{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BKNIAIDO6CX4VVQIMMQ4VDIO3J","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":"c54b969d4f0b98b08e022c16df200758975cc766943df460bb3592b1746a8985","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-20T18:02:42Z","title_canon_sha256":"812f8cca86fd04d948a9975afe479615bf5aec028e6d0e945dd08bfccf04727d"},"schema_version":"1.0","source":{"id":"2102.10407","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.10407","created_at":"2026-07-05T04:09:55Z"},{"alias_kind":"arxiv_version","alias_value":"2102.10407v5","created_at":"2026-07-05T04:09:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10407","created_at":"2026-07-05T04:09:55Z"},{"alias_kind":"pith_short_12","alias_value":"BKNIAIDO6CX4","created_at":"2026-07-05T04:09:55Z"},{"alias_kind":"pith_short_16","alias_value":"BKNIAIDO6CX4VVQI","created_at":"2026-07-05T04:09:55Z"},{"alias_kind":"pith_short_8","alias_value":"BKNIAIDO","created_at":"2026-07-05T04:09:55Z"}],"graph_snapshots":[{"event_id":"sha256:a03423c30ffd6093c4fd59c4f2615158773a06da8f88953be652ef510c39e131","target":"graph","created_at":"2026-07-05T04:09:55Z","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/2102.10407/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability to quickly learn from a small quantity oftraining data widens the range of machine learning applications. In this paper, we propose a data-efficient image captioning model, VisualGPT, which leverages the linguistic knowledge from a large pretrained language model(LM). A crucial challenge is to balance between the use of visual information in the image and prior linguistic knowledge acquired from pretraining. We designed a novel self-resurrecting encoder-decoder attention mechanism to quickly adapt the pretrained LM as the language decoder ona small amount of in-domain training data","authors_text":"Boyang Li, Han Guo, Jun Chen, Kai Yi, Mohamed Elhoseiny","cross_cats":["cs.AI","cs.CL","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-20T18:02:42Z","title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10407","kind":"arxiv","version":5},"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":"sha256:2495ada0ce1bb5f5e176ff97f0ce59cf5c41987a9acc104a50340c146d3d2fa7","target":"record","created_at":"2026-07-05T04:09:55Z","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":"c54b969d4f0b98b08e022c16df200758975cc766943df460bb3592b1746a8985","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-20T18:02:42Z","title_canon_sha256":"812f8cca86fd04d948a9975afe479615bf5aec028e6d0e945dd08bfccf04727d"},"schema_version":"1.0","source":{"id":"2102.10407","kind":"arxiv","version":5}},"canonical_sha256":"0a9a80206ef0afcad6086321ca8d0eda463b240c03920cf3ae99d02ef4681aa2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a9a80206ef0afcad6086321ca8d0eda463b240c03920cf3ae99d02ef4681aa2","first_computed_at":"2026-07-05T04:09:55.905144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:55.905144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JuZVyhZmSLTmp+ydC2UgY3pkI1TxwPScXYw4HBRFLThNPuwAHSGtPh1Z8QsJIooqTxdYB9sEk5vRmjvTquPUBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:55.905559Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.10407","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2495ada0ce1bb5f5e176ff97f0ce59cf5c41987a9acc104a50340c146d3d2fa7","sha256:a03423c30ffd6093c4fd59c4f2615158773a06da8f88953be652ef510c39e131"],"state_sha256":"6da2589f3fd0b2bc99d81160459af84a17d7ff46f6cec590eaadb6dd8c8d8302"}