{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IMSAR3R63P6E7PAAHJ3MZWHHJD","short_pith_number":"pith:IMSAR3R6","schema_version":"1.0","canonical_sha256":"432408ee3edbfc4fbc003a76ccd8e748d8b03ad122c610c8056f8580eca206f0","source":{"kind":"arxiv","id":"2212.14322","version":1},"attestation_state":"computed","paper":{"title":"BagFormer: Better Cross-Modal Retrieval via bag-wise interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.IR","authors_text":"Fengzong Lian, Haowen Hou, Xiaopeng Yan, Yigeng Zhang, Zhanhui Kang","submitted_at":"2022-12-29T14:32:41Z","abstract_excerpt":"In the field of cross-modal retrieval, single encoder models tend to perform better than dual encoder models, but they suffer from high latency and low throughput. In this paper, we present a dual encoder model called BagFormer that utilizes a cross modal interaction mechanism to improve recall performance without sacrificing latency and throughput. BagFormer achieves this through the use of bag-wise interactions, which allow for the transformation of text to a more appropriate granularity and the incorporation of entity knowledge into the model. Our experiments demonstrate that BagFormer is a"},"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":"2212.14322","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-12-29T14:32:41Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"9ab8ce40f90d99ceaeadde9515759c8a71fede79c6ac6eed399181022079534e","abstract_canon_sha256":"9b7348ac27dbf241dd9754888d634852c84750ae7ab8f7a1cc1c191d08117efe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:29:08.813028Z","signature_b64":"OAqb0frujZwAya3QvaefhPfnDEjIkmw2VJ8fZMKqwMy7d+3ImGY21bwiZqkODD7cin2BDTjMNN7q6MGIIW7gBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"432408ee3edbfc4fbc003a76ccd8e748d8b03ad122c610c8056f8580eca206f0","last_reissued_at":"2026-07-05T05:29:08.812582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:29:08.812582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BagFormer: Better Cross-Modal Retrieval via bag-wise interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.IR","authors_text":"Fengzong Lian, Haowen Hou, Xiaopeng Yan, Yigeng Zhang, Zhanhui Kang","submitted_at":"2022-12-29T14:32:41Z","abstract_excerpt":"In the field of cross-modal retrieval, single encoder models tend to perform better than dual encoder models, but they suffer from high latency and low throughput. In this paper, we present a dual encoder model called BagFormer that utilizes a cross modal interaction mechanism to improve recall performance without sacrificing latency and throughput. BagFormer achieves this through the use of bag-wise interactions, which allow for the transformation of text to a more appropriate granularity and the incorporation of entity knowledge into the model. Our experiments demonstrate that BagFormer is a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.14322","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/2212.14322/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":"2212.14322","created_at":"2026-07-05T05:29:08.812639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.14322v1","created_at":"2026-07-05T05:29:08.812639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.14322","created_at":"2026-07-05T05:29:08.812639+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMSAR3R63P6E","created_at":"2026-07-05T05:29:08.812639+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMSAR3R63P6E7PAA","created_at":"2026-07-05T05:29:08.812639+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMSAR3R6","created_at":"2026-07-05T05:29:08.812639+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/IMSAR3R63P6E7PAAHJ3MZWHHJD","json":"https://pith.science/pith/IMSAR3R63P6E7PAAHJ3MZWHHJD.json","graph_json":"https://pith.science/api/pith-number/IMSAR3R63P6E7PAAHJ3MZWHHJD/graph.json","events_json":"https://pith.science/api/pith-number/IMSAR3R63P6E7PAAHJ3MZWHHJD/events.json","paper":"https://pith.science/paper/IMSAR3R6"},"agent_actions":{"view_html":"https://pith.science/pith/IMSAR3R63P6E7PAAHJ3MZWHHJD","download_json":"https://pith.science/pith/IMSAR3R63P6E7PAAHJ3MZWHHJD.json","view_paper":"https://pith.science/paper/IMSAR3R6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.14322&json=true","fetch_graph":"https://pith.science/api/pith-number/IMSAR3R63P6E7PAAHJ3MZWHHJD/graph.json","fetch_events":"https://pith.science/api/pith-number/IMSAR3R63P6E7PAAHJ3MZWHHJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMSAR3R63P6E7PAAHJ3MZWHHJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMSAR3R63P6E7PAAHJ3MZWHHJD/action/storage_attestation","attest_author":"https://pith.science/pith/IMSAR3R63P6E7PAAHJ3MZWHHJD/action/author_attestation","sign_citation":"https://pith.science/pith/IMSAR3R63P6E7PAAHJ3MZWHHJD/action/citation_signature","submit_replication":"https://pith.science/pith/IMSAR3R63P6E7PAAHJ3MZWHHJD/action/replication_record"}},"created_at":"2026-07-05T05:29:08.812639+00:00","updated_at":"2026-07-05T05:29:08.812639+00:00"}