{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XMXB5DADKLNU5MFQ7QAJFXFI63","short_pith_number":"pith:XMXB5DAD","schema_version":"1.0","canonical_sha256":"bb2e1e8c0352db4eb0b0fc0092dca8f6e0b72a45ce9fe8cb5fad782acbec5050","source":{"kind":"arxiv","id":"2405.18003","version":1},"attestation_state":"computed","paper":{"title":"MAVIN: Multi-Action Video Generation with Diffusion Models via Transition Video Infilling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Haotian Lu, Na Ma, Qing Guo, Tianlin Li, Xiaofei Xie","submitted_at":"2024-05-28T09:46:09Z","abstract_excerpt":"Diffusion-based video generation has achieved significant progress, yet generating multiple actions that occur sequentially remains a formidable task. Directly generating a video with sequential actions can be extremely challenging due to the scarcity of fine-grained action annotations and the difficulty in establishing temporal semantic correspondences and maintaining long-term consistency. To tackle this, we propose an intuitive and straightforward solution: splicing multiple single-action video segments sequentially. The core challenge lies in generating smooth and natural transitions betwe"},"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":"2405.18003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T09:46:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7cc0d964faa09535514a472d70aff5cb9553895220776e2b83f06bdd1883d515","abstract_canon_sha256":"98c5a89d3e0e62df2b16f9bf40b0aa83839c965300e526fb6f0db30780fd5619"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:14.410611Z","signature_b64":"s+bJC0QR3a92SUl/F9Rsa94ihwVMcIavuP2ay/RdQnX/tr3A6mvA3FXfSOveex1fmspmZQOsbPk26idPOj5YAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb2e1e8c0352db4eb0b0fc0092dca8f6e0b72a45ce9fe8cb5fad782acbec5050","last_reissued_at":"2026-07-05T08:24:14.410175Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:14.410175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAVIN: Multi-Action Video Generation with Diffusion Models via Transition Video Infilling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Haotian Lu, Na Ma, Qing Guo, Tianlin Li, Xiaofei Xie","submitted_at":"2024-05-28T09:46:09Z","abstract_excerpt":"Diffusion-based video generation has achieved significant progress, yet generating multiple actions that occur sequentially remains a formidable task. Directly generating a video with sequential actions can be extremely challenging due to the scarcity of fine-grained action annotations and the difficulty in establishing temporal semantic correspondences and maintaining long-term consistency. To tackle this, we propose an intuitive and straightforward solution: splicing multiple single-action video segments sequentially. The core challenge lies in generating smooth and natural transitions betwe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18003","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/2405.18003/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":"2405.18003","created_at":"2026-07-05T08:24:14.410224+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18003v1","created_at":"2026-07-05T08:24:14.410224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18003","created_at":"2026-07-05T08:24:14.410224+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMXB5DADKLNU","created_at":"2026-07-05T08:24:14.410224+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMXB5DADKLNU5MFQ","created_at":"2026-07-05T08:24:14.410224+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMXB5DAD","created_at":"2026-07-05T08:24:14.410224+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19473","citing_title":"TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMXB5DADKLNU5MFQ7QAJFXFI63","json":"https://pith.science/pith/XMXB5DADKLNU5MFQ7QAJFXFI63.json","graph_json":"https://pith.science/api/pith-number/XMXB5DADKLNU5MFQ7QAJFXFI63/graph.json","events_json":"https://pith.science/api/pith-number/XMXB5DADKLNU5MFQ7QAJFXFI63/events.json","paper":"https://pith.science/paper/XMXB5DAD"},"agent_actions":{"view_html":"https://pith.science/pith/XMXB5DADKLNU5MFQ7QAJFXFI63","download_json":"https://pith.science/pith/XMXB5DADKLNU5MFQ7QAJFXFI63.json","view_paper":"https://pith.science/paper/XMXB5DAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18003&json=true","fetch_graph":"https://pith.science/api/pith-number/XMXB5DADKLNU5MFQ7QAJFXFI63/graph.json","fetch_events":"https://pith.science/api/pith-number/XMXB5DADKLNU5MFQ7QAJFXFI63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMXB5DADKLNU5MFQ7QAJFXFI63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMXB5DADKLNU5MFQ7QAJFXFI63/action/storage_attestation","attest_author":"https://pith.science/pith/XMXB5DADKLNU5MFQ7QAJFXFI63/action/author_attestation","sign_citation":"https://pith.science/pith/XMXB5DADKLNU5MFQ7QAJFXFI63/action/citation_signature","submit_replication":"https://pith.science/pith/XMXB5DADKLNU5MFQ7QAJFXFI63/action/replication_record"}},"created_at":"2026-07-05T08:24:14.410224+00:00","updated_at":"2026-07-05T08:24:14.410224+00:00"}