{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ERC6QWE6Z2EJSRGBGLP3LKKZJC","short_pith_number":"pith:ERC6QWE6","schema_version":"1.0","canonical_sha256":"2445e8589ece889944c132dfb5a9594893af56491f7bebc2b0ba495d2f223a48","source":{"kind":"arxiv","id":"2506.10019","version":1},"attestation_state":"computed","paper":{"title":"A Survey of Automatic Evaluation Methods on Text, Visual and Speech Generations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen Xu, Fanshu Sun, Heyan Huang, Junyu Luo, Rong-Cheng Tu, Rui-Qing Sun, Tian Lan, Xian-Ling Mao, Yang-Hao Zhou, Zhijing Wu, Zi-Ao Ma","submitted_at":"2025-06-06T11:09:46Z","abstract_excerpt":"Recent advances in deep learning have significantly enhanced generative AI capabilities across text, images, and audio. However, automatically evaluating the quality of these generated outputs presents ongoing challenges. Although numerous automatic evaluation methods exist, current research lacks a systematic framework that comprehensively organizes these methods across text, visual, and audio modalities. To address this issue, we present a comprehensive review and a unified taxonomy of automatic evaluation methods for generated content across all three modalities; We identify five fundamenta"},"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":"2506.10019","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T11:09:46Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"6176f261d04abb3db1d8c2a2decae5d7c3ea12469b44695fb069ea00cd41be7b","abstract_canon_sha256":"328d1322ddd42dc22c3f509a5d0b67a3943508553f9a2344391087e0e942a64a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:15.276978Z","signature_b64":"q/7GL1F4ObNjp0tqTMviD3yveVdkceeGAPHqJtWZy+n8JgMcYlxWpdE7srfivz4tsDOvTg3uq+hFmcgcujfvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2445e8589ece889944c132dfb5a9594893af56491f7bebc2b0ba495d2f223a48","last_reissued_at":"2026-07-05T11:20:15.276311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:15.276311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Automatic Evaluation Methods on Text, Visual and Speech Generations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen Xu, Fanshu Sun, Heyan Huang, Junyu Luo, Rong-Cheng Tu, Rui-Qing Sun, Tian Lan, Xian-Ling Mao, Yang-Hao Zhou, Zhijing Wu, Zi-Ao Ma","submitted_at":"2025-06-06T11:09:46Z","abstract_excerpt":"Recent advances in deep learning have significantly enhanced generative AI capabilities across text, images, and audio. However, automatically evaluating the quality of these generated outputs presents ongoing challenges. Although numerous automatic evaluation methods exist, current research lacks a systematic framework that comprehensively organizes these methods across text, visual, and audio modalities. To address this issue, we present a comprehensive review and a unified taxonomy of automatic evaluation methods for generated content across all three modalities; We identify five fundamenta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10019","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/2506.10019/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":"2506.10019","created_at":"2026-07-05T11:20:15.276404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10019v1","created_at":"2026-07-05T11:20:15.276404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10019","created_at":"2026-07-05T11:20:15.276404+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERC6QWE6Z2EJ","created_at":"2026-07-05T11:20:15.276404+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERC6QWE6Z2EJSRGB","created_at":"2026-07-05T11:20:15.276404+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERC6QWE6","created_at":"2026-07-05T11:20:15.276404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17404","citing_title":"ELSA: Acoustic Event-Level Semantic Alignment for Fine-Grained Reference-Free Text-to-Audio Evaluation","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERC6QWE6Z2EJSRGBGLP3LKKZJC","json":"https://pith.science/pith/ERC6QWE6Z2EJSRGBGLP3LKKZJC.json","graph_json":"https://pith.science/api/pith-number/ERC6QWE6Z2EJSRGBGLP3LKKZJC/graph.json","events_json":"https://pith.science/api/pith-number/ERC6QWE6Z2EJSRGBGLP3LKKZJC/events.json","paper":"https://pith.science/paper/ERC6QWE6"},"agent_actions":{"view_html":"https://pith.science/pith/ERC6QWE6Z2EJSRGBGLP3LKKZJC","download_json":"https://pith.science/pith/ERC6QWE6Z2EJSRGBGLP3LKKZJC.json","view_paper":"https://pith.science/paper/ERC6QWE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10019&json=true","fetch_graph":"https://pith.science/api/pith-number/ERC6QWE6Z2EJSRGBGLP3LKKZJC/graph.json","fetch_events":"https://pith.science/api/pith-number/ERC6QWE6Z2EJSRGBGLP3LKKZJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERC6QWE6Z2EJSRGBGLP3LKKZJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERC6QWE6Z2EJSRGBGLP3LKKZJC/action/storage_attestation","attest_author":"https://pith.science/pith/ERC6QWE6Z2EJSRGBGLP3LKKZJC/action/author_attestation","sign_citation":"https://pith.science/pith/ERC6QWE6Z2EJSRGBGLP3LKKZJC/action/citation_signature","submit_replication":"https://pith.science/pith/ERC6QWE6Z2EJSRGBGLP3LKKZJC/action/replication_record"}},"created_at":"2026-07-05T11:20:15.276404+00:00","updated_at":"2026-07-05T11:20:15.276404+00:00"}