{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YKXTKIP5AO76V5ILVBZPHHSN66","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":"f23c897260f7e420d516f7dd8c646c4e176f7d5cf54b9b738ecbc5d93635920a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-13T13:30:54Z","title_canon_sha256":"bc3ee50f7048b63917361b45a50b845adfbb2342ee33be7b5c61333108210162"},"schema_version":"1.0","source":{"id":"2502.09316","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09316","created_at":"2026-07-05T10:13:55Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09316v1","created_at":"2026-07-05T10:13:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09316","created_at":"2026-07-05T10:13:55Z"},{"alias_kind":"pith_short_12","alias_value":"YKXTKIP5AO76","created_at":"2026-07-05T10:13:55Z"},{"alias_kind":"pith_short_16","alias_value":"YKXTKIP5AO76V5IL","created_at":"2026-07-05T10:13:55Z"},{"alias_kind":"pith_short_8","alias_value":"YKXTKIP5","created_at":"2026-07-05T10:13:55Z"}],"graph_snapshots":[{"event_id":"sha256:726d1abe2a310eef2351fce1fdfd49178cac34e85d1a504cc95cbbd77108fbdd","target":"graph","created_at":"2026-07-05T10:13:55Z","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/2502.09316/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hiroaki Mikami, Kentaro Imajo, Masanori Hirano, Shuji Suzuki","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-13T13:30:54Z","title":"A Judge-free LLM Open-ended Generation Benchmark Based on the Distributional Hypothesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09316","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:d1e6e07c4f6b4eee6d00d92a1628f81a216f4f7daeef298797ff83e789a407ba","target":"record","created_at":"2026-07-05T10:13:55Z","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":"f23c897260f7e420d516f7dd8c646c4e176f7d5cf54b9b738ecbc5d93635920a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-13T13:30:54Z","title_canon_sha256":"bc3ee50f7048b63917361b45a50b845adfbb2342ee33be7b5c61333108210162"},"schema_version":"1.0","source":{"id":"2502.09316","kind":"arxiv","version":1}},"canonical_sha256":"c2af3521fd03bfeaf50ba872f39e4df78427dff7c1523172643c5817565df838","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2af3521fd03bfeaf50ba872f39e4df78427dff7c1523172643c5817565df838","first_computed_at":"2026-07-05T10:13:55.421024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:55.421024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Roa0ArN+uJTRxxieqgme/rFBqHGillWXk99ByVlweZXGgTKUONtJ09s5dqtYyjOMQr+9lj45qc0L7sjYFnE0Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:55.421553Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.09316","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1e6e07c4f6b4eee6d00d92a1628f81a216f4f7daeef298797ff83e789a407ba","sha256:726d1abe2a310eef2351fce1fdfd49178cac34e85d1a504cc95cbbd77108fbdd"],"state_sha256":"1d460c7827d201f9a58d3f6974aa55fa2ccc51ba5cd40c5ccf720d00694046fa"}