{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DLSD7PYKVDU223SFQFABHCKCWG","short_pith_number":"pith:DLSD7PYK","canonical_record":{"source":{"id":"2305.03785","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-05-05T18:37:15Z","cross_cats_sorted":[],"title_canon_sha256":"d8067d283dcaa6ccda52120d7776817877d06acbe311beb87d19ffa52414064b","abstract_canon_sha256":"764ae8c7b126ee8dede6cca70a56a221adfff70ebac9441e1cdf6170d0901792"},"schema_version":"1.0"},"canonical_sha256":"1ae43fbf0aa8e9ad6e458140138942b1852a0752c0820f1678ce467d0e8e39e8","source":{"kind":"arxiv","id":"2305.03785","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03785","created_at":"2026-07-05T07:10:24Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03785v2","created_at":"2026-07-05T07:10:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03785","created_at":"2026-07-05T07:10:24Z"},{"alias_kind":"pith_short_12","alias_value":"DLSD7PYKVDU2","created_at":"2026-07-05T07:10:24Z"},{"alias_kind":"pith_short_16","alias_value":"DLSD7PYKVDU223SF","created_at":"2026-07-05T07:10:24Z"},{"alias_kind":"pith_short_8","alias_value":"DLSD7PYK","created_at":"2026-07-05T07:10:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DLSD7PYKVDU223SFQFABHCKCWG","target":"record","payload":{"canonical_record":{"source":{"id":"2305.03785","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-05-05T18:37:15Z","cross_cats_sorted":[],"title_canon_sha256":"d8067d283dcaa6ccda52120d7776817877d06acbe311beb87d19ffa52414064b","abstract_canon_sha256":"764ae8c7b126ee8dede6cca70a56a221adfff70ebac9441e1cdf6170d0901792"},"schema_version":"1.0"},"canonical_sha256":"1ae43fbf0aa8e9ad6e458140138942b1852a0752c0820f1678ce467d0e8e39e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:24.352803Z","signature_b64":"VhnxJ8oXHs/F878BPVJxjPOcP4u3BR7hOtTmO/0S+JoSJ+WaHaNkgbzKiq1hOr++8JIo41tS92NJnncefBk9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ae43fbf0aa8e9ad6e458140138942b1852a0752c0820f1678ce467d0e8e39e8","last_reissued_at":"2026-07-05T07:10:24.352252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:24.352252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.03785","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:10:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bbg+LuGDwQlcUaz2JiM0ImHTSppIaweykW206GNMvcuZsUf/8VvWaN2iPHYFU7zr4Vpz76+rFSsd4FdimtMFDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T20:56:50.522188Z"},"content_sha256":"4ecb0cc4b76d4e0e0841552234d808dcf78dfde7b18bfde609d5fad2eba4ebe6","schema_version":"1.0","event_id":"sha256:4ecb0cc4b76d4e0e0841552234d808dcf78dfde7b18bfde609d5fad2eba4ebe6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DLSD7PYKVDU223SFQFABHCKCWG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zelda: Video Analytics using Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Caleb Winston, Christos Kozyrakis, Francisco Romero, Johann Hauswald, Matei Zaharia","submitted_at":"2023-05-05T18:37:15Z","abstract_excerpt":"Advances in ML have motivated the design of video analytics systems that allow for structured queries over video datasets. However, existing systems limit query expressivity, require users to specify an ML model per predicate, rely on complex optimizations that trade off accuracy for performance, and return large amounts of redundant and low-quality results. This paper focuses on the recently developed Vision-Language Models (VLMs) that allow users to query images using natural language like \"cars during daytime at traffic intersections.\" Through an in-depth analysis, we show VLMs address thre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03785","kind":"arxiv","version":2},"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/2305.03785/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":"2026-07-05T07:10:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RUMVjODXeNtxUFqRsQDNv45OCx7z4957ct5W7oMOM4ZZsjWZaZKt9efaLnNlFsHncm0TYmMsbrmGimcYICy2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T20:56:50.522567Z"},"content_sha256":"bdcf26468372dd4defef305cc6de77c735234b9c1f78f0cbd01fd68132b33857","schema_version":"1.0","event_id":"sha256:bdcf26468372dd4defef305cc6de77c735234b9c1f78f0cbd01fd68132b33857"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DLSD7PYKVDU223SFQFABHCKCWG/bundle.json","state_url":"https://pith.