{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YKXTKIP5AO76V5ILVBZPHHSN66","short_pith_number":"pith:YKXTKIP5","schema_version":"1.0","canonical_sha256":"c2af3521fd03bfeaf50ba872f39e4df78427dff7c1523172643c5817565df838","source":{"kind":"arxiv","id":"2502.09316","version":1},"attestation_state":"computed","paper":{"title":"A Judge-free LLM Open-ended Generation Benchmark Based on the Distributional Hypothesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hiroaki Mikami, Kentaro Imajo, Masanori Hirano, Shuji Suzuki","submitted_at":"2025-02-13T13:30:54Z","abstract_excerpt":"Evaluating the open-ended text generation of large language models (LLMs) is challenging because of the lack of a clear ground truth and the high cost of human or LLM-based assessments. We propose a novel benchmark that evaluates LLMs using n-gram statistics and rules, without relying on human judgement or LLM-as-a-judge approaches. Using 50 question and reference answer sets, we introduce three new metrics based on n-grams and rules: Fluency, Truthfulness, and Helpfulness. Our benchmark strongly correlates with GPT-4o-based evaluations while requiring significantly fewer computational resourc"},"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":"2502.09316","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-13T13:30:54Z","cross_cats_sorted":[],"title_canon_sha256":"bc3ee50f7048b63917361b45a50b845adfbb2342ee33be7b5c61333108210162","abstract_canon_sha256":"f23c897260f7e420d516f7dd8c646c4e176f7d5cf54b9b738ecbc5d93635920a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:55.421553Z","signature_b64":"Roa0ArN+uJTRxxieqgme/rFBqHGillWXk99ByVlweZXGgTKUONtJ09s5dqtYyjOMQr+9lj45qc0L7sjYFnE0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2af3521fd03bfeaf50ba872f39e4df78427dff7c1523172643c5817565df838","last_reissued_at":"2026-07-05T10:13:55.421024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:55.421024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Judge-free LLM Open-ended Generation Benchmark Based on the Distributional Hypothesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hiroaki Mikami, Kentaro Imajo, Masanori Hirano, Shuji Suzuki","submitted_at":"2025-02-13T13:30:54Z","abstract_excerpt":"Evaluating the open-ended text generation of large language models (LLMs) is challenging because of the lack of a clear ground truth and the high cost of human or LLM-based assessments. We propose a novel benchmark that evaluates LLMs using n-gram statistics and rules, without relying on human judgement or LLM-as-a-judge approaches. Using 50 question and reference answer sets, we introduce three new metrics based on n-grams and rules: Fluency, Truthfulness, and Helpfulness. Our benchmark strongly correlates with GPT-4o-based evaluations while requiring significantly fewer computational resourc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09316","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/2502.09316/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":"2502.09316","created_at":"2026-07-05T10:13:55.421088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.09316v1","created_at":"2026-07-05T10:13:55.421088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09316","created_at":"2026-07-05T10:13:55.421088+00:00"},{"alias_kind":"pith_short_12","alias_value":"YKXTKIP5AO76","created_at":"2026-07-05T10:13:55.421088+00:00"},{"alias_kind":"pith_short_16","alias_value":"YKXTKIP5AO76V5IL","created_at":"2026-07-05T10:13:55.421088+00:00"},{"alias_kind":"pith_short_8","alias_value":"YKXTKIP5","created_at":"2026-07-05T10:13:55.421088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YKXTKIP5AO76V5ILVBZPHHSN66","json":"https://pith.science/pith/YKXTKIP5AO76V5ILVBZPHHSN66.json","graph_json":"https://pith.science/api/pith-number/YKXTKIP5AO76V5ILVBZPHHSN66/graph.json","events_json":"https://pith.science/api/pith-number/YKXTKIP5AO76V5ILVBZPHHSN66/events.json","paper":"https://pith.science/paper/YKXTKIP5"},"agent_actions":{"view_html":"https://pith.science/pith/YKXTKIP5AO76V5ILVBZPHHSN66","download_json":"https://pith.science/pith/YKXTKIP5AO76V5ILVBZPHHSN66.json","view_paper":"https://pith.science/paper/YKXTKIP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.09316&json=true","fetch_graph":"https://pith.science/api/pith-number/YKXTKIP5AO76V5ILVBZPHHSN66/graph.json","fetch_events":"https://pith.science/api/pith-number/YKXTKIP5AO76V5ILVBZPHHSN66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YKXTKIP5AO76V5ILVBZPHHSN66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YKXTKIP5AO76V5ILVBZPHHSN66/action/storage_attestation","attest_author":"https://pith.science/pith/YKXTKIP5AO76V5ILVBZPHHSN66/action/author_attestation","sign_citation":"https://pith.science/pith/YKXTKIP5AO76V5ILVBZPHHSN66/action/citation_signature","submit_replication":"https://pith.science/pith/YKXTKIP5AO76V5ILVBZPHHSN66/action/replication_record"}},"created_at":"2026-07-05T10:13:55.421088+00:00","updated_at":"2026-07-05T10:13:55.421088+00:00"}