{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SR2SLFWWIY7EBDUH2FKCN33TYK","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":"41ca8a2d00681a3f497946c62fec5493e954e0420603f0162e8e837a7deff631","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T09:21:18Z","title_canon_sha256":"b712911025a98cf8b30f2a9bdebb8cdf07e9e3fc6a25559845eea582721ff378"},"schema_version":"1.0","source":{"id":"2112.08723","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08723","created_at":"2026-07-05T05:06:53Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08723v2","created_at":"2026-07-05T05:06:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08723","created_at":"2026-07-05T05:06:53Z"},{"alias_kind":"pith_short_12","alias_value":"SR2SLFWWIY7E","created_at":"2026-07-05T05:06:53Z"},{"alias_kind":"pith_short_16","alias_value":"SR2SLFWWIY7EBDUH","created_at":"2026-07-05T05:06:53Z"},{"alias_kind":"pith_short_8","alias_value":"SR2SLFWW","created_at":"2026-07-05T05:06:53Z"}],"graph_snapshots":[{"event_id":"sha256:3ba8c3a7b1a8802ef4503b5ba0d21fddea971fca23fda5162fc0090c8499d200","target":"graph","created_at":"2026-07-05T05:06:53Z","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/2112.08723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering. Dual-encoder models have a faster inference speed than fusion-encoder models and enable the pre-computation of images and text during inference. However, the shallow interaction module used in dual-encoder models is insufficient to handle complex vision-language understanding tasks. In order to learn deep interactions of images and text, we introduce cross-modal attention distillation, which uses the image-to-te","authors_text":"Bing Qin, Furu Wei, Haichao Zhu, Ming Liu, Wenhui Wang, Zekun Wang","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T09:21:18Z","title":"Distilled Dual-Encoder Model for Vision-Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08723","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:d36f2d03786f00cf8f3348fe6b3f9bd0e7d06d790b9d5c5269bbf10e891d49af","target":"record","created_at":"2026-07-05T05:06:53Z","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":"41ca8a2d00681a3f497946c62fec5493e954e0420603f0162e8e837a7deff631","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T09:21:18Z","title_canon_sha256":"b712911025a98cf8b30f2a9bdebb8cdf07e9e3fc6a25559845eea582721ff378"},"schema_version":"1.0","source":{"id":"2112.08723","kind":"arxiv","version":2}},"canonical_sha256":"94752596d6463e408e87d15426ef73c296ba57a8fe10ab49f4b98912e4bd47e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94752596d6463e408e87d15426ef73c296ba57a8fe10ab49f4b98912e4bd47e4","first_computed_at":"2026-07-05T05:06:53.758005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:53.758005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LWEgL262X85re3733qTvjJ/fNjFjfaagXpm2OsCguW9OR5tLGgKUbE1naY+JB8rPrDh30AOobRd4i5+Z3g1/Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:53.758499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.08723","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d36f2d03786f00cf8f3348fe6b3f9bd0e7d06d790b9d5c5269bbf10e891d49af","sha256:3ba8c3a7b1a8802ef4503b5ba0d21fddea971fca23fda5162fc0090c8499d200"],"state_sha256":"89f4a43d8b6293923d57dcb6e45c3202c38a8e79bbe48b0e56fa450e6e2c4879"}