{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZO7NAVSPSIOV7LBZDR44UJ2N7Z","short_pith_number":"pith:ZO7NAVSP","schema_version":"1.0","canonical_sha256":"cbbed0564f921d5fac391c79ca274dfe6487a79dd61cf9b7510fe389b9afe83d","source":{"kind":"arxiv","id":"2303.06129","version":1},"attestation_state":"computed","paper":{"title":"Single-branch Network for Multimodal Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arif Mahmood, Karthik Nandakumar, Muhammad Haris Khan, Muhammad Haroon Yousaf, Muhammad Saad Saeed, Muhammad Zaigham Zaheer, Shah Nawaz","submitted_at":"2023-03-10T18:48:40Z","abstract_excerpt":"With the rapid growth of social media platforms, users are sharing billions of multimedia posts containing audio, images, and text. Researchers have focused on building autonomous systems capable of processing such multimedia data to solve challenging multimodal tasks including cross-modal retrieval, matching, and verification. Existing works use separate networks to extract embeddings of each modality to bridge the gap between them. The modular structure of their branched networks is fundamental in creating numerous multimodal applications and has become a defacto standard to handle multiple "},"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":"2303.06129","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-10T18:48:40Z","cross_cats_sorted":[],"title_canon_sha256":"f62b69c7f4ec325ed317188f1d61c7093e0332c2168dfd0e499aa27834f4db20","abstract_canon_sha256":"97ce4d9b971a4b0420b8a2ed6be67a30a2cb9e4286b90ba6a822125b7cbfcc5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:01.125438Z","signature_b64":"oTkBPg7i/RCogrO4llYkRSJriHEEPp8O7jrCKurU9z+IvQX6O6fQSMaoZgvjqzwTr7dvxgLGhieggqCTUGj4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbbed0564f921d5fac391c79ca274dfe6487a79dd61cf9b7510fe389b9afe83d","last_reissued_at":"2026-07-05T05:50:01.124950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:01.124950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Single-branch Network for Multimodal Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arif Mahmood, Karthik Nandakumar, Muhammad Haris Khan, Muhammad Haroon Yousaf, Muhammad Saad Saeed, Muhammad Zaigham Zaheer, Shah Nawaz","submitted_at":"2023-03-10T18:48:40Z","abstract_excerpt":"With the rapid growth of social media platforms, users are sharing billions of multimedia posts containing audio, images, and text. Researchers have focused on building autonomous systems capable of processing such multimedia data to solve challenging multimodal tasks including cross-modal retrieval, matching, and verification. Existing works use separate networks to extract embeddings of each modality to bridge the gap between them. The modular structure of their branched networks is fundamental in creating numerous multimodal applications and has become a defacto standard to handle multiple "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06129","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/2303.06129/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":"2303.06129","created_at":"2026-07-05T05:50:01.125019+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.06129v1","created_at":"2026-07-05T05:50:01.125019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06129","created_at":"2026-07-05T05:50:01.125019+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZO7NAVSPSIOV","created_at":"2026-07-05T05:50:01.125019+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZO7NAVSPSIOV7LBZ","created_at":"2026-07-05T05:50:01.125019+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZO7NAVSP","created_at":"2026-07-05T05:50:01.125019+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/ZO7NAVSPSIOV7LBZDR44UJ2N7Z","json":"https://pith.science/pith/ZO7NAVSPSIOV7LBZDR44UJ2N7Z.json","graph_json":"https://pith.science/api/pith-number/ZO7NAVSPSIOV7LBZDR44UJ2N7Z/graph.json","events_json":"https://pith.science/api/pith-number/ZO7NAVSPSIOV7LBZDR44UJ2N7Z/events.json","paper":"https://pith.science/paper/ZO7NAVSP"},"agent_actions":{"view_html":"https://pith.science/pith/ZO7NAVSPSIOV7LBZDR44UJ2N7Z","download_json":"https://pith.science/pith/ZO7NAVSPSIOV7LBZDR44UJ2N7Z.json","view_paper":"https://pith.science/paper/ZO7NAVSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.06129&json=true","fetch_graph":"https://pith.science/api/pith-number/ZO7NAVSPSIOV7LBZDR44UJ2N7Z/graph.json","fetch_events":"https://pith.science/api/pith-number/ZO7NAVSPSIOV7LBZDR44UJ2N7Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZO7NAVSPSIOV7LBZDR44UJ2N7Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZO7NAVSPSIOV7LBZDR44UJ2N7Z/action/storage_attestation","attest_author":"https://pith.science/pith/ZO7NAVSPSIOV7LBZDR44UJ2N7Z/action/author_attestation","sign_citation":"https://pith.science/pith/ZO7NAVSPSIOV7LBZDR44UJ2N7Z/action/citation_signature","submit_replication":"https://pith.science/pith/ZO7NAVSPSIOV7LBZDR44UJ2N7Z/action/replication_record"}},"created_at":"2026-07-05T05:50:01.125019+00:00","updated_at":"2026-07-05T05:50:01.125019+00:00"}