{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:V6E7LS56LYY3GKZNTKNXIKRVOT","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":"9812edc00280273b42f3404c978c1a8a1ebed7f0fd3e339a0ff15ef751b2a66f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-19T18:10:18Z","title_canon_sha256":"e9809882d321debdcef1ddefe92f7dc7873209b46216a0e3cb46b937f6def7ea"},"schema_version":"1.0","source":{"id":"1812.08126","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.08126","created_at":"2026-05-17T23:57:54Z"},{"alias_kind":"arxiv_version","alias_value":"1812.08126v1","created_at":"2026-05-17T23:57:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.08126","created_at":"2026-05-17T23:57:54Z"},{"alias_kind":"pith_short_12","alias_value":"V6E7LS56LYY3","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"V6E7LS56LYY3GKZN","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"V6E7LS56","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:55da53d86a61c9faf64ab41d8ed7c5964b0d9dffb4f2eab288c2c63706ee5df5","target":"graph","created_at":"2026-05-17T23:57:54Z","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"},"paper":{"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","authors_text":"Abhijit Mahalunkar, Annika Lindh, Giancarlo Salton, John D. Kelleher, Robert J. Ross","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-19T18:10:18Z","title":"Generating Diverse and Meaningful Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.08126","kind":"arxiv","version":1},"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:cdfbe6cb71f6a378c7445b3ccef00d59a5135fdcffe311fd1806f76b35568ac8","target":"record","created_at":"2026-05-17T23:57:54Z","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":"9812edc00280273b42f3404c978c1a8a1ebed7f0fd3e339a0ff15ef751b2a66f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-19T18:10:18Z","title_canon_sha256":"e9809882d321debdcef1ddefe92f7dc7873209b46216a0e3cb46b937f6def7ea"},"schema_version":"1.0","source":{"id":"1812.08126","kind":"arxiv","version":1}},"canonical_sha256":"af89f5cbbe5e31b32b2d9a9b742a3574c12bc1b2ab8151129d2b6caa399cfeed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af89f5cbbe5e31b32b2d9a9b742a3574c12bc1b2ab8151129d2b6caa399cfeed","first_computed_at":"2026-05-17T23:57:54.771179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:54.771179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NAMfQcuohkzxw9v2Hta6NbRW5EFSHd/DzXBjqTLFXD9tIHsPYBO+EksaHhqHbgaeHb/lnWgk2N9NHomNwdz4AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:54.771716Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.08126","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdfbe6cb71f6a378c7445b3ccef00d59a5135fdcffe311fd1806f76b35568ac8","sha256:55da53d86a61c9faf64ab41d8ed7c5964b0d9dffb4f2eab288c2c63706ee5df5"],"state_sha256":"ff673b79c942ae582d7767585646e3a4985bcffedb66f7df0a47a3dc0c6b7efc"}