{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WWRBQ3FFMPDAN7C55ZISNMTI2S","short_pith_number":"pith:WWRBQ3FF","schema_version":"1.0","canonical_sha256":"b5a2186ca563c606fc5dee5126b268d484e93e0b22c866fbcfe02366ee7cd99c","source":{"kind":"arxiv","id":"2403.11956","version":5},"attestation_state":"computed","paper":{"title":"Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyi Li, Guangtao Zhai, Haoning Wu, Ning Liu, Tengchuan Kou, Xiaohong Liu, Xiongkuo Min, Zicheng Zhang","submitted_at":"2024-03-18T16:52:49Z","abstract_excerpt":"With the rapid development of generative models, Artificial Intelligence-Generated Contents (AIGC) have exponentially increased in daily lives. Among them, Text-to-Video (T2V) generation has received widespread attention. Though many T2V models have been released for generating high perceptual quality videos, there is still lack of a method to evaluate the quality of these videos quantitatively. To solve this issue, we establish the largest-scale Text-to-Video Quality Assessment DataBase (T2VQA-DB) to date. The dataset is composed of 10,000 videos generated by 9 different T2V models. We also c"},"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":"2403.11956","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T16:52:49Z","cross_cats_sorted":[],"title_canon_sha256":"c8405f51740370033c9d687dc0f3f5431d85f5415d407056bd3953b8112eecd5","abstract_canon_sha256":"2c8928cc5c4985faf1d955934f85b8aea326f72cf76209054659c190b8d5da59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:08.796050Z","signature_b64":"8U8YvZ3Tz1DmAqfepMvejI4mVx7fe8V9fxt0uvMFHy7UR/dcFd5aRzwAtOWV4kvazaJWQ42TbYZ+5pRG9ChxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5a2186ca563c606fc5dee5126b268d484e93e0b22c866fbcfe02366ee7cd99c","last_reissued_at":"2026-07-05T08:53:08.795557Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:08.795557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyi Li, Guangtao Zhai, Haoning Wu, Ning Liu, Tengchuan Kou, Xiaohong Liu, Xiongkuo Min, Zicheng Zhang","submitted_at":"2024-03-18T16:52:49Z","abstract_excerpt":"With the rapid development of generative models, Artificial Intelligence-Generated Contents (AIGC) have exponentially increased in daily lives. Among them, Text-to-Video (T2V) generation has received widespread attention. Though many T2V models have been released for generating high perceptual quality videos, there is still lack of a method to evaluate the quality of these videos quantitatively. To solve this issue, we establish the largest-scale Text-to-Video Quality Assessment DataBase (T2VQA-DB) to date. The dataset is composed of 10,000 videos generated by 9 different T2V models. We also c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11956","kind":"arxiv","version":5},"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/2403.11956/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":"2403.11956","created_at":"2026-07-05T08:53:08.795616+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11956v5","created_at":"2026-07-05T08:53:08.795616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11956","created_at":"2026-07-05T08:53:08.795616+00:00"},{"alias_kind":"pith_short_12","alias_value":"WWRBQ3FFMPDA","created_at":"2026-07-05T08:53:08.795616+00:00"},{"alias_kind":"pith_short_16","alias_value":"WWRBQ3FFMPDAN7C5","created_at":"2026-07-05T08:53:08.795616+00:00"},{"alias_kind":"pith_short_8","alias_value":"WWRBQ3FF","created_at":"2026-07-05T08:53:08.795616+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.17180","citing_title":"We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2406.03520","citing_title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WWRBQ3FFMPDAN7C55ZISNMTI2S","json":"https://pith.science/pith/WWRBQ3FFMPDAN7C55ZISNMTI2S.json","graph_json":"https://pith.science/api/pith-number/WWRBQ3FFMPDAN7C55ZISNMTI2S/graph.json","events_json":"https://pith.science/api/pith-number/WWRBQ3FFMPDAN7C55ZISNMTI2S/events.json","paper":"https://pith.science/paper/WWRBQ3FF"},"agent_actions":{"view_html":"https://pith.science/pith/WWRBQ3FFMPDAN7C55ZISNMTI2S","download_json":"https://pith.science/pith/WWRBQ3FFMPDAN7C55ZISNMTI2S.json","view_paper":"https://pith.science/paper/WWRBQ3FF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11956&json=true","fetch_graph":"https://pith.science/api/pith-number/WWRBQ3FFMPDAN7C55ZISNMTI2S/graph.json","fetch_events":"https://pith.science/api/pith-number/WWRBQ3FFMPDAN7C55ZISNMTI2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WWRBQ3FFMPDAN7C55ZISNMTI2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WWRBQ3FFMPDAN7C55ZISNMTI2S/action/storage_attestation","attest_author":"https://pith.science/pith/WWRBQ3FFMPDAN7C55ZISNMTI2S/action/author_attestation","sign_citation":"https://pith.science/pith/WWRBQ3FFMPDAN7C55ZISNMTI2S/action/citation_signature","submit_replication":"https://pith.science/pith/WWRBQ3FFMPDAN7C55ZISNMTI2S/action/replication_record"}},"created_at":"2026-07-05T08:53:08.795616+00:00","updated_at":"2026-07-05T08:53:08.795616+00:00"}