{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AWUL7JGUQF5Q4NWT44GSCDIY75","short_pith_number":"pith:AWUL7JGU","schema_version":"1.0","canonical_sha256":"05a8bfa4d4817b0e36d3e70d210d18ff5b8dec6a6745e04f46c3122227ce941a","source":{"kind":"arxiv","id":"2207.13162","version":2},"attestation_state":"computed","paper":{"title":"Retrieval-Augmented Transformer for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Lorenzo Baraldi, Marcella Cornia, Rita Cucchiara, Sara Sarto","submitted_at":"2022-07-26T19:35:49Z","abstract_excerpt":"Image captioning models aim at connecting Vision and Language by providing natural language descriptions of input images. In the past few years, the task has been tackled by learning parametric models and proposing visual feature extraction advancements or by modeling better multi-modal connections. In this paper, we investigate the development of an image captioning approach with a kNN memory, with which knowledge can be retrieved from an external corpus to aid the generation process. Our architecture combines a knowledge retriever based on visual similarities, a differentiable encoder, and a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2207.13162","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-26T19:35:49Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"8ea8248fe8bf820baeab21530fbf6abcc5fba65c8a682cc06ca420f82e89e67c","abstract_canon_sha256":"98ccd679f18c706ba5c8f89e96a7f6911c193e035b9e65bed531a9642696f57f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:50:19.068037Z","signature_b64":"gC01Ce2Ai7v4M+yxusF1FbCCZ0QDNbSvJS7dfVDjF6vdkU96koeuLgNH9jbVXaLb3ezafM73LY6wesOePF3QDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05a8bfa4d4817b0e36d3e70d210d18ff5b8dec6a6745e04f46c3122227ce941a","last_reissued_at":"2026-07-05T04:50:19.067636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:50:19.067636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-Augmented Transformer for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Lorenzo Baraldi, Marcella Cornia, Rita Cucchiara, Sara Sarto","submitted_at":"2022-07-26T19:35:49Z","abstract_excerpt":"Image captioning models aim at connecting Vision and Language by providing natural language descriptions of input images. In the past few years, the task has been tackled by learning parametric models and proposing visual feature extraction advancements or by modeling better multi-modal connections. In this paper, we investigate the development of an image captioning approach with a kNN memory, with which knowledge can be retrieved from an external corpus to aid the generation process. Our architecture combines a knowledge retriever based on visual similarities, a differentiable encoder, and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.13162","kind":"arxiv","version":2},"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/2207.13162/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2207.13162","created_at":"2026-07-05T04:50:19.067698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.13162v2","created_at":"2026-07-05T04:50:19.067698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.13162","created_at":"2026-07-05T04:50:19.067698+00:00"},{"alias_kind":"pith_short_12","alias_value":"AWUL7JGUQF5Q","created_at":"2026-07-05T04:50:19.067698+00:00"},{"alias_kind":"pith_short_16","alias_value":"AWUL7JGUQF5Q4NWT","created_at":"2026-07-05T04:50:19.067698+00:00"},{"alias_kind":"pith_short_8","alias_value":"AWUL7JGU","created_at":"2026-07-05T04:50:19.067698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.02640","citing_title":"Multispectral Pedestrian Detection with Sparsely Annotated Label","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AWUL7JGUQF5Q4NWT44GSCDIY75","json":"https://pith.science/pith/AWUL7JGUQF5Q4NWT44GSCDIY75.json","graph_json":"https://pith.science/api/pith-number/AWUL7JGUQF5Q4NWT44GSCDIY75/graph.json","events_json":"https://pith.science/api/pith-number/AWUL7JGUQF5Q4NWT44GSCDIY75/events.json","paper":"https://pith.science/paper/AWUL7JGU"},"agent_actions":{"view_html":"https://pith.science/pith/AWUL7JGUQF5Q4NWT44GSCDIY75","download_json":"https://pith.science/pith/AWUL7JGUQF5Q4NWT44GSCDIY75.json","view_paper":"https://pith.science/paper/AWUL7JGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.13162&json=true","fetch_graph":"https://pith.science/api/pith-number/AWUL7JGUQF5Q4NWT44GSCDIY75/graph.json","fetch_events":"https://pith.science/api/pith-number/AWUL7JGUQF5Q4NWT44GSCDIY75/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AWUL7JGUQF5Q4NWT44GSCDIY75/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AWUL7JGUQF5Q4NWT44GSCDIY75/action/storage_attestation","attest_author":"https://pith.science/pith/AWUL7JGUQF5Q4NWT44GSCDIY75/action/author_attestation","sign_citation":"https://pith.science/pith/AWUL7JGUQF5Q4NWT44GSCDIY75/action/citation_signature","submit_replication":"https://pith.science/pith/AWUL7JGUQF5Q4NWT44GSCDIY75/action/replication_record"}},"created_at":"2026-07-05T04:50:19.067698+00:00","updated_at":"2026-07-05T04:50:19.067698+00:00"}