{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5IEM3IDDHBVWX34BGPO6W4MEMJ","short_pith_number":"pith:5IEM3IDD","schema_version":"1.0","canonical_sha256":"ea08cda063386b6bef8133ddeb71846243bddee5b70e0cb18d6082e4ad3f7094","source":{"kind":"arxiv","id":"2006.14799","version":2},"attestation_state":"computed","paper":{"title":"Evaluation of Text Generation: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Asli Celikyilmaz, Elizabeth Clark, Jianfeng Gao","submitted_at":"2020-06-26T04:52:48Z","abstract_excerpt":"The paper surveys evaluation methods of natural language generation (NLG) systems that have been developed in the last few years. We group NLG evaluation methods into three categories: (1) human-centric evaluation metrics, (2) automatic metrics that require no training, and (3) machine-learned metrics. For each category, we discuss the progress that has been made and the challenges still being faced, with a focus on the evaluation of recently proposed NLG tasks and neural NLG models. We then present two examples for task-specific NLG evaluations for automatic text summarization and long text g"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2006.14799","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-26T04:52:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"491645c174f003e82e3259115e19b8fde186995fabfabc67e54cba3aa4232cda","abstract_canon_sha256":"7be339c9114a65778ee9fa786dbaec63ceaa7397540e826e7828e6a0b879c888"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:48.860853Z","signature_b64":"i804LYh/jiATtS+g+o/zG6zBzU0Ek4FTlhnbtI6siq33VQyB07ZvbIHn8u8LY9REHicMg+cF9gjbmRQj9rfZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea08cda063386b6bef8133ddeb71846243bddee5b70e0cb18d6082e4ad3f7094","last_reissued_at":"2026-07-05T02:40:48.860405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:48.860405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation of Text Generation: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Asli Celikyilmaz, Elizabeth Clark, Jianfeng Gao","submitted_at":"2020-06-26T04:52:48Z","abstract_excerpt":"The paper surveys evaluation methods of natural language generation (NLG) systems that have been developed in the last few years. We group NLG evaluation methods into three categories: (1) human-centric evaluation metrics, (2) automatic metrics that require no training, and (3) machine-learned metrics. For each category, we discuss the progress that has been made and the challenges still being faced, with a focus on the evaluation of recently proposed NLG tasks and neural NLG models. We then present two examples for task-specific NLG evaluations for automatic text summarization and long text g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.14799","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/2006.14799/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.14799","created_at":"2026-07-05T02:40:48.860465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.14799v2","created_at":"2026-07-05T02:40:48.860465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.14799","created_at":"2026-07-05T02:40:48.860465+00:00"},{"alias_kind":"pith_short_12","alias_value":"5IEM3IDDHBVW","created_at":"2026-07-05T02:40:48.860465+00:00"},{"alias_kind":"pith_short_16","alias_value":"5IEM3IDDHBVWX34B","created_at":"2026-07-05T02:40:48.860465+00:00"},{"alias_kind":"pith_short_8","alias_value":"5IEM3IDD","created_at":"2026-07-05T02:40:48.860465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":198,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19057","citing_title":"Quantifying and Auditing LLM Evaluation via Positive--Unlabeled Learning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07936","citing_title":"Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation","ref_index":132,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00274","citing_title":"SEFORA: Student Essays with Feedback Corpus and LLM Feedback Evaluation Framework","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":197,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":226,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29897","citing_title":"ExCAM: Explainable Cultural Awareness Metrics","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23244","citing_title":"Convex Optimization for Alignment and Preference Learning on a Single GPU","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2405.19088","citing_title":"Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2503.23137","citing_title":"When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2510.27106","citing_title":"Rating Roulette: Self-Inconsistency in LLM-As-A-Judge Frameworks","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09299","citing_title":"Synthetic Reflections on Resource Extraction","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2603.13683","citing_title":"Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2308.07201","citing_title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04665","citing_title":"Paraphrase-Induced Output-Mode Collapse: When LLMs Break Character Under Semantically Equivalent Inputs","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25482","citing_title":"From World-Gen to Quest-Line: A Dependency-Driven Prompt Pipeline for Coherent RPG Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04665","citing_title":"Paraphrase-Induced Output-Mode Collapse: When LLMs Break Character Under Semantically Equivalent Inputs","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18955","citing_title":"Assessing Capabilities of Large Language Models in Social Media Analytics: A Multi-task Quest","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10741","citing_title":"Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05900","citing_title":"AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysis","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5IEM3IDDHBVWX34BGPO6W4MEMJ","json":"https://pith.science/pith/5IEM3IDDHBVWX34BGPO6W4MEMJ.json","graph_json":"https://pith.science/api/pith-number/5IEM3IDDHBVWX34BGPO6W4MEMJ/graph.json","events_json":"https://pith.science/api/pith-number/5IEM3IDDHBVWX34BGPO6W4MEMJ/events.json","paper":"https://pith.science/paper/5IEM3IDD"},"agent_actions":{"view_html":"https://pith.science/pith/5IEM3IDDHBVWX34BGPO6W4MEMJ","download_json":"https://pith.science/pith/5IEM3IDDHBVWX34BGPO6W4MEMJ.json","view_paper":"https://pith.science/paper/5IEM3IDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.14799&json=true","fetch_graph":"https://pith.science/api/pith-number/5IEM3IDDHBVWX34BGPO6W4MEMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/5IEM3IDDHBVWX34BGPO6W4MEMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5IEM3IDDHBVWX34BGPO6W4MEMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5IEM3IDDHBVWX34BGPO6W4MEMJ/action/storage_attestation","attest_author":"https://pith.science/pith/5IEM3IDDHBVWX34BGPO6W4MEMJ/action/author_attestation","sign_citation":"https://pith.science/pith/5IEM3IDDHBVWX34BGPO6W4MEMJ/action/citation_signature","submit_replication":"https://pith.science/pith/5IEM3IDDHBVWX34BGPO6W4MEMJ/action/replication_record"}},"created_at":"2026-07-05T02:40:48.860465+00:00","updated_at":"2026-07-05T02:40:48.860465+00:00"}