{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7NRFTMGASQFHPQ5Y5YT424IWXL","short_pith_number":"pith:7NRFTMGA","canonical_record":{"source":{"id":"2401.07103","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T15:59:09Z","cross_cats_sorted":[],"title_canon_sha256":"e219a4e29de5b031a689788d77d6da84386995ddc7d857d7965eb8506066f3d0","abstract_canon_sha256":"90babc9a90e8a4a4bbacbc81ed96dbba5b212dfecd745d8896a5c85d86275ba7"},"schema_version":"1.0"},"canonical_sha256":"fb6259b0c0940a77c3b8ee27cd7116baff01f3c3c1e3a2214a752d0a4d9b6355","source":{"kind":"arxiv","id":"2401.07103","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.07103","created_at":"2026-07-05T08:30:31Z"},{"alias_kind":"arxiv_version","alias_value":"2401.07103v2","created_at":"2026-07-05T08:30:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07103","created_at":"2026-07-05T08:30:31Z"},{"alias_kind":"pith_short_12","alias_value":"7NRFTMGASQFH","created_at":"2026-07-05T08:30:31Z"},{"alias_kind":"pith_short_16","alias_value":"7NRFTMGASQFHPQ5Y","created_at":"2026-07-05T08:30:31Z"},{"alias_kind":"pith_short_8","alias_value":"7NRFTMGA","created_at":"2026-07-05T08:30:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7NRFTMGASQFHPQ5Y5YT424IWXL","target":"record","payload":{"canonical_record":{"source":{"id":"2401.07103","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T15:59:09Z","cross_cats_sorted":[],"title_canon_sha256":"e219a4e29de5b031a689788d77d6da84386995ddc7d857d7965eb8506066f3d0","abstract_canon_sha256":"90babc9a90e8a4a4bbacbc81ed96dbba5b212dfecd745d8896a5c85d86275ba7"},"schema_version":"1.0"},"canonical_sha256":"fb6259b0c0940a77c3b8ee27cd7116baff01f3c3c1e3a2214a752d0a4d9b6355","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:31.007383Z","signature_b64":"ACNDeRp+HTNL1H6fP1bs5UHLxG/G3xSGkrEAXplLd1bbElkFfCDW2/G5UtPs3HIfvBFdnV20lNn0TBSBGxCjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb6259b0c0940a77c3b8ee27cd7116baff01f3c3c1e3a2214a752d0a4d9b6355","last_reissued_at":"2026-07-05T08:30:31.006858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:31.006858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.07103","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":"2026-07-05T08:30:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iCN/MRR8MZS66zKxc3PNTQxcbJIjx6pSf74zmVwa01ikS2R3hB2Vm0CgM4udGEZGf7ws6lGNcZTIgSgZeFq7AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:41:14.413921Z"},"content_sha256":"7cb9881d1b1a924871b9089dbde2e7f2e6a09aebfd5d46af25f2e97b1c6dd2c2","schema_version":"1.0","event_id":"sha256:7cb9881d1b1a924871b9089dbde2e7f2e6a09aebfd5d46af25f2e97b1c6dd2c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7NRFTMGASQFHPQ5Y5YT424IWXL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Large Language Models for NLG Evaluation: Advances and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Can Xu, Chongyang Tao, Jia-Chen Gu, Shuai Ma, Tao Shen, Xiaohan Xu, Yuxuan Lai, Zhen Li","submitted_at":"2024-01-13T15:59:09Z","abstract_excerpt":"In the rapidly evolving domain of Natural Language Generation (NLG) evaluation, introducing Large Language Models (LLMs) has opened new avenues for assessing generated content quality, e.g., coherence, creativity, and context relevance. This paper aims to provide a thorough overview of leveraging LLMs for NLG evaluation, a burgeoning area that lacks a systematic analysis. We propose a coherent taxonomy for organizing existing LLM-based evaluation metrics, offering a structured framework to understand and compare these methods. Our detailed exploration includes critically assessing various LLM-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07103","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/2401.07103/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":"2026-07-05T08:30:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Mvbx0dfpiTID3kjhJZza5QHgXQqFp/4LUQlkIw1IpLrL+neDbVh126lsQSXDrC9bbw/VEbozNOPIY4femxJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:41:14.414573Z"},"content_sha256":"04866ca9801f94f3b94178ce050830aaa67826f6fc2ac7dd1aa07abf2a631138","schema_version":"1.0","event_id":"sha256:04866ca9801f94f3b94178ce050830aaa67826f6fc2ac7dd1aa07abf2a631138"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7NRFTMGASQFHPQ5Y5YT424IWXL/bundle.json","state_url":"https://pith.science/pith/7NRFTMGASQFHPQ5Y5YT424IWXL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7NRFTMGASQFHPQ5Y5YT424IWXL/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":"2026-08-12T22:41:14Z","links":{"resolver":"https://pith.science/pith/7NRFTMGASQFHPQ5Y5YT424IWXL","bundle":"https://pith.science/pith/7NRFTMGASQFHPQ5Y5YT424IWXL/bundle.json","state":"https://pith.science/pith/7NRFTMGASQFHPQ5Y5YT424IWXL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7NRFTMGASQFHPQ5Y5YT424IWXL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7NRFTMGASQFHPQ5Y5YT424IWXL","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":"90babc9a90e8a4a4bbacbc81ed96dbba5b212dfecd745d8896a5c85d86275ba7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T15:59:09Z","title_canon_sha256":"e219a4e29de5b031a689788d77d6da84386995ddc7d857d7965eb8506066f3d0"},"schema_version":"1.0","source":{"id":"2401.07103","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.07103","created_at":"2026-07-05T08:30:31Z"},{"alias_kind":"arxiv_version","alias_value":"2401.07103v2","created_at":"2026-07-05T08:30:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07103","created_at":"2026-07-05T08:30:31Z"},{"alias_kind":"pith_short_12","alias_value":"7NRFTMGASQFH","created_at":"2026-07-05T08:30:31Z"},{"alias_kind":"pith_short_16","alias_value":"7NRFTMGASQFHPQ5Y","created_at":"2026-07-05T08:30:31Z"},{"alias_kind":"pith_short_8","alias_value":"7NRFTMGA","created_at":"2026-07-05T08:30:31Z"}],"graph_snapshots":[{"event_id":"sha256:04866ca9801f94f3b94178ce050830aaa67826f6fc2ac7dd1aa07abf2a631138","target":"graph","created_at":"2026-07-05T08:30:31Z","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/2401.07103/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the rapidly evolving domain of Natural Language Generation (NLG) evaluation, introducing Large Language Models (LLMs) has opened new avenues for assessing generated content quality, e.g., coherence, creativity, and context relevance. This paper aims to provide a thorough overview of leveraging LLMs for NLG evaluation, a burgeoning area that lacks a systematic analysis. We propose a coherent taxonomy for organizing existing LLM-based evaluation metrics, offering a structured framework to understand and compare these methods. Our detailed exploration includes critically assessing various LLM-","authors_text":"Can Xu, Chongyang Tao, Jia-Chen Gu, Shuai Ma, Tao Shen, Xiaohan Xu, Yuxuan Lai, Zhen Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T15:59:09Z","title":"Leveraging Large Language Models for NLG Evaluation: Advances and Challenges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07103","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":"sha256:7cb9881d1b1a924871b9089dbde2e7f2e6a09aebfd5d46af25f2e97b1c6dd2c2","target":"record","created_at":"2026-07-05T08:30:31Z","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":"90babc9a90e8a4a4bbacbc81ed96dbba5b212dfecd745d8896a5c85d86275ba7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T15:59:09Z","title_canon_sha256":"e219a4e29de5b031a689788d77d6da84386995ddc7d857d7965eb8506066f3d0"},"schema_version":"1.0","source":{"id":"2401.07103","kind":"arxiv","version":2}},"canonical_sha256":"fb6259b0c0940a77c3b8ee27cd7116baff01f3c3c1e3a2214a752d0a4d9b6355","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb6259b0c0940a77c3b8ee27cd7116baff01f3c3c1e3a2214a752d0a4d9b6355","first_computed_at":"2026-07-05T08:30:31.006858Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:31.006858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ACNDeRp+HTNL1H6fP1bs5UHLxG/G3xSGkrEAXplLd1bbElkFfCDW2/G5UtPs3HIfvBFdnV20lNn0TBSBGxCjCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:31.007383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.07103","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cb9881d1b1a924871b9089dbde2e7f2e6a09aebfd5d46af25f2e97b1c6dd2c2","sha256:04866ca9801f94f3b94178ce050830aaa67826f6fc2ac7dd1aa07abf2a631138"],"state_sha256":"0f5acf1e4b1f73e0afc79795ef8e396f9021083854445491df045b7d90f2f4f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H6PBuVpiB82b6tBqAlKCO9y1fWtMHdekh0bjfaiqJmawzTZzLnAh9uYpa05o4vDmSYCU+0mfrT1LlDniJPzWAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T22:41:14.418987Z","bundle_sha256":"9d3beaf7be55068113d3ce0dffb5b8d7e707d29eb6931e0a47f0305fa2af4b0e"}}