{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UKCQ2WECUGZIG7RV7HS4D5WUOQ","short_pith_number":"pith:UKCQ2WEC","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"},"canonical_sha256":"a2850d5882a1b2837e35f9e5c1f6d4743715f4cc086a160f501f1b40ea46cfda","source":{"kind":"arxiv","id":"2412.11621","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11621","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11621v1","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11621","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"pith_short_12","alias_value":"UKCQ2WECUGZI","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"pith_short_16","alias_value":"UKCQ2WECUGZIG7RV","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"pith_short_8","alias_value":"UKCQ2WEC","created_at":"2026-07-05T09:49:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UKCQ2WECUGZIG7RV7HS4D5WUOQ","target":"record","payload":{"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"},"canonical_sha256":"a2850d5882a1b2837e35f9e5c1f6d4743715f4cc086a160f501f1b40ea46cfda","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"},"source_kind":"arxiv","source_id":"2412.11621","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QyjWWibTZ8lGf1XhOYNctVZ1nnaff5NrKg6KiwM0kXSmRLHggT/S4dU3E1hsSbtQrLKfGP+LvxJ2Vl/WF3ACCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T19:33:05.421933Z"},"content_sha256":"ff8c7f4abbff759b58f2503b35d9ebba5cac759c800fe02d8c3958a00ea22459","schema_version":"1.0","event_id":"sha256:ff8c7f4abbff759b58f2503b35d9ebba5cac759c800fe02d8c3958a00ea22459"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UKCQ2WECUGZIG7RV7HS4D5WUOQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WjJ9eg2hRBssuoccpLevb58CH2XSBePGrgrhjyxQGpxrjoWWYWkCo1B/qvHipgk29ZvOXcgMFRIfyAtmmMJPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T19:33:05.422840Z"},"content_sha256":"4d78edc6d7d9d6ad6570adc73d42fbef944195d4c0b40c521aae122335779b40","schema_version":"1.0","event_id":"sha256:4d78edc6d7d9d6ad6570adc73d42fbef944195d4c0b40c521aae122335779b40"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UKCQ2WECUGZIG7RV7HS4D5WUOQ/bundle.json","state_url":"https://pith.science/pith/UKCQ2WECUGZIG7RV7HS4D5WUOQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UKCQ2WECUGZIG7RV7HS4D5WUOQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-13T19:33:05Z","links":{"resolver":"https://pith.science/pith/UKCQ2WECUGZIG7RV7HS4D5WUOQ","bundle":"https://pith.science/pith/UKCQ2WECUGZIG7RV7HS4D5WUOQ/bundle.json","state":"https://pith.science/pith/UKCQ2WECUGZIG7RV7HS4D5WUOQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UKCQ2WECUGZIG7RV7HS4D5WUOQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UKCQ2WECUGZIG7RV7HS4D5WUOQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a7804706a4ea49255ce6f12f81114eab261468307fe956706254c91ebffb9ef1","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T10:08:38Z","title_canon_sha256":"f42710f9fcdae73ce2de75aa9e00ebe483c21131d1df6b9aff4f539a12dab041"},"schema_version":"1.0","source":{"id":"2412.11621","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11621","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11621v1","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11621","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"pith_short_12","alias_value":"UKCQ2WECUGZI","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"pith_short_16","alias_value":"UKCQ2WECUGZIG7RV","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"pith_short_8","alias_value":"UKCQ2WEC","created_at":"2026-07-05T09:49:48Z"}],"graph_snapshots":[{"event_id":"sha256:4d78edc6d7d9d6ad6570adc73d42fbef944195d4c0b40c521aae122335779b40","target":"graph","created_at":"2026-07-05T09:49:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.11621/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Ali Koksal, Burak Satar, Kevin Qinhong Lin, Mike Zheng Shou, Muhammet Furkan Ilaslan, Qianli Xu","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T10:08:38Z","title":"VG-TVP: Multimodal Procedural Planning via Visually Grounded Text-Video Prompting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11621","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ff8c7f4abbff759b58f2503b35d9ebba5cac759c800fe02d8c3958a00ea22459","target":"record","created_at":"2026-07-05T09:49:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a7804706a4ea49255ce6f12f81114eab261468307fe956706254c91ebffb9ef1","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T10:08:38Z","title_canon_sha256":"f42710f9fcdae73ce2de75aa9e00ebe483c21131d1df6b9aff4f539a12dab041"},"schema_version":"1.0","source":{"id":"2412.11621","kind":"arxiv","version":1}},"canonical_sha256":"a2850d5882a1b2837e35f9e5c1f6d4743715f4cc086a160f501f1b40ea46cfda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2850d5882a1b2837e35f9e5c1f6d4743715f4cc086a160f501f1b40ea46cfda","first_computed_at":"2026-07-05T09:49:48.616219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:48.616219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rLYhgv9/cHkKxazOvCoIf8QVtJ9hEvH/6p5EZ/MMEQ4wT0+WluLAtNHudds8NCaVYKr9dUJ5qhB07nwt4L3eBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:48.616749Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11621","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff8c7f4abbff759b58f2503b35d9ebba5cac759c800fe02d8c3958a00ea22459","sha256:4d78edc6d7d9d6ad6570adc73d42fbef944195d4c0b40c521aae122335779b40"],"state_sha256":"bd8c2ac934f8cf7a60aa3809af848bb569591830232d24938c9a367936118802"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mnkmG8F2x6BPYquUIJ2FFvoQE1h5SearMu7JIGt18wLYoUs5nkR9gZMQSDQO51n1iGtd1M+SJW9aX40eRUKrCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T19:33:05.429287Z","bundle_sha256":"656cce08eb77c1371671785be1df6cbbc98934a1bdb09b8ebba110a135d19510"}}