{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:H4HC2Z5S5GK33OBEENSM737EYJ","short_pith_number":"pith:H4HC2Z5S","schema_version":"1.0","canonical_sha256":"3f0e2d67b2e995bdb8242364cfefe4c275ba9d56394bb93a42a221d1b88c124e","source":{"kind":"arxiv","id":"2607.17675","version":1},"attestation_state":"computed","paper":{"title":"ShotPlan: Cinematic Video Generation with Learnable Planning Token","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi Zhang, Cong Liu, Guangce Liu, Haibin Huang, Haosen Yang, Hongxun Yao, Jiepeng Wang, Junqi Liu, Su Guo, Xuelong Li","submitted_at":"2026-07-20T08:27:18Z","abstract_excerpt":"Current video generation models achieve impressive results in single-shot generation, yet remain limited in cinematic video generation, where coherent narratives and effective multi-shot composition require explicit shot planning. To address this challenge, we propose ShotPlan, a framework for explicit multi-shot cinematic video generation built upon a video diffusion foundation model. Our method introduces learnable planning tokens that capture shot-level transition cues and can be seamlessly integrated with the original video generation tokens to control transition timestamps. Unlike standar"},"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":"2607.17675","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T08:27:18Z","cross_cats_sorted":[],"title_canon_sha256":"2e18f0af02c84e1838a71b01fecc0d53eca2e17a5854b3ab7e9dafa3ea2c11ca","abstract_canon_sha256":"c91f42a3b9a3ec17f93db1af24f9bdd689a638ce870aa49a6a55b49de4944838"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T02:21:54.034944Z","signature_b64":"22C+eqVuuhOgAfjAO2OBLmgRWckhN+yMTnQ99rAZVDobwNABuGjv43WWR2TK1HATA4UBNsBjtvjEY3+7xshbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f0e2d67b2e995bdb8242364cfefe4c275ba9d56394bb93a42a221d1b88c124e","last_reissued_at":"2026-07-21T02:21:54.034133Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T02:21:54.034133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ShotPlan: Cinematic Video Generation with Learnable Planning Token","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi Zhang, Cong Liu, Guangce Liu, Haibin Huang, Haosen Yang, Hongxun Yao, Jiepeng Wang, Junqi Liu, Su Guo, Xuelong Li","submitted_at":"2026-07-20T08:27:18Z","abstract_excerpt":"Current video generation models achieve impressive results in single-shot generation, yet remain limited in cinematic video generation, where coherent narratives and effective multi-shot composition require explicit shot planning. To address this challenge, we propose ShotPlan, a framework for explicit multi-shot cinematic video generation built upon a video diffusion foundation model. Our method introduces learnable planning tokens that capture shot-level transition cues and can be seamlessly integrated with the original video generation tokens to control transition timestamps. Unlike standar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17675","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/2607.17675/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":"2607.17675","created_at":"2026-07-21T02:21:54.034547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17675v1","created_at":"2026-07-21T02:21:54.034547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17675","created_at":"2026-07-21T02:21:54.034547+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4HC2Z5S5GK3","created_at":"2026-07-21T02:21:54.034547+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4HC2Z5S5GK33OBE","created_at":"2026-07-21T02:21:54.034547+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4HC2Z5S","created_at":"2026-07-21T02:21:54.034547+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/H4HC2Z5S5GK33OBEENSM737EYJ","json":"https://pith.science/pith/H4HC2Z5S5GK33OBEENSM737EYJ.json","graph_json":"https://pith.science/api/pith-number/H4HC2Z5S5GK33OBEENSM737EYJ/graph.json","events_json":"https://pith.science/api/pith-number/H4HC2Z5S5GK33OBEENSM737EYJ/events.json","paper":"https://pith.science/paper/H4HC2Z5S"},"agent_actions":{"view_html":"https://pith.science/pith/H4HC2Z5S5GK33OBEENSM737EYJ","download_json":"https://pith.science/pith/H4HC2Z5S5GK33OBEENSM737EYJ.json","view_paper":"https://pith.science/paper/H4HC2Z5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17675&json=true","fetch_graph":"https://pith.science/api/pith-number/H4HC2Z5S5GK33OBEENSM737EYJ/graph.json","fetch_events":"https://pith.science/api/pith-number/H4HC2Z5S5GK33OBEENSM737EYJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4HC2Z5S5GK33OBEENSM737EYJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4HC2Z5S5GK33OBEENSM737EYJ/action/storage_attestation","attest_author":"https://pith.science/pith/H4HC2Z5S5GK33OBEENSM737EYJ/action/author_attestation","sign_citation":"https://pith.science/pith/H4HC2Z5S5GK33OBEENSM737EYJ/action/citation_signature","submit_replication":"https://pith.science/pith/H4HC2Z5S5GK33OBEENSM737EYJ/action/replication_record"}},"created_at":"2026-07-21T02:21:54.034547+00:00","updated_at":"2026-07-21T02:21:54.034547+00:00"}