{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ELDBIY3UWFHDZ5ETT7INBONMTF","short_pith_number":"pith:ELDBIY3U","schema_version":"1.0","canonical_sha256":"22c6146374b14e3cf4939fd0d0b9ac9944f4832058688bf8aea3621b00c58895","source":{"kind":"arxiv","id":"2606.20799","version":1},"attestation_state":"computed","paper":{"title":"GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jingdong Wang, Kun Zhou, Siyu Zhu, Tianjia Shao, Weijia Dou, Yixuan Lai","submitted_at":"2026-06-18T18:00:03Z","abstract_excerpt":"Generating visually consistent multi-shot videos remains an open challenge. As videos span more shots, inconsistencies can accumulate across shots, causing entities that reappear across shots -- characters, objects, and locations -- to drift away from how they first appear. We observe that viewers judge consistency by comparing each later appearance of an entity with its first clear appearance; the visual quality of this initial appearance sets the consistency ceiling for all that follows. Motivated by this, we present \\textbf{GroundShot}, a training-free, model-agnostic agentic framework for "},"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":"2606.20799","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T18:00:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9f65a26ac7bd667fbf4fcfb37f166dbb58b98706c99ad6265eea13381aaa6f91","abstract_canon_sha256":"cdf2440b7993e32adc043a43ca31161b6012a38605b05b8cb69f412ceea02d13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T00:11:58.979002Z","signature_b64":"x7qYgcOY8r9LTOQ52X0zNXIYhA45eu3cNPi/6LCFEGVMuW3lJe29KmY0zcs02CMBu1pxEcAF+mCWyBtZJBeGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22c6146374b14e3cf4939fd0d0b9ac9944f4832058688bf8aea3621b00c58895","last_reissued_at":"2026-06-23T00:11:58.978606Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T00:11:58.978606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jingdong Wang, Kun Zhou, Siyu Zhu, Tianjia Shao, Weijia Dou, Yixuan Lai","submitted_at":"2026-06-18T18:00:03Z","abstract_excerpt":"Generating visually consistent multi-shot videos remains an open challenge. As videos span more shots, inconsistencies can accumulate across shots, causing entities that reappear across shots -- characters, objects, and locations -- to drift away from how they first appear. We observe that viewers judge consistency by comparing each later appearance of an entity with its first clear appearance; the visual quality of this initial appearance sets the consistency ceiling for all that follows. Motivated by this, we present \\textbf{GroundShot}, a training-free, model-agnostic agentic framework for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20799","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/2606.20799/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":"2606.20799","created_at":"2026-06-23T00:11:58.978662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20799v1","created_at":"2026-06-23T00:11:58.978662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20799","created_at":"2026-06-23T00:11:58.978662+00:00"},{"alias_kind":"pith_short_12","alias_value":"ELDBIY3UWFHD","created_at":"2026-06-23T00:11:58.978662+00:00"},{"alias_kind":"pith_short_16","alias_value":"ELDBIY3UWFHDZ5ET","created_at":"2026-06-23T00:11:58.978662+00:00"},{"alias_kind":"pith_short_8","alias_value":"ELDBIY3U","created_at":"2026-06-23T00:11:58.978662+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/ELDBIY3UWFHDZ5ETT7INBONMTF","json":"https://pith.science/pith/ELDBIY3UWFHDZ5ETT7INBONMTF.json","graph_json":"https://pith.science/api/pith-number/ELDBIY3UWFHDZ5ETT7INBONMTF/graph.json","events_json":"https://pith.science/api/pith-number/ELDBIY3UWFHDZ5ETT7INBONMTF/events.json","paper":"https://pith.science/paper/ELDBIY3U"},"agent_actions":{"view_html":"https://pith.science/pith/ELDBIY3UWFHDZ5ETT7INBONMTF","download_json":"https://pith.science/pith/ELDBIY3UWFHDZ5ETT7INBONMTF.json","view_paper":"https://pith.science/paper/ELDBIY3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20799&json=true","fetch_graph":"https://pith.science/api/pith-number/ELDBIY3UWFHDZ5ETT7INBONMTF/graph.json","fetch_events":"https://pith.science/api/pith-number/ELDBIY3UWFHDZ5ETT7INBONMTF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ELDBIY3UWFHDZ5ETT7INBONMTF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ELDBIY3UWFHDZ5ETT7INBONMTF/action/storage_attestation","attest_author":"https://pith.science/pith/ELDBIY3UWFHDZ5ETT7INBONMTF/action/author_attestation","sign_citation":"https://pith.science/pith/ELDBIY3UWFHDZ5ETT7INBONMTF/action/citation_signature","submit_replication":"https://pith.science/pith/ELDBIY3UWFHDZ5ETT7INBONMTF/action/replication_record"}},"created_at":"2026-06-23T00:11:58.978662+00:00","updated_at":"2026-06-23T00:11:58.978662+00:00"}