{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FDALLEMVRPTKOXRRPTAZPJBRZ3","short_pith_number":"pith:FDALLEMV","schema_version":"1.0","canonical_sha256":"28c0b591958be6a75e317cc197a431cec03cd0e79ea19e23b323512f85064c7c","source":{"kind":"arxiv","id":"2403.03994","version":1},"attestation_state":"computed","paper":{"title":"Video Relationship Detection Using Mixture of Experts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ala Shaabana, Paul Fieguth, Zahra Gharaee","submitted_at":"2024-03-06T19:08:34Z","abstract_excerpt":"Machine comprehension of visual information from images and videos by neural networks faces two primary challenges. Firstly, there exists a computational and inference gap in connecting vision and language, making it difficult to accurately determine which object a given agent acts on and represent it through language. Secondly, classifiers trained by a single, monolithic neural network often lack stability and generalization. To overcome these challenges, we introduce MoE-VRD, a novel approach to visual relationship detection utilizing a mixture of experts. MoE-VRD identifies language triplet"},"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":"2403.03994","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-06T19:08:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d7f8c2c38f6050852315030262439a0a9259f9321fd99820f682dd6176cf867d","abstract_canon_sha256":"5894b002c0c3d28faffd0761013902144e85e8a62a5c2995d45df916206ecb19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:16.819068Z","signature_b64":"mV3Gz4KtsWON1Bsqe4LfB4E28gVC+a2aO5MqAoQd9CnP4wMfZ2jIDJMmeuGZKrJOM12sdlG/6qxDeWWBJJo4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28c0b591958be6a75e317cc197a431cec03cd0e79ea19e23b323512f85064c7c","last_reissued_at":"2026-07-05T07:53:16.818582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:16.818582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Relationship Detection Using Mixture of Experts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ala Shaabana, Paul Fieguth, Zahra Gharaee","submitted_at":"2024-03-06T19:08:34Z","abstract_excerpt":"Machine comprehension of visual information from images and videos by neural networks faces two primary challenges. Firstly, there exists a computational and inference gap in connecting vision and language, making it difficult to accurately determine which object a given agent acts on and represent it through language. Secondly, classifiers trained by a single, monolithic neural network often lack stability and generalization. To overcome these challenges, we introduce MoE-VRD, a novel approach to visual relationship detection utilizing a mixture of experts. MoE-VRD identifies language triplet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03994","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/2403.03994/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":"2403.03994","created_at":"2026-07-05T07:53:16.818643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03994v1","created_at":"2026-07-05T07:53:16.818643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03994","created_at":"2026-07-05T07:53:16.818643+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDALLEMVRPTK","created_at":"2026-07-05T07:53:16.818643+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDALLEMVRPTKOXRR","created_at":"2026-07-05T07:53:16.818643+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDALLEMV","created_at":"2026-07-05T07:53:16.818643+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/FDALLEMVRPTKOXRRPTAZPJBRZ3","json":"https://pith.science/pith/FDALLEMVRPTKOXRRPTAZPJBRZ3.json","graph_json":"https://pith.science/api/pith-number/FDALLEMVRPTKOXRRPTAZPJBRZ3/graph.json","events_json":"https://pith.science/api/pith-number/FDALLEMVRPTKOXRRPTAZPJBRZ3/events.json","paper":"https://pith.science/paper/FDALLEMV"},"agent_actions":{"view_html":"https://pith.science/pith/FDALLEMVRPTKOXRRPTAZPJBRZ3","download_json":"https://pith.science/pith/FDALLEMVRPTKOXRRPTAZPJBRZ3.json","view_paper":"https://pith.science/paper/FDALLEMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03994&json=true","fetch_graph":"https://pith.science/api/pith-number/FDALLEMVRPTKOXRRPTAZPJBRZ3/graph.json","fetch_events":"https://pith.science/api/pith-number/FDALLEMVRPTKOXRRPTAZPJBRZ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDALLEMVRPTKOXRRPTAZPJBRZ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDALLEMVRPTKOXRRPTAZPJBRZ3/action/storage_attestation","attest_author":"https://pith.science/pith/FDALLEMVRPTKOXRRPTAZPJBRZ3/action/author_attestation","sign_citation":"https://pith.science/pith/FDALLEMVRPTKOXRRPTAZPJBRZ3/action/citation_signature","submit_replication":"https://pith.science/pith/FDALLEMVRPTKOXRRPTAZPJBRZ3/action/replication_record"}},"created_at":"2026-07-05T07:53:16.818643+00:00","updated_at":"2026-07-05T07:53:16.818643+00:00"}