{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RHPSIOTHEIA2ZMSVLRQVRWUU53","short_pith_number":"pith:RHPSIOTH","schema_version":"1.0","canonical_sha256":"89df243a672201acb2555c6158da94eec0ff5c6da0f9ccc2e684c27ce52acd49","source":{"kind":"arxiv","id":"1907.13487","version":2},"attestation_state":"computed","paper":{"title":"Use What You Have: Video Retrieval Using Representations From Collaborative Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Arsha Nagrani, Samuel Albanie, Yang Liu","submitted_at":"2019-07-31T13:19:37Z","abstract_excerpt":"The rapid growth of video on the internet has made searching for video content using natural language queries a significant challenge. Human-generated queries for video datasets `in the wild' vary a lot in terms of degree of specificity, with some queries describing specific details such as the names of famous identities, content from speech, or text available on the screen. Our goal is to condense the multi-modal, extremely high dimensional information from videos into a single, compact video representation for the task of video retrieval using free-form text queries, where the degree of spec"},"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":"1907.13487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-31T13:19:37Z","cross_cats_sorted":[],"title_canon_sha256":"1b962fe04d8c0d1a45f1a94ad27b4de9f76aebcddd8d01276fed9625fefcb53f","abstract_canon_sha256":"e33f1eb4a2dcdb355e19a5dff1e733b3d8f667f13d00b35d3416b05a8218f7e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:43.788988Z","signature_b64":"Hek/XHk6UIwyz5iic+PX5I5oIvSi15Id4OKBbdNwatJ50tmWqZ6FvGUpbvES2lIG99mpOs8Y3mY8g0Ahty/LAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89df243a672201acb2555c6158da94eec0ff5c6da0f9ccc2e684c27ce52acd49","last_reissued_at":"2026-07-05T00:40:43.788494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:43.788494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Use What You Have: Video Retrieval Using Representations From Collaborative Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Arsha Nagrani, Samuel Albanie, Yang Liu","submitted_at":"2019-07-31T13:19:37Z","abstract_excerpt":"The rapid growth of video on the internet has made searching for video content using natural language queries a significant challenge. Human-generated queries for video datasets `in the wild' vary a lot in terms of degree of specificity, with some queries describing specific details such as the names of famous identities, content from speech, or text available on the screen. Our goal is to condense the multi-modal, extremely high dimensional information from videos into a single, compact video representation for the task of video retrieval using free-form text queries, where the degree of spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.13487","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/1907.13487/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":"1907.13487","created_at":"2026-07-05T00:40:43.788551+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.13487v2","created_at":"2026-07-05T00:40:43.788551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.13487","created_at":"2026-07-05T00:40:43.788551+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHPSIOTHEIA2","created_at":"2026-07-05T00:40:43.788551+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHPSIOTHEIA2ZMSV","created_at":"2026-07-05T00:40:43.788551+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHPSIOTH","created_at":"2026-07-05T00:40:43.788551+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19062","citing_title":"DREAM: Extending Vision-Language Models with Dual-Objective Encoding for Cross-Modal Retrieval","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27894","citing_title":"Towards Unified Vision-Language Models with Incomplete Multi-Modal Inputs","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17959","citing_title":"Text-Video Retrieval With Global-Local Contrastive Consistency Learning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2508.06964","citing_title":"Adversarial Video Promotion Against Text-to-Video Retrieval","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04590","citing_title":"VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16671","citing_title":"Demystifying CLIP Data","ref_index":91,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RHPSIOTHEIA2ZMSVLRQVRWUU53","json":"https://pith.science/pith/RHPSIOTHEIA2ZMSVLRQVRWUU53.json","graph_json":"https://pith.science/api/pith-number/RHPSIOTHEIA2ZMSVLRQVRWUU53/graph.json","events_json":"https://pith.science/api/pith-number/RHPSIOTHEIA2ZMSVLRQVRWUU53/events.json","paper":"https://pith.science/paper/RHPSIOTH"},"agent_actions":{"view_html":"https://pith.science/pith/RHPSIOTHEIA2ZMSVLRQVRWUU53","download_json":"https://pith.science/pith/RHPSIOTHEIA2ZMSVLRQVRWUU53.json","view_paper":"https://pith.science/paper/RHPSIOTH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.13487&json=true","fetch_graph":"https://pith.science/api/pith-number/RHPSIOTHEIA2ZMSVLRQVRWUU53/graph.json","fetch_events":"https://pith.science/api/pith-number/RHPSIOTHEIA2ZMSVLRQVRWUU53/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHPSIOTHEIA2ZMSVLRQVRWUU53/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHPSIOTHEIA2ZMSVLRQVRWUU53/action/storage_attestation","attest_author":"https://pith.science/pith/RHPSIOTHEIA2ZMSVLRQVRWUU53/action/author_attestation","sign_citation":"https://pith.science/pith/RHPSIOTHEIA2ZMSVLRQVRWUU53/action/citation_signature","submit_replication":"https://pith.science/pith/RHPSIOTHEIA2ZMSVLRQVRWUU53/action/replication_record"}},"created_at":"2026-07-05T00:40:43.788551+00:00","updated_at":"2026-07-05T00:40:43.788551+00:00"}