{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:XGCYNPBRH4DBN7IKHUJ6PTNEWK","short_pith_number":"pith:XGCYNPBR","schema_version":"1.0","canonical_sha256":"b98586bc313f0616fd0a3d13e7cda4b2b98f35fcbe219725cb6978b9f5cfe523","source":{"kind":"arxiv","id":"1605.09553","version":2},"attestation_state":"computed","paper":{"title":"Attention Correctness in Neural Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Chenxi Liu, Fei Sha, Junhua Mao","submitted_at":"2016-05-31T10:04:20Z","abstract_excerpt":"Attention mechanisms have recently been introduced in deep learning for various tasks in natural language processing and computer vision. But despite their popularity, the \"correctness\" of the implicitly-learned attention maps has only been assessed qualitatively by visualization of several examples. In this paper we focus on evaluating and improving the correctness of attention in neural image captioning models. Specifically, we propose a quantitative evaluation metric for the consistency between the generated attention maps and human annotations, using recently released datasets with alignme"},"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":"1605.09553","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-31T10:04:20Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"38b11080066a015395cdf0352225884b253892405c7a751c4c4a931fb05012b0","abstract_canon_sha256":"06ee3abb119034d2bdaaaed2b8a16879886bf6b9ec4e8ac71b4488e6009c9c49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:57:04.401585Z","signature_b64":"9aav/P/pSAcF2HvhHtbPhnK6mNe/d59mgHq5Z7kFfqJDJULzA8kaEPhMRDGCEHIhnwWPHndgbncgA3kuiP0JAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b98586bc313f0616fd0a3d13e7cda4b2b98f35fcbe219725cb6978b9f5cfe523","last_reissued_at":"2026-05-18T00:57:04.400946Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:57:04.400946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention Correctness in Neural Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Chenxi Liu, Fei Sha, Junhua Mao","submitted_at":"2016-05-31T10:04:20Z","abstract_excerpt":"Attention mechanisms have recently been introduced in deep learning for various tasks in natural language processing and computer vision. But despite their popularity, the \"correctness\" of the implicitly-learned attention maps has only been assessed qualitatively by visualization of several examples. In this paper we focus on evaluating and improving the correctness of attention in neural image captioning models. Specifically, we propose a quantitative evaluation metric for the consistency between the generated attention maps and human annotations, using recently released datasets with alignme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.09553","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":""},"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":"1605.09553","created_at":"2026-05-18T00:57:04.401037+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.09553v2","created_at":"2026-05-18T00:57:04.401037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.09553","created_at":"2026-05-18T00:57:04.401037+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGCYNPBRH4DB","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGCYNPBRH4DBN7IK","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGCYNPBR","created_at":"2026-05-18T12:30:51.357362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XGCYNPBRH4DBN7IKHUJ6PTNEWK","json":"https://pith.science/pith/XGCYNPBRH4DBN7IKHUJ6PTNEWK.json","graph_json":"https://pith.science/api/pith-number/XGCYNPBRH4DBN7IKHUJ6PTNEWK/graph.json","events_json":"https://pith.science/api/pith-number/XGCYNPBRH4DBN7IKHUJ6PTNEWK/events.json","paper":"https://pith.science/paper/XGCYNPBR"},"agent_actions":{"view_html":"https://pith.science/pith/XGCYNPBRH4DBN7IKHUJ6PTNEWK","download_json":"https://pith.science/pith/XGCYNPBRH4DBN7IKHUJ6PTNEWK.json","view_paper":"https://pith.science/paper/XGCYNPBR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.09553&json=true","fetch_graph":"https://pith.science/api/pith-number/XGCYNPBRH4DBN7IKHUJ6PTNEWK/graph.json","fetch_events":"https://pith.science/api/pith-number/XGCYNPBRH4DBN7IKHUJ6PTNEWK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGCYNPBRH4DBN7IKHUJ6PTNEWK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGCYNPBRH4DBN7IKHUJ6PTNEWK/action/storage_attestation","attest_author":"https://pith.science/pith/XGCYNPBRH4DBN7IKHUJ6PTNEWK/action/author_attestation","sign_citation":"https://pith.science/pith/XGCYNPBRH4DBN7IKHUJ6PTNEWK/action/citation_signature","submit_replication":"https://pith.science/pith/XGCYNPBRH4DBN7IKHUJ6PTNEWK/action/replication_record"}},"created_at":"2026-05-18T00:57:04.401037+00:00","updated_at":"2026-05-18T00:57:04.401037+00:00"}