{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NZ3ALFUGRYZIIQ5KYZWSA6YVKW","short_pith_number":"pith:NZ3ALFUG","schema_version":"1.0","canonical_sha256":"6e760596868e328443aac66d207b155587a8e2bfffc87e1b931c67ac754e9b7a","source":{"kind":"arxiv","id":"2605.22818","version":1},"attestation_state":"computed","paper":{"title":"MotiMotion: Motion-Controlled Video Generation with Visual Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanwen Jiang, Jing Shi, Lee Hsin-Ying, Ming-Hsuan Yang, Yiqun Mei, Zhixin Shu","submitted_at":"2026-05-21T17:59:36Z","abstract_excerpt":"Current motion-controlled image-to-video generation models rigidly follow user-provided trajectories that are often sparse, imprecise, and causally incomplete. Such reliance often yields unnatural or implausible outcomes, especially by missing secondary causal consequences. To address this, we introduce MotiMotion, a novel framework that reformulates motion control as a reasoning-then-generation problem. To encourage causally grounded and commonsense-consistent interactions, we leverage a training-free vision-language reasoner to refine image-space coordinates of primary trajectories and to ha"},"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":"2605.22818","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T17:59:36Z","cross_cats_sorted":[],"title_canon_sha256":"a9a3881571eb14f5075c7a75e28ddd834f28cf235826a1a4ea33d930f2b51b1b","abstract_canon_sha256":"f00b8005a4a95f84db1de196033211bee91e927575a239d93fcc28d56e19c973"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T02:04:56.244987Z","signature_b64":"pLeLfXbMqm9+/zmnQ5AFdRe20RpnMt7KN0spA6KbEqTt1wISlZo7fJoQmzwLpxDb+8XqsLWuDg3NDr6uQAloAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e760596868e328443aac66d207b155587a8e2bfffc87e1b931c67ac754e9b7a","last_reissued_at":"2026-05-22T02:04:56.244482Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T02:04:56.244482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MotiMotion: Motion-Controlled Video Generation with Visual Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanwen Jiang, Jing Shi, Lee Hsin-Ying, Ming-Hsuan Yang, Yiqun Mei, Zhixin Shu","submitted_at":"2026-05-21T17:59:36Z","abstract_excerpt":"Current motion-controlled image-to-video generation models rigidly follow user-provided trajectories that are often sparse, imprecise, and causally incomplete. Such reliance often yields unnatural or implausible outcomes, especially by missing secondary causal consequences. To address this, we introduce MotiMotion, a novel framework that reformulates motion control as a reasoning-then-generation problem. To encourage causally grounded and commonsense-consistent interactions, we leverage a training-free vision-language reasoner to refine image-space coordinates of primary trajectories and to ha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22818","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/2605.22818/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":"2605.22818","created_at":"2026-05-22T02:04:56.244569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22818v1","created_at":"2026-05-22T02:04:56.244569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22818","created_at":"2026-05-22T02:04:56.244569+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZ3ALFUGRYZI","created_at":"2026-05-22T02:04:56.244569+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZ3ALFUGRYZIIQ5K","created_at":"2026-05-22T02:04:56.244569+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZ3ALFUG","created_at":"2026-05-22T02:04:56.244569+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/NZ3ALFUGRYZIIQ5KYZWSA6YVKW","json":"https://pith.science/pith/NZ3ALFUGRYZIIQ5KYZWSA6YVKW.json","graph_json":"https://pith.science/api/pith-number/NZ3ALFUGRYZIIQ5KYZWSA6YVKW/graph.json","events_json":"https://pith.science/api/pith-number/NZ3ALFUGRYZIIQ5KYZWSA6YVKW/events.json","paper":"https://pith.science/paper/NZ3ALFUG"},"agent_actions":{"view_html":"https://pith.science/pith/NZ3ALFUGRYZIIQ5KYZWSA6YVKW","download_json":"https://pith.science/pith/NZ3ALFUGRYZIIQ5KYZWSA6YVKW.json","view_paper":"https://pith.science/paper/NZ3ALFUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22818&json=true","fetch_graph":"https://pith.science/api/pith-number/NZ3ALFUGRYZIIQ5KYZWSA6YVKW/graph.json","fetch_events":"https://pith.science/api/pith-number/NZ3ALFUGRYZIIQ5KYZWSA6YVKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZ3ALFUGRYZIIQ5KYZWSA6YVKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZ3ALFUGRYZIIQ5KYZWSA6YVKW/action/storage_attestation","attest_author":"https://pith.science/pith/NZ3ALFUGRYZIIQ5KYZWSA6YVKW/action/author_attestation","sign_citation":"https://pith.science/pith/NZ3ALFUGRYZIIQ5KYZWSA6YVKW/action/citation_signature","submit_replication":"https://pith.science/pith/NZ3ALFUGRYZIIQ5KYZWSA6YVKW/action/replication_record"}},"created_at":"2026-05-22T02:04:56.244569+00:00","updated_at":"2026-05-22T02:04:56.244569+00:00"}