science/pith/DLSD7PYKVDU223SFQFABHCKCWG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DLSD7PYKVDU223SFQFABHCKCWG/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":"2026-07-11T20:56:50Z","links":{"resolver":"https://pith.science/pith/DLSD7PYKVDU223SFQFABHCKCWG","bundle":"https://pith.science/pith/DLSD7PYKVDU223SFQFABHCKCWG/bundle.json","state":"https://pith.science/pith/DLSD7PYKVDU223SFQFABHCKCWG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DLSD7PYKVDU223SFQFABHCKCWG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DLSD7PYKVDU223SFQFABHCKCWG","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":"764ae8c7b126ee8dede6cca70a56a221adfff70ebac9441e1cdf6170d0901792","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-05-05T18:37:15Z","title_canon_sha256":"d8067d283dcaa6ccda52120d7776817877d06acbe311beb87d19ffa52414064b"},"schema_version":"1.0","source":{"id":"2305.03785","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03785","created_at":"2026-07-05T07:10:24Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03785v2","created_at":"2026-07-05T07:10:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03785","created_at":"2026-07-05T07:10:24Z"},{"alias_kind":"pith_short_12","alias_value":"DLSD7PYKVDU2","created_at":"2026-07-05T07:10:24Z"},{"alias_kind":"pith_short_16","alias_value":"DLSD7PYKVDU223SF","created_at":"2026-07-05T07:10:24Z"},{"alias_kind":"pith_short_8","alias_value":"DLSD7PYK","created_at":"2026-07-05T07:10:24Z"}],"graph_snapshots":[{"event_id":"sha256:bdcf26468372dd4defef305cc6de77c735234b9c1f78f0cbd01fd68132b33857","target":"graph","created_at":"2026-07-05T07:10:24Z","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/2305.03785/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advances in ML have motivated the design of video analytics systems that allow for structured queries over video datasets. However, existing systems limit query expressivity, require users to specify an ML model per predicate, rely on complex optimizations that trade off accuracy for performance, and return large amounts of redundant and low-quality results. This paper focuses on the recently developed Vision-Language Models (VLMs) that allow users to query images using natural language like \"cars during daytime at traffic intersections.\" Through an in-depth analysis, we show VLMs address thre","authors_text":"Caleb Winston, Christos Kozyrakis, Francisco Romero, Johann Hauswald, Matei Zaharia","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-05-05T18:37:15Z","title":"Zelda: Video Analytics using Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03785","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":"sha256:4ecb0cc4b76d4e0e0841552234d808dcf78dfde7b18bfde609d5fad2eba4ebe6","target":"record","created_at":"2026-07-05T07:10:24Z","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":"764ae8c7b126ee8dede6cca70a56a221adfff70ebac9441e1cdf6170d0901792","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-05-05T18:37:15Z","title_canon_sha256":"d8067d283dcaa6ccda52120d7776817877d06acbe311beb87d19ffa52414064b"},"schema_version":"1.0","source":{"id":"2305.03785","kind":"arxiv","version":2}},"canonical_sha256":"1ae43fbf0aa8e9ad6e458140138942b1852a0752c0820f1678ce467d0e8e39e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ae43fbf0aa8e9ad6e458140138942b1852a0752c0820f1678ce467d0e8e39e8","first_computed_at":"2026-07-05T07:10:24.352252Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:24.352252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VhnxJ8oXHs/F878BPVJxjPOcP4u3BR7hOtTmO/0S+JoSJ+WaHaNkgbzKiq1hOr++8JIo41tS92NJnncefBk9CA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:24.352803Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.03785","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ecb0cc4b76d4e0e0841552234d808dcf78dfde7b18bfde609d5fad2eba4ebe6","sha256:bdcf26468372dd4defef305cc6de77c735234b9c1f78f0cbd01fd68132b33857"],"state_sha256":"849fbe09da117e3f2d3a49cc4b9e2b5dfac6929c6eb9fb4c765efb28fc3cec31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6QVbJ4nzILk4RFFT6lnXyqMqN7P4SpKc4cmeMGHreZFboZvxaleOjEeNOSbU9CCaohxLNvGzqVHNN/y/qg3cDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T20:56:50.524693Z","bundle_sha256":"5fa01c405972183ff282ae9d36af8a05c576f55b1086455d34f41d14f36979bd"}}