{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:BKNIAIDO6CX4VVQIMMQ4VDIO3J","short_pith_number":"pith:BKNIAIDO","canonical_record":{"source":{"id":"2102.10407","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-20T18:02:42Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"812f8cca86fd04d948a9975afe479615bf5aec028e6d0e945dd08bfccf04727d","abstract_canon_sha256":"c54b969d4f0b98b08e022c16df200758975cc766943df460bb3592b1746a8985"},"schema_version":"1.0"},"canonical_sha256":"0a9a80206ef0afcad6086321ca8d0eda463b240c03920cf3ae99d02ef4681aa2","source":{"kind":"arxiv","id":"2102.10407","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:BKNIAIDO6CX4VVQIMMQ4VDIO3J","target":"record","payload":{"canonical_record":{"source":{"id":"2102.10407","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-20T18:02:42Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"812f8cca86fd04d948a9975afe479615bf5aec028e6d0e945dd08bfccf04727d","abstract_canon_sha256":"c54b969d4f0b98b08e022c16df200758975cc766943df460bb3592b1746a8985"},"schema_version":"1.0"},"canonical_sha256":"0a9a80206ef0afcad6086321ca8d0eda463b240c03920cf3ae99d02ef4681aa2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:55.905559Z","signature_b64":"JuZVyhZmSLTmp+ydC2UgY3pkI1TxwPScXYw4HBRFLThNPuwAHSGtPh1Z8QsJIooqTxdYB9sEk5vRmjvTquPUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a9a80206ef0afcad6086321ca8d0eda463b240c03920cf3ae99d02ef4681aa2","last_reissued_at":"2026-07-05T04:09:55.905144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:55.905144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.10407","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:09:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i+C8GUMw0RNA+NqtpNJBHKs2xIbW0NUiuTjLRpYLv/UdMqDBlX7UjEDwZAFFq+futXQEl6g6eoUh0+eUAljaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:45:45.340138Z"},"content_sha256":"2495ada0ce1bb5f5e176ff97f0ce59cf5c41987a9acc104a50340c146d3d2fa7","schema_version":"1.0","event_id":"sha256:2495ada0ce1bb5f5e176ff97f0ce59cf5c41987a9acc104a50340c146d3d2fa7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:BKNIAIDO6CX4VVQIMMQ4VDIO3J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Boyang Li, Han Guo, Jun Chen, Kai Yi, Mohamed Elhoseiny","submitted_at":"2021-02-20T18:02:42Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10407","kind":"arxiv","version":5},"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/2102.10407/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:09:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"70+f0aphnstZwQJq9PAft+PuBC2NDvR5YYWXevU/SSMKVd6E4I6bRb4LY5fFD/R8fTt6oIYUYZEFdQZve1EGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:45:45.340631Z"},"content_sha256":"a03423c30ffd6093c4fd59c4f2615158773a06da8f88953be652ef510c39e131","schema_version":"1.0","event_id":"sha256:a03423c30ffd6093c4fd59c4f2615158773a06da8f88953be652ef510c39e131"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BKNIAIDO6CX4VVQIMMQ4VDIO3J/bundle.json","state_url":"https://pith.science/pith/BKNIAIDO6CX4VVQIMMQ4VDIO3J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BKNIAIDO6CX4VVQIMMQ4VDIO3J/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T14:45:45Z","links":{"resolver":"https://pith.science/pith/BKNIAIDO6CX4VVQIMMQ4VDIO3J","bundle":"https://pith.science/pith/BKNIAIDO6CX4VVQIMMQ4VDIO3J/bundle.json","state":"https://pith.science/pith/BKNIAIDO6CX4VVQIMMQ4VDIO3J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BKNIAIDO6CX4VVQIMMQ4VDIO3J/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MrW3uu/8iHxHAaCGC2vo/CCnitaae0Qan8XXdhTW6BApCzcUext+KM5eSVFlfCiEqRkZRWtBfi+ztIwEv4unBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T14:45:45.344711Z","bundle_sha256":"8bf63b6e4059885225b80991639b726d0f29842ece4e600cd99de61bda85438f"}}