{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UKCQ2WECUGZIG7RV7HS4D5WUOQ","short_pith_number":"pith:UKCQ2WEC","schema_version":"1.0","canonical_sha256":"a2850d5882a1b2837e35f9e5c1f6d4743715f4cc086a160f501f1b40ea46cfda","source":{"kind":"arxiv","id":"2412.11621","version":1},"attestation_state":"computed","paper":{"title":"VG-TVP: Multimodal Procedural Planning via Visually Grounded Text-Video Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Ali Koksal, Burak Satar, Kevin Qinhong Lin, Mike Zheng Shou, Muhammet Furkan Ilaslan, Qianli Xu","submitted_at":"2024-12-16T10:08:38Z","abstract_excerpt":"Large Language Model (LLM)-based agents have shown promise in procedural tasks, but the potential of multimodal instructions augmented by texts and videos to assist users remains under-explored. To address this gap, we propose the Visually Grounded Text-Video Prompting (VG-TVP) method which is a novel LLM-empowered Multimodal Procedural Planning (MPP) framework. It generates cohesive text and video procedural plans given a specified high-level objective. The main challenges are achieving textual and visual informativeness, temporal coherence, and accuracy in procedural plans. VG-TVP leverages "},"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":"2412.11621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T10:08:38Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"f42710f9fcdae73ce2de75aa9e00ebe483c21131d1df6b9aff4f539a12dab041","abstract_canon_sha256":"a7804706a4ea49255ce6f12f81114eab261468307fe956706254c91ebffb9ef1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:48.616749Z","signature_b64":"rLYhgv9/cHkKxazOvCoIf8QVtJ9hEvH/6p5EZ/MMEQ4wT0+WluLAtNHudds8NCaVYKr9dUJ5qhB07nwt4L3eBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2850d5882a1b2837e35f9e5c1f6d4743715f4cc086a160f501f1b40ea46cfda","last_reissued_at":"2026-07-05T09:49:48.616219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:48.616219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VG-TVP: Multimodal Procedural Planning via Visually Grounded Text-Video Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Ali Koksal, Burak Satar, Kevin Qinhong Lin, Mike Zheng Shou, Muhammet Furkan Ilaslan, Qianli Xu","submitted_at":"2024-12-16T10:08:38Z","abstract_excerpt":"Large Language Model (LLM)-based agents have shown promise in procedural tasks, but the potential of multimodal instructions augmented by texts and videos to assist users remains under-explored. To address this gap, we propose the Visually Grounded Text-Video Prompting (VG-TVP) method which is a novel LLM-empowered Multimodal Procedural Planning (MPP) framework. It generates cohesive text and video procedural plans given a specified high-level objective. The main challenges are achieving textual and visual informativeness, temporal coherence, and accuracy in procedural plans. VG-TVP leverages "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11621","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/2412.11621/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":"2412.11621","created_at":"2026-07-05T09:49:48.616290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11621v1","created_at":"2026-07-05T09:49:48.616290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11621","created_at":"2026-07-05T09:49:48.616290+00:00"},{"alias_kind":"pith_short_12","alias_value":"UKCQ2WECUGZI","created_at":"2026-07-05T09:49:48.616290+00:00"},{"alias_kind":"pith_short_16","alias_value":"UKCQ2WECUGZIG7RV","created_at":"2026-07-05T09:49:48.616290+00:00"},{"alias_kind":"pith_short_8","alias_value":"UKCQ2WEC","created_at":"2026-07-05T09:49:48.616290+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/UKCQ2WECUGZIG7RV7HS4D5WUOQ","json":"https://pith.science/pith/UKCQ2WECUGZIG7RV7HS4D5WUOQ.json","graph_json":"https://pith.science/api/pith-number/UKCQ2WECUGZIG7RV7HS4D5WUOQ/graph.json","events_json":"https://pith.science/api/pith-number/UKCQ2WECUGZIG7RV7HS4D5WUOQ/events.json","paper":"https://pith.science/paper/UKCQ2WEC"},"agent_actions":{"view_html":"https://pith.science/pith/UKCQ2WECUGZIG7RV7HS4D5WUOQ","download_json":"https://pith.science/pith/UKCQ2WECUGZIG7RV7HS4D5WUOQ.json","view_paper":"https://pith.science/paper/UKCQ2WEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11621&json=true","fetch_graph":"https://pith.science/api/pith-number/UKCQ2WECUGZIG7RV7HS4D5WUOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/UKCQ2WECUGZIG7RV7HS4D5WUOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UKCQ2WECUGZIG7RV7HS4D5WUOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UKCQ2WECUGZIG7RV7HS4D5WUOQ/action/storage_attestation","attest_author":"https://pith.science/pith/UKCQ2WECUGZIG7RV7HS4D5WUOQ/action/author_attestation","sign_citation":"https://pith.science/pith/UKCQ2WECUGZIG7RV7HS4D5WUOQ/action/citation_signature","submit_replication":"https://pith.science/pith/UKCQ2WECUGZIG7RV7HS4D5WUOQ/action/replication_record"}},"created_at":"2026-07-05T09:49:48.616290+00:00","updated_at":"2026-07-05T09:49:48.616290+00:00"}