{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VNDPRQPDPO6HXKCY5KDGBI3PM7","short_pith_number":"pith:VNDPRQPD","schema_version":"1.0","canonical_sha256":"ab46f8c1e37bbc7ba858ea8660a36f67f514abcd4c85159bbea5acf119fabad4","source":{"kind":"arxiv","id":"2406.02230","version":2},"attestation_state":"computed","paper":{"title":"I4VGen: Image as Free Stepping Stone for Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Huang, Jinlin Liu, Liefeng Bo, Miaomiao Cui, Xiefan Guo","submitted_at":"2024-06-04T11:48:44Z","abstract_excerpt":"Text-to-video generation has trailed behind text-to-image generation in terms of quality and diversity, primarily due to the inherent complexities of spatio-temporal modeling and the limited availability of video-text datasets. Recent text-to-video diffusion models employ the image as an intermediate step, significantly enhancing overall performance but incurring high training costs. In this paper, we present I4VGen, a novel video diffusion inference pipeline to leverage advanced image techniques to enhance pre-trained text-to-video diffusion models, which requires no additional training. Inst"},"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":"2406.02230","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-04T11:48:44Z","cross_cats_sorted":[],"title_canon_sha256":"f41d0ff7ac8933bc1eee9da329a988ba22aff039c9166890a8bf61d01792e02e","abstract_canon_sha256":"67c90ae6b6cc9f91ade7d7342980fca0884893d76fe6d5397404945d9e3d5adc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:11.059927Z","signature_b64":"C+AauEJ7gTFy6+GC0iI4jNQwE3AlhR2zYn4CEhmxjSBOxSXAz3MkEhhYkPfIuo7uoAt1hIbRGZ+rwDYOCIA0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab46f8c1e37bbc7ba858ea8660a36f67f514abcd4c85159bbea5acf119fabad4","last_reissued_at":"2026-07-05T09:15:11.059497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:11.059497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"I4VGen: Image as Free Stepping Stone for Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Huang, Jinlin Liu, Liefeng Bo, Miaomiao Cui, Xiefan Guo","submitted_at":"2024-06-04T11:48:44Z","abstract_excerpt":"Text-to-video generation has trailed behind text-to-image generation in terms of quality and diversity, primarily due to the inherent complexities of spatio-temporal modeling and the limited availability of video-text datasets. Recent text-to-video diffusion models employ the image as an intermediate step, significantly enhancing overall performance but incurring high training costs. In this paper, we present I4VGen, a novel video diffusion inference pipeline to leverage advanced image techniques to enhance pre-trained text-to-video diffusion models, which requires no additional training. Inst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02230","kind":"arxiv","version":2},"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/2406.02230/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":"2406.02230","created_at":"2026-07-05T09:15:11.059554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02230v2","created_at":"2026-07-05T09:15:11.059554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02230","created_at":"2026-07-05T09:15:11.059554+00:00"},{"alias_kind":"pith_short_12","alias_value":"VNDPRQPDPO6H","created_at":"2026-07-05T09:15:11.059554+00:00"},{"alias_kind":"pith_short_16","alias_value":"VNDPRQPDPO6HXKCY","created_at":"2026-07-05T09:15:11.059554+00:00"},{"alias_kind":"pith_short_8","alias_value":"VNDPRQPD","created_at":"2026-07-05T09:15:11.059554+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17248","citing_title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04569","citing_title":"LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention","ref_index":96,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VNDPRQPDPO6HXKCY5KDGBI3PM7","json":"https://pith.science/pith/VNDPRQPDPO6HXKCY5KDGBI3PM7.json","graph_json":"https://pith.science/api/pith-number/VNDPRQPDPO6HXKCY5KDGBI3PM7/graph.json","events_json":"https://pith.science/api/pith-number/VNDPRQPDPO6HXKCY5KDGBI3PM7/events.json","paper":"https://pith.science/paper/VNDPRQPD"},"agent_actions":{"view_html":"https://pith.science/pith/VNDPRQPDPO6HXKCY5KDGBI3PM7","download_json":"https://pith.science/pith/VNDPRQPDPO6HXKCY5KDGBI3PM7.json","view_paper":"https://pith.science/paper/VNDPRQPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02230&json=true","fetch_graph":"https://pith.science/api/pith-number/VNDPRQPDPO6HXKCY5KDGBI3PM7/graph.json","fetch_events":"https://pith.science/api/pith-number/VNDPRQPDPO6HXKCY5KDGBI3PM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VNDPRQPDPO6HXKCY5KDGBI3PM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VNDPRQPDPO6HXKCY5KDGBI3PM7/action/storage_attestation","attest_author":"https://pith.science/pith/VNDPRQPDPO6HXKCY5KDGBI3PM7/action/author_attestation","sign_citation":"https://pith.science/pith/VNDPRQPDPO6HXKCY5KDGBI3PM7/action/citation_signature","submit_replication":"https://pith.science/pith/VNDPRQPDPO6HXKCY5KDGBI3PM7/action/replication_record"}},"created_at":"2026-07-05T09:15:11.059554+00:00","updated_at":"2026-07-05T09:15:11.059554+00:00"}