{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NTHPBVL7T7SCRTOJXPFIVNALMQ","short_pith_number":"pith:NTHPBVL7","schema_version":"1.0","canonical_sha256":"6ccef0d57f9fe428cdc9bbca8ab40b641ed83918a4006aa175a223ac9f0247b6","source":{"kind":"arxiv","id":"2506.15838","version":1},"attestation_state":"computed","paper":{"title":"EchoShot: Multi-Shot Portrait Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Deng, Caixia Yan, Hualian Sheng, Jiahao Wang, Jieping Ye, Sijia Cai, Weizhan Zhang, Yachuang Feng","submitted_at":"2025-06-16T11:00:16Z","abstract_excerpt":"Video diffusion models substantially boost the productivity of artistic workflows with high-quality portrait video generative capacity. However, prevailing pipelines are primarily constrained to single-shot creation, while real-world applications urge for multiple shots with identity consistency and flexible content controllability. In this work, we propose EchoShot, a native and scalable multi-shot framework for portrait customization built upon a foundation video diffusion model. To start with, we propose shot-aware position embedding mechanisms within video diffusion transformer architectur"},"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":"2506.15838","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-16T11:00:16Z","cross_cats_sorted":[],"title_canon_sha256":"d089c99d557c39ad8dcd0c790947577617562ee2e995e3a6fd35029962f4b744","abstract_canon_sha256":"01618de6f134d3a0e8a2e1173f33a9d3cf4e4a0b83701c67b41dcbc527e114fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:53.277073Z","signature_b64":"cl9QdgfdacQfrT0esRzBEVgtYstzHQGRxQghHQEPWxFMFvYWEtHMtc+ODHDBuauYzxxTXPyBJODRiifk9/9FAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ccef0d57f9fe428cdc9bbca8ab40b641ed83918a4006aa175a223ac9f0247b6","last_reissued_at":"2026-07-05T11:23:53.276581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:53.276581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EchoShot: Multi-Shot Portrait Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Deng, Caixia Yan, Hualian Sheng, Jiahao Wang, Jieping Ye, Sijia Cai, Weizhan Zhang, Yachuang Feng","submitted_at":"2025-06-16T11:00:16Z","abstract_excerpt":"Video diffusion models substantially boost the productivity of artistic workflows with high-quality portrait video generative capacity. However, prevailing pipelines are primarily constrained to single-shot creation, while real-world applications urge for multiple shots with identity consistency and flexible content controllability. In this work, we propose EchoShot, a native and scalable multi-shot framework for portrait customization built upon a foundation video diffusion model. To start with, we propose shot-aware position embedding mechanisms within video diffusion transformer architectur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15838","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/2506.15838/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":"2506.15838","created_at":"2026-07-05T11:23:53.276642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15838v1","created_at":"2026-07-05T11:23:53.276642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15838","created_at":"2026-07-05T11:23:53.276642+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTHPBVL7T7SC","created_at":"2026-07-05T11:23:53.276642+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTHPBVL7T7SCRTOJ","created_at":"2026-07-05T11:23:53.276642+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTHPBVL7","created_at":"2026-07-05T11:23:53.276642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20799","citing_title":"GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NTHPBVL7T7SCRTOJXPFIVNALMQ","json":"https://pith.science/pith/NTHPBVL7T7SCRTOJXPFIVNALMQ.json","graph_json":"https://pith.science/api/pith-number/NTHPBVL7T7SCRTOJXPFIVNALMQ/graph.json","events_json":"https://pith.science/api/pith-number/NTHPBVL7T7SCRTOJXPFIVNALMQ/events.json","paper":"https://pith.science/paper/NTHPBVL7"},"agent_actions":{"view_html":"https://pith.science/pith/NTHPBVL7T7SCRTOJXPFIVNALMQ","download_json":"https://pith.science/pith/NTHPBVL7T7SCRTOJXPFIVNALMQ.json","view_paper":"https://pith.science/paper/NTHPBVL7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15838&json=true","fetch_graph":"https://pith.science/api/pith-number/NTHPBVL7T7SCRTOJXPFIVNALMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/NTHPBVL7T7SCRTOJXPFIVNALMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTHPBVL7T7SCRTOJXPFIVNALMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTHPBVL7T7SCRTOJXPFIVNALMQ/action/storage_attestation","attest_author":"https://pith.science/pith/NTHPBVL7T7SCRTOJXPFIVNALMQ/action/author_attestation","sign_citation":"https://pith.science/pith/NTHPBVL7T7SCRTOJXPFIVNALMQ/action/citation_signature","submit_replication":"https://pith.science/pith/NTHPBVL7T7SCRTOJXPFIVNALMQ/action/replication_record"}},"created_at":"2026-07-05T11:23:53.276642+00:00","updated_at":"2026-07-05T11:23:53.276642+00:00"}