{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:V6E7LS56LYY3GKZNTKNXIKRVOT","short_pith_number":"pith:V6E7LS56","schema_version":"1.0","canonical_sha256":"af89f5cbbe5e31b32b2d9a9b742a3574c12bc1b2ab8151129d2b6caa399cfeed","source":{"kind":"arxiv","id":"1812.08126","version":1},"attestation_state":"computed","paper":{"title":"Generating Diverse and Meaningful Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhijit Mahalunkar, Annika Lindh, Giancarlo Salton, John D. Kelleher, Robert J. Ross","submitted_at":"2018-12-19T18:10:18Z","abstract_excerpt":"Image Captioning is a task that requires models to acquire a multi-modal understanding of the world and to express this understanding in natural language text. While the state-of-the-art for this task has rapidly improved in terms of n-gram metrics, these models tend to output the same generic captions for similar images. In this work, we address this limitation and train a model that generates more diverse and specific captions through an unsupervised training approach that incorporates a learning signal from an Image Retrieval model. We summarize previous results and improve the state-of-the"},"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":"1812.08126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-19T18:10:18Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"e9809882d321debdcef1ddefe92f7dc7873209b46216a0e3cb46b937f6def7ea","abstract_canon_sha256":"9812edc00280273b42f3404c978c1a8a1ebed7f0fd3e339a0ff15ef751b2a66f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:54.771716Z","signature_b64":"NAMfQcuohkzxw9v2Hta6NbRW5EFSHd/DzXBjqTLFXD9tIHsPYBO+EksaHhqHbgaeHb/lnWgk2N9NHomNwdz4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af89f5cbbe5e31b32b2d9a9b742a3574c12bc1b2ab8151129d2b6caa399cfeed","last_reissued_at":"2026-05-17T23:57:54.771179Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:54.771179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Diverse and Meaningful Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhijit Mahalunkar, Annika Lindh, Giancarlo Salton, John D. Kelleher, Robert J. Ross","submitted_at":"2018-12-19T18:10:18Z","abstract_excerpt":"Image Captioning is a task that requires models to acquire a multi-modal understanding of the world and to express this understanding in natural language text. While the state-of-the-art for this task has rapidly improved in terms of n-gram metrics, these models tend to output the same generic captions for similar images. In this work, we address this limitation and train a model that generates more diverse and specific captions through an unsupervised training approach that incorporates a learning signal from an Image Retrieval model. We summarize previous results and improve the state-of-the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.08126","kind":"arxiv","version":1},"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":"1812.08126","created_at":"2026-05-17T23:57:54.771260+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.08126v1","created_at":"2026-05-17T23:57:54.771260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.08126","created_at":"2026-05-17T23:57:54.771260+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6E7LS56LYY3","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6E7LS56LYY3GKZN","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6E7LS56","created_at":"2026-05-18T12:32:59.047623+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/V6E7LS56LYY3GKZNTKNXIKRVOT","json":"https://pith.science/pith/V6E7LS56LYY3GKZNTKNXIKRVOT.json","graph_json":"https://pith.science/api/pith-number/V6E7LS56LYY3GKZNTKNXIKRVOT/graph.json","events_json":"https://pith.science/api/pith-number/V6E7LS56LYY3GKZNTKNXIKRVOT/events.json","paper":"https://pith.science/paper/V6E7LS56"},"agent_actions":{"view_html":"https://pith.science/pith/V6E7LS56LYY3GKZNTKNXIKRVOT","download_json":"https://pith.science/pith/V6E7LS56LYY3GKZNTKNXIKRVOT.json","view_paper":"https://pith.science/paper/V6E7LS56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.08126&json=true","fetch_graph":"https://pith.science/api/pith-number/V6E7LS56LYY3GKZNTKNXIKRVOT/graph.json","fetch_events":"https://pith.science/api/pith-number/V6E7LS56LYY3GKZNTKNXIKRVOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6E7LS56LYY3GKZNTKNXIKRVOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6E7LS56LYY3GKZNTKNXIKRVOT/action/storage_attestation","attest_author":"https://pith.science/pith/V6E7LS56LYY3GKZNTKNXIKRVOT/action/author_attestation","sign_citation":"https://pith.science/pith/V6E7LS56LYY3GKZNTKNXIKRVOT/action/citation_signature","submit_replication":"https://pith.science/pith/V6E7LS56LYY3GKZNTKNXIKRVOT/action/replication_record"}},"created_at":"2026-05-17T23:57:54.771260+00:00","updated_at":"2026-05-17T23:57:54.771260+00:00"}