{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2N4R4TFMXWGTDAGULSRENZRP7P","short_pith_number":"pith:2N4R4TFM","schema_version":"1.0","canonical_sha256":"d3791e4cacbd8d3180d45ca246e62ffbd7af2232cf25db24653d06b41e1a27b9","source":{"kind":"arxiv","id":"2502.04076","version":1},"attestation_state":"computed","paper":{"title":"Content-Rich AIGC Video Quality Assessment via Intricate Text Alignment and Motion-Aware Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Qu, Shangkun Sun, Wei Gao, Xiaoyu Liang","submitted_at":"2025-02-06T13:41:24Z","abstract_excerpt":"The advent of next-generation video generation models like \\textit{Sora} poses challenges for AI-generated content (AIGC) video quality assessment (VQA). These models substantially mitigate flickering artifacts prevalent in prior models, enable longer and complex text prompts and generate longer videos with intricate, diverse motion patterns. Conventional VQA methods designed for simple text and basic motion patterns struggle to evaluate these content-rich videos. To this end, we propose \\textbf{CRAVE} (\\underline{C}ontent-\\underline{R}ich \\underline{A}IGC \\underline{V}ideo \\underline{E}valuat"},"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":"2502.04076","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-06T13:41:24Z","cross_cats_sorted":[],"title_canon_sha256":"065441b9ef70386e73d94f96695fa4f2b168e11bc760b56e834ecb9715cfcd08","abstract_canon_sha256":"06c827e6b403595dc435a3cf25b3414b26cbd67a1832deb6b41532d9affb9dfa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:33.798215Z","signature_b64":"dg/U3EqMTX6gSHHRUMQyUuWRpxDXt91phHdwrRS/3uOme9nIFbh35MWycpLjO31e33j4yn+8eLzmFhl+8c01CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3791e4cacbd8d3180d45ca246e62ffbd7af2232cf25db24653d06b41e1a27b9","last_reissued_at":"2026-07-05T10:10:33.797809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:33.797809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Content-Rich AIGC Video Quality Assessment via Intricate Text Alignment and Motion-Aware Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Qu, Shangkun Sun, Wei Gao, Xiaoyu Liang","submitted_at":"2025-02-06T13:41:24Z","abstract_excerpt":"The advent of next-generation video generation models like \\textit{Sora} poses challenges for AI-generated content (AIGC) video quality assessment (VQA). These models substantially mitigate flickering artifacts prevalent in prior models, enable longer and complex text prompts and generate longer videos with intricate, diverse motion patterns. Conventional VQA methods designed for simple text and basic motion patterns struggle to evaluate these content-rich videos. To this end, we propose \\textbf{CRAVE} (\\underline{C}ontent-\\underline{R}ich \\underline{A}IGC \\underline{V}ideo \\underline{E}valuat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04076","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/2502.04076/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":"2502.04076","created_at":"2026-07-05T10:10:33.797859+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04076v1","created_at":"2026-07-05T10:10:33.797859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04076","created_at":"2026-07-05T10:10:33.797859+00:00"},{"alias_kind":"pith_short_12","alias_value":"2N4R4TFMXWGT","created_at":"2026-07-05T10:10:33.797859+00:00"},{"alias_kind":"pith_short_16","alias_value":"2N4R4TFMXWGTDAGU","created_at":"2026-07-05T10:10:33.797859+00:00"},{"alias_kind":"pith_short_8","alias_value":"2N4R4TFM","created_at":"2026-07-05T10:10:33.797859+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24196","citing_title":"Navigating User Behavior toward Personalized Multimodal Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23643","citing_title":"TailorMind: Towards Preference-Aligned Multimodal Content Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2511.18373","citing_title":"MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10806","citing_title":"PhyGround: Benchmarking Physical Reasoning in Generative World Models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17074","citing_title":"Comparison Drives Preference: Reference-Aware Modeling for AI-Generated Video Quality Assessment","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2N4R4TFMXWGTDAGULSRENZRP7P","json":"https://pith.science/pith/2N4R4TFMXWGTDAGULSRENZRP7P.json","graph_json":"https://pith.science/api/pith-number/2N4R4TFMXWGTDAGULSRENZRP7P/graph.json","events_json":"https://pith.science/api/pith-number/2N4R4TFMXWGTDAGULSRENZRP7P/events.json","paper":"https://pith.science/paper/2N4R4TFM"},"agent_actions":{"view_html":"https://pith.science/pith/2N4R4TFMXWGTDAGULSRENZRP7P","download_json":"https://pith.science/pith/2N4R4TFMXWGTDAGULSRENZRP7P.json","view_paper":"https://pith.science/paper/2N4R4TFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04076&json=true","fetch_graph":"https://pith.science/api/pith-number/2N4R4TFMXWGTDAGULSRENZRP7P/graph.json","fetch_events":"https://pith.science/api/pith-number/2N4R4TFMXWGTDAGULSRENZRP7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2N4R4TFMXWGTDAGULSRENZRP7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2N4R4TFMXWGTDAGULSRENZRP7P/action/storage_attestation","attest_author":"https://pith.science/pith/2N4R4TFMXWGTDAGULSRENZRP7P/action/author_attestation","sign_citation":"https://pith.science/pith/2N4R4TFMXWGTDAGULSRENZRP7P/action/citation_signature","submit_replication":"https://pith.science/pith/2N4R4TFMXWGTDAGULSRENZRP7P/action/replication_record"}},"created_at":"2026-07-05T10:10:33.797859+00:00","updated_at":"2026-07-05T10:10:33.797859+00:00"}