{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IMSAR3R63P6E7PAAHJ3MZWHHJD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9b7348ac27dbf241dd9754888d634852c84750ae7ab8f7a1cc1c191d08117efe","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-12-29T14:32:41Z","title_canon_sha256":"9ab8ce40f90d99ceaeadde9515759c8a71fede79c6ac6eed399181022079534e"},"schema_version":"1.0","source":{"id":"2212.14322","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.14322","created_at":"2026-07-05T05:29:08Z"},{"alias_kind":"arxiv_version","alias_value":"2212.14322v1","created_at":"2026-07-05T05:29:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.14322","created_at":"2026-07-05T05:29:08Z"},{"alias_kind":"pith_short_12","alias_value":"IMSAR3R63P6E","created_at":"2026-07-05T05:29:08Z"},{"alias_kind":"pith_short_16","alias_value":"IMSAR3R63P6E7PAA","created_at":"2026-07-05T05:29:08Z"},{"alias_kind":"pith_short_8","alias_value":"IMSAR3R6","created_at":"2026-07-05T05:29:08Z"}],"graph_snapshots":[{"event_id":"sha256:bcf011b532e80e98ca122bc4366f16fdaa666c8bad643c0c487f4fbd034cbb56","target":"graph","created_at":"2026-07-05T05:29:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2212.14322/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fengzong Lian, Haowen Hou, Xiaopeng Yan, Yigeng Zhang, Zhanhui Kang","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-12-29T14:32:41Z","title":"BagFormer: Better Cross-Modal Retrieval via bag-wise interaction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.14322","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:598120d1f1acf4e2ee502d1c85285c967ea6a2007b90a11cf5faa39a23b4f91b","target":"record","created_at":"2026-07-05T05:29:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9b7348ac27dbf241dd9754888d634852c84750ae7ab8f7a1cc1c191d08117efe","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-12-29T14:32:41Z","title_canon_sha256":"9ab8ce40f90d99ceaeadde9515759c8a71fede79c6ac6eed399181022079534e"},"schema_version":"1.0","source":{"id":"2212.14322","kind":"arxiv","version":1}},"canonical_sha256":"432408ee3edbfc4fbc003a76ccd8e748d8b03ad122c610c8056f8580eca206f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"432408ee3edbfc4fbc003a76ccd8e748d8b03ad122c610c8056f8580eca206f0","first_computed_at":"2026-07-05T05:29:08.812582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:29:08.812582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OAqb0frujZwAya3QvaefhPfnDEjIkmw2VJ8fZMKqwMy7d+3ImGY21bwiZqkODD7cin2BDTjMNN7q6MGIIW7gBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:29:08.813028Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.14322","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:598120d1f1acf4e2ee502d1c85285c967ea6a2007b90a11cf5faa39a23b4f91b","sha256:bcf011b532e80e98ca122bc4366f16fdaa666c8bad643c0c487f4fbd034cbb56"],"state_sha256":"93902d137d3b89e3cc6863e034f01bea142278f2e714696251db29e396a65392"}