{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FPOWRNIEQABIVKXSY3FTMFSUUJ","short_pith_number":"pith:FPOWRNIE","schema_version":"1.0","canonical_sha256":"2bdd68b50480028aaaf2c6cb361654a26a37b28638d9c13afcca9ab807c70c7b","source":{"kind":"arxiv","id":"2504.15032","version":2},"attestation_state":"computed","paper":{"title":"DyST-XL: Dynamic Layout Planning and Content Control for Compositional Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Wu, Mushui Liu, Weijie He, Yunlong Yu, Zhao Wang","submitted_at":"2025-04-21T11:41:22Z","abstract_excerpt":"Compositional text-to-video generation, which requires synthesizing dynamic scenes with multiple interacting entities and precise spatial-temporal relationships, remains a critical challenge for diffusion-based models. Existing methods struggle with layout discontinuity, entity identity drift, and implausible interaction dynamics due to unconstrained cross-attention mechanisms and inadequate physics-aware reasoning. To address these limitations, we propose DyST-XL, a \\textbf{training-free} framework that enhances off-the-shelf text-to-video models (e.g., CogVideoX-5B) through frame-aware contr"},"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":"2504.15032","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T11:41:22Z","cross_cats_sorted":[],"title_canon_sha256":"cd857241f47ee84e5d657a30cd5eb2b5b79024431d85d8e01ac241a00a87a8c7","abstract_canon_sha256":"0941619eec44f4c99f74acb64f55075e270b0a099035a38f34da7d0d661237d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:17.700435Z","signature_b64":"vbLz4uNwPcIqWm9UYGL4tVok/lzeCeAbV9bT6Gln7jUZYhT4TK3JXCsXfpayIuGfhWuRSV2E+oaCcS/cs6N7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bdd68b50480028aaaf2c6cb361654a26a37b28638d9c13afcca9ab807c70c7b","last_reissued_at":"2026-07-05T10:56:17.699908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:17.699908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DyST-XL: Dynamic Layout Planning and Content Control for Compositional Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Wu, Mushui Liu, Weijie He, Yunlong Yu, Zhao Wang","submitted_at":"2025-04-21T11:41:22Z","abstract_excerpt":"Compositional text-to-video generation, which requires synthesizing dynamic scenes with multiple interacting entities and precise spatial-temporal relationships, remains a critical challenge for diffusion-based models. Existing methods struggle with layout discontinuity, entity identity drift, and implausible interaction dynamics due to unconstrained cross-attention mechanisms and inadequate physics-aware reasoning. To address these limitations, we propose DyST-XL, a \\textbf{training-free} framework that enhances off-the-shelf text-to-video models (e.g., CogVideoX-5B) through frame-aware contr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15032","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/2504.15032/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":"2504.15032","created_at":"2026-07-05T10:56:17.699967+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15032v2","created_at":"2026-07-05T10:56:17.699967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15032","created_at":"2026-07-05T10:56:17.699967+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPOWRNIEQABI","created_at":"2026-07-05T10:56:17.699967+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPOWRNIEQABIVKXS","created_at":"2026-07-05T10:56:17.699967+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPOWRNIE","created_at":"2026-07-05T10:56:17.699967+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14988","citing_title":"Compositional Video Generation via Inference-Time Guidance","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPOWRNIEQABIVKXSY3FTMFSUUJ","json":"https://pith.science/pith/FPOWRNIEQABIVKXSY3FTMFSUUJ.json","graph_json":"https://pith.science/api/pith-number/FPOWRNIEQABIVKXSY3FTMFSUUJ/graph.json","events_json":"https://pith.science/api/pith-number/FPOWRNIEQABIVKXSY3FTMFSUUJ/events.json","paper":"https://pith.science/paper/FPOWRNIE"},"agent_actions":{"view_html":"https://pith.science/pith/FPOWRNIEQABIVKXSY3FTMFSUUJ","download_json":"https://pith.science/pith/FPOWRNIEQABIVKXSY3FTMFSUUJ.json","view_paper":"https://pith.science/paper/FPOWRNIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15032&json=true","fetch_graph":"https://pith.science/api/pith-number/FPOWRNIEQABIVKXSY3FTMFSUUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FPOWRNIEQABIVKXSY3FTMFSUUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPOWRNIEQABIVKXSY3FTMFSUUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPOWRNIEQABIVKXSY3FTMFSUUJ/action/storage_attestation","attest_author":"https://pith.science/pith/FPOWRNIEQABIVKXSY3FTMFSUUJ/action/author_attestation","sign_citation":"https://pith.science/pith/FPOWRNIEQABIVKXSY3FTMFSUUJ/action/citation_signature","submit_replication":"https://pith.science/pith/FPOWRNIEQABIVKXSY3FTMFSUUJ/action/replication_record"}},"created_at":"2026-07-05T10:56:17.699967+00:00","updated_at":"2026-07-05T10:56:17.699967+00:00"}