{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CU3ILSMR5LU6E6DNI5CHMW5XJJ","short_pith_number":"pith:CU3ILSMR","schema_version":"1.0","canonical_sha256":"153685c991eae9e2786d4744765bb74a789660d3cc44a8a9f042a36e1d1416f5","source":{"kind":"arxiv","id":"2309.10171","version":1},"attestation_state":"computed","paper":{"title":"Specification-Driven Video Search via Foundation Models and Formal Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.FL"],"primary_cat":"cs.CV","authors_text":"Jean-Rapha\\\"el Gaglione, Sandeep Chinchali, Ufuk Topcu, Yunhao Yang","submitted_at":"2023-09-18T21:40:08Z","abstract_excerpt":"The increasing abundance of video data enables users to search for events of interest, e.g., emergency incidents. Meanwhile, it raises new concerns, such as the need for preserving privacy. Existing approaches to video search require either manual inspection or a deep learning model with massive training. We develop a method that uses recent advances in vision and language models, as well as formal methods, to search for events of interest in video clips automatically and efficiently. The method consists of an algorithm to map text-based event descriptions into linear temporal logic over finit"},"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":"2309.10171","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T21:40:08Z","cross_cats_sorted":["cs.FL"],"title_canon_sha256":"8035201860835665b75c3088f2ab1ffab2e9431a627da38e75c95337d6eee31e","abstract_canon_sha256":"6c29b39034942b4aa25233353a1dc7461d877fa7dbe144fdd06b38d70ab324ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:51.838560Z","signature_b64":"C9fUNy4HmsY/wHwl2Fey0PDyxNL+ikKdA6eMZjOgwH6m5z+KEQLWVA57KJC+UM4hc3sO12+U6wuzG761HtuGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"153685c991eae9e2786d4744765bb74a789660d3cc44a8a9f042a36e1d1416f5","last_reissued_at":"2026-07-05T06:51:51.838105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:51.838105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Specification-Driven Video Search via Foundation Models and Formal Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.FL"],"primary_cat":"cs.CV","authors_text":"Jean-Rapha\\\"el Gaglione, Sandeep Chinchali, Ufuk Topcu, Yunhao Yang","submitted_at":"2023-09-18T21:40:08Z","abstract_excerpt":"The increasing abundance of video data enables users to search for events of interest, e.g., emergency incidents. Meanwhile, it raises new concerns, such as the need for preserving privacy. Existing approaches to video search require either manual inspection or a deep learning model with massive training. We develop a method that uses recent advances in vision and language models, as well as formal methods, to search for events of interest in video clips automatically and efficiently. The method consists of an algorithm to map text-based event descriptions into linear temporal logic over finit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10171","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/2309.10171/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":"2309.10171","created_at":"2026-07-05T06:51:51.838160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10171v1","created_at":"2026-07-05T06:51:51.838160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10171","created_at":"2026-07-05T06:51:51.838160+00:00"},{"alias_kind":"pith_short_12","alias_value":"CU3ILSMR5LU6","created_at":"2026-07-05T06:51:51.838160+00:00"},{"alias_kind":"pith_short_16","alias_value":"CU3ILSMR5LU6E6DN","created_at":"2026-07-05T06:51:51.838160+00:00"},{"alias_kind":"pith_short_8","alias_value":"CU3ILSMR","created_at":"2026-07-05T06:51:51.838160+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.17180","citing_title":"We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback","ref_index":89,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CU3ILSMR5LU6E6DNI5CHMW5XJJ","json":"https://pith.science/pith/CU3ILSMR5LU6E6DNI5CHMW5XJJ.json","graph_json":"https://pith.science/api/pith-number/CU3ILSMR5LU6E6DNI5CHMW5XJJ/graph.json","events_json":"https://pith.science/api/pith-number/CU3ILSMR5LU6E6DNI5CHMW5XJJ/events.json","paper":"https://pith.science/paper/CU3ILSMR"},"agent_actions":{"view_html":"https://pith.science/pith/CU3ILSMR5LU6E6DNI5CHMW5XJJ","download_json":"https://pith.science/pith/CU3ILSMR5LU6E6DNI5CHMW5XJJ.json","view_paper":"https://pith.science/paper/CU3ILSMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10171&json=true","fetch_graph":"https://pith.science/api/pith-number/CU3ILSMR5LU6E6DNI5CHMW5XJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/CU3ILSMR5LU6E6DNI5CHMW5XJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CU3ILSMR5LU6E6DNI5CHMW5XJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CU3ILSMR5LU6E6DNI5CHMW5XJJ/action/storage_attestation","attest_author":"https://pith.science/pith/CU3ILSMR5LU6E6DNI5CHMW5XJJ/action/author_attestation","sign_citation":"https://pith.science/pith/CU3ILSMR5LU6E6DNI5CHMW5XJJ/action/citation_signature","submit_replication":"https://pith.science/pith/CU3ILSMR5LU6E6DNI5CHMW5XJJ/action/replication_record"}},"created_at":"2026-07-05T06:51:51.838160+00:00","updated_at":"2026-07-05T06:51:51.838160+00:00"}