{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N6JHXV6YEWLMCMVQJLJX7A5SNH","short_pith_number":"pith:N6JHXV6Y","schema_version":"1.0","canonical_sha256":"6f927bd7d82596c132b04ad37f83b269d727b1ff91c2b306f030dde1ded6fc50","source":{"kind":"arxiv","id":"2505.21459","version":1},"attestation_state":"computed","paper":{"title":"LazyVLM: Neuro-Symbolic Approach to Video Analytics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IR","cs.MM"],"primary_cat":"cs.DB","authors_text":"Chao Zhang, M. Tamer \\\"Ozsu, Wei Pang, Xiangru Jian, Zhengyuan Dong","submitted_at":"2025-05-27T17:31:17Z","abstract_excerpt":"Current video analytics approaches face a fundamental trade-off between flexibility and efficiency. End-to-end Vision Language Models (VLMs) often struggle with long-context processing and incur high computational costs, while neural-symbolic methods depend heavily on manual labeling and rigid rule design. In this paper, we introduce LazyVLM, a neuro-symbolic video analytics system that provides a user-friendly query interface similar to VLMs, while addressing their scalability limitation. LazyVLM enables users to effortlessly drop in video data and specify complex multi-frame video queries us"},"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":"2505.21459","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-27T17:31:17Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IR","cs.MM"],"title_canon_sha256":"97aa4eda5b80ff81368a16bfef37212145016ff94aa49596355960f5b1e67c0e","abstract_canon_sha256":"8772400da8bbb481b34cd98dbe9ec543f54a34eef02efd13db99cd475ef03bb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:42.306677Z","signature_b64":"zIPn8HrcpaVSc2wLJrnSAzPLqxvSoxDQABMdR90vB9/tPo4Vkj0Nc142GasVYBo53q1zfFXxBOEMOQ7CpMcjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f927bd7d82596c132b04ad37f83b269d727b1ff91c2b306f030dde1ded6fc50","last_reissued_at":"2026-07-05T11:10:42.306173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:42.306173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LazyVLM: Neuro-Symbolic Approach to Video Analytics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IR","cs.MM"],"primary_cat":"cs.DB","authors_text":"Chao Zhang, M. Tamer \\\"Ozsu, Wei Pang, Xiangru Jian, Zhengyuan Dong","submitted_at":"2025-05-27T17:31:17Z","abstract_excerpt":"Current video analytics approaches face a fundamental trade-off between flexibility and efficiency. End-to-end Vision Language Models (VLMs) often struggle with long-context processing and incur high computational costs, while neural-symbolic methods depend heavily on manual labeling and rigid rule design. In this paper, we introduce LazyVLM, a neuro-symbolic video analytics system that provides a user-friendly query interface similar to VLMs, while addressing their scalability limitation. LazyVLM enables users to effortlessly drop in video data and specify complex multi-frame video queries us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21459","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/2505.21459/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":"2505.21459","created_at":"2026-07-05T11:10:42.306231+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21459v1","created_at":"2026-07-05T11:10:42.306231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21459","created_at":"2026-07-05T11:10:42.306231+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6JHXV6YEWLM","created_at":"2026-07-05T11:10:42.306231+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6JHXV6YEWLMCMVQ","created_at":"2026-07-05T11:10:42.306231+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6JHXV6Y","created_at":"2026-07-05T11:10:42.306231+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07413","citing_title":"FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N6JHXV6YEWLMCMVQJLJX7A5SNH","json":"https://pith.science/pith/N6JHXV6YEWLMCMVQJLJX7A5SNH.json","graph_json":"https://pith.science/api/pith-number/N6JHXV6YEWLMCMVQJLJX7A5SNH/graph.json","events_json":"https://pith.science/api/pith-number/N6JHXV6YEWLMCMVQJLJX7A5SNH/events.json","paper":"https://pith.science/paper/N6JHXV6Y"},"agent_actions":{"view_html":"https://pith.science/pith/N6JHXV6YEWLMCMVQJLJX7A5SNH","download_json":"https://pith.science/pith/N6JHXV6YEWLMCMVQJLJX7A5SNH.json","view_paper":"https://pith.science/paper/N6JHXV6Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21459&json=true","fetch_graph":"https://pith.science/api/pith-number/N6JHXV6YEWLMCMVQJLJX7A5SNH/graph.json","fetch_events":"https://pith.science/api/pith-number/N6JHXV6YEWLMCMVQJLJX7A5SNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6JHXV6YEWLMCMVQJLJX7A5SNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6JHXV6YEWLMCMVQJLJX7A5SNH/action/storage_attestation","attest_author":"https://pith.science/pith/N6JHXV6YEWLMCMVQJLJX7A5SNH/action/author_attestation","sign_citation":"https://pith.science/pith/N6JHXV6YEWLMCMVQJLJX7A5SNH/action/citation_signature","submit_replication":"https://pith.science/pith/N6JHXV6YEWLMCMVQJLJX7A5SNH/action/replication_record"}},"created_at":"2026-07-05T11:10:42.306231+00:00","updated_at":"2026-07-05T11:10:42.306231+00:00"}