{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:UZ4DCOSERRLA5P3Q3RMCDXXVB3","short_pith_number":"pith:UZ4DCOSE","schema_version":"1.0","canonical_sha256":"a678313a448c560ebf70dc5821def50ef8479d4f3f38d1f5976706df91e339c7","source":{"kind":"arxiv","id":"1610.03708","version":2},"attestation_state":"computed","paper":{"title":"Generating captions without looking beyond objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Arnold W.M. Smeulders, Christof Monz, Hendrik Heuer","submitted_at":"2016-10-12T13:42:03Z","abstract_excerpt":"This paper explores new evaluation perspectives for image captioning and introduces a noun translation task that achieves comparative image caption generation performance by translating from a set of nouns to captions. This implies that in image captioning, all word categories other than nouns can be evoked by a powerful language model without sacrificing performance on n-gram precision. The paper also investigates lower and upper bounds of how much individual word categories in the captions contribute to the final BLEU score. A large possible improvement exists for nouns, verbs, and prepositi"},"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":"1610.03708","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-10-12T13:42:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"332b055d2861189c12deff6b9d009a8136f15d357f737fa93d424e0987502b5b","abstract_canon_sha256":"e31073bea191c3c75b4a6b6f6875262abc8590a1fc74361b5358c4f1d62cd795"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:01:59.762617Z","signature_b64":"yk1cm8A9f1OxIJwu6hy1QGCcYeWeg9Kf6LvymYZeM85oDDPu82aRDsnzvcCxdQn3BavHF4s223J71lYtLKeJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a678313a448c560ebf70dc5821def50ef8479d4f3f38d1f5976706df91e339c7","last_reissued_at":"2026-05-18T01:01:59.762016Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:01:59.762016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating captions without looking beyond objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Arnold W.M. Smeulders, Christof Monz, Hendrik Heuer","submitted_at":"2016-10-12T13:42:03Z","abstract_excerpt":"This paper explores new evaluation perspectives for image captioning and introduces a noun translation task that achieves comparative image caption generation performance by translating from a set of nouns to captions. This implies that in image captioning, all word categories other than nouns can be evoked by a powerful language model without sacrificing performance on n-gram precision. The paper also investigates lower and upper bounds of how much individual word categories in the captions contribute to the final BLEU score. A large possible improvement exists for nouns, verbs, and prepositi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.03708","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":"1610.03708","created_at":"2026-05-18T01:01:59.762098+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.03708v2","created_at":"2026-05-18T01:01:59.762098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.03708","created_at":"2026-05-18T01:01:59.762098+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZ4DCOSERRLA","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZ4DCOSERRLA5P3Q","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZ4DCOSE","created_at":"2026-05-18T12:30:46.583412+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/UZ4DCOSERRLA5P3Q3RMCDXXVB3","json":"https://pith.science/pith/UZ4DCOSERRLA5P3Q3RMCDXXVB3.json","graph_json":"https://pith.science/api/pith-number/UZ4DCOSERRLA5P3Q3RMCDXXVB3/graph.json","events_json":"https://pith.science/api/pith-number/UZ4DCOSERRLA5P3Q3RMCDXXVB3/events.json","paper":"https://pith.science/paper/UZ4DCOSE"},"agent_actions":{"view_html":"https://pith.science/pith/UZ4DCOSERRLA5P3Q3RMCDXXVB3","download_json":"https://pith.science/pith/UZ4DCOSERRLA5P3Q3RMCDXXVB3.json","view_paper":"https://pith.science/paper/UZ4DCOSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.03708&json=true","fetch_graph":"https://pith.science/api/pith-number/UZ4DCOSERRLA5P3Q3RMCDXXVB3/graph.json","fetch_events":"https://pith.science/api/pith-number/UZ4DCOSERRLA5P3Q3RMCDXXVB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZ4DCOSERRLA5P3Q3RMCDXXVB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZ4DCOSERRLA5P3Q3RMCDXXVB3/action/storage_attestation","attest_author":"https://pith.science/pith/UZ4DCOSERRLA5P3Q3RMCDXXVB3/action/author_attestation","sign_citation":"https://pith.science/pith/UZ4DCOSERRLA5P3Q3RMCDXXVB3/action/citation_signature","submit_replication":"https://pith.science/pith/UZ4DCOSERRLA5P3Q3RMCDXXVB3/action/replication_record"}},"created_at":"2026-05-18T01:01:59.762098+00:00","updated_at":"2026-05-18T01:01:59.762098+00:00"}