{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CBPALY2QL5EAGX47TGNTXWK4SO","short_pith_number":"pith:CBPALY2Q","schema_version":"1.0","canonical_sha256":"105e05e3505f48035f9f999b3bd95c93a8243774578bffeecf764faadbf2b52e","source":{"kind":"arxiv","id":"2503.06310","version":4},"attestation_state":"computed","paper":{"title":"Scene-Action Prompt Fusion for Coherent Text-to-Video Storytelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Divya Kothandaraman, Ming C. Lin, Taewon Kang","submitted_at":"2025-03-08T19:04:36Z","abstract_excerpt":"Generating coherent long-form video sequences from discrete text prompts remains challenging due to difficulties in maintaining temporal coherence, semantic consistency, and scene-action continuity across segments. We propose a novel storytelling framework that integrates scene and action prompts through dynamics-inspired prompt mixing. Our approach combines three key components: (i) a bidirectional time-weighted latent blending strategy that enforces temporal consistency between consecutive video segments, (ii) a dynamics-informed prompt weighting (DIPW) mechanism that adaptively balances sce"},"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":"2503.06310","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-08T19:04:36Z","cross_cats_sorted":[],"title_canon_sha256":"4674a6772a947aeb258e2de87cd1455ed9ba7df3ea9f66a5c2a81682211fd15e","abstract_canon_sha256":"3f2494610519b89643d518dc5478f7dafefc10c8a40e818da5830930a3cd9a4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T02:05:32.874210Z","signature_b64":"Vz8cQoPRcXpuwWGQPNJAm8rdWmKKYy38DJrZF+KEtYwlk5/AN7ySqEMW3Me/J31kv8WvaTlu2sQQIE0mKtxZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"105e05e3505f48035f9f999b3bd95c93a8243774578bffeecf764faadbf2b52e","last_reissued_at":"2026-05-20T02:05:32.873514Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T02:05:32.873514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scene-Action Prompt Fusion for Coherent Text-to-Video Storytelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Divya Kothandaraman, Ming C. Lin, Taewon Kang","submitted_at":"2025-03-08T19:04:36Z","abstract_excerpt":"Generating coherent long-form video sequences from discrete text prompts remains challenging due to difficulties in maintaining temporal coherence, semantic consistency, and scene-action continuity across segments. We propose a novel storytelling framework that integrates scene and action prompts through dynamics-inspired prompt mixing. Our approach combines three key components: (i) a bidirectional time-weighted latent blending strategy that enforces temporal consistency between consecutive video segments, (ii) a dynamics-informed prompt weighting (DIPW) mechanism that adaptively balances sce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06310","kind":"arxiv","version":4},"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/2503.06310/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":"2503.06310","created_at":"2026-05-20T02:05:32.873597+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06310v4","created_at":"2026-05-20T02:05:32.873597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06310","created_at":"2026-05-20T02:05:32.873597+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBPALY2QL5EA","created_at":"2026-05-20T02:05:32.873597+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBPALY2QL5EAGX47","created_at":"2026-05-20T02:05:32.873597+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBPALY2Q","created_at":"2026-05-20T02:05:32.873597+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16819","citing_title":"Character-Centered Dialogue Generation from Scene-Level Prompts","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBPALY2QL5EAGX47TGNTXWK4SO","json":"https://pith.science/pith/CBPALY2QL5EAGX47TGNTXWK4SO.json","graph_json":"https://pith.science/api/pith-number/CBPALY2QL5EAGX47TGNTXWK4SO/graph.json","events_json":"https://pith.science/api/pith-number/CBPALY2QL5EAGX47TGNTXWK4SO/events.json","paper":"https://pith.science/paper/CBPALY2Q"},"agent_actions":{"view_html":"https://pith.science/pith/CBPALY2QL5EAGX47TGNTXWK4SO","download_json":"https://pith.science/pith/CBPALY2QL5EAGX47TGNTXWK4SO.json","view_paper":"https://pith.science/paper/CBPALY2Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06310&json=true","fetch_graph":"https://pith.science/api/pith-number/CBPALY2QL5EAGX47TGNTXWK4SO/graph.json","fetch_events":"https://pith.science/api/pith-number/CBPALY2QL5EAGX47TGNTXWK4SO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBPALY2QL5EAGX47TGNTXWK4SO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBPALY2QL5EAGX47TGNTXWK4SO/action/storage_attestation","attest_author":"https://pith.science/pith/CBPALY2QL5EAGX47TGNTXWK4SO/action/author_attestation","sign_citation":"https://pith.science/pith/CBPALY2QL5EAGX47TGNTXWK4SO/action/citation_signature","submit_replication":"https://pith.science/pith/CBPALY2QL5EAGX47TGNTXWK4SO/action/replication_record"}},"created_at":"2026-05-20T02:05:32.873597+00:00","updated_at":"2026-05-20T02:05:32.873597+00:00"}