{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:E7PLMPWAY42B64G54H3G2SFDHY","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":"7bdbedf10d78eb6e39704489d6c17195e3284170c6055e80ee29580d11214445","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.MM","submitted_at":"2022-07-04T14:08:59Z","title_canon_sha256":"f4dd784f7753c8c9d8597a5107bf25a9e4c9349de2457e71fc2c04fff32b07a4"},"schema_version":"1.0","source":{"id":"2207.01426","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.01426","created_at":"2026-07-05T04:37:11Z"},{"alias_kind":"arxiv_version","alias_value":"2207.01426v1","created_at":"2026-07-05T04:37:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01426","created_at":"2026-07-05T04:37:11Z"},{"alias_kind":"pith_short_12","alias_value":"E7PLMPWAY42B","created_at":"2026-07-05T04:37:11Z"},{"alias_kind":"pith_short_16","alias_value":"E7PLMPWAY42B64G5","created_at":"2026-07-05T04:37:11Z"},{"alias_kind":"pith_short_8","alias_value":"E7PLMPWA","created_at":"2026-07-05T04:37:11Z"}],"graph_snapshots":[{"event_id":"sha256:4eade4f04dfb3273ecdcb2255ba54984a0c1eaf2fe3dfe5ef2c21610019db054","target":"graph","created_at":"2026-07-05T04:37:11Z","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/2207.01426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although the vision-and-language pretraining (VLP) equipped cross-modal image-text retrieval (ITR) has achieved remarkable progress in the past two years, it suffers from a major drawback: the ever-increasing size of VLP models restricts its deployment to real-world search scenarios (where the high latency is unacceptable). To alleviate this problem, we present a novel plug-in dynamic contrastive distillation (DCD) framework to compress the large VLP models for the ITR task. Technically, we face the following two challenges: 1) the typical uni-modal metric learning approach is difficult to dir","authors_text":"Dacheng Tao, Jun Rao, Liang Ding, Li Shen, Meng Fang, Shuhan Qi, Yang Liu","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.MM","submitted_at":"2022-07-04T14:08:59Z","title":"Dynamic Contrastive Distillation for Image-Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.01426","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":"sha256:86f7a4144ae5f1e77ed2374664eec0b4c6338c2e6bf27f457c3a93b08fd04cb7","target":"record","created_at":"2026-07-05T04:37:11Z","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":"7bdbedf10d78eb6e39704489d6c17195e3284170c6055e80ee29580d11214445","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.MM","submitted_at":"2022-07-04T14:08:59Z","title_canon_sha256":"f4dd784f7753c8c9d8597a5107bf25a9e4c9349de2457e71fc2c04fff32b07a4"},"schema_version":"1.0","source":{"id":"2207.01426","kind":"arxiv","version":1}},"canonical_sha256":"27deb63ec0c7341f70dde1f66d48a33e3b069ef1a1d0bd17ed1d9d4bd4379170","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27deb63ec0c7341f70dde1f66d48a33e3b069ef1a1d0bd17ed1d9d4bd4379170","first_computed_at":"2026-07-05T04:37:11.784324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:37:11.784324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rUbqXYMhU7N/nyrkfjquIyMxbJKTC+SBUKiP9xCqWBW/m5bxA9IkZAWz2amxWA/VwX5jzbVAX0gWnXjEwCfaDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:37:11.784731Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.01426","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86f7a4144ae5f1e77ed2374664eec0b4c6338c2e6bf27f457c3a93b08fd04cb7","sha256:4eade4f04dfb3273ecdcb2255ba54984a0c1eaf2fe3dfe5ef2c21610019db054"],"state_sha256":"3ce653dca131cc7f1c5a6196af81a25b35c61e0591e8b555d60de7947afa5ef7"}