{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FPOWRNIEQABIVKXSY3FTMFSUUJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0941619eec44f4c99f74acb64f55075e270b0a099035a38f34da7d0d661237d2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T11:41:22Z","title_canon_sha256":"cd857241f47ee84e5d657a30cd5eb2b5b79024431d85d8e01ac241a00a87a8c7"},"schema_version":"1.0","source":{"id":"2504.15032","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15032","created_at":"2026-07-05T10:56:17Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15032v2","created_at":"2026-07-05T10:56:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15032","created_at":"2026-07-05T10:56:17Z"},{"alias_kind":"pith_short_12","alias_value":"FPOWRNIEQABI","created_at":"2026-07-05T10:56:17Z"},{"alias_kind":"pith_short_16","alias_value":"FPOWRNIEQABIVKXS","created_at":"2026-07-05T10:56:17Z"},{"alias_kind":"pith_short_8","alias_value":"FPOWRNIE","created_at":"2026-07-05T10:56:17Z"}],"graph_snapshots":[{"event_id":"sha256:ae3162da78f83f9ed42827a35f4fb79efa7710e5f357b8fad330927a22be1a79","target":"graph","created_at":"2026-07-05T10:56:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.15032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chao Wu, Mushui Liu, Weijie He, Yunlong Yu, Zhao Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T11:41:22Z","title":"DyST-XL: Dynamic Layout Planning and Content Control for Compositional Text-to-Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15032","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2b191231a380b3a96b5d585b74239d3855c13ce68cb974133727581190f961ce","target":"record","created_at":"2026-07-05T10:56:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0941619eec44f4c99f74acb64f55075e270b0a099035a38f34da7d0d661237d2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T11:41:22Z","title_canon_sha256":"cd857241f47ee84e5d657a30cd5eb2b5b79024431d85d8e01ac241a00a87a8c7"},"schema_version":"1.0","source":{"id":"2504.15032","kind":"arxiv","version":2}},"canonical_sha256":"2bdd68b50480028aaaf2c6cb361654a26a37b28638d9c13afcca9ab807c70c7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bdd68b50480028aaaf2c6cb361654a26a37b28638d9c13afcca9ab807c70c7b","first_computed_at":"2026-07-05T10:56:17.699908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:56:17.699908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vbLz4uNwPcIqWm9UYGL4tVok/lzeCeAbV9bT6Gln7jUZYhT4TK3JXCsXfpayIuGfhWuRSV2E+oaCcS/cs6N7Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:56:17.700435Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.15032","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b191231a380b3a96b5d585b74239d3855c13ce68cb974133727581190f961ce","sha256:ae3162da78f83f9ed42827a35f4fb79efa7710e5f357b8fad330927a22be1a79"],"state_sha256":"660f79c604563849ea6f8e4988ecf7357b9a5e75116c78c4d7272ff7050eb9c8"}