402f5cf0b092de5e3c7154b60b16c9fe2bb47"},"schema_version":"1.0"},"canonical_sha256":"d8161fdd91b5d0fb93ad27f0e991b0dc9d30c5c3a88c83d8e70abd5924b50732","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:21.708719Z","signature_b64":"hZedTSim8K3KYNs5nSUI6xtUE33vRYPbnOaX737kiGiMKXFcLa8UJtOROGxanYSdOMcHSBNBbPLNQqfzRzsCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8161fdd91b5d0fb93ad27f0e991b0dc9d30c5c3a88c83d8e70abd5924b50732","last_reissued_at":"2026-07-05T10:02:21.708159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:21.708159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.19740","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":"2026-07-05T10:02:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DPeljY8WfapNazFV2cy5b0QXxIwJ0FMRDKullibzoocj+gUSZZ7na44nI9M7fjr8E+mYKHSSCouLQJ5qcymAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:07:48.712368Z"},"content_sha256":"125e4534a94e0162af2b1592c8701691fa3dca42a29f19bd6ef1dea406c083e9","schema_version":"1.0","event_id":"sha256:125e4534a94e0162af2b1592c8701691fa3dca42a29f19bd6ef1dea406c083e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3ALB7XMRWXIPXE5NE7YOTENQ3S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Leyang Cui, Lingpeng Kong, Qintong Li, Wei Bi","submitted_at":"2023-10-30T17:04:35Z","abstract_excerpt":"Previous work adopts large language models (LLMs) as evaluators to evaluate natural language process (NLP) tasks. However, certain shortcomings, e.g., fairness, scope, and accuracy, persist for current LLM evaluators. To analyze whether LLMs can serve as reliable alternatives to humans, we examine the fine-grained alignment between LLM evaluators and human annotators, particularly in understanding the target evaluation tasks and conducting evaluations that meet diverse criteria. This paper explores both conventional tasks (e.g., story generation) and alignment tasks (e.g., math reasoning), eac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19740","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/2310.19740/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":"2026-07-05T10:02:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GJgOnPEecIXskljRLQ/+lRlus+2nYB8yFek7AjqM0deTwDxrtyVi1cFA1+CEppib8ovr18d22P6dnWmxKfncAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:07:48.713221Z"},"content_sha256":"a8a039a1235527bf834a934275e4d4234ffc9eb3f4748d78c365ce1649a735a2","schema_version":"1.0","event_id":"sha256:a8a039a1235527bf834a934275e4d4234ffc9eb3f4748d78c365ce1649a735a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3ALB7XMRWXIPXE5NE7YOTENQ3S/bundle.json","state_url":"https://pith.science/pith/3ALB7XMRWXIPXE5NE7YOTENQ3S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3ALB7XMRWXIPXE5NE7YOTENQ3S/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":"2026-08-15T17:07:48Z","links":{"resolver":"https://pith.science/pith/3ALB7XMRWXIPXE5NE7YOTENQ3S","bundle":"https://pith.science/pith/3ALB7XMRWXIPXE5NE7YOTENQ3S/bundle.json","state":"https://pith.science/pith/3ALB7XMRWXIPXE5NE7YOTENQ3S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3ALB7XMRWXIPXE5NE7YOTENQ3S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3ALB7XMRWXIPXE5NE7YOTENQ3S","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":"6ec54b336a01a0b7694b39f6c09402f5cf0b092de5e3c7154b60b16c9fe2bb47","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T17:04:35Z","title_canon_sha256":"ad921c7c2e23938c7cd59e57acdad2373fb9848fa649e28accfee761e3370b1a"},"schema_version":"1.0","source":{"id":"2310.19740","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19740","created_at":"2026-07-05T10:02:21Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19740v2","created_at":"2026-07-05T10:02:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19740","created_at":"2026-07-05T10:02:21Z"},{"alias_kind":"pith_short_12","alias_value":"3ALB7XMRWXIP","created_at":"2026-07-05T10:02:21Z"},{"alias_kind":"pith_short_16","alias_value":"3ALB7XMRWXIPXE5N","created_at":"2026-07-05T10:02:21Z"},{"alias_kind":"pith_short_8","alias_value":"3ALB7XMR","created_at":"2026-07-05T10:02:21Z"}],"graph_snapshots":[{"event_id":"sha256:a8a039a1235527bf834a934275e4d4234ffc9eb3f4748d78c365ce1649a735a2","target":"graph","created_at":"2026-07-05T10:02:21Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.19740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Previous work adopts large language models (LLMs) as evaluators to evaluate natural language process (NLP) tasks. However, certain shortcomings, e.g., fairness, scope, and accuracy, persist for current LLM evaluators. To analyze whether LLMs can serve as reliable alternatives to humans, we examine the fine-grained alignment between LLM evaluators and human annotators, particularly in understanding the target evaluation tasks and conducting evaluations that meet diverse criteria. This paper explores both conventional tasks (e.g., story generation) and alignment tasks (e.g., math reasoning), eac","authors_text":"Leyang Cui, Lingpeng Kong, Qintong Li, Wei Bi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T17:04:35Z","title":"Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19740","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":"sha256:125e4534a94e0162af2b1592c8701691fa3dca42a29f19bd6ef1dea406c083e9","target":"record","created_at":"2026-07-05T10:02:21Z","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":"6ec54b336a01a0b7694b39f6c09402f5cf0b092de5e3c7154b60b16c9fe2bb47","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T17:04:35Z","title_canon_sha256":"ad921c7c2e23938c7cd59e57acdad2373fb9848fa649e28accfee761e3370b1a"},"schema_version":"1.0","source":{"id":"2310.19740","kind":"arxiv","version":2}},"canonical_sha256":"d8161fdd91b5d0fb93ad27f0e991b0dc9d30c5c3a88c83d8e70abd5924b50732","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8161fdd91b5d0fb93ad27f0e991b0dc9d30c5c3a88c83d8e70abd5924b50732","first_computed_at":"2026-07-05T10:02:21.708159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:21.708159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hZedTSim8K3KYNs5nSUI6xtUE33vRYPbnOaX737kiGiMKXFcLa8UJtOROGxanYSdOMcHSBNBbPLNQqfzRzsCBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:21.708719Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.19740","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:125e4534a94e0162af2b1592c8701691fa3dca42a29f19bd6ef1dea406c083e9","sha256:a8a039a1235527bf834a934275e4d4234ffc9eb3f4748d78c365ce1649a735a2"],"state_sha256":"d5d00b08825f9d62bcdc3f0e6a9185b4834a5ad67c549fb20486656a113a58c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AccNzRLH6q+d13/NSUXaaxfqeXedH+xkKZZnMO7n7+x1cgxGp0Dzi55nuPoJVCsJ3MouJL+NZIEjjElGLkr8Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:07:48.719411Z","bundle_sha256":"fafc6b3e89148cd0f7cbc9987e83bc34a1e5859829227f3f040715672b246955"}}