{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AZEDAHF3QQNVGBTMSL76UQVH6J","short_pith_number":"pith:AZEDAHF3","schema_version":"1.0","canonical_sha256":"0648301cbb841b53066c92ffea42a7f27edff9c2b4223ef9f41ee4c9ed5c51f8","source":{"kind":"arxiv","id":"2605.23245","version":1},"attestation_state":"computed","paper":{"title":"SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gao Wang, Jiang Lin, Jizhi Zhang, Mingjie Wang, Qiang Tang, Qian Wang, Shenyi Wang, Song Wu, Xinyu Chen, Yuyi Qian, Zhiqiu Zhang, Zili Yi","submitted_at":"2026-05-22T05:28:56Z","abstract_excerpt":"Video object insertion requires ensuring spatio-temporal coherence and interactive realism, extending far beyond simple content placement. However, current approaches are often hindered by a reliance on explicit motion engineering or resource-intensive retraining, restricting their flexibility and generalization. To bridge this gap, we present \\textit{SimInsert}, a training-free paradigm that efficiently decouples the task into intuitive single-frame editing and semantic motion description. By harnessing the robust generative priors of image-to-video diffusion models, SimInsert propagates edit"},"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":"2605.23245","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T05:28:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8beb56effa8cd978b68638df83bd33008f9e2f077db3cd95b7eae34fa72d04e1","abstract_canon_sha256":"a7a323786044a4758ff32bf43d7eeda0a26457d76e1459203e130c0a3b3350a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:45.491371Z","signature_b64":"y2UkiZu2IZ9Yv41v2gSnAmTRgdOmg9NRVver+1/nDmeaKC2TkoLBiR+Q1AYpP68VD1OmBr5RGZvIBp0gsEGqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0648301cbb841b53066c92ffea42a7f27edff9c2b4223ef9f41ee4c9ed5c51f8","last_reissued_at":"2026-05-25T02:01:45.490776Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:45.490776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gao Wang, Jiang Lin, Jizhi Zhang, Mingjie Wang, Qiang Tang, Qian Wang, Shenyi Wang, Song Wu, Xinyu Chen, Yuyi Qian, Zhiqiu Zhang, Zili Yi","submitted_at":"2026-05-22T05:28:56Z","abstract_excerpt":"Video object insertion requires ensuring spatio-temporal coherence and interactive realism, extending far beyond simple content placement. However, current approaches are often hindered by a reliance on explicit motion engineering or resource-intensive retraining, restricting their flexibility and generalization. To bridge this gap, we present \\textit{SimInsert}, a training-free paradigm that efficiently decouples the task into intuitive single-frame editing and semantic motion description. By harnessing the robust generative priors of image-to-video diffusion models, SimInsert propagates edit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23245","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/2605.23245/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":"2605.23245","created_at":"2026-05-25T02:01:45.490884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23245v1","created_at":"2026-05-25T02:01:45.490884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23245","created_at":"2026-05-25T02:01:45.490884+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZEDAHF3QQNV","created_at":"2026-05-25T02:01:45.490884+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZEDAHF3QQNVGBTM","created_at":"2026-05-25T02:01:45.490884+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZEDAHF3","created_at":"2026-05-25T02:01:45.490884+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/AZEDAHF3QQNVGBTMSL76UQVH6J","json":"https://pith.science/pith/AZEDAHF3QQNVGBTMSL76UQVH6J.json","graph_json":"https://pith.science/api/pith-number/AZEDAHF3QQNVGBTMSL76UQVH6J/graph.json","events_json":"https://pith.science/api/pith-number/AZEDAHF3QQNVGBTMSL76UQVH6J/events.json","paper":"https://pith.science/paper/AZEDAHF3"},"agent_actions":{"view_html":"https://pith.science/pith/AZEDAHF3QQNVGBTMSL76UQVH6J","download_json":"https://pith.science/pith/AZEDAHF3QQNVGBTMSL76UQVH6J.json","view_paper":"https://pith.science/paper/AZEDAHF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23245&json=true","fetch_graph":"https://pith.science/api/pith-number/AZEDAHF3QQNVGBTMSL76UQVH6J/graph.json","fetch_events":"https://pith.science/api/pith-number/AZEDAHF3QQNVGBTMSL76UQVH6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZEDAHF3QQNVGBTMSL76UQVH6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZEDAHF3QQNVGBTMSL76UQVH6J/action/storage_attestation","attest_author":"https://pith.science/pith/AZEDAHF3QQNVGBTMSL76UQVH6J/action/author_attestation","sign_citation":"https://pith.science/pith/AZEDAHF3QQNVGBTMSL76UQVH6J/action/citation_signature","submit_replication":"https://pith.science/pith/AZEDAHF3QQNVGBTMSL76UQVH6J/action/replication_record"}},"created_at":"2026-05-25T02:01:45.490884+00:00","updated_at":"2026-05-25T02:01:45.490884+00:00"}