{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QFUH2T7IXDDWXWJDXYKAGUXXOC","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":"28b21962e35a468661b8eca398b942c674176ac26e13133e18bb7224b045adc2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-07-17T06:33:51Z","title_canon_sha256":"0ca879ba802b1bf3fac69df6d80237f213ef955847516561124b93fe6671a1ab"},"schema_version":"1.0","source":{"id":"2407.12341","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12341","created_at":"2026-07-05T11:52:56Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12341v2","created_at":"2026-07-05T11:52:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12341","created_at":"2026-07-05T11:52:56Z"},{"alias_kind":"pith_short_12","alias_value":"QFUH2T7IXDDW","created_at":"2026-07-05T11:52:56Z"},{"alias_kind":"pith_short_16","alias_value":"QFUH2T7IXDDWXWJD","created_at":"2026-07-05T11:52:56Z"},{"alias_kind":"pith_short_8","alias_value":"QFUH2T7I","created_at":"2026-07-05T11:52:56Z"}],"graph_snapshots":[{"event_id":"sha256:bc5e24c9d4332763f19942ac0a72c0bc2d2fed1062fac88c3da5f63db8809eaf","target":"graph","created_at":"2026-07-05T11:52:56Z","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/2407.12341/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-video retrieval answers user queries through searches based on concepts and embeddings. However, due to limitations in the size of the concept bank and the amount of training data, answering queries in the wild is not always effective because of the out-of-vocabulary problem. Furthermore, neither concept-based nor embedding-based search can perform reasoning to consolidate search results for complex queries that include logical and spatial constraints. To address these challenges, we leverage large language models (LLMs) to paraphrase queries using text-to-text (T2T), text-to-image (T2","authors_text":"Chong-Wah Ngo, Jiaxin Wu, Qing Li, Sheng-hua Zhong, Wing-Kwong Chan, Xiong-Yong Wei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-07-17T06:33:51Z","title":"Multimodal LLM-based Query Paraphrasing for Video Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12341","kind":"arxiv","version":2},"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:de22fd2594f061897f10a5e74d8ad5248515131e0065605c5f37b0436e57a2f2","target":"record","created_at":"2026-07-05T11:52:56Z","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":"28b21962e35a468661b8eca398b942c674176ac26e13133e18bb7224b045adc2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-07-17T06:33:51Z","title_canon_sha256":"0ca879ba802b1bf3fac69df6d80237f213ef955847516561124b93fe6671a1ab"},"schema_version":"1.0","source":{"id":"2407.12341","kind":"arxiv","version":2}},"canonical_sha256":"81687d4fe8b8c76bd923be140352f770ae6e98bfe13e904726f9bb9f98f1e120","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81687d4fe8b8c76bd923be140352f770ae6e98bfe13e904726f9bb9f98f1e120","first_computed_at":"2026-07-05T11:52:56.183250Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:56.183250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"91AbU1bPdT/IZfvcHMTRR4Gf0oCTqgIbgpA/iIDHx6IS7JtwmNxvZUHcttylJpNlrPG9BmrxTXDh1A9ERhPgDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:56.183696Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12341","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de22fd2594f061897f10a5e74d8ad5248515131e0065605c5f37b0436e57a2f2","sha256:bc5e24c9d4332763f19942ac0a72c0bc2d2fed1062fac88c3da5f63db8809eaf"],"state_sha256":"50d36ecb2c9f44d4ef9253ab3ca3d6feccc751a4797c58fd041d4a9a7452a2f1"}