{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5GL5QJHIN6RJZ73P3LQF3YRPR7","short_pith_number":"pith:5GL5QJHI","schema_version":"1.0","canonical_sha256":"e997d824e86fa29cff6fdae05de22f8fc125c9953982bbabea5aeb08160bb20c","source":{"kind":"arxiv","id":"2606.06853","version":1},"attestation_state":"computed","paper":{"title":"MotionEnhancer: Leveraging Video Diffusion for Motion-Enhanced Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Fei Gao, Jiaxing Qi, Ruifei Ma, Yifan Xu, Zhifei Yang, Zhipeng Chen","submitted_at":"2026-06-05T02:56:48Z","abstract_excerpt":"The new era has witnessed a remarkable capability to extend Vision-Language Models (VLMs) for tackling tasks of video understanding. While current VLMs excel at event- or story-level understanding, their ability to capture fine-grained motion details remains limited, primarily due to their focus on high-level static semantic structures and macro-event logic. In contrast, Video Diffusion Models (VDMs) are adept at modeling dynamic motion patterns, benefiting from large-scale video data and the intrinsic requirement of temporal generation. In this paper, we introduce MotionEnhancer, a novel appr"},"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":"2606.06853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T02:56:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4169690db3978babd498a7c74482a7c1688fe43f3ef0c3f25044d721062236b6","abstract_canon_sha256":"887b1528f0ea93fbb7c1c947c07ceea3f2c7025f1417021b16e21998f3a225a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:31.905904Z","signature_b64":"JYeVtmg2xq5OPPxTUJH8dVFOP+E3QhEKJQtkndFamj+e3ojp8rDrOx0aM7+/DWMPn/4gAhfScFijTG4EyddpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e997d824e86fa29cff6fdae05de22f8fc125c9953982bbabea5aeb08160bb20c","last_reissued_at":"2026-06-08T01:04:31.904987Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:31.904987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MotionEnhancer: Leveraging Video Diffusion for Motion-Enhanced Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Fei Gao, Jiaxing Qi, Ruifei Ma, Yifan Xu, Zhifei Yang, Zhipeng Chen","submitted_at":"2026-06-05T02:56:48Z","abstract_excerpt":"The new era has witnessed a remarkable capability to extend Vision-Language Models (VLMs) for tackling tasks of video understanding. While current VLMs excel at event- or story-level understanding, their ability to capture fine-grained motion details remains limited, primarily due to their focus on high-level static semantic structures and macro-event logic. In contrast, Video Diffusion Models (VDMs) are adept at modeling dynamic motion patterns, benefiting from large-scale video data and the intrinsic requirement of temporal generation. In this paper, we introduce MotionEnhancer, a novel appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06853","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/2606.06853/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":"2606.06853","created_at":"2026-06-08T01:04:31.905149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06853v1","created_at":"2026-06-08T01:04:31.905149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06853","created_at":"2026-06-08T01:04:31.905149+00:00"},{"alias_kind":"pith_short_12","alias_value":"5GL5QJHIN6RJ","created_at":"2026-06-08T01:04:31.905149+00:00"},{"alias_kind":"pith_short_16","alias_value":"5GL5QJHIN6RJZ73P","created_at":"2026-06-08T01:04:31.905149+00:00"},{"alias_kind":"pith_short_8","alias_value":"5GL5QJHI","created_at":"2026-06-08T01:04:31.905149+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/5GL5QJHIN6RJZ73P3LQF3YRPR7","json":"https://pith.science/pith/5GL5QJHIN6RJZ73P3LQF3YRPR7.json","graph_json":"https://pith.science/api/pith-number/5GL5QJHIN6RJZ73P3LQF3YRPR7/graph.json","events_json":"https://pith.science/api/pith-number/5GL5QJHIN6RJZ73P3LQF3YRPR7/events.json","paper":"https://pith.science/paper/5GL5QJHI"},"agent_actions":{"view_html":"https://pith.science/pith/5GL5QJHIN6RJZ73P3LQF3YRPR7","download_json":"https://pith.science/pith/5GL5QJHIN6RJZ73P3LQF3YRPR7.json","view_paper":"https://pith.science/paper/5GL5QJHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06853&json=true","fetch_graph":"https://pith.science/api/pith-number/5GL5QJHIN6RJZ73P3LQF3YRPR7/graph.json","fetch_events":"https://pith.science/api/pith-number/5GL5QJHIN6RJZ73P3LQF3YRPR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5GL5QJHIN6RJZ73P3LQF3YRPR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5GL5QJHIN6RJZ73P3LQF3YRPR7/action/storage_attestation","attest_author":"https://pith.science/pith/5GL5QJHIN6RJZ73P3LQF3YRPR7/action/author_attestation","sign_citation":"https://pith.science/pith/5GL5QJHIN6RJZ73P3LQF3YRPR7/action/citation_signature","submit_replication":"https://pith.science/pith/5GL5QJHIN6RJZ73P3LQF3YRPR7/action/replication_record"}},"created_at":"2026-06-08T01:04:31.905149+00:00","updated_at":"2026-06-08T01:04:31.905149+00:00"}