{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3IKWCWD3PDTWMCNWSDS7M4C7HR","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":"44392102f5e1e057cdb508757799bd36257656bb33971d890a4f52f8efb8333a","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-16T00:35:28Z","title_canon_sha256":"1325a5414837da20e6940ff7fbb6dd894df95b111619c7e50d5b1da029ac4400"},"schema_version":"1.0","source":{"id":"2103.08784","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.08784","created_at":"2026-07-05T02:31:04Z"},{"alias_kind":"arxiv_version","alias_value":"2103.08784v2","created_at":"2026-07-05T02:31:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.08784","created_at":"2026-07-05T02:31:04Z"},{"alias_kind":"pith_short_12","alias_value":"3IKWCWD3PDTW","created_at":"2026-07-05T02:31:04Z"},{"alias_kind":"pith_short_16","alias_value":"3IKWCWD3PDTWMCNW","created_at":"2026-07-05T02:31:04Z"},{"alias_kind":"pith_short_8","alias_value":"3IKWCWD3","created_at":"2026-07-05T02:31:04Z"}],"graph_snapshots":[{"event_id":"sha256:351a2e357ad0d3d2498d56f145e0f7d93d172745aab3ac2d7da86837c2a12a3d","target":"graph","created_at":"2026-07-05T02:31:04Z","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/2103.08784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jingjing Liu, Linjie Li, Shuohang Wang, Siqi Sun, Yen-Chun Chen, Yuwei Fang","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-16T00:35:28Z","title":"LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.08784","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:bd9dec60812ce15fa5c29001548bf7a71bb123f0f6bc99d781fba21eca368ed1","target":"record","created_at":"2026-07-05T02:31:04Z","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":"44392102f5e1e057cdb508757799bd36257656bb33971d890a4f52f8efb8333a","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-16T00:35:28Z","title_canon_sha256":"1325a5414837da20e6940ff7fbb6dd894df95b111619c7e50d5b1da029ac4400"},"schema_version":"1.0","source":{"id":"2103.08784","kind":"arxiv","version":2}},"canonical_sha256":"da1561587b78e76609b690e5f6705f3c4858d71078b7ba0ccc3335c6e5b9a077","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da1561587b78e76609b690e5f6705f3c4858d71078b7ba0ccc3335c6e5b9a077","first_computed_at":"2026-07-05T02:31:04.801713Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:31:04.801713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8y+cJtCdahwwFvrOQbL/MrHcA0hoWCMaRmFEWMeFVPFH2HVIVhXI9kqYAvW8US3UwNRKNwl7Vr2t3XW52vQuAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:31:04.802193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.08784","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd9dec60812ce15fa5c29001548bf7a71bb123f0f6bc99d781fba21eca368ed1","sha256:351a2e357ad0d3d2498d56f145e0f7d93d172745aab3ac2d7da86837c2a12a3d"],"state_sha256":"1ac7e625ceb0c240a18d786c23abafc1ab0a45a594c5fe41a12764b44da46165"}