{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MSHU6CPT4B2RY4NCQ6Z4SGING7","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":"bd23c48b2548c1359dcf1f497cf6e3c315cef05d07e98daed15cca7ff28becde","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-13T04:20:45Z","title_canon_sha256":"e618c4995d1fc7438dd8b1568afa6ea01cddb0d517320d987c2c34920f07e9f0"},"schema_version":"1.0","source":{"id":"2411.08328","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.08328","created_at":"2026-07-05T09:34:45Z"},{"alias_kind":"arxiv_version","alias_value":"2411.08328v1","created_at":"2026-07-05T09:34:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08328","created_at":"2026-07-05T09:34:45Z"},{"alias_kind":"pith_short_12","alias_value":"MSHU6CPT4B2R","created_at":"2026-07-05T09:34:45Z"},{"alias_kind":"pith_short_16","alias_value":"MSHU6CPT4B2RY4NC","created_at":"2026-07-05T09:34:45Z"},{"alias_kind":"pith_short_8","alias_value":"MSHU6CPT","created_at":"2026-07-05T09:34:45Z"}],"graph_snapshots":[{"event_id":"sha256:8dc3ec671bd16712d495ae1fab6a1727b431441b3e80f5f9637f1fe81c8fa338","target":"graph","created_at":"2026-07-05T09:34:45Z","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/2411.08328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing text-to-video (T2V) models often struggle with generating videos with sufficiently pronounced or complex actions. A key limitation lies in the text prompt's inability to precisely convey intricate motion details. To address this, we propose a novel framework, MVideo, designed to produce long-duration videos with precise, fluid actions. MVideo overcomes the limitations of text prompts by incorporating mask sequences as an additional motion condition input, providing a clearer, more accurate representation of intended actions. Leveraging foundational vision models such as GroundingDINO ","authors_text":"Hao Li, Nianzu Yang, Qiang Zhou, Shaofeng Zhang, Ye Qian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-13T04:20:45Z","title":"Motion Control for Enhanced Complex Action Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08328","kind":"arxiv","version":1},"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:ba6cf53a8cff94d35dab964de844d0fe8cb58a6c77675a57e6b59f3eed40ab58","target":"record","created_at":"2026-07-05T09:34:45Z","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":"bd23c48b2548c1359dcf1f497cf6e3c315cef05d07e98daed15cca7ff28becde","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-13T04:20:45Z","title_canon_sha256":"e618c4995d1fc7438dd8b1568afa6ea01cddb0d517320d987c2c34920f07e9f0"},"schema_version":"1.0","source":{"id":"2411.08328","kind":"arxiv","version":1}},"canonical_sha256":"648f4f09f3e0751c71a287b3c9190d37f1955d5ff257937309bda57243bd65c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"648f4f09f3e0751c71a287b3c9190d37f1955d5ff257937309bda57243bd65c1","first_computed_at":"2026-07-05T09:34:45.355007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:45.355007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LZZ53WWYpo8K6edco23mGQOhRWYTUyQaUowm9CTTIpIkSJvGobweYuP9tnUlXJEwGu3ZgGS4xKsWnNgV/Ef0Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:45.355496Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.08328","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba6cf53a8cff94d35dab964de844d0fe8cb58a6c77675a57e6b59f3eed40ab58","sha256:8dc3ec671bd16712d495ae1fab6a1727b431441b3e80f5f9637f1fe81c8fa338"],"state_sha256":"07336b30c4cae8340b1df938080ed755613e7bae5730ad2506eabf9337e3c5e6"}