{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4AZOJBEB2NJKS24IZIMYT5BW67","short_pith_number":"pith:4AZOJBEB","schema_version":"1.0","canonical_sha256":"e032e48481d352a96b88ca1989f436f7ddf887ba4249ee5d5f2554e79f3af787","source":{"kind":"arxiv","id":"2508.14483","version":4},"attestation_state":"computed","paper":{"title":"Vivid-VR: Distilling Concepts from Text-to-Video Diffusion Transformer for Photorealistic Video Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Canqian Yang, Haoran Bai, Sibin Deng, Xiaoxu Chen, Ying Chen, Zongyao He","submitted_at":"2025-08-20T07:14:01Z","abstract_excerpt":"We present Vivid-VR, a DiT-based generative video restoration method built upon an advanced T2V foundation model, where ControlNet is leveraged to control the generation process, ensuring content consistency. However, conventional fine-tuning of such controllable pipelines frequently suffers from distribution drift due to limitations in imperfect multimodal alignment, resulting in compromised texture realism and temporal coherence. To tackle this challenge, we propose a concept distillation training strategy that utilizes the pretrained T2V model to synthesize training samples with embedded te"},"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":"2508.14483","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-20T07:14:01Z","cross_cats_sorted":[],"title_canon_sha256":"70c78df9005866f98ece56e1fa1a5b6b9329d9e7e76e6e4d32746b2a007baa5c","abstract_canon_sha256":"2aad105a851c70d7692e30682f3a10f55bdb0a221d18d3467aab731ed9a06ee1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:24.481682Z","signature_b64":"C4785k1X4yepI3LdtnFrN/3qlRBsP6ycl+LF+ov5xih+As9kKHAkD8QOUIZGmBzA8/kwgxw9IzyAj1F4pcSkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e032e48481d352a96b88ca1989f436f7ddf887ba4249ee5d5f2554e79f3af787","last_reissued_at":"2026-06-30T01:16:24.480774Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:24.480774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vivid-VR: Distilling Concepts from Text-to-Video Diffusion Transformer for Photorealistic Video Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Canqian Yang, Haoran Bai, Sibin Deng, Xiaoxu Chen, Ying Chen, Zongyao He","submitted_at":"2025-08-20T07:14:01Z","abstract_excerpt":"We present Vivid-VR, a DiT-based generative video restoration method built upon an advanced T2V foundation model, where ControlNet is leveraged to control the generation process, ensuring content consistency. However, conventional fine-tuning of such controllable pipelines frequently suffers from distribution drift due to limitations in imperfect multimodal alignment, resulting in compromised texture realism and temporal coherence. To tackle this challenge, we propose a concept distillation training strategy that utilizes the pretrained T2V model to synthesize training samples with embedded te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14483","kind":"arxiv","version":4},"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/2508.14483/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":"2508.14483","created_at":"2026-06-30T01:16:24.480898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.14483v4","created_at":"2026-06-30T01:16:24.480898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14483","created_at":"2026-06-30T01:16:24.480898+00:00"},{"alias_kind":"pith_short_12","alias_value":"4AZOJBEB2NJK","created_at":"2026-06-30T01:16:24.480898+00:00"},{"alias_kind":"pith_short_16","alias_value":"4AZOJBEB2NJKS24I","created_at":"2026-06-30T01:16:24.480898+00:00"},{"alias_kind":"pith_short_8","alias_value":"4AZOJBEB","created_at":"2026-06-30T01:16:24.480898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.25801","citing_title":"PixelWizard: Towards Efficient High-Fidelity Video Generation at Ultra-Large Spatial Resolution","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4AZOJBEB2NJKS24IZIMYT5BW67","json":"https://pith.science/pith/4AZOJBEB2NJKS24IZIMYT5BW67.json","graph_json":"https://pith.science/api/pith-number/4AZOJBEB2NJKS24IZIMYT5BW67/graph.json","events_json":"https://pith.science/api/pith-number/4AZOJBEB2NJKS24IZIMYT5BW67/events.json","paper":"https://pith.science/paper/4AZOJBEB"},"agent_actions":{"view_html":"https://pith.science/pith/4AZOJBEB2NJKS24IZIMYT5BW67","download_json":"https://pith.science/pith/4AZOJBEB2NJKS24IZIMYT5BW67.json","view_paper":"https://pith.science/paper/4AZOJBEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.14483&json=true","fetch_graph":"https://pith.science/api/pith-number/4AZOJBEB2NJKS24IZIMYT5BW67/graph.json","fetch_events":"https://pith.science/api/pith-number/4AZOJBEB2NJKS24IZIMYT5BW67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4AZOJBEB2NJKS24IZIMYT5BW67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4AZOJBEB2NJKS24IZIMYT5BW67/action/storage_attestation","attest_author":"https://pith.science/pith/4AZOJBEB2NJKS24IZIMYT5BW67/action/author_attestation","sign_citation":"https://pith.science/pith/4AZOJBEB2NJKS24IZIMYT5BW67/action/citation_signature","submit_replication":"https://pith.science/pith/4AZOJBEB2NJKS24IZIMYT5BW67/action/replication_record"}},"created_at":"2026-06-30T01:16:24.480898+00:00","updated_at":"2026-06-30T01:16:24.480898+00:00"}