{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZRCIDZ7N53KOPLD2PDPEP3QK6D","short_pith_number":"pith:ZRCIDZ7N","schema_version":"1.0","canonical_sha256":"cc4481e7edeed4e7ac7a78de47ee0af0de6905524a2d3596ceb246a4a1f82cf0","source":{"kind":"arxiv","id":"2507.13753","version":1},"attestation_state":"computed","paper":{"title":"Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyan Liu, Chengyu Wang, Dongming Lu, Jun Huang, Tongtong Su","submitted_at":"2025-07-18T08:59:02Z","abstract_excerpt":"In recent years, large text-to-video (T2V) synthesis models have garnered considerable attention for their abilities to generate videos from textual descriptions. However, achieving both high imaging quality and effective motion representation remains a significant challenge for these T2V models. Existing approaches often adapt pre-trained text-to-image (T2I) models to refine video frames, leading to issues such as flickering and artifacts due to inconsistencies across frames. In this paper, we introduce EVS, a training-free Encapsulated Video Synthesizer that composes T2I and T2V models to en"},"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":"2507.13753","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-18T08:59:02Z","cross_cats_sorted":[],"title_canon_sha256":"026833466c18829988f415cb6c7f0560682c3cd50940292dd0e6a0490f1941d5","abstract_canon_sha256":"a6eee1ad4104049197ccd072fed8e911e311a31a994df9fb3d704b28e8e3fc12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:22.360308Z","signature_b64":"iVjp5N4P1Jgpo4VzAqFv/IKnkolZzTqAAxoWn3Up2kQOe4zATElGCGVhkY+ujHMlswRwFKojHwnd7TbU9VyMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc4481e7edeed4e7ac7a78de47ee0af0de6905524a2d3596ceb246a4a1f82cf0","last_reissued_at":"2026-07-05T11:39:22.359863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:22.359863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyan Liu, Chengyu Wang, Dongming Lu, Jun Huang, Tongtong Su","submitted_at":"2025-07-18T08:59:02Z","abstract_excerpt":"In recent years, large text-to-video (T2V) synthesis models have garnered considerable attention for their abilities to generate videos from textual descriptions. However, achieving both high imaging quality and effective motion representation remains a significant challenge for these T2V models. Existing approaches often adapt pre-trained text-to-image (T2I) models to refine video frames, leading to issues such as flickering and artifacts due to inconsistencies across frames. In this paper, we introduce EVS, a training-free Encapsulated Video Synthesizer that composes T2I and T2V models to en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13753","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/2507.13753/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":"2507.13753","created_at":"2026-07-05T11:39:22.359918+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13753v1","created_at":"2026-07-05T11:39:22.359918+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13753","created_at":"2026-07-05T11:39:22.359918+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRCIDZ7N53KO","created_at":"2026-07-05T11:39:22.359918+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRCIDZ7N53KOPLD2","created_at":"2026-07-05T11:39:22.359918+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRCIDZ7N","created_at":"2026-07-05T11:39:22.359918+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZRCIDZ7N53KOPLD2PDPEP3QK6D","json":"https://pith.science/pith/ZRCIDZ7N53KOPLD2PDPEP3QK6D.json","graph_json":"https://pith.science/api/pith-number/ZRCIDZ7N53KOPLD2PDPEP3QK6D/graph.json","events_json":"https://pith.science/api/pith-number/ZRCIDZ7N53KOPLD2PDPEP3QK6D/events.json","paper":"https://pith.science/paper/ZRCIDZ7N"},"agent_actions":{"view_html":"https://pith.science/pith/ZRCIDZ7N53KOPLD2PDPEP3QK6D","download_json":"https://pith.science/pith/ZRCIDZ7N53KOPLD2PDPEP3QK6D.json","view_paper":"https://pith.science/paper/ZRCIDZ7N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13753&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRCIDZ7N53KOPLD2PDPEP3QK6D/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRCIDZ7N53KOPLD2PDPEP3QK6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRCIDZ7N53KOPLD2PDPEP3QK6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRCIDZ7N53KOPLD2PDPEP3QK6D/action/storage_attestation","attest_author":"https://pith.science/pith/ZRCIDZ7N53KOPLD2PDPEP3QK6D/action/author_attestation","sign_citation":"https://pith.science/pith/ZRCIDZ7N53KOPLD2PDPEP3QK6D/action/citation_signature","submit_replication":"https://pith.science/pith/ZRCIDZ7N53KOPLD2PDPEP3QK6D/action/replication_record"}},"created_at":"2026-07-05T11:39:22.359918+00:00","updated_at":"2026-07-05T11:39:22.359918+00:00"}