{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NA7BA4NSPEFQBEGJSHOSOUT73C","short_pith_number":"pith:NA7BA4NS","schema_version":"1.0","canonical_sha256":"683e1071b2790b0090c991dd27527fd897ec97b9cea06bd9ed6b70d8d3dd333b","source":{"kind":"arxiv","id":"2501.12011","version":1},"attestation_state":"computed","paper":{"title":"Reference-free Evaluation Metrics for Text Generation: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jun Suzuki, Kees van Deemter, Takumi Ito","submitted_at":"2025-01-21T10:05:48Z","abstract_excerpt":"A number of automatic evaluation metrics have been proposed for natural language generation systems. The most common approach to automatic evaluation is the use of a reference-based metric that compares the model's output with gold-standard references written by humans. However, it is expensive to create such references, and for some tasks, such as response generation in dialogue, creating references is not a simple matter. Therefore, various reference-free metrics have been developed in recent years. In this survey, which intends to cover the full breadth of all NLG tasks, we investigate the "},"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":"2501.12011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-21T10:05:48Z","cross_cats_sorted":[],"title_canon_sha256":"24d4e3901402c89b26d7b1f154f2894100d645040e002a47cf06d23b01485b78","abstract_canon_sha256":"cf8d6719a373a87e3e5bb4aecbd940bf84c31c69b4772f0d0f0371865a7deaab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:30.440597Z","signature_b64":"p93JDxPSDvDsNb7mLNLffqy4nrEJFrYpdSxr5Q/eovPAzsxRUiff8YW0cxho6u7wRtjOm1lQ4aynk84UlIGkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"683e1071b2790b0090c991dd27527fd897ec97b9cea06bd9ed6b70d8d3dd333b","last_reissued_at":"2026-07-05T10:03:30.440044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:30.440044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reference-free Evaluation Metrics for Text Generation: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jun Suzuki, Kees van Deemter, Takumi Ito","submitted_at":"2025-01-21T10:05:48Z","abstract_excerpt":"A number of automatic evaluation metrics have been proposed for natural language generation systems. The most common approach to automatic evaluation is the use of a reference-based metric that compares the model's output with gold-standard references written by humans. However, it is expensive to create such references, and for some tasks, such as response generation in dialogue, creating references is not a simple matter. Therefore, various reference-free metrics have been developed in recent years. In this survey, which intends to cover the full breadth of all NLG tasks, we investigate the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12011","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/2501.12011/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":"2501.12011","created_at":"2026-07-05T10:03:30.440102+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12011v1","created_at":"2026-07-05T10:03:30.440102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12011","created_at":"2026-07-05T10:03:30.440102+00:00"},{"alias_kind":"pith_short_12","alias_value":"NA7BA4NSPEFQ","created_at":"2026-07-05T10:03:30.440102+00:00"},{"alias_kind":"pith_short_16","alias_value":"NA7BA4NSPEFQBEGJ","created_at":"2026-07-05T10:03:30.440102+00:00"},{"alias_kind":"pith_short_8","alias_value":"NA7BA4NS","created_at":"2026-07-05T10:03:30.440102+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/NA7BA4NSPEFQBEGJSHOSOUT73C","json":"https://pith.science/pith/NA7BA4NSPEFQBEGJSHOSOUT73C.json","graph_json":"https://pith.science/api/pith-number/NA7BA4NSPEFQBEGJSHOSOUT73C/graph.json","events_json":"https://pith.science/api/pith-number/NA7BA4NSPEFQBEGJSHOSOUT73C/events.json","paper":"https://pith.science/paper/NA7BA4NS"},"agent_actions":{"view_html":"https://pith.science/pith/NA7BA4NSPEFQBEGJSHOSOUT73C","download_json":"https://pith.science/pith/NA7BA4NSPEFQBEGJSHOSOUT73C.json","view_paper":"https://pith.science/paper/NA7BA4NS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12011&json=true","fetch_graph":"https://pith.science/api/pith-number/NA7BA4NSPEFQBEGJSHOSOUT73C/graph.json","fetch_events":"https://pith.science/api/pith-number/NA7BA4NSPEFQBEGJSHOSOUT73C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NA7BA4NSPEFQBEGJSHOSOUT73C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NA7BA4NSPEFQBEGJSHOSOUT73C/action/storage_attestation","attest_author":"https://pith.science/pith/NA7BA4NSPEFQBEGJSHOSOUT73C/action/author_attestation","sign_citation":"https://pith.science/pith/NA7BA4NSPEFQBEGJSHOSOUT73C/action/citation_signature","submit_replication":"https://pith.science/pith/NA7BA4NSPEFQBEGJSHOSOUT73C/action/replication_record"}},"created_at":"2026-07-05T10:03:30.440102+00:00","updated_at":"2026-07-05T10:03:30.440102+00:00"}