{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PJXFSY5ZOAF4F3HW5JWTWKMVYV","short_pith_number":"pith:PJXFSY5Z","schema_version":"1.0","canonical_sha256":"7a6e5963b9700bc2ecf6ea6d3b2995c5674671fc4fcf7639613f8d884e56ddd2","source":{"kind":"arxiv","id":"2504.15681","version":3},"attestation_state":"computed","paper":{"title":"Vidi: Large Multimodal Models for Video Understanding and Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Celong Liu, Chia-Wen Kuo, Dawei Du, Fan Chen, Guang Chen, Jiamin Yuan, Lingxi Zhang, Longyin Wen, Lu Guo, Lusha Li, Qingyu Chen, Rachel Deng, Sijie Zhu, Stuart Siew, Tong Jin, Vidi Team, Wei Lu, Wen Zhong, Xiaohui Shen, Xing Mei, Xin Gu, Xueqiong Qu, Zhenfang Chen","submitted_at":"2025-04-22T08:04:45Z","abstract_excerpt":"Humans naturally share information with those they are connected to, and video has become one of the dominant mediums for communication and expression on the Internet. To support the creation of high-quality large-scale video content, a modern pipeline requires a comprehensive understanding of both the raw input materials (e.g., the unedited footage captured by cameras) and the editing components (e.g., visual effects). In video editing scenarios, models must process multiple modalities (e.g., vision, audio, text) with strong background knowledge and handle flexible input lengths (e.g., hour-l"},"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":"2504.15681","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T08:04:45Z","cross_cats_sorted":[],"title_canon_sha256":"00c9d22bcc57c8c08fc3cf010a3184a6e9a6f1a71f9129e37614ea7cf1dddc0d","abstract_canon_sha256":"5f766ff5f2a9afce46b1d458401dc1216dbbf59c815af62abcb2badbd08d8e38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:28.936392Z","signature_b64":"6U/OyuFM+/p7lm+bqY1r3aFuSUe5eMBXmT7xOllOR03/zxYXSJglAQv9iAeTNQjWbbFdUPy6XhLuNd5TbL2DAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a6e5963b9700bc2ecf6ea6d3b2995c5674671fc4fcf7639613f8d884e56ddd2","last_reissued_at":"2026-07-05T11:38:28.935863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:28.935863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vidi: Large Multimodal Models for Video Understanding and Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Celong Liu, Chia-Wen Kuo, Dawei Du, Fan Chen, Guang Chen, Jiamin Yuan, Lingxi Zhang, Longyin Wen, Lu Guo, Lusha Li, Qingyu Chen, Rachel Deng, Sijie Zhu, Stuart Siew, Tong Jin, Vidi Team, Wei Lu, Wen Zhong, Xiaohui Shen, Xing Mei, Xin Gu, Xueqiong Qu, Zhenfang Chen","submitted_at":"2025-04-22T08:04:45Z","abstract_excerpt":"Humans naturally share information with those they are connected to, and video has become one of the dominant mediums for communication and expression on the Internet. To support the creation of high-quality large-scale video content, a modern pipeline requires a comprehensive understanding of both the raw input materials (e.g., the unedited footage captured by cameras) and the editing components (e.g., visual effects). In video editing scenarios, models must process multiple modalities (e.g., vision, audio, text) with strong background knowledge and handle flexible input lengths (e.g., hour-l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15681","kind":"arxiv","version":3},"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/2504.15681/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":"2504.15681","created_at":"2026-07-05T11:38:28.935927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15681v3","created_at":"2026-07-05T11:38:28.935927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15681","created_at":"2026-07-05T11:38:28.935927+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJXFSY5ZOAF4","created_at":"2026-07-05T11:38:28.935927+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJXFSY5ZOAF4F3HW","created_at":"2026-07-05T11:38:28.935927+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJXFSY5Z","created_at":"2026-07-05T11:38:28.935927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23198","citing_title":"StoryTR: Narrative-Centric Video Temporal Retrieval with Theory of Mind Reasoning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJXFSY5ZOAF4F3HW5JWTWKMVYV","json":"https://pith.science/pith/PJXFSY5ZOAF4F3HW5JWTWKMVYV.json","graph_json":"https://pith.science/api/pith-number/PJXFSY5ZOAF4F3HW5JWTWKMVYV/graph.json","events_json":"https://pith.science/api/pith-number/PJXFSY5ZOAF4F3HW5JWTWKMVYV/events.json","paper":"https://pith.science/paper/PJXFSY5Z"},"agent_actions":{"view_html":"https://pith.science/pith/PJXFSY5ZOAF4F3HW5JWTWKMVYV","download_json":"https://pith.science/pith/PJXFSY5ZOAF4F3HW5JWTWKMVYV.json","view_paper":"https://pith.science/paper/PJXFSY5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15681&json=true","fetch_graph":"https://pith.science/api/pith-number/PJXFSY5ZOAF4F3HW5JWTWKMVYV/graph.json","fetch_events":"https://pith.science/api/pith-number/PJXFSY5ZOAF4F3HW5JWTWKMVYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJXFSY5ZOAF4F3HW5JWTWKMVYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJXFSY5ZOAF4F3HW5JWTWKMVYV/action/storage_attestation","attest_author":"https://pith.science/pith/PJXFSY5ZOAF4F3HW5JWTWKMVYV/action/author_attestation","sign_citation":"https://pith.science/pith/PJXFSY5ZOAF4F3HW5JWTWKMVYV/action/citation_signature","submit_replication":"https://pith.science/pith/PJXFSY5ZOAF4F3HW5JWTWKMVYV/action/replication_record"}},"created_at":"2026-07-05T11:38:28.935927+00:00","updated_at":"2026-07-05T11:38:28.935927+00:00"}