{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SSK7Z4B7SM25GAQQM7E3SUBXEC","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":"2048a9d97adddf40d3b143c173996e9e63bb77bbdfc7384ee43db1997a41fa7d","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-01T16:29:17Z","title_canon_sha256":"34abc4a8470b0f0f9d3696947e3543e7380524f076ef79764fd7876d67f82b2c"},"schema_version":"1.0","source":{"id":"2101.00265","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.00265","created_at":"2026-07-05T02:42:03Z"},{"alias_kind":"arxiv_version","alias_value":"2101.00265v2","created_at":"2026-07-05T02:42:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00265","created_at":"2026-07-05T02:42:03Z"},{"alias_kind":"pith_short_12","alias_value":"SSK7Z4B7SM25","created_at":"2026-07-05T02:42:03Z"},{"alias_kind":"pith_short_16","alias_value":"SSK7Z4B7SM25GAQQ","created_at":"2026-07-05T02:42:03Z"},{"alias_kind":"pith_short_8","alias_value":"SSK7Z4B7","created_at":"2026-07-05T02:42:03Z"}],"graph_snapshots":[{"event_id":"sha256:bfba2bd4438517ae57488500defc42c82e2bce5d04c10b36560fcff33a6970f7","target":"graph","created_at":"2026-07-05T02:42:03Z","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/2101.00265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-image retrieval is an essential task in cross-modal information retrieval, i.e., retrieving relevant images from a large and unlabelled dataset given textual queries. In this paper, we propose VisualSparta, a novel (Visual-text Sparse Transformer Matching) model that shows significant improvement in terms of both accuracy and efficiency. VisualSparta is capable of outperforming previous state-of-the-art scalable methods in MSCOCO and Flickr30K. We also show that it achieves substantial retrieving speed advantages, i.e., for a 1 million image index, VisualSparta using CPU gets ~391X spe","authors_text":"Kyusong Lee, Tiancheng Zhao, Xiaopeng Lu","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-01T16:29:17Z","title":"VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00265","kind":"arxiv","version":2},"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":"sha256:36d22d9e864358d67e7b6b46e7cd466992788832a8a1910804d0155d965689a3","target":"record","created_at":"2026-07-05T02:42:03Z","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":"2048a9d97adddf40d3b143c173996e9e63bb77bbdfc7384ee43db1997a41fa7d","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-01T16:29:17Z","title_canon_sha256":"34abc4a8470b0f0f9d3696947e3543e7380524f076ef79764fd7876d67f82b2c"},"schema_version":"1.0","source":{"id":"2101.00265","kind":"arxiv","version":2}},"canonical_sha256":"9495fcf03f9335d3021067c9b9503720b20f1bf439914e659f67bfc583e64802","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9495fcf03f9335d3021067c9b9503720b20f1bf439914e659f67bfc583e64802","first_computed_at":"2026-07-05T02:42:03.236310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:42:03.236310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VcyANAPZFXTB/ymkMIH8atjTpw1H/QLD6zK5Qzt6KknDsIEWlwOOplqZtPbCRoIUK4BFXophZXlxcyPedvnmAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:42:03.236780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.00265","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36d22d9e864358d67e7b6b46e7cd466992788832a8a1910804d0155d965689a3","sha256:bfba2bd4438517ae57488500defc42c82e2bce5d04c10b36560fcff33a6970f7"],"state_sha256":"53beea87af187c3fd83a88acff7157b47f467a01bc7cb61ba07435617c47cb8b"}