{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4PQFCDQCKRHNV3SHKXEHH5HH4M","short_pith_number":"pith:4PQFCDQC","schema_version":"1.0","canonical_sha256":"e3e0510e02544edaee4755c873f4e7e3283bb8c9de7706dec60678f84719ffb6","source":{"kind":"arxiv","id":"2602.12819","version":2},"attestation_state":"computed","paper":{"title":"WISE: A Multimodal Search Engine for Visual Scenes, Audio, Objects, Faces, Speech, and Metadata","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.IR","authors_text":"Abhishek Dutta, Andrew Zisserman, David M. S. Pinto, Horace Lee, Prasanna Sridhar","submitted_at":"2026-02-13T11:03:06Z","abstract_excerpt":"In this paper, we present WISE, an open-source audiovisual search engine which integrates a range of multimodal retrieval capabilities into a single, practical tool accessible to users without machine learning expertise. WISE supports natural-language and reverse-image queries at both the scene level (e.g. empty street) and object level (e.g. horse) across images and videos; face-based search for specific individuals; audio retrieval of acoustic events using text (e.g. wood creak) or an audio file; search over automatically transcribed speech; and filtering by user-provided metadata. Rich insi"},"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":"2602.12819","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-02-13T11:03:06Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7ead55fc927bf9cd228d708dc8c76723a3e9c41136240f17124f67a45f987f56","abstract_canon_sha256":"9d9cf380b5c78a5d7fd59653f765b700af7ed4d6817a0f7578d7753397c222d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:38.757378Z","signature_b64":"bt2WpFbXyDLcFFQINC5wKiyisCcZU0UJZHjWQiEboayNVoTYUPor6waSbLRU7jsgKR3xWm8Y5uTZAatwcjkvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3e0510e02544edaee4755c873f4e7e3283bb8c9de7706dec60678f84719ffb6","last_reissued_at":"2026-06-02T03:04:38.756829Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:38.756829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WISE: A Multimodal Search Engine for Visual Scenes, Audio, Objects, Faces, Speech, and Metadata","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.IR","authors_text":"Abhishek Dutta, Andrew Zisserman, David M. S. Pinto, Horace Lee, Prasanna Sridhar","submitted_at":"2026-02-13T11:03:06Z","abstract_excerpt":"In this paper, we present WISE, an open-source audiovisual search engine which integrates a range of multimodal retrieval capabilities into a single, practical tool accessible to users without machine learning expertise. WISE supports natural-language and reverse-image queries at both the scene level (e.g. empty street) and object level (e.g. horse) across images and videos; face-based search for specific individuals; audio retrieval of acoustic events using text (e.g. wood creak) or an audio file; search over automatically transcribed speech; and filtering by user-provided metadata. Rich insi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.12819","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/2602.12819/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":"2602.12819","created_at":"2026-06-02T03:04:38.756893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.12819v2","created_at":"2026-06-02T03:04:38.756893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12819","created_at":"2026-06-02T03:04:38.756893+00:00"},{"alias_kind":"pith_short_12","alias_value":"4PQFCDQCKRHN","created_at":"2026-06-02T03:04:38.756893+00:00"},{"alias_kind":"pith_short_16","alias_value":"4PQFCDQCKRHNV3SH","created_at":"2026-06-02T03:04:38.756893+00:00"},{"alias_kind":"pith_short_8","alias_value":"4PQFCDQC","created_at":"2026-06-02T03:04:38.756893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4PQFCDQCKRHNV3SHKXEHH5HH4M","json":"https://pith.science/pith/4PQFCDQCKRHNV3SHKXEHH5HH4M.json","graph_json":"https://pith.science/api/pith-number/4PQFCDQCKRHNV3SHKXEHH5HH4M/graph.json","events_json":"https://pith.science/api/pith-number/4PQFCDQCKRHNV3SHKXEHH5HH4M/events.json","paper":"https://pith.science/paper/4PQFCDQC"},"agent_actions":{"view_html":"https://pith.science/pith/4PQFCDQCKRHNV3SHKXEHH5HH4M","download_json":"https://pith.science/pith/4PQFCDQCKRHNV3SHKXEHH5HH4M.json","view_paper":"https://pith.science/paper/4PQFCDQC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.12819&json=true","fetch_graph":"https://pith.science/api/pith-number/4PQFCDQCKRHNV3SHKXEHH5HH4M/graph.json","fetch_events":"https://pith.science/api/pith-number/4PQFCDQCKRHNV3SHKXEHH5HH4M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4PQFCDQCKRHNV3SHKXEHH5HH4M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4PQFCDQCKRHNV3SHKXEHH5HH4M/action/storage_attestation","attest_author":"https://pith.science/pith/4PQFCDQCKRHNV3SHKXEHH5HH4M/action/author_attestation","sign_citation":"https://pith.science/pith/4PQFCDQCKRHNV3SHKXEHH5HH4M/action/citation_signature","submit_replication":"https://pith.science/pith/4PQFCDQCKRHNV3SHKXEHH5HH4M/action/replication_record"}},"created_at":"2026-06-02T03:04:38.756893+00:00","updated_at":"2026-06-02T03:04:38.756893+00:00"}