{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3IKWCWD3PDTWMCNWSDS7M4C7HR","short_pith_number":"pith:3IKWCWD3","schema_version":"1.0","canonical_sha256":"da1561587b78e76609b690e5f6705f3c4858d71078b7ba0ccc3335c6e5b9a077","source":{"kind":"arxiv","id":"2103.08784","version":2},"attestation_state":"computed","paper":{"title":"LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Jingjing Liu, Linjie Li, Shuohang Wang, Siqi Sun, Yen-Chun Chen, Yuwei Fang","submitted_at":"2021-03-16T00:35:28Z","abstract_excerpt":"Multimodal pre-training has propelled great advancement in vision-and-language research. These large-scale pre-trained models, although successful, fatefully suffer from slow inference speed due to enormous computation cost mainly from cross-modal attention in Transformer architecture. When applied to real-life applications, such latency and computation demand severely deter the practical use of pre-trained models. In this paper, we study Image-text retrieval (ITR), the most mature scenario of V+L application, which has been widely studied even prior to the emergence of recent pre-trained mode"},"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":"2103.08784","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-16T00:35:28Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1325a5414837da20e6940ff7fbb6dd894df95b111619c7e50d5b1da029ac4400","abstract_canon_sha256":"44392102f5e1e057cdb508757799bd36257656bb33971d890a4f52f8efb8333a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:04.802193Z","signature_b64":"8y+cJtCdahwwFvrOQbL/MrHcA0hoWCMaRmFEWMeFVPFH2HVIVhXI9kqYAvW8US3UwNRKNwl7Vr2t3XW52vQuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da1561587b78e76609b690e5f6705f3c4858d71078b7ba0ccc3335c6e5b9a077","last_reissued_at":"2026-07-05T02:31:04.801713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:04.801713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Jingjing Liu, Linjie Li, Shuohang Wang, Siqi Sun, Yen-Chun Chen, Yuwei Fang","submitted_at":"2021-03-16T00:35:28Z","abstract_excerpt":"Multimodal pre-training has propelled great advancement in vision-and-language research. These large-scale pre-trained models, although successful, fatefully suffer from slow inference speed due to enormous computation cost mainly from cross-modal attention in Transformer architecture. When applied to real-life applications, such latency and computation demand severely deter the practical use of pre-trained models. In this paper, we study Image-text retrieval (ITR), the most mature scenario of V+L application, which has been widely studied even prior to the emergence of recent pre-trained mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.08784","kind":"arxiv","version":2},"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/2103.08784/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":"2103.08784","created_at":"2026-07-05T02:31:04.801771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.08784v2","created_at":"2026-07-05T02:31:04.801771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.08784","created_at":"2026-07-05T02:31:04.801771+00:00"},{"alias_kind":"pith_short_12","alias_value":"3IKWCWD3PDTW","created_at":"2026-07-05T02:31:04.801771+00:00"},{"alias_kind":"pith_short_16","alias_value":"3IKWCWD3PDTWMCNW","created_at":"2026-07-05T02:31:04.801771+00:00"},{"alias_kind":"pith_short_8","alias_value":"3IKWCWD3","created_at":"2026-07-05T02:31:04.801771+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/3IKWCWD3PDTWMCNWSDS7M4C7HR","json":"https://pith.science/pith/3IKWCWD3PDTWMCNWSDS7M4C7HR.json","graph_json":"https://pith.science/api/pith-number/3IKWCWD3PDTWMCNWSDS7M4C7HR/graph.json","events_json":"https://pith.science/api/pith-number/3IKWCWD3PDTWMCNWSDS7M4C7HR/events.json","paper":"https://pith.science/paper/3IKWCWD3"},"agent_actions":{"view_html":"https://pith.science/pith/3IKWCWD3PDTWMCNWSDS7M4C7HR","download_json":"https://pith.science/pith/3IKWCWD3PDTWMCNWSDS7M4C7HR.json","view_paper":"https://pith.science/paper/3IKWCWD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.08784&json=true","fetch_graph":"https://pith.science/api/pith-number/3IKWCWD3PDTWMCNWSDS7M4C7HR/graph.json","fetch_events":"https://pith.science/api/pith-number/3IKWCWD3PDTWMCNWSDS7M4C7HR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3IKWCWD3PDTWMCNWSDS7M4C7HR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3IKWCWD3PDTWMCNWSDS7M4C7HR/action/storage_attestation","attest_author":"https://pith.science/pith/3IKWCWD3PDTWMCNWSDS7M4C7HR/action/author_attestation","sign_citation":"https://pith.science/pith/3IKWCWD3PDTWMCNWSDS7M4C7HR/action/citation_signature","submit_replication":"https://pith.science/pith/3IKWCWD3PDTWMCNWSDS7M4C7HR/action/replication_record"}},"created_at":"2026-07-05T02:31:04.801771+00:00","updated_at":"2026-07-05T02:31:04.801771+00:00"}