{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:45UTR2J2E75IUFQKPNT6NK7JA6","short_pith_number":"pith:45UTR2J2","schema_version":"1.0","canonical_sha256":"e76938e93a27fa8a160a7b67e6abe907892cdc07dd23b77e3ac2ae4b7efdef3b","source":{"kind":"arxiv","id":"2302.02908","version":1},"attestation_state":"computed","paper":{"title":"LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Can Xu, Chongyang Tao, Daxin Jiang, Jing Ma, Pu Zhao, Qingwen Lin, Tao Shen, Xiubo Geng, Ziyang Luo","submitted_at":"2023-02-06T16:24:41Z","abstract_excerpt":"Image-text retrieval (ITR) is a task to retrieve the relevant images/texts, given the query from another modality. The conventional dense retrieval paradigm relies on encoding images and texts into dense representations using dual-stream encoders, however, it faces challenges with low retrieval speed in large-scale retrieval scenarios. In this work, we propose the lexicon-weighting paradigm, where sparse representations in vocabulary space are learned for images and texts to take advantage of the bag-of-words models and efficient inverted indexes, resulting in significantly reduced retrieval l"},"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":"2302.02908","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-06T16:24:41Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"ea977cbd2565f0fb75ef5e8f8474f6d01c61e63c9e6bdb178125773d4c9eea9a","abstract_canon_sha256":"07933ee30258b87cc147b8de448a974d3d09e271e1cce5976c5695653b8bd74f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:08.007163Z","signature_b64":"jqzO+/cCYhj+ygVr7sm9mitpED8Ar9nvwQzJ00EKAHq8cAY6XpZd0TZQYqD3alGc7K0xvmEgzG63QdV56Sf6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e76938e93a27fa8a160a7b67e6abe907892cdc07dd23b77e3ac2ae4b7efdef3b","last_reissued_at":"2026-07-05T05:39:08.006776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:08.006776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Can Xu, Chongyang Tao, Daxin Jiang, Jing Ma, Pu Zhao, Qingwen Lin, Tao Shen, Xiubo Geng, Ziyang Luo","submitted_at":"2023-02-06T16:24:41Z","abstract_excerpt":"Image-text retrieval (ITR) is a task to retrieve the relevant images/texts, given the query from another modality. The conventional dense retrieval paradigm relies on encoding images and texts into dense representations using dual-stream encoders, however, it faces challenges with low retrieval speed in large-scale retrieval scenarios. In this work, we propose the lexicon-weighting paradigm, where sparse representations in vocabulary space are learned for images and texts to take advantage of the bag-of-words models and efficient inverted indexes, resulting in significantly reduced retrieval l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02908","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/2302.02908/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":"2302.02908","created_at":"2026-07-05T05:39:08.006834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.02908v1","created_at":"2026-07-05T05:39:08.006834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02908","created_at":"2026-07-05T05:39:08.006834+00:00"},{"alias_kind":"pith_short_12","alias_value":"45UTR2J2E75I","created_at":"2026-07-05T05:39:08.006834+00:00"},{"alias_kind":"pith_short_16","alias_value":"45UTR2J2E75IUFQK","created_at":"2026-07-05T05:39:08.006834+00:00"},{"alias_kind":"pith_short_8","alias_value":"45UTR2J2","created_at":"2026-07-05T05:39:08.006834+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/45UTR2J2E75IUFQKPNT6NK7JA6","json":"https://pith.science/pith/45UTR2J2E75IUFQKPNT6NK7JA6.json","graph_json":"https://pith.science/api/pith-number/45UTR2J2E75IUFQKPNT6NK7JA6/graph.json","events_json":"https://pith.science/api/pith-number/45UTR2J2E75IUFQKPNT6NK7JA6/events.json","paper":"https://pith.science/paper/45UTR2J2"},"agent_actions":{"view_html":"https://pith.science/pith/45UTR2J2E75IUFQKPNT6NK7JA6","download_json":"https://pith.science/pith/45UTR2J2E75IUFQKPNT6NK7JA6.json","view_paper":"https://pith.science/paper/45UTR2J2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.02908&json=true","fetch_graph":"https://pith.science/api/pith-number/45UTR2J2E75IUFQKPNT6NK7JA6/graph.json","fetch_events":"https://pith.science/api/pith-number/45UTR2J2E75IUFQKPNT6NK7JA6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45UTR2J2E75IUFQKPNT6NK7JA6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45UTR2J2E75IUFQKPNT6NK7JA6/action/storage_attestation","attest_author":"https://pith.science/pith/45UTR2J2E75IUFQKPNT6NK7JA6/action/author_attestation","sign_citation":"https://pith.science/pith/45UTR2J2E75IUFQKPNT6NK7JA6/action/citation_signature","submit_replication":"https://pith.science/pith/45UTR2J2E75IUFQKPNT6NK7JA6/action/replication_record"}},"created_at":"2026-07-05T05:39:08.006834+00:00","updated_at":"2026-07-05T05:39:08.006834+00:00"}